Pub Date : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865324
Astri Wulandari, Arfianto Fahmi, N. Adriansyah
Device-to-Device (D2D) communication is one of the key technologies to achieving higher speeds, lower latency, and less energy. D2D communication is direct link communication between two communication devices, meaning that communication can occur without going through the base station. However, because communication occurs without going through the base station and D2D users do not have their resources, D2D users simultaneously use the resources owned by Cellular User Equipment (CUE) to communicate and cause interference. Power allocation is optimized to mitigate the interference between D2D users and CUEs and maximize the system's overall sum rate. The traditional power allocation scheme in D2D communication still has problems related to the efficiency of the allocation, coordination of interference, and limitations for operating in real-time systems. This work focuses on designing the Long Short Term Memory with Fully Convolutional Network (LSTM-FCN) algorithm suitable for the power control problem on a D2D underlay communication system with an uplink-side multi-cell scheme. The simulation results show that enhancement of CUE can increase the system's sum rate and energy efficiency. At the same time, enhancement of the D2D pair can also increase the sum rate but decrease energy efficiency. Both LSTM-FCN, LSTM, and FCN can approximate the performance of the conventional scheme (CA-based algorithm). Besides that, LSTM-FCN gets the smallest time complexity compared to the other two algorithms and gets the closest performance to CA in both scenarios above 97% accuracy.
{"title":"Power Allocation Based LSTM-FCN in D2D Underlaying with Multi-Cell Cellular Network","authors":"Astri Wulandari, Arfianto Fahmi, N. Adriansyah","doi":"10.1109/CyberneticsCom55287.2022.9865324","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865324","url":null,"abstract":"Device-to-Device (D2D) communication is one of the key technologies to achieving higher speeds, lower latency, and less energy. D2D communication is direct link communication between two communication devices, meaning that communication can occur without going through the base station. However, because communication occurs without going through the base station and D2D users do not have their resources, D2D users simultaneously use the resources owned by Cellular User Equipment (CUE) to communicate and cause interference. Power allocation is optimized to mitigate the interference between D2D users and CUEs and maximize the system's overall sum rate. The traditional power allocation scheme in D2D communication still has problems related to the efficiency of the allocation, coordination of interference, and limitations for operating in real-time systems. This work focuses on designing the Long Short Term Memory with Fully Convolutional Network (LSTM-FCN) algorithm suitable for the power control problem on a D2D underlay communication system with an uplink-side multi-cell scheme. The simulation results show that enhancement of CUE can increase the system's sum rate and energy efficiency. At the same time, enhancement of the D2D pair can also increase the sum rate but decrease energy efficiency. Both LSTM-FCN, LSTM, and FCN can approximate the performance of the conventional scheme (CA-based algorithm). Besides that, LSTM-FCN gets the smallest time complexity compared to the other two algorithms and gets the closest performance to CA in both scenarios above 97% accuracy.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126081571","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}
It has widely known that Online Customer Reviews have become an integral part of customer decision-making before making online purchases. Sellers and platforms alike develop a strategy to shape reviews profitably under the pretext of increasing sales. Review Solicitation has been used to increase review volume and review valance in the online review platform. Interestingly, while much research is conducted to find the impact of review solicitation on the characteristics of reviews generated, there is not much research done on the perception of customers who have experienced the review solicitation strategy that might pose a problem for parties involved. This study aims to fill the gap of previous studies in finding the answer to what happens to the review credibility and Trust from the customer perspective after review solicitation. The research used Sequential Equation Modeling (SEM) process from 112 data obtained using Purposive sampling with online respondents around the Jabodetabek area in Indonesia in March 2022. There are five variables (Review Solicitation Awareness, Review Solicitation experience, Review Credibility, Trust, and Purchase Intention) with four hypotheses in this study. This study found that customers' Reviews Solicitation Experience significantly influences review credibility. At the same time, customers' Reviews of Solicitation Awareness significantly influence Trust. Then, Trust significantly influences Purchase Intention.
