Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288592
Y. T. Wiranti, H. J. Saputra, D. B. Tandirau, T. P. Fiqar, M. G. Langgawan P, E. Ramadhani, A. I. N. F. Abdullah
Ministry of Research, Technology, and Higher Education of the Republic of Indonesia stated that every university in Indonesia needs to implement information technology governance, one of which is information technology service governance. XYZ University as one of the universities in Indonesia needs to implement the governance of information technology services. The implementation of information technology service governance can be using the Information Technology Infrastructure Library Version 3 (ITIL V3) framework. One of the information system services that often have issues with help desk services is academic information systems. The issue of academic information system help desk service issues is resolved by using one of the processes in ITIL V3, namely service level management. In this observation, a service level management process was carried out to produce three documents, namely the Service Level Requirement (SLR), Service Level Agreement (SLA), and Operational Level Agreement (OLA). This research includes three main processes, namely collecting data and information, creating documents, and verification and validation. The method of collecting data and information is carried out using interview techniques, the process of making documents, validation, and verification is carried out by conducting group discussion forums with service providers and service users. In this case, service users are the academics of XYZ University, while service users are the Information and Communication Technology Department of XYZ University. This observation resulted in three main documents in service level management, namely SLR, SLA, and OLA, for academic information system help desk services.
{"title":"Managing Service Level for Academic Information System Help Desk for XYZ University Based on ITIL V3 Framework","authors":"Y. T. Wiranti, H. J. Saputra, D. B. Tandirau, T. P. Fiqar, M. G. Langgawan P, E. Ramadhani, A. I. N. F. Abdullah","doi":"10.1109/ICIC50835.2020.9288592","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288592","url":null,"abstract":"Ministry of Research, Technology, and Higher Education of the Republic of Indonesia stated that every university in Indonesia needs to implement information technology governance, one of which is information technology service governance. XYZ University as one of the universities in Indonesia needs to implement the governance of information technology services. The implementation of information technology service governance can be using the Information Technology Infrastructure Library Version 3 (ITIL V3) framework. One of the information system services that often have issues with help desk services is academic information systems. The issue of academic information system help desk service issues is resolved by using one of the processes in ITIL V3, namely service level management. In this observation, a service level management process was carried out to produce three documents, namely the Service Level Requirement (SLR), Service Level Agreement (SLA), and Operational Level Agreement (OLA). This research includes three main processes, namely collecting data and information, creating documents, and verification and validation. The method of collecting data and information is carried out using interview techniques, the process of making documents, validation, and verification is carried out by conducting group discussion forums with service providers and service users. In this case, service users are the academics of XYZ University, while service users are the Information and Communication Technology Department of XYZ University. This observation resulted in three main documents in service level management, namely SLR, SLA, and OLA, for academic information system help desk services.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125880526","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288570
Kusuma Ayu Laksitowening, Zainal Arifin Hasibuan, Harry Budi Santoso
E-Learning personalization can be a solution to accommodate the variation of students' type since e-Learning allows the learning process of each student not to interfere with each other. Many variables may affect students' condition and behavior throughout the semester. Hence, students' type may change over time and different from one subject to another subject. Accordingly, the personalization should also be dynamic towards the changes that occur. In this research, we analyzed the students' type by processing the access log available on Learning Management Systems (LMS) from time to time. The results of the student analysis then become the reference for learning personalization using ontology. By utilizing ontology, personalization was presented by linking the students' type with activities that match the topic. The proposed personalized learning was applied to the prototype LMS later for testing and evaluation. The evaluation results indicated that personalized learning affects significantly to increase learning activities.
