Multi-label classification is a unique challenge in machine learning designed for two targets with each containing one or multiple classes. This problem can be resolved using several methods, including the classification of the targets individually or simultaneously.However, most models cannot classify the target simultaneously, and this is not expected to happen in the modeling rule. This studywas conducted to propose a novel solution in the form of a Vector Generalized Additive Model Using Cross-Validation (VGAMCV) toaddress these problems. The proposed method leverages the Vector Generalized Additive Model (VGAM), which is a semi-parametricmodel combining both parametric and non-parametric components as the underlying base model. Cross-validation was also appliedto tune the parameters to optimize the performance of the method. Moreover, the methodology of VGAMCV was compared with atree-based model, Random Forest, commonly used in multi-label classification to evaluate its effectiveness based on fourteen metricscores. The results showed positive outcomes as indicated by 0.703 average accuracy and 0.601 Area Under Curve (AUC) recorded, butthese improvements were not statistically significant. Meanwhile, the method offered a viable alternative for multi-label classificationtasks, and its introduction served as a contribution to the expanding repertoire of methods available for this purpose.
{"title":"Multi-label Classification Using Vector Generalized Additive Model via Cross-Validation","authors":"Amri Muhaimin, Wahyu Wibowo, Prismahardi Aji Riyantoko","doi":"10.32890/jict2023.22.4.5","DOIUrl":"https://doi.org/10.32890/jict2023.22.4.5","url":null,"abstract":"Multi-label classification is a unique challenge in machine learning designed for two targets with each containing one or multiple classes. This problem can be resolved using several methods, including the classification of the targets individually or simultaneously.However, most models cannot classify the target simultaneously, and this is not expected to happen in the modeling rule. This studywas conducted to propose a novel solution in the form of a Vector Generalized Additive Model Using Cross-Validation (VGAMCV) toaddress these problems. The proposed method leverages the Vector Generalized Additive Model (VGAM), which is a semi-parametricmodel combining both parametric and non-parametric components as the underlying base model. Cross-validation was also appliedto tune the parameters to optimize the performance of the method. Moreover, the methodology of VGAMCV was compared with atree-based model, Random Forest, commonly used in multi-label classification to evaluate its effectiveness based on fourteen metricscores. The results showed positive outcomes as indicated by 0.703 average accuracy and 0.601 Area Under Curve (AUC) recorded, butthese improvements were not statistically significant. Meanwhile, the method offered a viable alternative for multi-label classificationtasks, and its introduction served as a contribution to the expanding repertoire of methods available for this purpose.","PeriodicalId":43747,"journal":{"name":"Journal of Information and Communication Technology-Malaysia","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135217927","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 : 2023-10-25DOI: 10.32890/jict2023.22.4.1
Muhammad Thesa Ghozali
The dynamic field of the Internet of Things (IoT) is constantly increasing, providing a plethora of potential integration across various sectors, most notably healthcare. The IoT represents a significant technological leap in healthcare management systems, coinciding with the rising preference for personalized, proactive, cost-effective treatment techniques. This review aimed to thoroughly assess the existing literature through a systematic review and bibliometric analysis, identifying untapped research routes and possible domains for further exploration. The overarching goal was to provide healthcare professionals with significant insights into the impact of IoT technology on Patient Medication Adherence (PMA) and related outcomes. An extensive review of 314 scientific articles on the deployment of IoT within pharmaceutical care services revealed a rising trend in publication volume, with a significant increase in recent years. Pertinently, from the 33 publications finally selected, substantial data support the potential of the IoT to improve PMA, particularly among senior patients with chronic conditions. This paper also comments on various regularly implemented IoT-based systems, noting their unique benefits and limitations. In conclusion, the critical relevance of PMA is highlighted, arguing for its emphasis in future discussions. Furthermore, the need for additional research endeavors is proposed to face and overcome existing constraints and establish the long-term effectiveness of IoT technologies in maximizing patient outcomes.
