The research of the Study and Develop Online Communities to promote quality of life for the elderly in Urban Society is a research and development by integrating qualitative and quantitative methods. The objectives of the study are: 1) to study the problems and needs of the urban elderly in Nang Rong Municipality, Nang Rong District, Buriram Province. 2) to analyze and to design an online community to promote quality of life for the elderly in urban society of Nang Rong Municipality, Nang Rong District, Buriram Province and 3) to develop an online community model for promoting the quality of life of the urban elderly in Nang Rong municipality, Nang Rong District, Buriram Province.The population in this study were the elderly in Nang Rong municipal area, Nang Rong Subdistrict, Nang Rong District, Buriram Province (Young-old persons aged. 60 to 69) by using purposive sampling method and the chosen population were the retired teachers having experience in using online media, the senior school instructors, doctors, and senior welfare officers. The instruments used in this research were questionnaires for collecting quantitative data and interview, group discussion, lesson conclusion, and participant observation were the methods for collecting qualitative data. The statistics used to analyze data were the average and the standard deviation.For the result of the online life-quality promoting in the online model for the urban elderly, it was found that the elderly can post pictures, write blogs, send messages to the senior school instructors, doctors, and senior welfare officers, read press releases from the elderly welfare department, attend elderly school, read health articles, read community blogs, create polls and write a trading post in the online market. And the overall result of the online community performance and satisfaction to promote the quality of life of the elderly in the urban society from the local elderly, the senior school instructors, doctors, and senior welfare officers is a high level.
{"title":"The Development of Online Community Model to Promote the Life Quality Level of the Elderly in Urban Society","authors":"Napaphat Wannatrong, Sujitra Yoannok, Kulganya Srisuk","doi":"10.1109/ICTKE.2018.8612369","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612369","url":null,"abstract":"The research of the Study and Develop Online Communities to promote quality of life for the elderly in Urban Society is a research and development by integrating qualitative and quantitative methods. The objectives of the study are: 1) to study the problems and needs of the urban elderly in Nang Rong Municipality, Nang Rong District, Buriram Province. 2) to analyze and to design an online community to promote quality of life for the elderly in urban society of Nang Rong Municipality, Nang Rong District, Buriram Province and 3) to develop an online community model for promoting the quality of life of the urban elderly in Nang Rong municipality, Nang Rong District, Buriram Province.The population in this study were the elderly in Nang Rong municipal area, Nang Rong Subdistrict, Nang Rong District, Buriram Province (Young-old persons aged. 60 to 69) by using purposive sampling method and the chosen population were the retired teachers having experience in using online media, the senior school instructors, doctors, and senior welfare officers. The instruments used in this research were questionnaires for collecting quantitative data and interview, group discussion, lesson conclusion, and participant observation were the methods for collecting qualitative data. The statistics used to analyze data were the average and the standard deviation.For the result of the online life-quality promoting in the online model for the urban elderly, it was found that the elderly can post pictures, write blogs, send messages to the senior school instructors, doctors, and senior welfare officers, read press releases from the elderly welfare department, attend elderly school, read health articles, read community blogs, create polls and write a trading post in the online market. And the overall result of the online community performance and satisfaction to promote the quality of life of the elderly in the urban society from the local elderly, the senior school instructors, doctors, and senior welfare officers is a high level.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134521159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612352
Tommanee Sooksai
Nowadays, electrical and electronics industries are now playing important role in the economy of the country. The growth of industries partly resulted from the expansion of the investments of the leader electrical and electronics companies of the world. This study aims to study the factors of the competitive advantage or the advantage creation for competitive electrical and electronics industries in the central region of Thailand. The defined samples for the study would be business companies in Bangkok and around the outskirt ones in the electrical and electronics industries; the senior executives of the defined ones would answer the proper Questionnaires of Logistics Scorecard. The defined sampling groups from 20 selected companies would be classified into those of Electrical, Electrical Parts, Electronics, Trader, Supporting Industries, and Other defined by the method of the Purposive Sampling and used the mathematics comparison of the Rule of Three to find the numbers of the samplings in each category of the defined companies. The data analysis with the technique of the Cronbach’s Alpha would be applied to measure the Reliability of the questionnaires. The findings showed that the factors of the strategy establishment of the companies could provide the highest influence to the competitive advantage and it could show the results at the Mean of 2.73, and at the SD of 0.43. Secondarily, the factors of the performance and effectiveness in logistics could provide high influence to the competitive advantage and it could show the results at the Mean of 2.71, and at the SD of 0.09. The factors of the planning and competency of the operations could provide moderate influence to the competitive advantage and it could show the results at the Mean of 2.31, and at the SD of 0.13. The factors of the cooperation of the companies could provide only low influence to the competitive advantage and it could show the results at the Mean of 1.90, and at the SD of 0.03. Finally, the factors of the information and technology management of the companies could provide only lowest influence to the competitive advantage and it could show the results at the Mean of 1.85, and at the SD of 0.12.
