Assistant Dean for Organizational Digital Transformation
Faculty of Engineering, Mahidol University, Thailand
Assistant Professor at
Mahidol University: Faculty of Engineering: Technology of Information System Management Division
Director of Datalent Team: Data Talent Development Research Group
Faculty of Engineering, Mahidol University, Thailand
Technology of Information System Management Division, Faculty of Engineering, Mahidol University, Thailand
Datalent Team- Data Science and Governance Talent Development Research Group
Technology of Information System Management Division, Faculty of Engineering, Mahidol University, Thailand
Information Technology Management Society Transactions on Innovation and Business Engineering (ITMSOC-IBE)
Information Technology Management Society Transactions on Information Technology Management (ITMSOC-ITM)
Possible Space Co., Ltd.
Possible Space Creative Math and English School
B2Media Co., Ltd.
Computer Engineering Department, Faculty of Engineering, Mahidol University, Thailand
Fun-A Private Tutor
Ph.D. (Information Technology)-English Program
King Mongkut's University Technology Thonburi, Thailand
Ph.D. Dissertation
A Classifier of Charges and Range of Punishments under Criminal Law of Civil Law System: Cases in the Offences against Life and Body Section (Abstract: EN / TH)
Dissertation Advisor
Asst. Prof. Dr. Bunthit Watanapa and Dr. Udom Silparcha
B.Eng. (Computer Engineering)
Mahidol University, Thailand
Senior Project
English Search Engine
Senior Project Advisor
Lect. Phansiri Athikomrungsarit
National Security Management for Executives (National Intelligent Agency)
หลักสูตรบริหารจัดการความมั่นคงแห่งชาติ (บมช.) รุ่นที่ 12 โดยสำนักข่าวกรองแห่งชาติ
Expert Committee 4 (Health and Research)
Committee- Privacy Index and Privacy Maturity Model Criteria Development
Subcommittee on Rights, Advancement, and Position Determination in Community Public Health Profession
Committee
Advisory
Committee
Vice Chair
Vice Chair
Advisory
Committee
Committee
Advisory
Committee
Advisory
Advisory
Committee
Committee
Committee
Advisory Committee
Committee
Committee
Committee
Big Data Advisory Board
Committee
Drafting Committee
Committee
Committee
Chairman of Drafting Committee
Secretary and Committee
Program Critque Committee
Reviewer
Reviewer
Reviewer
Reviewer
Reviewer
Reviewer
Reviewer
The Official Research Journal of the City College of Angeles
Editorial Board
Reviewer
Reviewer
PDPA Compliance Improvement
State Railway of Thailand
Master Data Standard
State Railway of Thailand
Data Governance Policy and Data Catalog
Geo-Informatics and Space Technology Development Agency
Data Governance and Data Catalog Implementation
State Railway of Thailand
Data Governance and PDPA
Industrial Estate Authority of Thailand
Data Governance Implementation
Bangkok Life Assurance PLC
Data Governance Implementation
Department of Energy Business
PDPA Compliance
Secom Security Thailand
Data Governance and Data Quality Policy
Industrial Estate Authority of Thailand
Data Governance and Data Catalog Implementation
State Railway of Thailand
Data Catalog Implementation
Industrial Estate Authority of Thailand
Data Governance and Data Architecture Implementation
Office of Insurance Commission
Data Governance Communication Implementation
FWD Thailand Co., Ltd.
Data Governance Framework and Implementation
Pruksa Realestates Co., Ltd.
Big Data Master Plan Revision
Sports Authority of Thailand
Data Governance Framework and Policy
Sports Authority of Thailand
Big Data Master Plan Revision
Sports Authority of Thailand
Enterprise and Data Architecture
The Gem and Jewelry Institute of Thailand (Public Organization)
Data Governance Assessment
Thanachart Insurance
PDPA Compliance
State Railway of Thailand
Big Data Master Plan
The Civil Aviation Authority of Thailand
Big Data Master Plan Revision
Sports Authority of Thailand
Data Governance Framework for State Railway of Thailand
State Railway of Thailand
Data Science Skill Development
Community Development Department
Data Governance Framework for Sansiri
Sansiri Plc.
Big Data Master Plan
Sports Authority of Thailand
Regional Committee
The 2ND Management and Innovation Technology International Conference (MITiCON2015)
Secretary Chair
The 18th Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES-2014)
Program Committee
The 1ST Management and Innovation Technology International Conference (MITiCON2014)
Steering Committee
Lecturer-M.Sc.(IT Management) Students
Lecturer-M.Sc.(IT Management) Students
Lecturer-M.Sc.(IT Management) Students
Lecturer-M.Sc.(IT Management) Students
Lecturer-M.Sc.(IT Management) Students
Lecturer-M.Sc.(IT Management) Students
Lecturer-M.Sc.(IT Management) Students
Guest Lecturer-M.Sc.(Health Informatics) Students
Lecturer-M.Sc.(IT Management) Students
Tutor- BBA Students
Guest Lecturer-1st Year Engineering, Faculty of Engineering
Guest Lecturer-3rd Year Computer Engineering, Faculty of Engineering
Tutor- B.Sc.(CS) Students
Tutor- B.Sc.(CS) Students
Tutor- B.Sc.(CS) Students
Tutor- B.Sc.(CS) Students
Total: 220 rounds (949 hours)
2024: 20 rounds (71 hours)
2023: 44 rounds (193 hours)
2022: 64 rounds (299 hours)
2021: 33 rounds (166 hours)
2020: 14 rounds (41 hours)
2019: 18 rounds (86 hours)
2018: 16 rounds (57 hours)
2017: 6 rounds (19 hours)
2016: 2 rounds (7 hours)
2015: 1 rounds (3 hours)
2012: 1 rounds (1 hours)
2007: 1 rounds (6 hours)
Mahidol Quality Fair 2022: Good Governance in Digital Era (1 hours)
Speaker-Mahidol University
Introduction to Big Data (3 hours)
Guest Lecturer- Bachelor Degree in Electrical Engineering, Mahidol University
Big Data and Data Analytics (3 hours)
Invited Speaker- Office of the Pubic Sector Development Commission
Introduction to Data Science (2 hours)
Instructor-Data Science Clinic with R Programming
Digital Economy and Digital Literacy (6 hours)
Instructor-Bangkok Metropolitant Administration Office
Business Analysis Essential (6 hours)
Instructor-Bangkok Metropolitant Administration Office
Digital and Media Literacy (6 hours)
Guest Lecturer-Valaya Alongkorn Rajabhat University
Introduction to Big Data (3 hours)
Intructor-Department of Disease Control
An Integration of Data Mining Methods in Identification of Criminal Law Sentences (1 hours)
Speaker-The International Neural Network Society Workshop on Trends in Natural and Machine Intelligence (TNMI2012)
Data Warehousing for Decision Support System (6 hours)
Instructor-Faculty of Engineering, Mahidol University
Total: 131 rounds (1630 hours)
2023: 14 rounds (144 hours)
2022: 25 rounds (306 hours)
2021: 33 rounds (432 hours)
2020: 25 rounds (274 hours)
2019: 16 rounds (231 hours)
2018: 12 rounds (177 hours)
2017: 6 rounds (66 hours)
Deep Learning for Image Analytics with Google Co-Lab (12 hours)
Director-Datalent Team Course Series
Deep Learning for Image Analytics with Google Co-Lab (12 hours)
Director and Co-instructor-Datalent Team Course Series
Data Visualization and Business Intelligence with Tableau Desktop (24 hours)
Director and CoInstructor-Datalent Team Course Series
Advanced Data Analysis and Reports with Power Query and Power BI (12 hours)
Director and CoInstructor-Datalent Team Course Series
Data Visualization and Visual Analytics with Microsoft PowerBI (12 hours)
Director and CoInstructor-Datalent Team Course Series
Python Programming for Data Science (12 hours)
Director and CoInstructor-Datalent Team Course Series
Data Visualization and Business Intelligence with Tableau Desktop (24 hours)
Director and CoInstructor-Datalent Team Course Series
Advanced Data Analysis and Reports with Power Query and Power BI (12 hours)
Director and CoInstructor-Datalent Team Course Series
Data Visualization and Visual Analytics with Microsoft PowerBI (12 hours)
Director and CoInstructor-Datalent Team Course Series
Python Programming for Data Science (12 hours)
Director and CoInstructor-Datalent Team Course Series
Fundamental Python Programming for Data Science (12 hours)
Director and CoInstructor-Datalent Team Course Series
Data Mining Essentials with RapidMiner Studio (24 hours)
Instructor-Datalent Team Course Series
Data Visualization and Business Intelligence with Tableau Desktop (24 hours)
Director and CoInstructor-Datalent Team Course Series
Fundamental Python Programming for Data Science (12 hours)
Director and CoInstructor-Datalent Team Course Series
Data Governance for Business Leaders (12 hours)
Instructor-Datalent Team Course Series
Advanced Data Mining for Business and Research with RapidMiner Studio (18 hours)
Instructor-Datalent Team Course Series
Data Visualization and Business Intelligence with Tableau Desktop (18 hours)
Director and CoInstructor-Datalent Team Course Series
Data Science Ecosystem and Data Mining with RapidMiner Studio (24 hours)
Instructor-Datalent Team Course Series
Data Science Ecosystem and Data Mining with RapidMiner Studio (24 hours)
Instructor-Datalent Team Course Series
Data Governance for Business Leaders (12 hours)
Instructor-Datalent Team Course Series
Data Visualization and Business Intelligence with Tableau Desktop (12 hours)
Director and CoInstructor-Datalent Team Course Series
Data Visualization and Business Intelligence with Microsoft PowerBI (12 hours)
Director and CoInstructor-Datalent Team Course Series
Data Visualization and Business Intelligence with Tableau Desktop (12 hours)
Director and CoInstructor-Datalent Team Course Series
Data Wrangling and Data Quality Essential with SQL and RapidMiner Studio (12 hours)
Instructor-Datalent Team Course Series
Learning Data Science Ecosystem and Data Mining with RapidMiner Studio (18 hours)
Instructor-Datalent Team Course Series
Introduction to Data Mining and Data Visualization with RapidMiner and Microsoft Power BI (6 hours)
Instructor-Datalent Team Course Series
Introduction to Data Science and Data Mining for Business using RapidMiner (6 hours)
Instructor-Datalent Team Course Series
Total: 110 rounds (1603 hours)
2024: 9 rounds (114 hours)
2023: 16 rounds (303 hours)
2022: 22 rounds (312 hours)
2021: 17 rounds (267 hours)
2020: 16 rounds (159 hours)
2019: 15 rounds (187 hours)
2018: 14 rounds (255 hours)
2007: 1 rounds (6 hours)
Government Data Scientist (Batch 3) (27 hours)
Instructor-Thailand Digital Government Academy (TDGA)
Government Data Scientist (Batch 2) (27 hours)
Instructor-Thailand Digital Government Academy (TDGA)
Government Data Scientist (Batch 1) (27 hours)
Instructor-Thailand Digital Government Academy (TDGA)
Introduction to Microsoft Access (6 hours)
Instructor- Indian Guest
Phd | Thesis | Thematic | Total Students | Net Load | |
Official | 6 | 1 | 5 | 12 | 82⁄3 |
Unofficial | 2 | 0 | 4 | 6 | 31⁄3 |
Total | 8 | 1 | 9 | 18 | 12 |
This research introduces a personalized hybrid tourist destination recommendation system tailored for the growing trend of independent travel, which leverages social media data for trip planning. The system sets itself apart from traditional models by incorporating both emotional and sentiment data from social platforms to create customized travel experiences. The proposed approach utilizes Machine Learning techniques to improve recommendation accuracy, employing Collaborative Filtering for emotional pattern recognition and Content-based Filtering for sentiment-driven destination analysis. This integration results in a sophisticated weighted hybrid model that effectively balances the strengths of both filtering techniques. Empirical evaluations produced RMSE, MAE, and MSE scores of 0.301, 0.317, and 0.311, respectively, indicating the system's superior performance in predicting user preferences and interpreting emotional data. These findings highlight a significant advancement over previous recommendation systems, demonstrating how the integration of emotional and sentiment analysis can not only improve accuracy but also enhance user satisfaction by providing more personalized and contextually relevant travel suggestions. Furthermore, this study underscores the broader implications of such analysis in various industries, opening new avenues for future research and practical implementation in fields where personalized recommendations are crucial for enhancing user experience and engagement.