{"title":"The Impact on Review Credibility and Trust from Review Solicitation on E-commerce","authors":"Erwin Ardianto Halim, Zahran Fawwaz Muzakir, Marylise Hebrard","doi":"10.1109/CyberneticsCom55287.2022.9865619","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865619","url":null,"abstract":"It has widely known that Online Customer Reviews have become an integral part of customer decision-making before making online purchases. Sellers and platforms alike develop a strategy to shape reviews profitably under the pretext of increasing sales. Review Solicitation has been used to increase review volume and review valance in the online review platform. Interestingly, while much research is conducted to find the impact of review solicitation on the characteristics of reviews generated, there is not much research done on the perception of customers who have experienced the review solicitation strategy that might pose a problem for parties involved. This study aims to fill the gap of previous studies in finding the answer to what happens to the review credibility and Trust from the customer perspective after review solicitation. The research used Sequential Equation Modeling (SEM) process from 112 data obtained using Purposive sampling with online respondents around the Jabodetabek area in Indonesia in March 2022. There are five variables (Review Solicitation Awareness, Review Solicitation experience, Review Credibility, Trust, and Purchase Intention) with four hypotheses in this study. This study found that customers' Reviews Solicitation Experience significantly influences review credibility. At the same time, customers' Reviews of Solicitation Awareness significantly influence Trust. Then, Trust significantly influences Purchase Intention.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126246993","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865317
Ardiansyah Kamal Alkaff, B. Prasetiyo
Convolutional Neural Network (CNN) has been successfully applied to image classification, one of which is plant or leaf disease. However, choosing the optimal architecture and hyperparameters is a challenge in its implementation. The purpose of this study was to optimize the Convolutional Neural Network (CNN) hyperparameter on the classification of tomato leaf diseases. In this research, optimization of hyperparameter Convolutional Neural Network (CNN) using Hyperband on Tomato Leaf Disease Detection dataset. The dataset consists of 10,000 training data and 1,000 testing data with 10 classes. In the training data, the distribution of the dataset is 80% for training data and 20% for data validation. This study uses the Keras-Tuner library which aims to optimize two hyperparameters, namely the number of dense neurons and the learning rate. The best hyperparameter value resulting from hyperparameter optimization is 128 for the number of dense neurons and 0.001 for the learning rate. The proposed method succeeded in achieving an accuracy value of 95.690% in the training phase and 88.50% in the validation phase. These results were obtained from model training of 50 epochs. In addition, the model testing obtained an accuracy value of 88.60%. Therefore, hyperparameter optimization on Convolutional Neural Network (CNN) using Hyperband can be an alternative in choosing the optimal architecture and hyperparameters.
{"title":"Hyperparameter Optimization on CNN Using Hyperband on Tomato Leaf Disease Classification","authors":"Ardiansyah Kamal Alkaff, B. Prasetiyo","doi":"10.1109/CyberneticsCom55287.2022.9865317","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865317","url":null,"abstract":"Convolutional Neural Network (CNN) has been successfully applied to image classification, one of which is plant or leaf disease. However, choosing the optimal architecture and hyperparameters is a challenge in its implementation. The purpose of this study was to optimize the Convolutional Neural Network (CNN) hyperparameter on the classification of tomato leaf diseases. In this research, optimization of hyperparameter Convolutional Neural Network (CNN) using Hyperband on Tomato Leaf Disease Detection dataset. The dataset consists of 10,000 training data and 1,000 testing data with 10 classes. In the training data, the distribution of the dataset is 80% for training data and 20% for data validation. This study uses the Keras-Tuner library which aims to optimize two hyperparameters, namely the number of dense neurons and the learning rate. The best hyperparameter value resulting from hyperparameter optimization is 128 for the number of dense neurons and 0.001 for the learning rate. The proposed method succeeded in achieving an accuracy value of 95.690% in the training phase and 88.50% in the validation phase. These results were obtained from model training of 50 epochs. In addition, the model testing obtained an accuracy value of 88.60%. Therefore, hyperparameter optimization on Convolutional Neural Network (CNN) using Hyperband can be an alternative in choosing the optimal architecture and hyperparameters.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114838081","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865609
Anggun Barokhah, M. L. Hamzah, Eki Saputra, Fitriani Muttakin
Media Website “Diskominfotik” Bengkalis is a form of e-learning developed by the Department of Communication, Information and Statistics which plays an important role in the development of Bengkalis district. The services and features provided are in the form of bengkalis news, activity galleries, important announcements, activity videos, public information and activity agendas. This study is based on the fact that users are dissatisfied with the services provided by the Bengkalis Diskominfotik website, such as the lack of updated information that users need. The aim of this study was to measure the level of satisfaction of website users using the EUCS method with five perspectives, namely content, accuracy, format, ease of use, and timeliness and the IPA method to find out the attributes that are important to improve or need to be interpreted in the form of a matrix. The results of this study indicated that all attributes in terms of importance had the category of satisfied and quite satisfied, and the performance attribute was also in the category of satisfied and quite satisfied. namely the variable content, accuracy, ease of use, with the category satisfied, while the format with the category quite satisfied.