{"title":"Factors of Advantage Creation for Competitive Electrical and Electronics Industries in Central Region of Thailand","authors":"Tommanee Sooksai","doi":"10.1109/ICTKE.2018.8612352","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612352","url":null,"abstract":"Nowadays, electrical and electronics industries are now playing important role in the economy of the country. The growth of industries partly resulted from the expansion of the investments of the leader electrical and electronics companies of the world. This study aims to study the factors of the competitive advantage or the advantage creation for competitive electrical and electronics industries in the central region of Thailand. The defined samples for the study would be business companies in Bangkok and around the outskirt ones in the electrical and electronics industries; the senior executives of the defined ones would answer the proper Questionnaires of Logistics Scorecard. The defined sampling groups from 20 selected companies would be classified into those of Electrical, Electrical Parts, Electronics, Trader, Supporting Industries, and Other defined by the method of the Purposive Sampling and used the mathematics comparison of the Rule of Three to find the numbers of the samplings in each category of the defined companies. The data analysis with the technique of the Cronbach’s Alpha would be applied to measure the Reliability of the questionnaires. The findings showed that the factors of the strategy establishment of the companies could provide the highest influence to the competitive advantage and it could show the results at the Mean of 2.73, and at the SD of 0.43. Secondarily, the factors of the performance and effectiveness in logistics could provide high influence to the competitive advantage and it could show the results at the Mean of 2.71, and at the SD of 0.09. The factors of the planning and competency of the operations could provide moderate influence to the competitive advantage and it could show the results at the Mean of 2.31, and at the SD of 0.13. The factors of the cooperation of the companies could provide only low influence to the competitive advantage and it could show the results at the Mean of 1.90, and at the SD of 0.03. Finally, the factors of the information and technology management of the companies could provide only lowest influence to the competitive advantage and it could show the results at the Mean of 1.85, and at the SD of 0.12.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133940039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612310
Kazuki Konda, Yoshiro Yamamoto
In this study, we analyze customer classification by the transition of the time series. We use customer information in the hair salon chain stores of two years, received the offer of POS input data. We watched habits of customers with the aim of analysis and classification. Furthermore, we propose regarding marketing for the benefit of the store. We use the programming language R to analysis. And we use the RFM analysis based on decyl analysis. As an analytical technique, performed from the purchase information the customer classification of every certain period of time. We can see how change the buying habits that the time from the period in which there is a them to the next period of time to transition, from use store, age, gender, the purchase content and so on. Further, by using the shiny packages and visNetwork package in R, we create the application to visualize them interactively.