#Recommendations #HybridRecommendationSystem #CollaborativeFiltering #ContentBasedFiltering #SocialMediaData #TravelPlanning
Organic farming is of the utmost importance in promoting environmentally sustainable agricultural practices, minimizing environmental contamination, and avoiding using chemical fertilizers and genetically modified organisms (GMOs). Even inexperienced and seasoned farmers frequently encounter formidable obstacles when attempting to authenticate their organic farming status by acquiring organic agriculture certification. The current level of agricultural land maturity is accurately assessed by a comprehensive model presented in this study, which also provides a framework for the transition to organic farming standards. These maturity models were formulated through an exhaustive analysis of agricultural standards, an extensive review of pertinent literature, and expert interviews conducted in 15 distinct locations, with each expert holding certification in a minimum of three organic agricultural standards. Identifying characteristics germane to organic standards, integrating them into maturity models, and establishing maturity items and dimensions are also components of the study. The outcome of our investigation is the Sustainable Organic Farming Maturity (SOFaM) model, which consists of five levels and eight dimensions, as well as a standard operating procedure manual for organic agricultural standard certification applications. This model's potential as an assessment instrument for determining the maturity level of agricultural land has been validated by experts who hold credentials in three distinct domains and three locations. The SOFaM model has the potential to function as a paradigm shift in the agricultural sector, streamline the certification process following organic farming standards, and guarantee adherence to predetermined criteria.
#OrganicFarming #SustainableAgriculture #MaturityModel #Certification #AgricultureStandards
The coronavirus disease (COVID-19) pandemic produced adverse effects which spreads globally and throughout all the nations. During the outbreak, govern-ments announced emergency policies geared to control the situation. Subsequently, researchers have attempted to determine the advantages and disadvantages of these policies. We developed a method for evaluating COVID-19 policy in Thailand from January 2020 to March 2022. The Policy Model Consistency (PMC) Index is introduced as the primary model with 10 powerful indicators for policy evaluation. Additionally, the stock price changes while the COVID-19 policy was being enforced, as recorded in the Securities Exchange of Thailand (SET) database, are also observed with the other indicators for a measure of public confidence. All indicators are scored on a binary basis based on the policy consistency. The result of PMC-score is outputted as a contour surface graph. The PMC-surface result shows the good and adverse point of the policy to a policymaker, and it is successfully discussed to present the internal relationship of the indicators from the policymaker’s perspective. This tool benefits policymakers by facilitating early identification of policy’s strengths and weaknesses and the findings of policy angles in all related perspectives are significant to policymakers to address and improve in the next enhancement as well.
SPOC (Small Private Online Course) is an online learning platform combining classroom and online lessons. For the development of the SPOC, it is worth looking at learning behaviors in-depth throughout the course. As Higher Education courses in Thailand focus on English language benchmarking, this research decided to choose English Level 1 as a content course for the reading and grammar skills from August 2020 to June 2021. The descriptive analytics study conducted by Visual Analytics and K-Means Clustering, both student-level and lesson-level learning behavior. The result found four types of learners in Student-level learning behavior: 1) Intelligent, 2) Weak-cognitive, 3) Inattentive 4) Unenthusiastic. Moreover, Predictive Analytics, for predicting learning quality through learning behaviors of each cluster by four machine learning models, were comparatively experimented with: Generalized Linear Model, Decision Tree, Random Forest, and Gradient Boosted Trees. The Optimization method is used for tuning the optimum parameter of each method. For student-level behavior prediction, the Unenthusiastic Decision Tree was 0.0449, and Lesson-level Weak-cognitive Gradient Boosted Trees was 0.0371 relative error. Additionally, the factor of importance in quality prediction was found that amount of quizzes was the essential variable among all clusters. The result of this research is that the instructors can further develop content and teaching methods in the course to truly meet the learners' needs.
#SPOC #OnlineLearning #DescriptiveAnalytics #PredictiveAnalytics
Data governance is defined as general data management practices and redundant data structures; it sets direction and controls to ensure compliance with rules, policies, and regulations. However, large organizations with large amounts of data and complex structures require more focus on people and interactions, based on the agile concept. It entrusts a co-design and decision-making team with no invasion of the original role to support the organization’s business in operations. The data should be embedded in the analysis group to sprint the data analysis cycles. This research focused on an operating model, the medical agile noninvasive data governance, which aimed to formally assign roles and responsibilities to groups with specific expertise. The resulting streamlined workflow benefited from various planning strategies for further healthcare services; thus, the healthcare organization in Thailand chose this as a case study. This research emphasized the roles and responsibilities throughout the organization to show a more accurate imple-mentation process of the prototype. Implementation and evaluation were categorized into two levels: organizational and operational. An in-depth organizational-level interview evaluated the resulting the responsible-accountable-supportive-consulted-informed matrix for the policy establishment process. The operational-level assessment made the function of the concept visible through a role-playing representation of data operations. A questionnaire of role-playing roles was used for assessment in terms of agility, connectivity, redundancy, reducing roles, and process responsibilities. The highest level of overall satisfaction was 4.65 on a 5-point rating scale. After comparing the results of existing frameworks or studies, the researchers found that this prototype design was complete, with coverage of both roles and responsibilities of each level according to the organizational structure. It could streamline work processes and lead to analytics to connect with valuable, accurate, and transparent targeted outcomes for organizations.
#DataGovernance #NoninvasiveDataGovernance #Agile #Healthcare
An industry sector is important for the economic growth in Thailand. Among those industries, the electrical and mechanical parts manufacturers are also essential to drive the production process in the factory. Due to the foundation activity supporting, the industrial part manufacturer has become more competitive. The business report in 2019 stated the lost customers and open status of quotations are increasing dramatically. In order to solve and further prevent these problems and gain more competitive advantage, the data mining technique would be necessary to descriptively understand and predict customer behavior which can improve the business strategy to be more effective, which the return-of-investment of the simulated business scenario will prove. The data used in this paper is customer data between 2017 and 2020 in two entities: 1) customer characteristic data, including registered capital, industry code, business type, business size value, and 2) customer transaction data, including purchase history. The combination of descriptive segmentation and predictive modeling toward decision-making strategies that tend to increase the return-of-investment of the industries is challenging, and the main contribution is specified in electrical and mechanical parts manufacturing. The expected results should support the Sales and Marketing team in increasing sales value and new customers and maintaining existing customers by offering highly accurate strategy segmentation.
#DataMining #CustomerBehavior #StrategySelectionSegmentation #IndustrialPartManufacturer #kMeansClustering #DBSCANClustering
The main objective of the present study is to explore the relationship among factors of talent value proposition namely organization branding, talent branding and employer branding, talent management process and high-performance working systems (HPWS). Therefore, the data of the present study was collected from the IT personnel who are employees in the bureaucratic organization of Thailand. The data of this study was collected through questionnaires by using stratified random sampling. The usable response rate was 63.2%. The gathered data was analyzed using structural equation modelling (SEM). The findings of the study point of that TVP factors namely organization branding, talent branding and employer branding play significant role to develop TMP that later impact HPWS. This study also confirms the mediating role of TMP as well. The findings of the present study can be used by the policy makers and practitioners for the practical implementation of talent management practices so the high-performance working systems can be enhanced to increase the employee commitment. This study also discussed the limitations and novelty in detail.
#BureaucraticOrganization #InformationTechnologyPersonnel #OrganizationManagement #TalentManagement
The objective of this study is to examine the role of HRM and supply chain to promote business performance (BP) sustainability in Thai textile firms. Meditating role of employee skills and raw material is examined. Therefore, the relationship between HRM, supply chain, employee skills, raw material and BP sustainability was examined. Population of the study is textile firms of Thailand. Employees of these textile firms were selected as respondents. 300 questionnaires were distributed among the textile firms of Thailand. Results of the study shows the positive role of HRM in BP sustainability. Better practices of HRM have the ability to promote BP sustainability. HRM has a positive role in employee skills development which further enhances BP sustainability. Moreover, supply chains in textile firms also play a major role to promote BP sustainability. Better supply chain increases the availability of raw material which causes BP sustainability.
#HumanResourceManagement #SupplyChain #EmployeeSkills #RawMaterial #BusinessPerformance #Sustainability
In the current global situation, which is the high pace for every business and organization, talent management is critical for the organization, particularly the bureaucratic organization, which is vast in size and broad in its chain of command to survive in the digital transformation era. The purpose of this study was to examine the relationship between talent management processes (TVP), talent value propositions (TVP), and high-performance working systems (HPWS), as well as the mediation effect of talent management processes on the effect of talent value propositions on high-performance working systems. Through an online survey, data were collected from 365 information technology talents in Thailand's government organizations and analyzed using structural equation modeling (SEM). The results indicate that both talent management processes and talent value propositions positively affect high-performance working systems. That talent management processes have a strong mediating effect on the effect of talent value propositions on high-performance working systems, which will be the primary force propelling the organization forward during the digital transformation era.
#HighPerformanceWorkingSystem #MediationEffect #TalentManagementProcess #TalentValueProposition
The number of deaths from diseases related to smoking is 11.6% of all Thai populations. So helping smokers to quit smoking cigarettes is one of the essential tasks of the medical personnel. This research developed a hybrid prediction model to support decision-making in the medical treatment of smoking cessation, which consists of medication decisions, the likelihood of three-month and six-month quitting, and medication choices using the data mining process. This research collected the treatment data from Thai Physicians Alliance Against Tobacco between 2015 to 2017 and was processed by data selection, data cleansing, data transformation, data resampling, and comparative experiments. Overall results were over 70% accuracy based on gradient boosted trees and neural network based on evolutionary parameter optimisation and ten-fold cross-validation evaluation method. Finally, the findings from the study would be beneficial to health personnel in making clinical decision support for better coverage of treatment for smokers.