{"title":"Implementation of the IoT-Based Technology on Patient Medication Adherence: A Comprehensive Bibliometric and Systematic Review","authors":"Muhammad Thesa Ghozali","doi":"10.32890/jict2023.22.4.1","DOIUrl":"https://doi.org/10.32890/jict2023.22.4.1","url":null,"abstract":"The dynamic field of the Internet of Things (IoT) is constantly increasing, providing a plethora of potential integration across various sectors, most notably healthcare. The IoT represents a significant technological leap in healthcare management systems, coinciding with the rising preference for personalized, proactive, cost-effective treatment techniques. This review aimed to thoroughly assess the existing literature through a systematic review and bibliometric analysis, identifying untapped research routes and possible domains for further exploration. The overarching goal was to provide healthcare professionals with significant insights into the impact of IoT technology on Patient Medication Adherence (PMA) and related outcomes. An extensive review of 314 scientific articles on the deployment of IoT within pharmaceutical care services revealed a rising trend in publication volume, with a significant increase in recent years. Pertinently, from the 33 publications finally selected, substantial data support the potential of the IoT to improve PMA, particularly among senior patients with chronic conditions. This paper also comments on various regularly implemented IoT-based systems, noting their unique benefits and limitations. In conclusion, the critical relevance of PMA is highlighted, arguing for its emphasis in future discussions. Furthermore, the need for additional research endeavors is proposed to face and overcome existing constraints and establish the long-term effectiveness of IoT technologies in maximizing patient outcomes.","PeriodicalId":43747,"journal":{"name":"Journal of Information and Communication Technology-Malaysia","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135170798","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 : 2023-10-25DOI: 10.32890/jict2023.22.4.4
Noraziah ChePa, Sie-Yi Laura Lim, Nooraini Yusoff, Wan Ahmad Jaafar Wan Yahaya, Rusdi Ishak
Game-based psychotherapy intervention is a promising alternative to non-pharmacological approaches in treating memory disorders. Nevertheless, the game-based approach is yet to be included systematically in existing intervention models for treating memorydisorders. Hence, this article discusses how a proposed gamebased psychotherapy intervention is developed and validated usingneurofeedback approach. The proposed model consists of nine exogenous and six instantaneous factors as the main components. Toensure its applicability, a validation procedure has been carried out through a series of psychotherapy experiments involving the elderly with memory disorder symptoms. Electroencephalogram (EEG) data captured from the experiments are thoroughly analysed to validate relationships among factors in the model. Experimental findings have proven that all relationships are successfully validated and supported except for the belief component with the cut-off point of 56.6%. The novelty of this study can be attributed to the integration of digital games and neurofeedback in psychotherapy for memory disorders. The model is believed to be a guideline in planning suitable cognitive training and rehabilitation for people with memory disorders towards improving the quality of the elderly life.