{"title":"Ontology-Based Approach for Dynamic E-Learning Personalization","authors":"Kusuma Ayu Laksitowening, Zainal Arifin Hasibuan, Harry Budi Santoso","doi":"10.1109/ICIC50835.2020.9288570","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288570","url":null,"abstract":"E-Learning personalization can be a solution to accommodate the variation of students' type since e-Learning allows the learning process of each student not to interfere with each other. Many variables may affect students' condition and behavior throughout the semester. Hence, students' type may change over time and different from one subject to another subject. Accordingly, the personalization should also be dynamic towards the changes that occur. In this research, we analyzed the students' type by processing the access log available on Learning Management Systems (LMS) from time to time. The results of the student analysis then become the reference for learning personalization using ontology. By utilizing ontology, personalization was presented by linking the students' type with activities that match the topic. The proposed personalized learning was applied to the prototype LMS later for testing and evaluation. The evaluation results indicated that personalized learning affects significantly to increase learning activities.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128578089","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9335917
Bryanza Novirahman, H. Santoso, R. Isal
Human Resources X Information System or “Sistem Informasi Kepegawaian X (SIPEG-X)” is a staffing information system that is used to monitor staff performance at a large public university in Indonesia. Since this information system was first developed, there has been no significant update on the system, especially if it is viewed in terms of user-interface (UI) or user experience (UX). This then led to the difficulty of assessing performance against the university staff because of a lack of satisfaction and comfort in using the information system. Therefore, usability evaluation and design refinement of these university staffing information systems was carried out using user-centered design methodology so that a new system in the form of a mobile application was developed to provide solutions to the interface of this staffing information system. Evaluation is conducted through surveys, usability testing, and contextual interviews to assess the usability aspects of the current implemented website application. The evaluation results show that the usability of these information systems needs to be improved and based on the principle of Shneiderman's Eight Golden Rules of Interaction Design, a prototype is proposed to improve the interface as well as the user experience.
人力资源X信息系统或“System Informasi Kepegawaian X (SIPEG-X)”是一个人员配置信息系统，用于监控印度尼西亚一所大型公立大学的员工绩效。自从这个信息系统首次开发以来，就没有对系统进行重大更新，特别是从用户界面(UI)或用户体验(UX)的角度来看。由于在使用信息系统时缺乏满意度和舒适感，这就导致了很难对大学员工的表现进行评估。因此，采用以用户为中心的设计方法，对这些高校人事信息系统进行可用性评估和设计细化，并以移动应用程序的形式开发新系统，为该人事信息系统的界面提供解决方案。评估是通过调查、可用性测试和上下文访谈来评估当前实施的网站应用程序的可用性方面。评估结果表明，这些信息系统的可用性有待提高，并基于Shneiderman交互设计的8条黄金法则的原则，提出了一个原型来改善界面和用户体验。
{"title":"Usability Evaluation and User Interface Design of University Staffing Information System","authors":"Bryanza Novirahman, H. Santoso, R. Isal","doi":"10.1109/ICIC50835.2020.9335917","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9335917","url":null,"abstract":"Human Resources X Information System or “Sistem Informasi Kepegawaian X (SIPEG-X)” is a staffing information system that is used to monitor staff performance at a large public university in Indonesia. Since this information system was first developed, there has been no significant update on the system, especially if it is viewed in terms of user-interface (UI) or user experience (UX). This then led to the difficulty of assessing performance against the university staff because of a lack of satisfaction and comfort in using the information system. Therefore, usability evaluation and design refinement of these university staffing information systems was carried out using user-centered design methodology so that a new system in the form of a mobile application was developed to provide solutions to the interface of this staffing information system. Evaluation is conducted through surveys, usability testing, and contextual interviews to assess the usability aspects of the current implemented website application. The evaluation results show that the usability of these information systems needs to be improved and based on the principle of Shneiderman's Eight Golden Rules of Interaction Design, a prototype is proposed to improve the interface as well as the user experience.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129357623","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}
The problem with bodyweight management is the inability to calculate the number of calories burned and consumed. Many applications can help to calculate it and one of them is implementing Human Activity Recognition using wearable sensors and smartphones. In this paper, an activity recognition model is built using the Reduced Kernel Extreme Learning Machine (RKELM) algorithm using an accelerometer sensor embedded in a smartphone that is used for calculating calories burned. This model was improved from the Extreme Learning Machine with the addition of the Gaussian kernel. The dataset comes from the London py data event in 2016 which consists of five activity labels. The proposed model will be compared with five other models and evaluated using precision, recall, f1score, training time, and testing time. The results have been validated with 10-fold cross-validation. The experimental results show that the RKELM-based recognition model has a higher performance than the other models with acceptable training and testing time, with an f1 score of 97% and less than 0.06 seconds.