#SmokingCessation #DataMining #PredictiveModelling #GradientBoostedTrees
Admission Systems around the world are different in characteristics and processes. In Thailand, five different admission rounds affect admission strategic planning, students, and universities. This research proposes the course performance prediction and optimization to predict student performance data and find the optimum criteria for recruiting students in each engineering major respected for the undergraduate engineering program's admission round. The research use data from undergraduate students in an engineering faculty in Thailand during 2018-2020. The data preparation methods, such as missing value handling, feature generation, and correlation analysis for each course, are used. Predictive analytics aims to predict three engineering courses' average course grades using the Generalized Linear Model, Deep Learning, and Gradient Booted Tree. The model is evaluated by using Relative Error, Root Mean Square Error, and Absolute Error. Gradient Boosted Tree outperforms the other algorithms, which are 0-0.4% relative error. Prescriptive Analytics is consequently used to optimize factors to get the optimum students to the faculty and major by using evolutionary optimization algorithms. This model is used to optimize decision-making in Admission Strategic Planning of an engineering faculty by optimizing students' number in each major and admission round.
#AdmissionStrategicPlanning #DataScience #CoursePerformance #PredictiveAnalytics #PrescriptiveAnalytics
In the era of disruptive change, a data-driven approach is vital to Human Resource Management (HRM) of any leading organization, for it is used to gain a competitive advantage. HR analytics (HRA) has emerged as innovative technologies since advanced analytics, i.e., predictive or prescriptive analytics, were widely used in the High Performing Organizations (HPOs). Therefore, many organizations elevate themselves to become HPOs through Data Science on the “people side.” This paper proposes a systematic literature review using the Literature Weighted Scoring (LWS) to develop a conceptual framework based on three adoption theories, which are the Technology-Organization-Environment (TOE), Diffusion of Innovation (DOI), and Unified Theory of Acceptance and Use of Technology (UTAUT). The results show that a total of 13 theory-derived factors are determined as influential factors affecting HRA adoption, and the top three factors are “Quantitative Self-Efficacy,” “Top Management Support,” and “Data Availability.” The conceptual framework with hypotheses is proposed to provide a foundation for further studies on organizational HRA adoption.
#HRAnalyticsAdoption #InnovationAdoption #TOEFramework #SystematicLiterature Review #WeightedScoring
The single housing industry is currently experiencing a continuous expansion in demand for housing. Addressing the needs of different customer groups is the key to increasing the sales rate. The objective of this research is to propose a single house customer journey analytical model that consists of two stages. The first stage concerns the customer journey between registration and reservation processes. The second one identifies the customer loyalty from the reservation to the transfer stage. We experimented with four classification data mining techniques. The experimental results include comparison of the accuracy and F-Measure. We also performed statistical testing. The Artificial Neural Network was the most accurate model for both stages. This model analyzes the probability of the customer progressing through the stages to the conclusion of purchase by learning the customer’s characteristics and the factors involved in the customer’s decision. The model displaysthe reservation and transfer result for customers who have achieved the respective reservation and transference steps according to their registration profile. Experiments showed that the proposed two-stage models could predict customer loyalty, thereby enhancing relationship management between customers and organizations. It also confers a competitive advantage within the industry.
#RealEstate #CustomerRelationshipManagement #CustomerJourney #DataMining #SingleHouse
This paper presents the data mining process that was used for building a stroke prediction model based on demographic information and medical screening data. The data that was gathered from a physical therapy center in Thailand comprised of outpatients’ medical records, medical screening forms, and a target variable. A group of 147 stroke patients and 294 non-stroke individuals with six demographic predictors were selected for the study. Three classification algorithms were used in the study. These were; Naïve Bayes, Decision Tree, and Artificial Neural Network (ANN). They were used to analyze the data collected and the results were compared. They were evaluated by use of a 10-fold cross-validation method. The selection criteria were primarily measured by accuracy and the area under ROC curve (AUC). The secondary selection criteria were indicated by False-Positive Rate (FPR) and False-Negative Rate (FNR). The results showed that the best performing algorithm that was studied was ANN combined with integrated data. This approach have an overall accuracy of 0.84, an AUC of 0.90, a FPR of 0.12 and an FNR of 0.25. The results of the study demonstrated that ANN with the integration of demographic and medical screening data produced the best predictive performance compared to the other models. This result was found according to both the primary and secondary model selection criteria.
World Health Organization (WHO) reports that coronary heart disease (CHD), one of the non-communicable diseases (NCD), is the leading cause of death around the world. The main risk factors are mostly medical factors such as hypertension, diabetes and physical inactivity. This research proposes new additional factors including economic and environmental factors to create a predictive model of coronary heart disease in global aspect using data mining process. The based medical risk factors and new blended variables were reviewed from WHO report and some reliable related research. The historical data were collected from public health organization reports. The classification techniques used to predict for the prevalence of coronary disease were experimented by several techniques. The finding of this research showed that the decision tree algorithm provided the best classification model, and gradient boosted tree algorithm provided the best regression model. The most important factor of the decision tree model was an average income per household. The result of this research can present a risk of CHD on visualization to support the management of medical resources.
Max Weber’s bureaucratic theory has been one of the most powerful and well known practical method for the organization for a very long time. Since the globalization, the world has changed the way of doing business, especially in the cultural and human resources for organizations. While facing the pressure from the practice in digital transformation era, the bureaucratic organizations still working in the paperwork could not suddenly transform into the other business practice based on digitization. This paper will discuss how the bureaucratic organizations in the digital transformation era are doing and how they can survive by the talent management (the better human resource) to improve the organization’s working efficiency.
The objective of this research is to review the data governance aspects, especially the use of open data law in different countries including USA, Republic of Korea, and Thailand. Currently, a draft version of Thailand Open Government Data Law is based on Data Governance Framework and Components from Data Governance Institute (DGI). This comparative study could be a guideline for both legislators and government to refine some aspects of law suitable for the context of Thailand.
Diabetes is a chronic disease that increases the risk of developing a number of serious health problems, and still requires the expensive prolonged treatment throughout lifespan for inpatients. The diabetes inpatients should receive the appropriate treatments in order to reduce the rates of both severe complications and premature mortality. This research aims to develop the classification model based on medical record of diabetic inpatients for medication adjustment, by applying the control chart patterns into an Artificial Neural Network (ANN) as a feature extraction process. This research is extended from the previous work which proposed the comparison between the Independent Dose Titration Model (IDT) and the Historical Dose Titration Model (HDT), especially for the Insulin, the lowest performance drug type. The results of this paper could support the decision making in medication adjustment for diabetes inpatients, particularly type-2 diabetes inpatients.
In this research, an identification system is proposed for the benefit of determining a possible sentence and retrieving the related cases under criminal law codes of Thailand. The system is based on the developed criminal law ontology for the advantage of structuralizing and semanticizing in selected articles. From the underlying legal elements described in law codes textually, the ontology shall provide the determination of possible sentences which consist of judgment and theoretically figured range of punishments. An application has been designed and demonstrated in two consequential modules: the legal elements identification and the sentence identification. The developed ontology and its extended web application will be shown and illustrated as a sequential flow and evaluated by the legal experts and the end-users. The evaluation results showed that the averaged satisfactions for both groups of experts and end-users were 89% and 84%, respectively.
The main objective of education is to offer the best quality of life to the student. One way to achieve the best quality of life is to reduce and improve adolescent problem by discovering knowledge for providing the problem factors to the institution. In this research, the knowledge is extractable through student database. The decision tree data mining technique is used to build six adolescent students behavior models and to provide an overall accuracy of 90%. Six classification models are constructed based on risk behavior groups, and are then used to create student behavior guideline to support teacher decision making.
This paper applies the association rules method to discover the relationship between metabolic syndrome and its chronic diseases. The sample data used in this research is medical records specified to metabolic syndrome patients in a large government hospital. The Apriori and FP-Growth algorithms are chosen to be compared in the performance and applicable results of extracting the relationship of the metabolic syndrome patient records represented by ICD-10 code. The results show that the Apriori can extract 6 rules and 724 rules from FP-Growth. The comparative results between Apriori and FP-Growth found that 6 rules are common. The overall results show that the metabolic syndrome patients mostly have strong relationships with hypertension, obesity and diabetes. Interestingly, these diseases often occur with the patients was diagnosed that was metabolic syndrome. Additionally, the results would bring to the suggestion in metabolic syndrome patients to know about the relationship of these chronic diseases. Moreover, the physicians could use this guide for the treatment strategy in the future.
This paper focuses on the text mining approach of the gold prices volatility prediction model from the textual of economic indicators news articles. The model is designed and developed to analyze how the news articles influence gold price volatility. The selected reliable source of news articles is provided by FXStreet which offers several economic indicators such as Economic Activity, Markit Manufacturing PMI, Bill Auction, Building Permits, ISM Manufacturing Index, Redbook index, Retail Sales, Durable Goods Orders, etc. The data will be used to build text classifiers and news group affecting volatility price of gold. According to the fundamental of data mining process, each news article is firstly transformed in to feature by TF-IDF method. Then, the comparative experiment is set up to measure the accuracy of combination of two attributes weighting approaches, which are Support Vector Machine (SVM) and Chi-Squared Statistic, and three classification algorithms, which are the k-Nearest Neighbour, SVM and Naive Bayes. The results show that the SVM method is the most superior to other methods in both attributes weighting and classifier viewpoint.
This paper proposes a loyalty measurement model of individual customer for the benefit in creating of marketing campaign and activities as well as the suitable products and services for customers and establishment of good customer relationship. This study adapts the concept of RFM (Recency- Frequency-Monetary) model and applies to database of customer purchases and the customer type. The business type of selected organization is commercial business. To apply the RFM concept to find customer loyalty according to type of customer, the customer loyalty is partitioned into 5 classes using k-means clustering algorithm and is heuristically assigned customer types: Platinum, Gold, and Silver. Type of customers is then brought into consideration the extending of the RFM Model with customer analytics to make it even better customer classification performance. Finally, the classification system generates decision rules to find out the loyalty of new future customers using C4.5 decision tree algorithm.
Customer Relationship Management (CRM) is critical and essential to such organization, especially to the large scale organization since its involved customers may be covered to the people, citizen, organization or government sections. Anyway, according to the nature and culture of the traditional job design, their business processes are costly and inconsistent because of their actor (or department) oriented design which leads to the difficulties in improvements. This paper proposes an idea of improving the business processes, based on Business Process Improvement (BPI) concept in function-oriented, to solve the existing work problems and suggest the possible solution for the future to achieve the organization goal. The evaluation was done by both the officer and the executive.
This paper proposes an identification framework of the possible criminal offences charges based on textual criminal cases of the Civil Law system. The framework is constructed as the model, devised as a multi-stage based on the defined charges structure in criminal law codes. The first stage is to modularly identify type of action which is designed based on the offences charges abstractly categorized by defined criminal elements. The second stage is to identify the additional legal elements, leading to general provisions which may affect to the sentence or amount of punishments. This classification stage is designed as multiple autonomous classification system. The integrated model is expected to be able to categorize charge type and provisional legal elements and to predict the final possible sentence and range of punishment. An evaluation aims to achieve high accuracy of classification while reserving explainable results, which is required in an application of legal domain.
A two-stage classifier is proposed that identifies criminal charges and a range of punishments given a set of case facts and attributes. Our supervised-learning model focuses only on the offences against life and body section of the criminal law code of Thailand. The first stage identifies a set of diagnostic issues from the case facts using a set of artificial neural networks (ANNs) modularized in hierarchical order. The second stage extracts a set of legal elements from the diagnostic issues by employing a set of C4.5 decision tree classifiers. These linked modular networks of ANNs and decision trees form an effective system in terms of determining power and the ability to trace or infer the relevant legal reasoning behind the determination. Isolated and system-integrated experiments are conducted to measure the performance of the proposed system. The overall accuracy of the integrated system can exceed 90%. An actual case is also demonstrated to show the effectiveness of the proposed system.