{"title":"Analyze the trends of customer purchase data and visualize by the Shiny application","authors":"Kazuki Konda, Yoshiro Yamamoto","doi":"10.1109/ICTKE.2018.8612310","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612310","url":null,"abstract":"In this study, we analyze customer classification by the transition of the time series. We use customer information in the hair salon chain stores of two years, received the offer of POS input data. We watched habits of customers with the aim of analysis and classification. Furthermore, we propose regarding marketing for the benefit of the store. We use the programming language R to analysis. And we use the RFM analysis based on decyl analysis. As an analytical technique, performed from the purchase information the customer classification of every certain period of time. We can see how change the buying habits that the time from the period in which there is a them to the next period of time to transition, from use store, age, gender, the purchase content and so on. Further, by using the shiny packages and visNetwork package in R, we create the application to visualize them interactively.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133963704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612390
Kotchakorn Koosawad, Norranut Saguansakdiyotin, P. Palangsantikul, P. Porouhan, W. Premchaiswadi
The main objectives of this paper is to investigate and study the sales process of an automobile company by applying Fuzzy Miner process mining technique on a set of data/event logs previously collected from the sales department of the company. The current work aims to analyze the behavior of unsuccessful (or bad) employees in the automobile’s sales department with the intention of benchmarking the performance of the sales operation management team leading to increased/improved efficiency, effectiveness and productivity. After initial analysis of the collected event logs (data), it was found out that although each employee in the sales department has played a role (i.e., contribution) in the selling car process, but the time spent in each stage to accomplish the assigned job, in addition to the accuracy of the tasks performed by each individual, were not the same. Accordingly, it was realized that 3% of the sales staff could not achieve the selling targets successfully and therefore they were ranked amongst the Bad Sellers. However, 30% of the employees could outperform the defined selling targets and therefore they were ranked amongst the Excellent Sellers, while 67% of the sales people exhibited an average performance and therefore they were considered as the Normal Sellers. Consequently, the appliance of the Fuzzy Miner technique could help the sales administrators/managers to track, trace, visualize and simulate the behavior of Excellent and Bad Sellers in novel ways. The discovery and revelation of such information could be beneficial to improve the overall performance of the sales department leading to increased amount of sales, improved customer satisfaction and emergence of more opportunities for the automobile company.
{"title":"Improving Sales Process of an Automotive Company with Fuzzy Miner Techniques","authors":"Kotchakorn Koosawad, Norranut Saguansakdiyotin, P. Palangsantikul, P. Porouhan, W. Premchaiswadi","doi":"10.1109/ICTKE.2018.8612390","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612390","url":null,"abstract":"The main objectives of this paper is to investigate and study the sales process of an automobile company by applying Fuzzy Miner process mining technique on a set of data/event logs previously collected from the sales department of the company. The current work aims to analyze the behavior of unsuccessful (or bad) employees in the automobile’s sales department with the intention of benchmarking the performance of the sales operation management team leading to increased/improved efficiency, effectiveness and productivity. After initial analysis of the collected event logs (data), it was found out that although each employee in the sales department has played a role (i.e., contribution) in the selling car process, but the time spent in each stage to accomplish the assigned job, in addition to the accuracy of the tasks performed by each individual, were not the same. Accordingly, it was realized that 3% of the sales staff could not achieve the selling targets successfully and therefore they were ranked amongst the Bad Sellers. However, 30% of the employees could outperform the defined selling targets and therefore they were ranked amongst the Excellent Sellers, while 67% of the sales people exhibited an average performance and therefore they were considered as the Normal Sellers. Consequently, the appliance of the Fuzzy Miner technique could help the sales administrators/managers to track, trace, visualize and simulate the behavior of Excellent and Bad Sellers in novel ways. The discovery and revelation of such information could be beneficial to improve the overall performance of the sales department leading to increased amount of sales, improved customer satisfaction and emergence of more opportunities for the automobile company.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124424443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612429
Wanwan Zheng, Mingzhe Jin
Feature selection (FS) is becoming critical in this data era. Selecting effective features from datasets is a particularly important part in text classification, data mining, pattern recognition and artificial intelligence. FS excludes irrelevant features from the classification task, reduces the dimensionality of a dataset, allows us to better understand data, improves the performance of machine learning techniques, and minimizes the computation requirement. Thus far, a large number of FS methods have been proposed, however the most effective one in practice remains unclear. Though it is conceivable that different categories of FS methods have different evaluation criteria for variables, there are few studies fixating on evaluating various categories of FS methods. This article gathers ten superior FS methods under four different categories, and fixates on evaluating and comparing them in general versatility (constant ability to select out the useful features) regarding authorship attribution problems. Besides, this article tries to identify which method is most effective. SVM (support vector machine) serves as the classifier. Different categories of features, different numbers of top variables in feature rankings, and different performance measures are employed to measure the effectiveness and general versatility of these methods together. Finally, rank aggregation method Schulze (SSD) is employed to make a ranking of the ten FS methods. The analysis results suggest that Mahalanobis distance is the best method on the whole.