{"title":"Human Activity Recognition using Reduced Kernel Extreme Learning Machine for Body Weight Management","authors":"Arwin Halim, Erick Kwantan, Silfi Langie, Vinson Chandra, Hernawati Gohzali","doi":"10.1109/ICIC50835.2020.9288546","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288546","url":null,"abstract":"The problem with bodyweight management is the inability to calculate the number of calories burned and consumed. Many applications can help to calculate it and one of them is implementing Human Activity Recognition using wearable sensors and smartphones. In this paper, an activity recognition model is built using the Reduced Kernel Extreme Learning Machine (RKELM) algorithm using an accelerometer sensor embedded in a smartphone that is used for calculating calories burned. This model was improved from the Extreme Learning Machine with the addition of the Gaussian kernel. The dataset comes from the London py data event in 2016 which consists of five activity labels. The proposed model will be compared with five other models and evaluated using precision, recall, f1score, training time, and testing time. The results have been validated with 10-fold cross-validation. The experimental results show that the RKELM-based recognition model has a higher performance than the other models with acceptable training and testing time, with an f1 score of 97% and less than 0.06 seconds.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130078619","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288547
Indriana Novitiara, D. Pratami, Achmad Fuad Bay
In several telecommunication projects, during the monitoring and controlling phases, the quality control and validate scope processes only rely on the receipt test form and handover minutes. Whereas quality errors, in general, can only be seen in the final project phase. If the project deliverables do not meet the customer requirement, the rework must be done or the worst possibility is that the project must be stopped. A quality metric using the internal control method is a project document that can be used to prevent possible problems. There is a quality metric template from previous research proposed for telecommunication projects, but the factors used as variable critical success criteria have not included other important factors that support project success. Therefore, this study will discuss the development of an existing quality metric template and what processes will be affected by the use of this quality metric in a project. It was found that procedures and human factors are critical success factors that can support project success, and quality metrics have an impact on the quality control process and validate scope. It can be concluded that this study produces a quality metric template that has been developed and this quality metric can be used as a template for other projects such as construction projects or IT projects.
{"title":"Developing a Quality Metric in Controlling the Project Task","authors":"Indriana Novitiara, D. Pratami, Achmad Fuad Bay","doi":"10.1109/ICIC50835.2020.9288547","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288547","url":null,"abstract":"In several telecommunication projects, during the monitoring and controlling phases, the quality control and validate scope processes only rely on the receipt test form and handover minutes. Whereas quality errors, in general, can only be seen in the final project phase. If the project deliverables do not meet the customer requirement, the rework must be done or the worst possibility is that the project must be stopped. A quality metric using the internal control method is a project document that can be used to prevent possible problems. There is a quality metric template from previous research proposed for telecommunication projects, but the factors used as variable critical success criteria have not included other important factors that support project success. Therefore, this study will discuss the development of an existing quality metric template and what processes will be affected by the use of this quality metric in a project. It was found that procedures and human factors are critical success factors that can support project success, and quality metrics have an impact on the quality control process and validate scope. It can be concluded that this study produces a quality metric template that has been developed and this quality metric can be used as a template for other projects such as construction projects or IT projects.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132450519","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288530
R. Rizal Isnanto, Oky Dwi Nurhayati, Tyas Panorama Nan Cerah
The calculation of the area of mangrove forests by conventional methods requires much time and energy. In this study, a tool for calculating the area of mangrove forests in Southeast Sulawesi Province, Indonesia, using satellite imagery is developed on the basis of two segmentation methods, k-means clustering and region growing. We then compare those two methods to obtain the optimal method to calculate the area of mangrove forests. Before this research, there were no researchers who calculated the area of mangrove forests in Southeast Sulawesi using both methods. We constructed a calculation algorithm using Matlab, which includes different stages of digital image processing. The area of mangrove forests is calculated on the basis of the number of pixels with an area density of 900 m2/pixel. The accuracy of the two segmentation methods is compared for identical areas obtained by the National Institute of Aviation and Space in Indonesia (LAPAN), i.e., the area obtained by LAPAN is used as a reference in calculating the accuracy. The accuracy of the region growing segmentation method is 33.33%, whereas that by the k-means clustering segmentation method under optimum conditions is 59.26% in the application of 12 clusters.