A knowledge discovery model has been developed to manage the facts discovered in criminal cases in the court of law and to identify the relevant diagnostic issues. This study focuses on the offence against life and body section of the criminal law codes of Thailand. To identify the criminal case diagnostic issues, a set of artificial neural networks (ANN) classifiers is heuristically configured and modularly organized to operate upon the discovered facts. This modular network of ANNs forms an effective system in terms of determining power and ability to trace or infer the relevant reasoning of such a determination. Experiments have been conducted to demonstrate the applicability of ANN for various case studies and to generate comparative results for providing insights into both technical and legal aspects of these cases. In this study, a modular ANN with the support of Principal Component Analysis (PCA) as an automatic input selection mechanism provided the best results with accuracy up to 99%, using 10-fold cross-validation. A sample case is included to illustrate the effectiveness of the proposed system.
This paper proposes a framework to identify the relevant law articles consisting of sentences and range of punishments, given facts discovered in the criminal case of interest. The model is formulated as a two-stage classifier according to the concept of machine learning. The first stage is to determine a set of case diagnostic issues, using a modular Artificial Neural Network (mANN), and the second stage is to determine the relevant legal elements which lead to legal charges identification, using SVM-equipped C4.5. The integrated multi-stage model aims at achieving high accuracy of classification while reserving “arguability”. Hypothetically, mANN handles well for digesting complexity in case-level issues analysis with acceptable explanatory power and C4.5 addresses the lesser extent of contingency and provides human-interpretable logic concerning the high-level context of legal codes.
This paper proposed a developed graphical user interface (GUI) prototype, which is supported by the framework of data mining techniques-based criminal judicial reasoning system. The GUI sequences of the prototype are satisfied with criminal judicial procedure in civil law system. Initially, user must build the model by input the existing incident and specifying the detail of objects, elements of crime, charge and judgment. After enough training, the prototype will be ready to determine judgments from new occurred incidents. The prototype shows only the results of each module which help in the decision process. This GUI prototype is useful with lawyers, courts or other people who want to determine the guilt, charges and judgments in their incidents.
CORONA VIRUS 2019, also known as COVID-19, began to spread in December 2019. The first affected covid-19 person was found in Wuhan district, China, then COVID-19 impacted worldwide, including Thailand. This research uses the Data Mining technique by applying the Association Rule to understand customer behavior in people who buy orchid pots during the first coronavirus pandemic in Thailand. This study applies to the database of customer purchase transactions who buy orchid pots. This research adopts the FP-Growth model to understand the groups of products customers typically buy. Finally, the Association rule generates seven rules of orchid pot types that customers purchase in the same basket. Each rule shows Confidence, Lift, and Conviction range from 0.833 – 0.857, 2.629 – 5.602, 4.098 – 5.929, respectively. This study also deployed Predictive modeling by utilizing the Generalized linear model, Deep learning, Random Forest, and Gradient Boosted Tree. As a result of the Predictive model, Gradient Boosted Tree without Auto feature selection and feature extractions methods produce the lowest relative error at 15.2%. The association rule finds an orchid pot that customers purchased one of the items in the group. The expected result of this study is that orchid entrepreneurs can adopt this outcome from Association Rule and Predictive Modeling Analytics when a problematic situation similar to the COVID-19 pandemic happens again.
#AssociationRule #PredictiveModeling #OrchidPots #Covid19 #CustomerBehavior
Sepsis and Septic shock are the major health problems that effect to more mortality rates of patients in Thailand and worldwide including Ratchaburi Hospital. It’s the big government hospital in Thailand and it has sepsis and septic shock patients approximately 6,697 cases. We applied the data mining to create the prediction model of patients who are survival and create decision rules for help the doctor to decide about discharge status of sepsis and septic shock patients who have surgery or procedures and compare the various methods are Naive Bayes, Logistic Regression, Deep learning, Decision tree and Gradient Boosted Trees. The results showed Gradient Boosted Trees is the highest performance but Decision tree is the method that simple to understand and not complicated more than Gradient Boosted Trees and the performance of Decision tree is slightly different between highest performance method. So, we choose the model of Decision tree to create rules for decision making followed by the objectives of the research. The results of this research maybe increase the efficiency of preoperative risk assessment and it maybe decrease the mortality rates including the doctor can make effective decisions before discharge that maybe effect to lower re-admission.
This academic article presents Human Resource Analytics (HR analytics) in several aspects which are: evolution, element, lesson learnt, and future trends. Our study base on research and academic articles from reliable sources. Nowadays HR analytics has essential roles to link between HR activities and business outcomes. This study found that HR analytics process has continuous improvement, and many organizations primarily invest in HR analytics that adds value to themselves. Many organizations have been shifting Human Resource from an Inside/outside (Inside Out) to an Outside/inside (Outside In) approach, so they have been making HR practitioner as a professional and a business partner. The crucial factors are organizational structure and analytical skills that support HR analytics in the organizations and succeed. Finally, it is imperative that study and understands the lesson learnt, and the suggestions are change HR analytics from management fashion to management decisions. This article shows broader viewpoint of HR analytics, in-depth adaptation, and cooperate challenge.
This research aimsto create a correlation and predictive model for O-NET score level of sixth-grade students based on teacherand schoolcharacteristics to be used as a guide in planning and promoting the quality and the standards of education by the stakeholders. The models were experimented by the Neural Network based on the schools and teacher’s characteristics along with the O-NET scores of eight subjects. The characteristics included the teaching experience, graduated fields, size of the schools, and average scores for each school. The results showed that there was more than 80% accuracy for each subject. This could be proved by the selected variables affected the O-NET score level since they were not inter-correlated when measured by correlation matrix. This research could predict the O-NET Score with reasonable accuracy and could be applied to worked better results.
The oil and gas business isan important energy-related sector needed for high quality standard due to the safety of involving persons and environment. The business licensing is a process which is legally regulated to control this standard.Thus, they are supervised by the regulator andperform according to the law. Currently,the oil and gas business licensing service is runningbased on the complex and redundantprocesses, conditionsand procedures.It consists ofvariousdocument forms, several servicechannels,and manyredundantproceduresupon the business characteristicand causes the difficulties for the officers and regulators to proceed the business in time. This also leadsto the waste of time in work process and low performance in the organization.According to mentioned situation,this paperproposes the design and evaluation of business and information architectureblueprintbased on the concept of the enterprise architecture concept.The blueprint is evaluated by simulated situations and the results show that it can reduce theoperational time and redundancy.
#EnterpriseArchitecture #BusinessArchitecture #DataArchitecture
This study aimed to build a decision model in Information Technology (IT) Management curriculum enrollment based on attitude factors in social media usage. The samples used in this study consisted of 208 people who are studying or interest in IT-related fields such as Computer Engineering, Computer Science, Information Technology, Information Technology Management, etc. The data from the questionnaire was pre-analyzed to discover the relationship between attitude factors and enrollment decisions. Consequently, the decision model based on the Decision Tree was built to plan the admission strategies. This model was built from four factor groups: demographic factors, education factors, media awareness factors, and attitude in social media factors. A set of decision rules obtained from the model was applied for the effective strategic planning of new student enrollment via social media. The results of the public relations showed that a number of enrollees were superior than the traditional and non-strategic methods.
Due to inadequate domestic crude oil production, Thailand must import crude oil from other countries. Following the Alternative Energy Development Plan (AEDP), Thailand has incorporated biofuels as a blending component in fuel production to mitigate oil price fluctuations. The primary feedstocks used are food crops, which raises concerns about the potential impact on food prices due to biofuel production. Therefore, this research study examines the correlation between biofuel production and food prices in Thailand during the monthly period from March 2017 to December 2022, using wavelet analysis to identify high and low-frequency movements, representing short-term, mediumterm, and long-term effects. The findings indicate empirical evidence for a significant correlation between biofuel production and food prices in the short term. These outcomes benefit energy policymakers in designing appropriate policies and offer valuable insights for shaping sustainable energy in Thailand's future
#BiofuelProduction #FoodPrices #OilPrices #WaveletAnalysis #ContinuousWaveletCoherence
This study underscores the importance of standard data analytics governance within organizations to leverage the potential of increasing volumes of big data. Even though Thailand has operative frameworks for data governance and AI governance, there lacks a concrete framework specifically for analytics governance. To fill this void, the research utilizes the Data Governance Framework from the Digital Government Development Agency (DGA), the Artificial Intelligence Governance for e-Business and Digital Services from the Electronic Transactions Development Agency (ETDA), and the Data Management Capability Assessment Model (DCAM) within the Analytics Management section. The design and evaluation of the analytics governance framework are carried out using feedback from experts via a questionnaire. The ultimate objective of this study is to pinpoint the relevant components necessary for formulating an analytics governance framework in organizations in Thailand, which have already implemented data governance.
#AnalyticsGovernance #DataGovernance #AIGovernance #DataManagement
Data has become a crucial element powering the fourth industrial revolution, making it more important than ever for employees at various organizations to be able to work with data. The value of data literacy is rapidly increasing across the globe. According to Forrester's research, by 2025, approximately 70% of employees are expected to work extensively with data, up from only 40% in 2018. Organizations that integrate data literacy into their workplace culture will have a competitive advantage in the increasingly complex global economy. Therefore, The Objective of this study is to develop a data literacy framework that covers all job positions for government officers in Thailand. This will be based on a gap analysis from international data literacy standards and national digital literacy standards to enhance the data skills of government officers. Additionally, required courses and related skills will be analyzed and synthesized from various frameworks with international standards on digital and data skills, and a gap analysis will also be performed to identify the most suitable data knowledge framework for government agencies.
Personal data is used to define customer requirements. Organizations should securely collect and process such data, using data protection policies aligned with the applicable regulations. The General Data Protection Regulation (GDPR), an EU data protection law, has include a data protection assessment method called Data Protection Impact Assessment (DPIA) to ensure personal data security. The maritime industry is also concerned about personal data protection. However, there is a still a lack of practical methods to assess data protection risks. This article aims to introduce the conceptual framework for a new method for risk assessment in maritime systems, using DPIA and various systems-theoretic risk approaches as a conceptual basis. The ICT system is a central system in which personal data is utilized in the architecture of maritime systems. In this article, this system will be taken as a basis for illustrating the newly proposed method for personal data security risk assessment in a DPIA context. The conceptual framework will be further concretized and tested in follow-up research.