{"title":"A Game-based Psychotherapy Intervention Model for Memory Disorder: Model Validation Using EEG Neurofeedback Data","authors":"Noraziah ChePa, Sie-Yi Laura Lim, Nooraini Yusoff, Wan Ahmad Jaafar Wan Yahaya, Rusdi Ishak","doi":"10.32890/jict2023.22.4.4","DOIUrl":"https://doi.org/10.32890/jict2023.22.4.4","url":null,"abstract":"Game-based psychotherapy intervention is a promising alternative to non-pharmacological approaches in treating memory disorders. Nevertheless, the game-based approach is yet to be included systematically in existing intervention models for treating memorydisorders. Hence, this article discusses how a proposed gamebased psychotherapy intervention is developed and validated usingneurofeedback approach. The proposed model consists of nine exogenous and six instantaneous factors as the main components. Toensure its applicability, a validation procedure has been carried out through a series of psychotherapy experiments involving the elderly with memory disorder symptoms. Electroencephalogram (EEG) data captured from the experiments are thoroughly analysed to validate relationships among factors in the model. Experimental findings have proven that all relationships are successfully validated and supported except for the belief component with the cut-off point of 56.6%. The novelty of this study can be attributed to the integration of digital games and neurofeedback in psychotherapy for memory disorders. The model is believed to be a guideline in planning suitable cognitive training and rehabilitation for people with memory disorders towards improving the quality of the elderly life.","PeriodicalId":43747,"journal":{"name":"Journal of Information and Communication Technology-Malaysia","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135219240","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 : 2023-10-25DOI: 10.32890/jict2023.22.4.6
Dr. Alawiyah Abd Wahab, Huda H. Ibrahim, Shehu SarkinTudu
As Blockchain projects gain popularity among developers, the number of patched codes rapidly increases. With such growth, it is difficult for the few committers to maintain it in a timely manner. Subsequently, the community is always in search of new committers. This highlights the imperative importance of committer assessment decisions towards the success of Blockchain. However, the practices come with risks whereby new committers may harm the project. For example, a new committer may initiate a hard fork that splits a project. Numerous systematic literature reviews have investigated developer turnover’s impact on open-source software (OSS) projects. These studies mainly focused on aspects such as community participation, engagement, and motivation. However, previous reviews often overlooked committer assessment practices, particularly in the context of Blockchain projects. Although Blockchain operates as OSS, its distinct attributes, such as decentralisation and cryptography, justify the need for a dedicated review. Therefore, the objectives of this review are to 1) identify committer assessment practices, 2) identify problems in committer assessment, 3) identify existing factors in committer assessment, and 4) suggest some possible research topics. These goals were achieved through a systematic review of literature published between 2010 and 2022. The findings suggest that previous assessment models are usefulbut mainly focus on technical factors. The results also indicate that studies focusing on behavioural tendencies, which influence human activities, have so far been neglected. Finally, the paper concludes by charting potential open research opportunities.
{"title":"Committer Assessment Practice in Blockchain Project: A Systematic Literature Review","authors":"Dr. Alawiyah Abd Wahab, Huda H. Ibrahim, Shehu SarkinTudu","doi":"10.32890/jict2023.22.4.6","DOIUrl":"https://doi.org/10.32890/jict2023.22.4.6","url":null,"abstract":"As Blockchain projects gain popularity among developers, the number of patched codes rapidly increases. With such growth, it is difficult for the few committers to maintain it in a timely manner. Subsequently, the community is always in search of new committers. This highlights the imperative importance of committer assessment decisions towards the success of Blockchain. However, the practices come with risks whereby new committers may harm the project. For example, a new committer may initiate a hard fork that splits a project. Numerous systematic literature reviews have investigated developer turnover’s impact on open-source software (OSS) projects. These studies mainly focused on aspects such as community participation, engagement, and motivation. However, previous reviews often overlooked committer assessment practices, particularly in the context of Blockchain projects. Although Blockchain operates as OSS, its distinct attributes, such as decentralisation and cryptography, justify the need for a dedicated review. Therefore, the objectives of this review are to 1) identify committer assessment practices, 2) identify problems in committer assessment, 3) identify existing factors in committer assessment, and 4) suggest some possible research topics. These goals were achieved through a systematic review of literature published between 2010 and 2022. The findings suggest that previous assessment models are usefulbut mainly focus on technical factors. The results also indicate that studies focusing on behavioural tendencies, which influence human activities, have so far been neglected. Finally, the paper concludes by charting potential open research opportunities.","PeriodicalId":43747,"journal":{"name":"Journal of Information and Communication Technology-Malaysia","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135218246","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 : 2023-10-25DOI: 10.32890/jict2023.22.4.2