{"title":"Area of Mangrove Forests Calculated by Color Image Segmentation using K-Means Clustering and Region Growing)","authors":"R. Rizal Isnanto, Oky Dwi Nurhayati, Tyas Panorama Nan Cerah","doi":"10.1109/ICIC50835.2020.9288530","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288530","url":null,"abstract":"The calculation of the area of mangrove forests by conventional methods requires much time and energy. In this study, a tool for calculating the area of mangrove forests in Southeast Sulawesi Province, Indonesia, using satellite imagery is developed on the basis of two segmentation methods, k-means clustering and region growing. We then compare those two methods to obtain the optimal method to calculate the area of mangrove forests. Before this research, there were no researchers who calculated the area of mangrove forests in Southeast Sulawesi using both methods. We constructed a calculation algorithm using Matlab, which includes different stages of digital image processing. The area of mangrove forests is calculated on the basis of the number of pixels with an area density of 900 m2/pixel. The accuracy of the two segmentation methods is compared for identical areas obtained by the National Institute of Aviation and Space in Indonesia (LAPAN), i.e., the area obtained by LAPAN is used as a reference in calculating the accuracy. The accuracy of the region growing segmentation method is 33.33%, whereas that by the k-means clustering segmentation method under optimum conditions is 59.26% in the application of 12 clusters.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131933609","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288533
Wenty Dwi Yuniarti, E. Winarko, Aina Musdholifah
The diffusion of technology in learning is increasingly massive, marked by the rapid transfer of learning into online environments such as e-Learning. Assessment is an important element of education. Assessment in e-Learning requires methods to be efficient and effective. Data mining is a method of analysis to reveal and recognize hidden patterns in educational databases. Deepening data mining for assessment in e-Learning is both an interesting and a challenge for teachers and institutions to find the right method and make a significant contribution in this area. Therefore, we conducted a literature review and presented state-of-the-art data mining for student assessment in e-Learning from relevant literature publishing from 2016 to 2020. We specifically focus on student assessment research in e-Learning, namely the scope of utilizing data mining, a comparison of several methods, and an analysis of several aspects related to assessment. This study also sheds light on future research directions. We identify the process mining approach as a data mining sub-discipline for the current trend assessment.
{"title":"Data Mining for Student Assessment in e-Leaming: A Survey","authors":"Wenty Dwi Yuniarti, E. Winarko, Aina Musdholifah","doi":"10.1109/ICIC50835.2020.9288533","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288533","url":null,"abstract":"The diffusion of technology in learning is increasingly massive, marked by the rapid transfer of learning into online environments such as e-Learning. Assessment is an important element of education. Assessment in e-Learning requires methods to be efficient and effective. Data mining is a method of analysis to reveal and recognize hidden patterns in educational databases. Deepening data mining for assessment in e-Learning is both an interesting and a challenge for teachers and institutions to find the right method and make a significant contribution in this area. Therefore, we conducted a literature review and presented state-of-the-art data mining for student assessment in e-Learning from relevant literature publishing from 2016 to 2020. We specifically focus on student assessment research in e-Learning, namely the scope of utilizing data mining, a comparison of several methods, and an analysis of several aspects related to assessment. This study also sheds light on future research directions. We identify the process mining approach as a data mining sub-discipline for the current trend assessment.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123257113","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288605
Tuti Nurhaeni, Indri Handayani, Frizca Budiarty, Desy Apriani, P. A. Sunarya
The important role of an educational certificate is very influential in playing professionalism in the ecosystem of a company. Because the certificate is very valuable, it is necessary to store the long term storage space available in a Tamper-proof ledger. The heavy Focus in the research conducted is to present a revolutionary Blockchain technology for education in response to an effective solution in validating the certificate by implementing a blockchain-owned advantage that is a system of Distributed and cryptography, the presence of blockchain technology will be able to eliminate the existence of false diplomas. The study adopted two methods namely, the method of descriptive analysis and the library study method. Blockchain is expected to contribute to success and improve the quality of national education.
{"title":"Adoption of Upcoming Blockchain Revolution in Higher Education: Its Potential in Validating Certificates","authors":"Tuti Nurhaeni, Indri Handayani, Frizca Budiarty, Desy Apriani, P. A. Sunarya","doi":"10.1109/ICIC50835.2020.9288605","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288605","url":null,"abstract":"The important role of an educational certificate is very influential in playing professionalism in the ecosystem of a company. Because the certificate is very valuable, it is necessary to store the long term storage space available in a Tamper-proof ledger. The heavy Focus in the research conducted is to present a revolutionary Blockchain technology for education in response to an effective solution in validating the certificate by implementing a blockchain-owned advantage that is a system of Distributed and cryptography, the presence of blockchain technology will be able to eliminate the existence of false diplomas. The study adopted two methods namely, the method of descriptive analysis and the library study method. Blockchain is expected to contribute to success and improve the quality of national education.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"380 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122767769","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}
A stroke is an attack that often requires long-term rehabilitation. One result of this condition can be seen from abnormal electrical signals in the brain, recorded by an electroencephalogram (EEG). Therefore, EEG can be used for monitoring and evaluation of post-stroke rehabilitation. Neurologists usually observe EEG signals based on their density, amplitude, waveform, and comparison of the channel pairs, but this analysis is not easy. Besides, using machine learning, such as Backpropagation, is sometimes constrained by random initial weights. This state can lead to a long convergence. This paper proposes the selection of initial weights in Backpropagation training using Genetic Algorithms. The use of Genetic Algorithms can optimize the initial weight selection in Backpropagation. The EEG signal used has been extracted into Alpha, Theta, Delta, and Mu waves. The experimental results show that using the Genetic Algorithm can increase non-training data accuracy to 75%, compared to only 65% without the genetic algorithm. Genetic Algorithms can overcome overfitting and local maximums. The results also show that the use of Wavelet transform for feature extraction can increase the accuracy from 60% to 75%. The optimization of training parameters also determines the accuracy.