#DataProtectionImpactAssessment #MaritimeIndustry #BridgeAutonomous System #RiskAssessment #RiskManagement
The epidemic situation of the Coronavirus Disease 2019 (COVID-19) and the measures to control the spread of the disease that the government enforced have greatly affected the daily lives of Thai people because they must suffer various pressures, stress, and anxiety. For this research, the researchers compared the anxiety caused by the novel coronavirus disease 2019 (COVID-19) between the UK and Thailand to see if they are similar or different. In sentiment analysis, the collection of data comes from the discussion on the web forums. In this research, the researcher used information from pantip.com to collect topics related to coronavirus disease 2019 and disease control measures from the government from March 2020 to May 2020. It was found that 10,746 available thread titles were extracted from all topics, and the first collected threads were then re-checked to see if their content could be used for further analysis. The chosen topics were analyzed by counting words that expressed various emotions. Thailand's information will use the AI for THAI platform, which provides artificial intelligence (AI) services under the concept of "Thai AI" by extracting emojis to express emotions that will be converted into words. The results found that Thai people responded most emotionally to the matter in a sad mood. The results are compared with the UK data, including a sample of 2,500 people living in the UK, by having respondents write a short text and a long text of 5,000 examples of how they felt about the epidemic situation and government measures at that time. Emotions were extracted through the LIWC technique, and the results showed that most of them had more anxiety than other feelings, which were different from those in Thailand. However, most of the sorrows and worries influence jobs and incomes in both countries, but in Thailand, debt is another factor that causes more sadness than just worry. According to this research, researchers consider it essential to study and analyze people's emotions to know the impact on people's emotions, which may affect their lifestyles when faced with other serious disease outbreaks in the future. The agency or organization can use this information to plan and adapt the measurements to have the least impact on people's mental health.
#COVID19 #SentimentAnalysis #Pandemics #AnxietyDisorders #Government #BiomedicalMeasurement #TimeMeasurement
Recommendation systems are rapidly gaining popularity in software development, including e-commerce, news, advertising, social networking, and entertainment. It filters appropriate information for user decisions. The most popular approaches of recommendation systems are content-based and collaborative filtering-based, which are created as a model by using user preferences and providing recommendations. Additionally, the hybrid approach is proposed to improve recommendations typically by combining the advantages of two techniques to increase efficiency and prediction performance. However, general recommendation systems typically abandon users’ contextual preferences such as culture, emotions, and other details in different situations. Researchers are attempting to apply knowledge from other scientific fields to improve the performance of their recommendation systems. Psychology is one of approaches that can be applied to understand and explain humanity and shows that emotions influence decision-driven, efficient, and predictable. This paper reviews relevant research analyzes state-of-arts, gaps, and further recommendation system research based on emotion. We find that most of the selected research use sentiment data extracted from open data sources and social networks. As for the data extraction and data analysis depend on data sciences and statistics theory, and Cold start is still a challenge for researchers. However, we find that the data from social media reaction can compare with the emotional wheel in psychology and present emotion as more complex than sentiment. Future research on an individual recommendation system will bring the complexity of psychological emotion into improving the system.
The student performance monitoring process is essential because it can rapidly help students who have problems studying before they fail during the semester, causing them to be retired and impacting institutes. Thus, this research was conducted to analyze student performance toward the admission system to predict student probation status respected to other factors before ending the semester to help students. The research also conducted prescriptive analytics to optimize factors that may impact students' probation status using the evolutionary optimization algorithm. This analytics aims to generate an action plan for monitoring student characteristics that may fail and improve the educational process and support admission strategic planning before recruiting students. The five machine learning algorithms are used in the research consists of Logistic Regression, Deep Learning, Decision Tree, Random Forrest, and Gradient Boosted Tree. The model that gives the highest accuracy is GBT, which gives 96.2% and is chosen to use in prescriptive analytics, giving the action plan for the institutes.
#DataScience #ProbationStatus #PredictiveAnalytics #PrescriptiveAnalytics #Higher Education
The General Data Protection Regulation (GDPR) has been enforced since May 2019 and became a disruptive issue to every organization due to its severe penalties in the data breaches or use of personal data for illegal purposes, e.g., lack of the consent of data subject. Therefore, the data Pseudonymization and Anonymization are one of the employed techniques to protect and reduce the privacy risks from the data breach. Unfortunately, they also destroy the pattern of the data, which represents the fact that it could be analyzed or monetized to gain useful insights by data analytics or data science approaches. This paper focuses on optimizing the privacy and insight method that the data could be useful for analyzing and also compliance with the GDPR. This paper proposes the guideline consists of three techniques: tokenization, suppression, and generalization to protect personal data by calculating risk scores from two methods: data classification and data uniqueness. The criteria in the guideline are experimented to achieve the optimized classification performance in protected data compared with five original open data by analyzing with three data mining algorithms with the hyperparameter tuning process. The results show that the protected data by the proposed guideline can protect adequate information and achieve insignificant classification performance when compared to the unprotected data.
Major Depressive Disorder (MDD) is one of the most significant medical problems. The total number of people living with depression in the world is more than 300 million. Nowadays, people use social communities to communicate with each other and express their mindset and emotion that are the sign of depression sealed under their feelings and could be the cause of suicide. This research proposes a two-stage predictive model for major depressive disorder risk screening assistance by using emotion values based on textual data from social community. The contents from social community are identified six emotional dimensions; angry, bored, excited, fear, happy, and sad. These emotions are then categorized into emotion-based clusters using DBSCAN algorithm and examined by medical and psychological experts with Patient Health Questionnaire-2 (PHQ-2). The labeled clusters is used to train and optimize classification model for each screening question with several algorithms; Decision Tree (DT), Random Forest (RF), and Gradient Boosted Tree (GBT). The experimental result shows that the GBT is the best model for Q1 and the RF is the best model for Q2 with 98.32% and 99.98% accuracy respectively. This research will be beneficial in the further study in identifying depression from text-based emotion.
#MajorDepressiveDisorder #EmotionalAnalysis #SocialCommunity #PredictiveModeling #DataMining
Thai University Central Admission System (TCAS) is the university admission system used in Thailand since 2018 and has 5 admission rounds a year. The impact from TCAS to the universities is that the universities got the different level of student performance in each TCAS rounds. Data from several domains are fed into the system and would be beneficial for insights gaining towards process improvements or optimization. Data monetization is a framework to turn growing valuable asset such as data into currency or other benefits to the organizations. The purpose of this paper is to demonstrate data monetization value chain for applying data analytics to improve university admission process under TCAS and use the case from universities in Thailand as a case study.
#DataMonetization #EducationalProcessImprovement #AdmissionProcess #DataAnalytics
Data Governance for open government data is a significant process which defines the roles and responsibilities of the person in charge of data management in a government agency to gain the open government data and to use it correctly, ensure the security of personal data including defining the standardization of data, consistency and effectively link and use open data between the agencies. Many countries have already considered data governance and dissemination of open government data to the citizen imperative. Although Thailand has prescribed a draft of public information act, data governance for government data is still unclear. Hence, this research proposes a conceptual legal framework for open government data in data governance aspects. The results of preliminary studies from the previous research are used in this paper including gap analysis and compare results between Public Information Act of the United States of America, the Republic of Korea and the current draft of Public Information Act of Thailand. The coverage issues are on the organizational structure, organizational roles, and responsibilities of Public Information Committee. The proposed amendments is applied in the current draft of the Public Information act for Thailand. This includes defining the standardization and security on open data by taking the existing data governance framework as a guideline for determining the procedures and compliance according to the data governance framework for Thailand.
Material requirement planning is an essential role of a manufacturing business. Manufacturers need to find an effective way to manage material planning among the changes. This research is designed to create an integrated model of time series purchasing forecasting model and customer segmentation model in electrical equipment procurement for risk assessment and prescriptive model building. The methods used for forecasting are compared between Gradient Boosted Tree (GBT), Artificial Neural Network (ANN) and Decision Trees (DT) while the K-Means Clustering is selected to segment customers optimally. Henceforth, customers can be classified into three groups; Good, Moderate and Normal. The results of both methods are then used to generate a risk assessment matrix. Finally, the researcher analyze with the prescriptive analytics driven by the evolutionary optimization method to create a strategy and allocate parts which align to customer behaviour and according to the company policy.
#DataScience #PrescriptiveAnalytics #PredictiveAnalytics #DescriptiveAnalytics
Max Weber’s bureaucratic theory has been one of the most powerful and well known practical method for the organization for a very long time. Since the globalization, the world has changed the way of doing business, especially in the cultural and human resources for organizations. While facing the pressure from the practice in digital transformation era, the bureaucratic organizations still working in the paperwork could not suddenly transform into the other business practice based on digitization. This paper will discuss how the bureaucratic organizations in the digital transformation era are doing and how they can survive by the talent management (the better human resource) to improve the organization’s working efficiency.
The objective of this research is to review the data governance aspects, especially the use of open data law in different countries including USA, Republic of Korea, and Thailand. Currently, a draft version of Thailand Open Government Data Law is based on Data Governance Framework and Components from Data Governance Institute (DGI). This comparative study could be a guideline for both legislators and government to refine some aspects of law suitable for the context of Thailand.
Smoking in Thailand has tended to rise. The study on the burden of disease from risk behavior in Thai population revealed the number of deaths from diseases related to smoking is 11.6 percent of the total death. Successful smoking cessation is considered to be difficult. Helping smokers to quit smoking is an important duty of medical personnel whose roles to treatment. The two treatment options are pharmacological treatment and non-pharmacological treatment. In this research, the data provided by clinics participating in the smoking cessation program under the Thai Physicians Alliance against Tobacco (TPAAT). This paper aims to develop the classification model for prescription drug to smoking cessation based on personal health record by applying these algorithms; Decision Tree, Random Forest, k-Nearest Neighbor, Artificial Neural Network with multiple hidden layers.Finding from the study is beneficial for health personnel to make clinical decision support for the better coverage of treatment for smokers.
World Health Organization (WHO) reports that coronary heart disease (CHD), one of the noncommunicable diseases (NCD) is main causes of death around the world .The main risk factors are mostly medical factors. This research proposes a new additional factors by blending economic and environmental factors to create a predictive model of coronary heart disease using data mining process. The based medical risk factors and new blended variables were reviewed from WHO report, related research, and experimental economic factors. The data were collected from public health organization reports. The classification techniques used to predict for the prevalence of coronary disease are compared between linear regression, neural network, polynomial regression and Support Vector Machine. The model was measured a relative error to identify the best model. The result of this research can present a risk of CHD on visualization to support the management of medical resources.
This study led the ETL process (Extract-Transform-Load) to manage data valid and appropriate for water use in the development of breast cancer risk prediction model based on non-cancer drugs use data. Starting with the extraction of data from multiple large databases, and selecting only the required data and transforming the data into a form that can be used cleaning, joining, mapping, filtering and finally loading to data warehouse. In the future, if the database management system has the same storage format and all data is merged into a centralized database, it will make the data utilization to beeasier and faster.
At the presents, the justice in criminal cases are significantly involved by several domain of stakeholders in the process. Those stakeholders include the police, investigative staff, the Forensic Science Institute, the Office of the Narcotics Control Board, justice court agent, the Department of Corrections, the Department of Juvenile Observation and Protection, the Department of Probation, and the Department of Rights and Liberties Protection. The process of each aforementioned cooperative sector consists of a process of evidence consideration, which is very important to trial and prosecution of the offender and the rights of victims in the criminal justice system. In the present, however, the data transferring between each sector is ineffective due to the lack of unity of the structure, which varies in both document and digital data transferring. Thus, this leads to imbalance and misconnection in data exchange within sectors, and monitoring and management of the judicial proceedings. Nowadays, this undeniable not industry refuses to implement technology in their operation to improve their value and performance. Nevertheless, most of the data which could be beneficial are unstructured data due to the disruption of Big Data technology. Although, it is necessary to build an integrating paradigm for data architecture as the guideline to visualize and understand the process of data input and output from the source to destination, including the scope of accessing rights of the related units. This research would be beneficial for adding value, resolving data conflicts, and to the improvement of access to justice in the judicial process in a transparent manner in big data era.