{"title":"An Integration of End User Computing Satisfaction and Importance Performance Analysis on Website","authors":"Anggun Barokhah, M. L. Hamzah, Eki Saputra, Fitriani Muttakin","doi":"10.1109/CyberneticsCom55287.2022.9865609","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865609","url":null,"abstract":"Media Website “Diskominfotik” Bengkalis is a form of e-learning developed by the Department of Communication, Information and Statistics which plays an important role in the development of Bengkalis district. The services and features provided are in the form of bengkalis news, activity galleries, important announcements, activity videos, public information and activity agendas. This study is based on the fact that users are dissatisfied with the services provided by the Bengkalis Diskominfotik website, such as the lack of updated information that users need. The aim of this study was to measure the level of satisfaction of website users using the EUCS method with five perspectives, namely content, accuracy, format, ease of use, and timeliness and the IPA method to find out the attributes that are important to improve or need to be interpreted in the form of a matrix. The results of this study indicated that all attributes in terms of importance had the category of satisfied and quite satisfied, and the performance attribute was also in the category of satisfied and quite satisfied. namely the variable content, accuracy, ease of use, with the category satisfied, while the format with the category quite satisfied.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116975114","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 : 2022-06-16DOI: 10.1109/cyberneticscom55287.2022.9865555
Arfianto Fahmi
{"title":"Welcome Message from General Chair The 6th Cyberneticscom 2022","authors":"Arfianto Fahmi","doi":"10.1109/cyberneticscom55287.2022.9865555","DOIUrl":"https://doi.org/10.1109/cyberneticscom55287.2022.9865555","url":null,"abstract":"","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114342651","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865624
Iis Setiawan Mangkunegara, P. Purwono
Viruses and bacteria are constantly evolving in the world. Early identification of pathogens is one way that can be used to spread the spread of disease to drug design. DNA sequence classification is an essential aspect of computational biology. Pathogen identification was carried out by comparing data between sequenced genomes with NCBI data. Machine learning technology can classify DNA whose nature is unclear, and the sequence is considered long and challenging to find. The SVM classification model is proposed in this study. The resulting accuracy is still considered not optimal, so optimization is needed. In contrast to previous studies, we used the grid search cv optimization technique on the SVM classification model. Kernel polynomial with 2 degrees is the best parameter recommendation from the grid search cv technique. The accuracy before the optimization is 77%, while it is 90% after optimization. This shows an increase in accuracy of 14% after applying the grid search cv method to DNA sequence classification using the SVM model.
{"title":"Analysis of DNA Sequence Classification Using SVM Model with Hyperparameter Tuning Grid Search CV","authors":"Iis Setiawan Mangkunegara, P. Purwono","doi":"10.1109/CyberneticsCom55287.2022.9865624","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865624","url":null,"abstract":"Viruses and bacteria are constantly evolving in the world. Early identification of pathogens is one way that can be used to spread the spread of disease to drug design. DNA sequence classification is an essential aspect of computational biology. Pathogen identification was carried out by comparing data between sequenced genomes with NCBI data. Machine learning technology can classify DNA whose nature is unclear, and the sequence is considered long and challenging to find. The SVM classification model is proposed in this study. The resulting accuracy is still considered not optimal, so optimization is needed. In contrast to previous studies, we used the grid search cv optimization technique on the SVM classification model. Kernel polynomial with 2 degrees is the best parameter recommendation from the grid search cv technique. The accuracy before the optimization is 77%, while it is 90% after optimization. This shows an increase in accuracy of 14% after applying the grid search cv method to DNA sequence classification using the SVM model.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124577406","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865244
A. Suraji, Fitri Marisa, Candra Aditya, Faqih Rofii, A. Sudjianto, R. Riman
Expansive soil has a fairly high shrinkage rate and will affect the strength of the road pavement structure. This paper aims to analyze the condition of expansive soil associated with road pavement damage. The method of collecting road damage data is done by data mining from the GIS portal database owned by Bina Marga. Meanwhile, data on soil conditions was taken from the portal belonging to the Geological Agency. The analytical method used is the statistical approach t- Test - Paired Two Sample for Means. The results of the study show that there is a correlation between expansive soil conditions and road damage. Expansive soil has a significant effect on road damage.