None Nur Atiqah Rochin Demong, None Melissa Shahrom, None Ramita Abdul Rahim, None Emi Normalina Omar, None Mornizan Yahya
The global trend of student social well-being has steadily declined in recent years. As a result, the need for a personalized recommendation classification model that can accurately assess and identify the individual student’s social well-being has become increasingly important. This article will discuss the development of an adaptive personalized recommendation classification model for students’ social well-being based on personality trait determinants. Social well-being is a field that analyses society, individual behavioural patterns, behavioural networks, and cultural elements of daily life. Social well-being develops critical thinking by understanding the social frameworks that affect humans by exposing the social basis of daily actions. For instance, when students are pleased, their academic achievement, behaviour, social integration, and happiness improve. This study classifies the effects of the Big 5 Personality Traits (Extraversion, Openness, Agreeableness, Emotional Stability, and Conscientiousness) on students’ Industry 4.0 Social Well-being levels by analyzing their demographic and personality traits. A dataset was gathered through a survey distributed to students in a selected institution. The classifier’s accuracy was assessed using the WEKA tool on a data set of 286 occurrences and 19 traits, and a confusion matrix was constructed. After analyzing the results of all algorithms, it was determined that the IBk and Randomizable Filtered Classifier algorithms give the best accuracy on social well-being readiness, with a comparable percentage value of 91.26%. The agreeableness personality trait, which represents a person’s level of pleasantness, politeness, and helpfulness, had the greatest influence on the social well-being of the students. They have a positive outlook on human behaviour and get along well with others. Since social well-being contributes to a person’s increased quality of life and happiness, improving students’ current quality of life would lead to the development of a social parameter that can assess the growth of a country and the increased happiness offamilies and communities. Personality traits models have become an increasingly important tool for understanding and predicting human behavior. By analyzing different personality trait models, we can gain insights into how accurately and reliably they can predict individual behavior. This is especially useful in fields such as psychology, marketing, and recruitment, where understanding the nuances of individual personalities can be critical to success. In this study, how different personality trait models compare in terms of accuracy and reliability is explored using different machine learning algorithms using the WEKA tool. Personality trait models are increasingly being used to measure social well-being. This model is based on the idea that individuals’ personalities are composed of a set of underlying traits which can be measured and compared. By understanding thes
{"title":"Personalized Recommendation Classification Model of Students’ Social Well-being Based on Personality Trait Determinants Using Machine Learning Algorithms","authors":"None Nur Atiqah Rochin Demong, None Melissa Shahrom, None Ramita Abdul Rahim, None Emi Normalina Omar, None Mornizan Yahya","doi":"10.32890/jict2023.22.4.2","DOIUrl":"https://doi.org/10.32890/jict2023.22.4.2","url":null,"abstract":"The global trend of student social well-being has steadily declined in recent years. As a result, the need for a personalized recommendation classification model that can accurately assess and identify the individual student’s social well-being has become increasingly important. This article will discuss the development of an adaptive personalized recommendation classification model for students’ social well-being based on personality trait determinants. Social well-being is a field that analyses society, individual behavioural patterns, behavioural networks, and cultural elements of daily life. Social well-being develops critical thinking by understanding the social frameworks that affect humans by exposing the social basis of daily actions. For instance, when students are pleased, their academic achievement, behaviour, social integration, and happiness improve. This study classifies the effects of the Big 5 Personality Traits (Extraversion, Openness, Agreeableness, Emotional Stability, and Conscientiousness) on students’ Industry 4.0 Social Well-being levels by analyzing their demographic and personality traits. A dataset was gathered through a survey distributed to students in a selected institution. The classifier’s accuracy was assessed using the WEKA tool on a data set of 286 occurrences and 19 traits, and a confusion matrix was constructed. After analyzing the results of all algorithms, it was determined that the IBk and Randomizable Filtered Classifier algorithms give the best accuracy on social well-being readiness, with a comparable percentage value of 91.26%. The agreeableness personality trait, which