The residential industry currently presents an expansion of demand in the residential which has been increasing in transference for 57. Against to step up to be Thailand’s top 5 property development companies there are strategic. Approaching to the needs of different customer groups is the key for enhancing the quality of customer’s life and delivering good things to the society. This paper proposes a neural networkbased customer retention model to predict the loyalty of customers. The proposed client prediction model consists of two stages including registration to reservation and registration to transference. A technique used in this research is the neural network with multiple hidden layers. The experiment shows that the proposed model could predict the willing of customers in reservation and transference achievement due to their registration profile.
Different types of internet attack have currently increased exponentially. One of internet attacks that have been used for many years is Phishing which affects to some internet users. This trend has caused an enormous scale of losses to victims. This research proposes the text classification and association system for analyzing phishing email contents based on the specified eight pre-defined features. The dataset of this study is provided by www.419scam.org. The classification model was created by the C4.5 Decision Tree method, and the FP-Growth algorithm was chosen for association model. The overall classification model performance is greater than 80% when the binary occurrence is used as an indicator. The decision-making rules are further analyzed facilitated by the association rules discovery method to determine the relation of features for creating the final phishing determination model. This research could help in analyzing email contents and determining whether there is a risk of them being phishing emails. In the future, it is therefore suggested the research should be extended to analyzing other email components such as the domain reliability and files attached in the email.
The purpose of this paper is to create a model for material requirement time-series forecasting model for electrical devices, regarding thematerialrequirement is core manufacturing business, and it consists of many raw materials which have different lead-time and condition to purchase. The paper used data collection (2016-2017) from Supply Chain Management Department, one of the electronic company in Ayutthaya. In this study, the Neural network and Linear Regression are utilized for time series forecasting. The researcher creates time series forecasting for MRP equipment by optimization. The results can be concluded Neural network provide the lowest relative error comparing to another method.
This research introduces a design of data architecture for procedures of sex reassignment surgery including social impact after the transition .By the theory of The Open Group Architecture Framework)TOGAF .(There are according to several organizations such as surgical hospital, health services agency for transsexuals, health insurance, government agencies and other related establishments .The purpose of regularizing a data of transsexual procedures for stakeholder can access data from the identical data center . Both centralized a data for psychiatric diagnosis, hormone replacement therapy, sex reassignment surgery and simplify data to gender recognition of transsexual citizen after the transition .Not only process of surgery, but also care procedures of social aspects .The results are planned to be evaluated in two ways, Expert Assessment and Scenario.
At the present, many dysfunctional family problems have been found in Thailand. Parallelly, the social network applications have become famous, especially in Thailand, and its addiction and adoption is very essential. Therefore, the objective of this research is the design of social network application framework to support the close-knit family. The solution of the proposed framework is based on Agile Project Management concept since it is an IT project management to support the frequency tracking work by daily and weekly which is expected to support and solve the family problems efficiently. The proposed framework was designed as the add-in functions into Facebook which aims to reduce the family problems from the previous study. The proposed framework is presented as mock-up video presentation and was evaluated by experts in IT, social science, psychology field and family expertise.
The oil and gas are the importance resource, energy, for alive. The fuel for transportation and electricity production. Thus, the oil and gas supplier must perform according to the fuel control law. The one method for control is the licensing. The oil and gas business must inform, register or permitted, upon the business type, before carry out. The condition and procedure of fuel business licensing, are complexity. There are variety forms format and several government authorities that provide licensing service separately. It is difficult to interconnect, data communicate and data collection for energy business statistic. Therefore, this paper studies as-is of the oil and gas business licensing and create the baseline of further enterprise architecture development.
At the present, the social becomes like an extensive globalization which are adapted for deterritorialization, interconnectedness between people, reducing velocity of human activities, cultural affect, politics, and economic. There are the innovation for digital economy in Thailand that using Information Technology to manage the economic leading to improve the management process. Among of available channels the social network applications such as Facebook, Line, Twitter, and Instagram had become famous nowadays. This research would like to study the factors which related between the family social and using social network applications via survey and discussion the result for virtual presentation. The survey was tested the validity and reliability before the public survey. The results from 450 respondents show that the top three of the dysfunctional family problems related to social network as a solution are asynchronous time, sharing idea, and spending time together.
Diabetes is a chronic disease that requires continuous treatment throughout lifespan and increased risk opportunity of developing a number of serious health problems, which are high treatment cost. Admitted diabetes inpatients should receive the appropriate treatment in order to reduce rating of severe complications and premature death. This research aims to develop the classification model for diabetic medication adjustment based on historical medical record of diabetic inpatients by applying control chart patterns as a feature extraction procedure and Artificial neural network (ANN). This research is extended and improved from the previous work which proposed the comparison between the Independent Dose Titration Model (IDT) and the Historical Dose Titration Model (HDT), especially for the Insulin which was the lowest performance drug type. The results of this paper could support the decision making in medication adjustment of diabetes inpatients, particularly type-2 diabetes inpatients.
Diabetes is a chronic disease that requires continuous treatment throughout lifespan and increased risk opportunity of developing a number of serious health problems, which are high treatment cost. Admitted diabetes inpatients should receive the appropriate treatment in order to reduce rating of severe complications and premature death. This paper aims to develop the classification model for diabetic medication adjustment based on historical medical record of diabetic inpatients by applying three algorithms; Decision Tree, Naive Bayes and Artificial neural network By comparison of the results of each method, Decision Tree is outperformed than others for Independent Dose Titration Model (IDT) dataset and Artificial Neural Network algorithm generated model with high accuracy and ROC Curve for Historical Dose Titration Model (HDT) dataset. The results of this paper could support the decision making in medication adjustment of diabetes inpatients, particularly type-2 diabetes inpatients.
Nowadays stroke is the third leading cause of mortality of all life periods. The statistics from the Office of the National Economic and Social Development Board (NESDB) between 1994 and 2013 found that the stroke caused 255,307 cases mortality. Period of treatment in stroke patients depends on symptom and damage of organs. It seems to be beneficial if the data analysis method likes data mining can be used to predict stroke disease to reduce amount of risk patients before initial disease. In this study, three classification algorithms: Decision Tree, Naive Bayes and Neural Network are used for predicting stroke which are model-based, superior to general statistics, and got a proper model for identification. The scope of data use is the demographic information of patients. This work was initialized by attributes selection, grouping, and resampling before modeling. This study uses the accuracy and area under ROC curve (AUC) as the indicators for evaluation. Decision tree is the most accurate and Naive Bayes is the best in AUC. The further research should also include patients' diagnosis.
Currently, the term “Fine Art” is on the verge of disappearing in Thailand. This is due to the influence of modern technology which has come to replace the old ways of Thai culture, especially in the sector of communication and the advancements of the internet. The knowledge of fine arts has suffered as a consequence to these advancements in technology and the World Wide Web. It is a very noticeable difference comparing the past and the present in terms of the knowledge of fine arts. The objective of this research is to create and develop ontology to help retrieval of knowledge regarding fine arts and present its semantic knowledge. The results of the study are that the entire class consisting of 51 subjects. There were also 11 relationships in the form of part-of, has-a, and has-is, and showed the benefits they have gained or not from this research. The base model of semantic knowledge of the fine arts is based on the concept of ontologies. Those who are interested in fine arts can be given access to knowledge of fine arts with more accuracy and it will be more comprehensive.
Customer Relationship Management (CRM) is the key management tools to gain sustainable competitive advantage and survive business among the intense competitive environment. Prior than planning and building up CRM strategies, the organization should prioritize customers into segment in order to properly manage relationship and provide services properly. This research aims to develop CRM strategies in case study; Chemical Industry by applying clustering techniques to segment customer, use Business Intelligence (BI) as the visualized tools to represent knowledge in various business dimensions and finally bring out CRM strategies to deploy in business. According to the customer data used in customer clustering, the RFM model was applied and added to the existing attributes. The clustering methods applied in this research are K-Means and EM algorithm. The clusters are generated and defined as 4 classes: Diamond, Platinum, Gold and Silver respectively. Each cluster is different in characteristic, but still not well interpreted enough to making decision without powerful presentation tools like BI. Finally, knowledge acquired from dimensional aspects in BI could lead to CRM strategies .The Organization could strengthen good relationship with individual customer and appropriately provide personalized products and services by based on customer segment.
#CustomerRelationshipManagement #DataMining #DataScience #BusinessIntelligence #DataVisualization
Nowadays, Transportation cost is one of the significant parts in the Business operation. This method will be able to reduce the expenses of the transportation especially the factors which consumed in this case it about the truck tires. This research proposes the prediction model for the worthiness of the truck tires into dimension of distance and last long. This research uses the technology of data mining, The Artificial Neural Network model and the Liner Regression Model as the selected classification algorithm. Acquired accuracies are 99.63% and 99.54% respectively for distance and lifetime to determine the worth. The integrated to reduce the cost.
Currently, the Big Data technology has been deployed in several and various business. Specific to the adoption of Big Data applications in recruiting, the goal is to find an efficient workforce which meets the organization's needs by consideration based on the factors of Big Data technology and affected factors of recruitment. The experts estimate factors that are related to the benefits of Big Data technology applied in recruitment. Then those benefits are then matched with the factors for Technology Valuation. This two-stage factor mapping is for finding the worthy values of Big Data technology applications. This paper proposes the study of factors in three domains; Big Data, recruitment, and technology valuation. Those factors are then used to construct a hierarchical model in the valuation of applying Big Data technology in recruitment section.
Facebook is a well-known social media in this century which allows people to connect and promote their life with others by its various features including posting and sharing text, photos or clips. Especially in the era of “Big Data”, its features become more intelligent. However, the advance of Facebook popularity does not solely come from its intelligent functions. This study ultimately proposes to analyze the function of Facebook relating to the understanding of Performance Studies in everyday life to investigate how people ‘perform’ themselves on Facebook and how Facebook functions support user’s demanding. More importantly, this study depicts how the Big Data and social computing context related to the social context has affected the rising number of Facebook users in the present. According to wide conceptions of Performance Studies, this study has mainly adopted theories of Erving Goffman’s, a sociologist, which emphasizes on a ‘self presentation’ in everyday life in order to theorize and explain presentation of self performed by Facebook users.
This study is conducted due to at present a technology that is popular among students is translation tool; Google Translate (GT). It can be used with sentence, article, or the whole page documents. However, the grammar of the translated articles by GT are often not correct, so the researcher chose the translation tool GT to study the attitudes and behaviors of the students and at the same time, study the translation skill of the students. The result of the study shown that among the representative sample, the objectives of GT usage are for learning and understanding the lessons. It includes translate the articles or sentences in order to understand the subject. The attitudes of these students towards GT are it is free of charge, easy to access, convenient, and the translation can be done quickly. However, once the translation tests were given to the students, it is found that those who use GT not so frequently have higher scores than those who frequently use GT. This leads to the conclusion that the use of GT does not have any effect on students’ skills, indicated by machine translation criteria, and higher quality in English translation.