{"title":"Comparing Feature Selection Methods by Using Rank Aggregation","authors":"Wanwan Zheng, Mingzhe Jin","doi":"10.1109/ICTKE.2018.8612429","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612429","url":null,"abstract":"Feature selection (FS) is becoming critical in this data era. Selecting effective features from datasets is a particularly important part in text classification, data mining, pattern recognition and artificial intelligence. FS excludes irrelevant features from the classification task, reduces the dimensionality of a dataset, allows us to better understand data, improves the performance of machine learning techniques, and minimizes the computation requirement. Thus far, a large number of FS methods have been proposed, however the most effective one in practice remains unclear. Though it is conceivable that different categories of FS methods have different evaluation criteria for variables, there are few studies fixating on evaluating various categories of FS methods. This article gathers ten superior FS methods under four different categories, and fixates on evaluating and comparing them in general versatility (constant ability to select out the useful features) regarding authorship attribution problems. Besides, this article tries to identify which method is most effective. SVM (support vector machine) serves as the classifier. Different categories of features, different numbers of top variables in feature rankings, and different performance measures are employed to measure the effectiveness and general versatility of these methods together. Finally, rank aggregation method Schulze (SSD) is employed to make a ranking of the ten FS methods. The analysis results suggest that Mahalanobis distance is the best method on the whole.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128611301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612447
Erlito M. Albina, A. Hernandez
An increasing elderly population presents challenges and issues on elderly care and support. Assistive Technologies is one of the alternatives to address the growing care needs among the elderly. Beyond technological aspects, the needs, benefits, and barriers play a vital role in the successful use of assistive technologies, which account on this situation, is relatively unexplored in the Philippines. This study attempts to provide an initial understanding of the perceived needs, benefits and barriers to assistive technologies, through a survey among the elderly in the Philippines. Results from the survey indicate that elderly respondents positively perceived the needs of assistive technologies for emergencies, daily activity and health monitoring, navigation, and communication with family and peers. Moreover, the elderly respondents notably perceived benefits from assistive technologies usage includes support for daily activities, assistance in an emergency, increase safety, social interaction, and improve health condition. However, the results also indicate that cost, fear of dependence, need for assistance, privacy and security, and control and autonomy as barriers in the assistive technologies usage. The results of this study will be used as input in a current project of designing an intelligent assistive technology for elderly in the Philippines. Therefore, this study extends understanding on elderly perspectives on assistive technologies in a developing country perspective. Implications for theory and practice are presented.
{"title":"Assessment of the Elderly on Perceived Needs, Benefits and Barriers: Inputs for the Design of Intelligent Assistive Technology","authors":"Erlito M. Albina, A. Hernandez","doi":"10.1109/ICTKE.2018.8612447","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612447","url":null,"abstract":"An increasing elderly population presents challenges and issues on elderly care and support. Assistive Technologies is one of the alternatives to address the growing care needs among the elderly. Beyond technological aspects, the needs, benefits, and barriers play a vital role in the successful use of assistive technologies, which account on this situation, is relatively unexplored in the Philippines. This study attempts to provide an initial understanding of the perceived needs, benefits and barriers to assistive technologies, through a survey among the elderly in the Philippines. Results from the survey indicate that elderly respondents positively perceived the needs of assistive technologies for emergencies, daily activity and health monitoring, navigation, and communication with family and peers. Moreover, the elderly respondents notably perceived benefits from assistive technologies usage includes support for daily activities, assistance in an emergency, increase safety, social interaction, and improve health condition. However, the results also indicate that cost, fear of dependence, need for assistance, privacy and security, and control and autonomy as barriers in the assistive technologies usage. The results of this study will be used as input in a current project of designing an intelligent assistive technology for elderly in the Philippines. Therefore, this study extends understanding on elderly perspectives on assistive technologies in a developing country perspective. Implications for theory and practice are presented.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132894990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612435
Sisavath Xayyasith, A. Promwungkwa, K. Ngamsanroaj
This paper presents machine learning (ML) application for predictive maintenance of a water cooling system in Nam Ngum-1 (NNG-1) hydropower plant located in Vientiane province, Lao PDR. Data used for the learning algorithm is from log sheets 31 months, compiled by a temperature in/out heat exchanger unit and maintenance history. The data is separated into two sets: training and testing sets. This paper uses the Classification Learner Application to train model. The application supports 22 classifier types, which can be organized in six major classification algorithms including Decision Trees, Discriminant Analysis, Support Vector Machines (SVM), Logistic Regression, k-Nearest Neighbors (KNN), and Ensemble Classification. It was shown that the SVM and Decision Trees are better at predicting results compared to the other algorithms. Using ML with the recorded maintenance data demonstrated that the predictive maintenance could be done and provides good and acceptance criteria. The model helps operators to be at ease, with the ability to visualize and monitor the system.