{"title":"Learning Optimization Using Genetic Algorithm in Post-Stroke EEG Signal Classification","authors":"Esmeralda Contessa Djamal, Mita Amara, Daswara Djajasasmita, Sandy Lesmana Liem Limanjaya","doi":"10.1109/ICIC50835.2020.9288559","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288559","url":null,"abstract":"A stroke is an attack that often requires long-term rehabilitation. One result of this condition can be seen from abnormal electrical signals in the brain, recorded by an electroencephalogram (EEG). Therefore, EEG can be used for monitoring and evaluation of post-stroke rehabilitation. Neurologists usually observe EEG signals based on their density, amplitude, waveform, and comparison of the channel pairs, but this analysis is not easy. Besides, using machine learning, such as Backpropagation, is sometimes constrained by random initial weights. This state can lead to a long convergence. This paper proposes the selection of initial weights in Backpropagation training using Genetic Algorithms. The use of Genetic Algorithms can optimize the initial weight selection in Backpropagation. The EEG signal used has been extracted into Alpha, Theta, Delta, and Mu waves. The experimental results show that using the Genetic Algorithm can increase non-training data accuracy to 75%, compared to only 65% without the genetic algorithm. Genetic Algorithms can overcome overfitting and local maximums. The results also show that the use of Wavelet transform for feature extraction can increase the accuracy from 60% to 75%. The optimization of training parameters also determines the accuracy.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126377210","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288612
F. Azzahro, Muhammad Adil, Arya Fathurrahman, Athifah Fidelia Sectianri, Nabila Laili Halimah, A. Hidayanto, Adhi Yuniarto Laurentius Yohanes
The emerging ride-hailing services providing services to 60.7 million customers daily has, in aggregate, become a US$5,261 million industry in Indonesia. Such a flourishing industry is being overpowered by two companies, GOJEK and GRAB. Most research is focused on how to maintain and gain more customers in ride-hailing companies while forgetting that drivers are as essential as customers in the industry. This paper aims to understand GOJEK drivers' loyalty toward the company, by examining the role of partnership and service quality provided by GOJEK for them. The study uses a quantitative approach to 150 respondents and then analyze the data using PLS-SEM. The study shows that partnership has a significant influence on trust, service quality, and driver satisfaction towards the company. Meanwhile, trust and satisfaction have a significant direct effect on loyalty. Thus, to improve drivers' loyalty, GOJEK needs to strengthen its partnership with drivers and provide better service quality for them.
{"title":"Examining GOJEK Drivers' Loyalty: The Influence of GOJEK's Partnership Mechanism and Service Quality","authors":"F. Azzahro, Muhammad Adil, Arya Fathurrahman, Athifah Fidelia Sectianri, Nabila Laili Halimah, A. Hidayanto, Adhi Yuniarto Laurentius Yohanes","doi":"10.1109/ICIC50835.2020.9288612","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288612","url":null,"abstract":"The emerging ride-hailing services providing services to 60.7 million customers daily has, in aggregate, become a US$5,261 million industry in Indonesia. Such a flourishing industry is being overpowered by two companies, GOJEK and GRAB. Most research is focused on how to maintain and gain more customers in ride-hailing companies while forgetting that drivers are as essential as customers in the industry. This paper aims to understand GOJEK drivers' loyalty toward the company, by examining the role of partnership and service quality provided by GOJEK for them. The study uses a quantitative approach to 150 respondents and then analyze the data using PLS-SEM. The study shows that partnership has a significant influence on trust, service quality, and driver satisfaction towards the company. Meanwhile, trust and satisfaction have a significant direct effect on loyalty. Thus, to improve drivers' loyalty, GOJEK needs to strengthen its partnership with drivers and provide better service quality for them.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114184560","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：