represents a person’s level of pleasantness, politeness, and helpfulness, had the greatest influence on the social well-being of the students. They have a positive outlook on human behaviour and get along well with others. Since social well-being contributes to a person’s increased quality of life and happiness, improving students’ current quality of life would lead to the development of a social parameter that can assess the growth of a country and the increased happiness offamilies and communities. Personality traits models have become an increasingly important tool for understanding and predicting human behavior. By analyzing different personality trait models, we can gain insights into how accurately and reliably they can predict individual behavior. This is especially useful in fields such as psychology, marketing, and recruitment, where understanding the nuances of individual personalities can be critical to success. In this study, how different personality trait models compare in terms of accuracy and reliability is explored using different machine learning algorithms using the WEKA tool. Personality trait models are increasingly being used to measure social well-being. This model is based on the idea that individuals’ personalities are composed of a set of underlying traits which can be measured and compared. By understanding thes","PeriodicalId":43747,"journal":{"name":"Journal of Information and Communication Technology-Malaysia","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135113392","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 : 2023-10-25DOI: 10.32890/jict2023.22.4.3
None Vinod Prakash, None Dharmender Kumar
Epilepsy is one of the most severe non-communicable brain disorders associated with sudden attacks. Electroencephalography (EEG), a non-invasive technique, records brain activities, and these recordings are routinely used for the clinical evaluation of epilepsy. EEG signal analysis for seizure identification relies on expert manual examination, which is labour-intensive, time-consuming, and prone to human error. To overcome these limitations, researchers have proposed machine learning and deep learning approaches. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) have shown significant results in automating seizure prediction, but due to complex gated mechanisms and the storage of excessive redundant information, these approaches face slow convergence and a low learning rate. The proposed modified GRU approach includes an improved update gate unit that adjusts the update gate based on the output of the reset gate. By decreasing the amount of superfluous data in the reset gate, convergence is speeded, which improves both learning efficiency and the accuracy of epilepsy seizure prediction. The performance of the proposed approach is verified on a publicly available epileptic EEG dataset collected from the University of California, Irvine machine learning repository (UCI) in terms of performance metrics such as accuracy, precision, recall, and F1 score when it comes to diagnosing epileptic seizures. The proposed modified GRU has obtained 98.84% accuracy, 96.9% precision, 97.1 recall, and 97% F1 score. The performance results are significant because they could enhance the diagnosis and treatment of neurological disorders, leading to better patient outcomes.
{"title":"A Modified Gated Recurrent Unit Approach for Epileptic Electroencephalography Classification","authors":"None Vinod Prakash, None Dharmender Kumar","doi":"10.32890/jict2023.22.4.3","DOIUrl":"https://doi.org/10.32890/jict2023.22.4.3","url":null,"abstract":"Epilepsy is one of the most severe non-communicable brain disorders associated with sudden attacks. Electroencephalography (EEG), a non-invasive technique, records brain activities, and these recordings are routinely used for the clinical evaluation of epilepsy. EEG signal analysis for seizure identification relies on expert manual examination, which is labour-intensive, time-consuming, and prone to human error. To overcome these limitations, researchers have proposed machine learning and deep learning approaches. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) have shown significant results in automating seizure prediction, but due to complex gated mechanisms and the storage of excessive redundant information, these approaches face slow convergence and a low learning rate. The proposed modified GRU approach includes an improved update gate unit that adjusts the update gate based on the output of the reset gate. By decreasing the amount of superfluous data in the reset gate, convergence is speeded, which improves both learning efficiency and the accuracy of epilepsy seizure prediction. The performance of the proposed approach is verified on a publicly available epileptic EEG dataset collected from the University of California, Irvine machine learning repository (UCI) in terms of performance metrics such as accuracy, precision, recall, and F1 score when it comes to diagnosing epileptic seizures. The proposed modified GRU has obtained 98.84% accuracy, 96.9% precision, 97.1 recall, and 97% F1 score. The performance results are significant because they could enhance the diagnosis and treatment of neurological disorders, leading to better patient outcomes.","PeriodicalId":43747,"journal":{"name":"Journal of Information and Communication Technology-Malaysia","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135112685","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：