{"title":"Application of Machine Learning for Predictive Maintenance Cooling System in Nam Ngum-1 Hydropower Plant","authors":"Sisavath Xayyasith, A. Promwungkwa, K. Ngamsanroaj","doi":"10.1109/ICTKE.2018.8612435","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612435","url":null,"abstract":"This paper presents machine learning (ML) application for predictive maintenance of a water cooling system in Nam Ngum-1 (NNG-1) hydropower plant located in Vientiane province, Lao PDR. Data used for the learning algorithm is from log sheets 31 months, compiled by a temperature in/out heat exchanger unit and maintenance history. The data is separated into two sets: training and testing sets. This paper uses the Classification Learner Application to train model. The application supports 22 classifier types, which can be organized in six major classification algorithms including Decision Trees, Discriminant Analysis, Support Vector Machines (SVM), Logistic Regression, k-Nearest Neighbors (KNN), and Ensemble Classification. It was shown that the SVM and Decision Trees are better at predicting results compared to the other algorithms. Using ML with the recorded maintenance data demonstrated that the predictive maintenance could be done and provides good and acceptance criteria. The model helps operators to be at ease, with the ability to visualize and monitor the system.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130631964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612402
P. Porouhan, W. Premchaiswadi
The main objective of this study is to compare and distinguish both behavioral differences and emotional changes of a group of students who "earned a certificate" after the end of a MOOC (Massive Open Online Course), versus another groups of students who "dropped out" the course unsuccessfully. To do this, a process mining process discovery technique so-called Fuzzy Miner, based on Frequency-Based and Time-Performance metrics, was applied on a set of event logs previously collected from an authentic learning environment. The resulting fuzzy graphs/models showed a significant dissimilarity between the two groups in terms of the behavioral structure and the sequence of the performed/executed tasks (and activities), the average (mean) duration of the waiting times (or inactive interval/time gaps) in addition to the emotional mood shifts and changes. The findings of the study can be beneficial to not only the MOOC course developers, but to lecturers and researchers as well, in such a way leading to higher attrition rate running online courses and syllabuses.
{"title":"Behavioral Performance Evaluation and Emotion Analytics of a MOOC Course via Fuzzy Modeling","authors":"P. Porouhan, W. Premchaiswadi","doi":"10.1109/ICTKE.2018.8612402","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612402","url":null,"abstract":"The main objective of this study is to compare and distinguish both behavioral differences and emotional changes of a group of students who \"earned a certificate\" after the end of a MOOC (Massive Open Online Course), versus another groups of students who \"dropped out\" the course unsuccessfully. To do this, a process mining process discovery technique so-called Fuzzy Miner, based on Frequency-Based and Time-Performance metrics, was applied on a set of event logs previously collected from an authentic learning environment. The resulting fuzzy graphs/models showed a significant dissimilarity between the two groups in terms of the behavioral structure and the sequence of the performed/executed tasks (and activities), the average (mean) duration of the waiting times (or inactive interval/time gaps) in addition to the emotional mood shifts and changes. The findings of the study can be beneficial to not only the MOOC course developers, but to lecturers and researchers as well, in such a way leading to higher attrition rate running online courses and syllabuses.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126777686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612331
Apichit Pattawaro, Chantri Polprasert
In this paper, we propose an anomaly-based network intrusion detection system based on a combination of feature selection, K-Means clustering and XGBoost classification model. We test the performance of our proposed system over NSL-KDD dataset using KDDTest+ dataset. A feature selection method based on attribute ratio (AR) [14] is applied to construct a reduced feature subset of NSL-KDD dataset. After applying K-Means clustering, hyperparameter tuning of each classification model corresponding to each cluster is implemented. Using only 2 clusters, our proposed model obtains accuracy equal to 84.41% with detection rate equal to 86.36% and false alarm rate equal to 18.20% for KDDTest+ dataset. The performance of our proposed model outperforms those obtained using the recurrent neural network (RNN)-based deep neural network and other tree-based classifiers. In addition, due to feature selection, our proposed model employs only 75 out of 122 features (61.47%) to achieve this level of performance comparable to those using full number of features to train the model.