The main objective of education is to offer the best quality of life to student. One way to achieve the best quality of life is reduce and improve adolescent problem by discovering knowledge for providing the problem factors to institution. In this research, the knowledge is extractable through student database. The decision tree data mining technique is used to build six adolescent students behavior models and provide an overall accuracy over 90%. Six classification models are constructed based on risk behavior groups and are then used create student behavior guideline to support teacher decision making.
The purpose of this paper is to apply the data mining techniques to discover and predict the recovery duration from physical therapy equipment usage patterns based on a classification system and establish selection rules of physical therapy techniques based on the association rule discovery method to support the decision making for physical therapists in the treatment of shoulder pain patients. The prediction system is driven by the usage patterns of physical therapy equipment and the association rule discovering method is applied for studying of the association in the amount of physical therapy equipment. The classification system is experimented and compared among the Naïve Bayes, Neural Network, and Decision Tree. The best result is 91.35% accurate. In addition, we present the association rule discovering method for study the association within equipment usage amount of physical therapy equipment. The best top five interesting rules are demonstrated. Both data mining applications of this research could support the decision making in the treatment of shoulder pain patients.
The paper presents a model for management classifier air quality by algorithm of decision tree using air quality index in Thailand including a pollutant's concentration e.g. O3, NO2, CO, SO2, PM10 and levels of healthy concern. The purpose of this research is to establish rules of separated air quality classification by levels of healthy concern. The results of this study are correctly classified into instances of training set of 96.80% and testing set of 91.07%. The ROC curve shows that the training set data and testing set data are similar to such results. The algorithm of decision tree can use to become rules of separated air quality classification by levels of healthy concern.
This paper proposes an identifying methodology of the relevant criminal offences charges, given textual information of the criminal cases in the Civil Law system. The model is devised as a multi-stage based on the criminal law codes. The first stage is to identify action types, using modular classifier. The modularity is designed based on the offences charges, which were abstractly categorized by elements of crimes in criminal codes. The second stage is to identify the legal elements, leading to general provisions. This classification stage is designed as independent multi-classifiers. The input data is preprocessed from text to features by some natural language processing methods. The integrated model aims at achieving high accuracy of classification while reserving explainable results, which is required in an application of legal domain.
Among of the travel agency business in Thailand, Agoda (www.agoda.com) has boomed in recent years with the number of online agents offering for hotels booking. When customers need to make decision, they typically explore by investigating the opinions attached with each hotel in online agent. This paper proposes a framework of feature-based opinion mining by using scores which essentially relies on the usage of two main lexiconizing levels, features and polar words. An approach for extracting features and polar words from textual opinion is based on syntactic pattern analysis. The evaluation is performed with existing opinions and compared the statistical resulted scores with the existing scores of each hotel. The proposed scoring method is proven for the effectiveness of the score from Agoda and could facilitate the further text retrieval application development for the benefit of automatic customer's opinion detection.
The measurements of performance for healthcare processing are important to healthcare system of the country, the accuracy of information makes the right decision for the leader who set a policies and strategies. According to the Health Promotion and Prevention strategies of The Ministry of Public Health 2011 shown that the major condition affected to Thai people's health are Diabetes Mellitus, Hypertension, Ischemic Heart Disease (IHD), Cerebrovascular Accident (CVA) and other injury. The processes of information analysis are started from compiling and collecting data. Beside, data cleansing and reporting must be also included in the process. Finally, the useful of accuracy KPIs will return its result to patients, healthcare unit, hospital and the Public Health.
The effective public security depends on the efficiency of the judicial process and procedure. Approaching to the supply chain management domain, the judicial procedures can be viewed as the complete stream sections. The legal agencies have also to deal with the information flow which need for integrating, interchanging and inter-cooperation among them. Anyway, the study in the intelligent system in the field of information technology, including data mining, is also consecutively studied and applied to various aspects in the legal domain. The study in this paper applied some of the existing technology and also suggests the possible application in intelligent judicial system. We then proposed a framework of the extension and integration for the intelligent judicial information system in Thailand. The designing methodology of this supply chain-core framework is based on the consistent cooperating of the information flow, the traditional and intelligent legal agencies.
In this study, criminal law ontology is developed to structuralize the selected parts of criminal law codes of Thailand for the benefit of semanticizing possible sentence identification and retrieval of the related cases. From the underlying legal elements which are textually described in law codes, this ontology shall enable the inference of the possible sentences which consist of judgment and theoretically figured range of punishments. For insights, an application has been designed and demonstrated in two modules: the legal elements identification and sentence identification.
This paper proposed a developed graphical user interface (GUI) prototype, which is supported by the framework of data mining techniques-based criminal judicial reasoning system. The GUI sequences of the prototype are satisfied with criminal judicial procedure in civil law system. Initially, user must build the model by input the existing incident and specifying the detail of objects, elements of crime, charge and judgment. After enough training, the prototype will be ready to determine judgments from new occurred incidents. The prototype shows only the results of each module which help in the decision process. This GUI prototype is useful with lawyers, courts or other people who want to determine the guilt, charges and judgments in their incidents.
One of the most complex legal activities in court level is judicial reasoning. Since Thailandpsilas civil law system initially judges with abstract rules and principles before apply them to various cases. This paper proposes a framework of criminal judicial reasoning system using data mining techniques as a knowledge discovery tool to determine reasons from court verdicts. Each module of the system is based on legal rules and principles that are used to construct computer-based knowledge by data mining algorithms. Thai criminal case Supreme Court verdicts in TCXML (Thai Court XML) format are used as training data set. This research benefits from the advantages of using XML standard in document structuring and supporting in judicial decision support system that guides the way in judgment supported by law theories and principles.
#DataScience #DataMining #CriminalLaw #ApplicationDevelopment
One of the most complex legal activities in court level is judicial reasoning. Since Thailandpsilas civil law system initially judges with abstract rules and principles before apply them to various cases. This paper proposes a framework of criminal judicial reasoning system using data mining techniques as a knowledge discovery tool to determine reasons from court verdicts. Each module of the system is based on legal rules and principles that are used to construct computer-based knowledge by data mining algorithms. Thai criminal case Supreme Court verdicts in TCXML (Thai Court XML) format are used as training data set. This research benefits from the advantages of using XML standard in document structuring and supporting in judicial decision support system that guides the way in judgment supported by law theories and principles.
Currently, the Big Data technology becomes a major focus of cyber world and is applied in various business sections which provide more opportunities to drive the business, including the recruitment section. The recruitment aims to find an efficient workforce which meets the organization's needs. This paper proposes a conceptual model for technology valuation to valuate applying of big data technology on recruitment section. The proposed model is presented in hierarchy and consists of the perceptional factors in big data, recruitment, and valuation domains. This hierarchical model is weighted by domain experts and then used to identify the technology contribution factor which then leads to final valuation model which is co-considered with financial and economic factors. This final model is validated with real perception and financial statements of five firms. This proposed model provides the opportunities for extending to other domains and technologies.
Customer Relationship Management (CRM) is the key management tools to gain the sustainable competitive advantage and to survive business among the intense competitive environment. Before building up CRM strategies, the organization should prioritize the customers into the segment in order to manage the relationship and to provide the services properly. This research aims to develop CRM strategies in a case study of the chemical industry company by applying the clustering techniques to segment customer, use Business Intelligence (BI) as the visualized tools to represent the knowledge in various dimensions and finally bring out CRM strategies to deploy in business. The clustering method applied in this research is K-Means. The clusters are generated and defined as 4 classes, including Diamond, Platinum, Gold, and Silver, respectively. However, its interpretation still not well enough to make the decision without powerful presentation tools like BI. Finally, the knowledge acquired from dimensional aspects in BI could lead to CRM strategies. The organization could be strengthen the good relationship with the individual customer, and appropriately provides the personalized products and services based on customer segment.
#CustomerRelationshipManagement #DataMining #DataScience #DataVisualization #BusinessIntelligence
This research presents the use of infographics to improve the representation of healthcare information publicity. In general, a hospital also uses the posters with only text for the public media of health information, which is unattractive and cannot be read by same medical service users, causing a decrease in the number of medical media consumers of medical services. Therefore, the infographic design is proposed to solve the problems. The concept of infographic design also includes beauty, attractiveness, notability, and accessibility for efficient communication in the health information publicity. In addition, infographic design should consider impressive representation to influence the participants through the graphic content. The summarization of health information and analysis are rearranged and demonstrated as more attractive graphic posters for convenience. In our experiment, with the assessment of both medical service users and experts in health information publicity, the satisfaction result of the posters based on infographic design was at an excellent level. Furthermore, it is also helpful and can clearly communicate to consumers regarding concern for harmful diseases in daily life.
The organizations usually emphasize in managing of organizational knowledge because it has been considered as the value assets in the organizations, and it helps the organizations to be a more competitive advantage and be efficient in decision making. Therefore, the knowledge management (KM) has been used to manage in many organizations. Unfortunately, it found that many organizations unsuccessfully to implement KM since they did not aware in their organizational knowledge. The knowledge prioritizing may be as the approach that can help the organizations know what knowledge are essential for the employee and can contribute to win business. In this research, the knowledge prioritizing by prioritization matrix was used as a tool by employing organizational success factors as variables for knowledge prioritizing in the real estate agent and consulting company, the selected case study. It appeared that the ability and expertise are the most valuable knowledge. The results have been accepted by the four levels of employees: head of the business line, manager, officer, and secretary. The different aspects of each level are also discussed. Finally, the knowledge prioritizing approach also has been accepted that it can actually be used in the organization, depends on the needs of each organization.
Extensible Markup Language (XML) has been widely accepted as a standard format for structured data. Such a data format is used in storing and transferring data. Within the concepts of XML, variations of data formats have been developed to suit particular applications, eg., ebXML is a standard format for electronic transactions, etc. In the world of justice, XML is well applied for its data representation. One of the world-wide standards is Global Justice XML (GJXML). Applying GJXML to Thailand’s justice system will be beneficial to the people. This paper introduced GJXML to some extent, and proposed the Thai Court XML (TCXML), an adaptive version of GJXML, that would be suitable for the collection of verdicts from the Thai Dika Court. Our experiment showed that TCXML could represent upto 90 percents of the verdict keywords.
Click to view student statistic dashboard.