{"title":"Anomaly-Based Network Intrusion Detection System through Feature Selection and Hybrid Machine Learning Technique","authors":"Apichit Pattawaro, Chantri Polprasert","doi":"10.1109/ICTKE.2018.8612331","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612331","url":null,"abstract":"In this paper, we propose an anomaly-based network intrusion detection system based on a combination of feature selection, K-Means clustering and XGBoost classification model. We test the performance of our proposed system over NSL-KDD dataset using KDDTest+ dataset. A feature selection method based on attribute ratio (AR) [14] is applied to construct a reduced feature subset of NSL-KDD dataset. After applying K-Means clustering, hyperparameter tuning of each classification model corresponding to each cluster is implemented. Using only 2 clusters, our proposed model obtains accuracy equal to 84.41% with detection rate equal to 86.36% and false alarm rate equal to 18.20% for KDDTest+ dataset. The performance of our proposed model outperforms those obtained using the recurrent neural network (RNN)-based deep neural network and other tree-based classifiers. In addition, due to feature selection, our proposed model employs only 75 out of 122 features (61.47%) to achieve this level of performance comparable to those using full number of features to train the model.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"44 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115816952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/ICTKE.2018.8612356
Halford M. Bermudez, Praxedis S. Marquez
This study focuses in urban spaces such as Manila Philippines where urban locations have experienced intense flooding which leads to loss or damage of properties, destruction of homes or suspension of classes. In this point, although flood risk cannot be totally eliminated, this research will be instrumental in flood forecasting as a key tool in flood warning which can provide adequate lead time for the public to play down flood casualties. The purpose of this research is to design an application that will provide flood hazard in the next 2 to 4 hours base from users selected locations and GPS locations, using the source data from PAGASA’s hourly forecast, the system transforms the data into a notification warning via Android Application. A Rapid Application Development Prototyping was utilized by the researcher as a model during the development of the study. It used a total population purposive sampling in the evaluation performance of the system. Furthermore, the developed system was scored with a mean of 4.94 which exhibits that the respondents strongly agree with the capabilities of the developed system. It was then concluded that the developed system was able to supply Flood Hazard Analytics for Urban Spaces to guide the local government, and the Filipino people to spot possible flood behavior in a given location.
{"title":"Flood Hazard Analytics for Urban Spaces","authors":"Halford M. Bermudez, Praxedis S. Marquez","doi":"10.1109/ICTKE.2018.8612356","DOIUrl":"https://doi.org/10.1109/ICTKE.2018.8612356","url":null,"abstract":"This study focuses in urban spaces such as Manila Philippines where urban locations have experienced intense flooding which leads to loss or damage of properties, destruction of homes or suspension of classes. In this point, although flood risk cannot be totally eliminated, this research will be instrumental in flood forecasting as a key tool in flood warning which can provide adequate lead time for the public to play down flood casualties. The purpose of this research is to design an application that will provide flood hazard in the next 2 to 4 hours base from users selected locations and GPS locations, using the source data from PAGASA’s hourly forecast, the system transforms the data into a notification warning via Android Application. A Rapid Application Development Prototyping was utilized by the researcher as a model during the development of the study. It used a total population purposive sampling in the evaluation performance of the system. Furthermore, the developed system was scored with a mean of 4.94 which exhibits that the respondents strongly agree with the capabilities of the developed system. It was then concluded that the developed system was able to supply Flood Hazard Analytics for Urban Spaces to guide the local government, and the Filipino people to spot possible flood behavior in a given location.","PeriodicalId":342802,"journal":{"name":"2018 16th International Conference on ICT and Knowledge Engineering (ICT&KE)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127573174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：