Phd | Thesis | Thematic | Total Students | Net Load | |
2023 | 2 | 3 | 14 | 19 | 92⁄3 |
2022 | - | 1 | 7 | 8 | 31⁄3 |
2021 | 1 | 6 | 7 | 14 | 91⁄3 |
2020 | 1 | 1 | 3 | 5 | 3 |
2019 | - | 1 | 4 | 5 | 21⁄3 |
2018 | - | 4 | 3 | 7 | 5 |
2017 | - | 6 | 1 | 7 | 61⁄3 |
2016 | - | 4 | 15 | 19 | 9 |
2015 | - | 9 | 12 | 21 | 13 |
2014 | - | 1 | 14 | 15 | 52⁄3 |
Total | 4 | 36 | 80 | 120 | 662⁄3 |
#OrganicFarming #MaturityModel #Ifoam
Generation: 59 (2016)
Graduation: 2023
Time spent: 7 years
#Recommender #ColaborativeFiltering #Emotion #Attractions
Generation: 60 (2017)
Graduation: 2023
Time spent: 6 years
#DataLiteracy #Education #Competency #Skills
Generation: 63 (2020)
Graduation: 2023
Time spent: 3.5 years
#Energy #WaveletAnalysis #BiofelPrice #FoodPrice
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#AnalyticsGovernance #DataGovernance #AIGovernance #AnalyticsManagement
Generation: 64 (2021)
Graduation: 2023
Time spent: 2.5 years
#JewellyProduction #DataVisualization #BusinessIntelligence #Dashboard
Generation: 64 (2021)
Graduation: 2023
Time spent: 2.5 years
#DatingApplication #UserBehaviour #UserAcceptance #LongTermRelationship
Generation: 64 (2021)
Graduation: 2023
Time spent: 2.5 years
#CourseTrends #DataVisualization #Cousera #GoogleTrends
Generation: 64 (2021)
Graduation: 2023
Time spent: 2.5 years
#SAP #ProgramInterfacing #BusinessIntelligent
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#HRAnalytics #EmployeeTurnover #DataVisualization #BusinessIntelligence #Dashboard
Generation: 64 (2021)
Graduation: 2023
Time spent: 2.5 years
#NCDs #PredictiveAnalytics #AssociationRules
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#GDPR #LawfulBasis #DataScience
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#DataProtection #PDPA #ROPA #HumanResources
Generation: 64 (2021)
Graduation: 2023
Time spent: 2.5 years
#SystemAnalysisAndDesign #UML #ChatBots
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#CyberRange #RiskManagement #CyberSecurity #NIST
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#CallCenterAgent #DataVisualization #Dashboard
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#DataProtection #PDPA #ROPA #Education
Generation: 64 (2021)
Graduation: 2023
Time spent: 2.5 years
#DataGovernance #DataSteward #CommunicationPlan
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#DataGovernance #DataSteward #SoftSkills
Generation: 64 (2021)
Graduation: 2023
Time spent: 2 years
#Covid19 #PolicyModeling #PMCIndex #StockMarket
Generation: 63 (2020)
Graduation: 2022
Time spent: 2 years
#ElectricityTrading #DemandResponse #BusinessIntelligence
Generation: 64 (2021)
Graduation: 2022
Time spent: 1.5 years
#DataQuality #DataQualityManagement #ISO8000
Generation: 64 (2021)
Graduation: 2022
Time spent: 1.5 years
#AlgorithmicTrading #RiskManagement #COBIT #CryptoCurrency
Generation: 64 (2021)
Graduation: 2022
Time spent: 1.5 years
#Education #LearningDisabilities #Dyslexia #ResponseToIntervention #InclusiveEducation
Generation: 62 (2019)
Graduation: 2022
Time spent: 3.5 years
#DataScience #BabySchema #PredictiveAnalytics #CuteDog #Relaxation
Generation: 63 (2020)
Graduation: 2022
Time spent: 2 years
#Ontology #HealthInformatics #SemanticSearchSystem #ICD10 #InfectiousDisease
Generation: 63 (2020)
Graduation: 2022
Time spent: 2 years
#DataQuality #ISO8000 #DistributionBusiness #DataQualityManagement
Generation: 60 (2017)
Graduation: 2022
Time spent: 5 years
#HumanResourceManagement #TalentManagement #TalentValueProposition #Bureaucratic #ITPersonel
Generation: 59 (2016)
Graduation: 2021
Time spent: 5 years
#DataScience #DataMining #TCAS #Education #DescriptiveAnalytics #PredictiveAnalytics #PrescriptiveAnalytics
Generation: 62 (2019)
Graduation: 2021
Time spent: 2 years
#DataGovernance #Agile #AgileGovernance #NonInvasiveDataGovernance #Healthcare #HealthInformatics
Generation: 62 (2019)
Graduation: 2021
Time spent: 2.5 years
#DataScience #DataMining #CustomerAnalytics #AssociationRules #PredictiveAnalytics #Orchids
Generation: 61 (2018)
Graduation: 2021
Time spent: 3.5 years
#DataScience #DataMining #SpOC #OnlineLearning #Clustering #PrediciveAnalytics #Education
Generation: 63 (2020)
Graduation: 2021
Time spent: 1.5 years
#DataScience #PredictiveAnalytics #EmotionAnalytics #Depression #Worry #LIWC #Pantip
Generation: 61 (2018)
Graduation: 2021
Time spent: 3.5 years
#DataScience #DescriptiveAnalytics #DataMining #CustomerAnalytics #RFM #KMeans #DBSCAN
Generation: 62 (2019)
Graduation: 2021
Time spent: 2.5 years
#HealthInformatics #Chatbot #AIEthics #DataEthics #Depression
Generation: 63 (2020)
Graduation: 2021
Time spent: 1.5 years
#KnowledgeManagement #SocialMedia #UserBehavior #MediaAttraction
Generation: 59 (2016)
Graduation: 2021
Time spent: 5 years
#HumanResourceManagement #EmergingJob #DataScienceJob #DataScience
Generation: 63 (2020)
Graduation: 2021
Time spent: 1.5 years
#DataScience #MLM #PredictiveAnalytics
Generation: 62 (2019)
Graduation: 2021
Time spent: 2 years
#B2BEcommerce #Ecommerce #SME #Adoption
Generation: 63 (2020)
Graduation: 2021
Time spent: 1.5 years
#PredictiveAnalytics #DataMining #TargetMarketing #Personalization
Generation: 62 (2019)
Graduation: 2021
Time spent: 2.5 years
#RPA #Accounting #RiskAnalysis #COBIT5
Generation: 63 (2020)
Graduation: 2021
Time spent: 1.5 years
#HumanResourceManagement #HumanResourceAnalytics #Adoption #StateOwnedEnterprise
Generation: 60 (2017)
Graduation: 2020
Time spent: 3.5 years
#GDPR #DataPrivacy #DataProtection #DataSecurity #DataMasking #Optimization #DataMining
Generation: 60 (2017)
Graduation: 2020
Time spent: 3 years
#ElectricUse #BusinessIntelligence #DataVisualization
Generation: 61 (2018)
Graduation: 2020
Time spent: 2 years
#MutualFunds #NetAssetValues #NeuralNetwork #TimeSeriesAnalysis #DataScience
Generation: 60 (2017)
Graduation: 2020
Time spent: 3 years
#GDPR #DataPrivacy #DataProtection #DataSecurity #ComlianceChecklist
Generation: 61 (2018)
Graduation: 2020
Time spent: 2 years
#DataScience #DataMining #TextMining #DepressiveDisorder #EmotionAnalytics
Generation: 60 (2017)
Graduation: 2019
Time spent: 2.5 years
#DataScience #DataVisualization #BusinessIntelligence #Education
Generation: 60 (2017)
Graduation: 2019
Time spent: 2.5 years
#DataScience #TextMining #CriminalLaw #MalfeasanceInOffice
Generation: 59 (2016)
Graduation: 2019
Time spent: 3.5 years
#DataScience #DataMining #TextMining #Education
Generation: 60 (2017)
Graduation: 2019
Time spent: 2.5 years
#TrustModel #DataGovernance #CloudComputing
Generation: 60 (2017)
Graduation: 2019
Time spent: 2 years
#DataArchitecture #EnterpriseArchitecture #Justice #DataSupplyChain #DataIntegration
Generation: 59 (2016)
Graduation: 2018
Time spent: 2 years
#DataScience #DataMining #PredictiveAnalytics #PrescriptiveAnalytics #CustomerSegmentation
Generation: 59 (2016)
Graduation: 2018
Time spent: 2 years
#DataScience #DataMining #PredictiveModeling #AssociationRules #Clustering #Sepsis #SepticShock #HealthInformatics
Generation: 59 (2016)
Graduation: 2018
Time spent: 2 years
#DataScience #DataMining #BreastCancer #HealthInformatics #PredictiveAnalytics
Generation: 59 (2016)
Graduation: 2018
Time spent: 2 years
#ITJobs #Education #Competency #BusinessIntelligence
Generation: 58 (2015)
Graduation: 2018
Time spent: 3 years
#TextVisualization #WebServices #TextLexiconization #TextMining
Generation: 59 (2016)
Graduation: 2018
Time spent: 2 years
#DataVisualization #SmokingCessation #BusinessIntelligence
Generation: 59 (2016)
Graduation: 2018
Time spent: 2.5 years
#DataScience #DataMining #CustomerRelationshipManagement #PredictiveAnalytics
Generation: 59 (2016)
Graduation: 2017
Time spent: 1.5 years
#DataScience #DataMining #HealthInformatics #Environment
Generation: 59 (2016)
Graduation: 2017
Time spent: 1.5 years
#DataScience #DataMining #HealthInformatics
Generation: 59 (2016)
Graduation: 2017
Time spent: 1.5 years
#DataGovernance #OpenData #Law
Generation: 59 (2016)
Graduation: 2017
Time spent: 1.5 years
#DataArchitecture #Transsexual #Citizen
Generation: 59 (2016)
Graduation: 2017
Time spent: 1.5 years
#BigData #Recruitment #TechnologyValuation
Generation: 56 (2013)
Graduation: 2017
Time spent: 4 years
#Tracibility #Organic #ApplicationDevelopment
Generation: 58 (2015)
Graduation: 2017
Time spent: 2 years
#Agile #SocialMedia #SocialScience #UserAcceptance
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#EnterpriseArchitecture #Energy
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#Education #DataMining #DataScience
Generation: 56 (2013)
Graduation: 2016
Time spent: 3.5 years
#DataMining #DataScience #Healthcare
Generation: 57 (2014)
Graduation: 2016
Time spent: 2 years
#ApplicationDevelopment #CriminalLaw
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#ApplicationDevelopment #Datawarehouse #Healthcare
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#ApplicationDevelopment #Education #InformationRetrieval
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#BusinessIntelligence #NetworkAnalysis #DataVisualization
Generation: 57 (2014)
Graduation: 2016
Time spent: 2.5 years
#ApplicationDevelopment #Education
Generation: 56 (2013)
Graduation: 2016
Time spent: 3.5 years
#DataMining #DataScience #TextMining
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#BusinessProcessImprovement #Education
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#Education #ApplicationDevelopment
Generation: 57 (2014)
Graduation: 2016
Time spent: 2 years
#BusinessProcessImprovement #Education
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#KnowledgeManagement #RealEstates
Generation: 57 (2014)
Graduation: 2016
Time spent: 2 years
#BusinessIntelligence #DataVisualization #Economics
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#DataMining #DataScience #Banking
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#DataScience #BankFraud
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#DataScience #DataVisualization #GIS #Taxation
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#BusinessProcessImprovement #Education
Generation: 58 (2015)
Graduation: 2016
Time spent: 1.5 years
#DataMining #DataScience #TextMining #Economics
Generation: 56 (2013)
Graduation: 2015
Time spent: 2 years
#DataMining #DataScience #HealthInformatics
Generation: 54 (2011)
Graduation: 2015
Time spent: 4 years
#DataMining #DataScience #Logistics
Generation: 56 (2013)
Graduation: 2015
Time spent: 2.5 years
#DataMining #DataScience #CustomerRelationshipManagement
Generation: 56 (2013)
Graduation: 2015
Time spent: 2 years
#DataMining #DataScience #Healthcare #BiomedicalEngineering
Generation: 57 (2014)
Graduation: 2015
Time spent: 1.5 years
#DataMining #DataScience #Healthcare
Generation: 56 (2013)
Graduation: 2015
Time spent: 2 years