{"title":"Correlation of Expansive Soil and Road Pavement Conditions Using Data Mining from GIS Portal","authors":"A. Suraji, Fitri Marisa, Candra Aditya, Faqih Rofii, A. Sudjianto, R. Riman","doi":"10.1109/CyberneticsCom55287.2022.9865244","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865244","url":null,"abstract":"Expansive soil has a fairly high shrinkage rate and will affect the strength of the road pavement structure. This paper aims to analyze the condition of expansive soil associated with road pavement damage. The method of collecting road damage data is done by data mining from the GIS portal database owned by Bina Marga. Meanwhile, data on soil conditions was taken from the portal belonging to the Geological Agency. The analytical method used is the statistical approach t- Test - Paired Two Sample for Means. The results of the study show that there is a correlation between expansive soil conditions and road damage. Expansive soil has a significant effect on road damage.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132903584","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865640
Ivan Bashofi, Muhammad Salman
Cyberspace was created by the development of Information and Communication Technology (ICT). This makes it easier to access, manage information faster and more accurately, and improve the efficiency of performing activities and achieving business goals. On the other hand, the higher the usage of information technology, the higher the potential for organizational security incident gaps and cybercrime. Addressing this issue requires security standards that are appropriate and meet the requirements for organizations to know the maturity of cybersecurity. XYZ Organization is one of the government instances managing Indonesia's critical infrastructures. Although some international security standards have been implemented, the results of preparing for information security management are not yet optimal. Analysis of the NIST, CIS Controls v8, and ISO27002 standards was performed in this research. In addition, the analysis results are used as resources to create a cybersecurity maturity framework through the three standard approaches that underlie ICT management. And for the result, the proposed concepts of the 21 integrated cybersecurity categories are expected to become an asset in terms of XYZ organization's ICT management performance.
{"title":"Cybersecurity Maturity Assessment Design Using NISTCSF, CIS CONTROLS v8 and ISO/IEC 27002","authors":"Ivan Bashofi, Muhammad Salman","doi":"10.1109/CyberneticsCom55287.2022.9865640","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865640","url":null,"abstract":"Cyberspace was created by the development of Information and Communication Technology (ICT). This makes it easier to access, manage information faster and more accurately, and improve the efficiency of performing activities and achieving business goals. On the other hand, the higher the usage of information technology, the higher the potential for organizational security incident gaps and cybercrime. Addressing this issue requires security standards that are appropriate and meet the requirements for organizations to know the maturity of cybersecurity. XYZ Organization is one of the government instances managing Indonesia's critical infrastructures. Although some international security standards have been implemented, the results of preparing for information security management are not yet optimal. Analysis of the NIST, CIS Controls v8, and ISO27002 standards was performed in this research. In addition, the analysis results are used as resources to create a cybersecurity maturity framework through the three standard approaches that underlie ICT management. And for the result, the proposed concepts of the 21 integrated cybersecurity categories are expected to become an asset in terms of XYZ organization's ICT management performance.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130135190","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865313
A. Eviyanti, Ahmad Saikhu, C. Fatichah
Seizures are a common symptom of epilepsy, a nervous system disease. Epilepsy can be detected with an Electroencephalogram (EEG) signal that records brain nerve activity. Visual observations cannot be done on a routine basis because the EEG signal has a large volume and high dimensions, so a method for dimension reduction is needed to maintain signal information. Appropriate features should be selected to reduce computational complexity and classification time in detecting epileptic seizures. This study compares the performance of Machine Learning and Deep Learning models to detect epileptic seizures to get the best performing model. The feature extraction process using Discrete Wavelet Transform (DWT) taking feature values, namely maximum, minimum, standard deviation, mean, median, and energy. Furthermore, feature selection uses correlation variables, namely removing uncorrelated variables using threshold variations. The improvement of this study is to use six features, namely the maximum, minimum, standard deviation, mean, median, and energy values, as input values in the classification process. Non-seizure signals and epileptic seizures were classified using Machine Learning: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Decision Tree (DT), and Deep Learning: Long Short-Term Memory (LSTM). The trials used three variations of datasets, namely dataset 1: 96 signals, dataset 134 signals, and dataset 3: 182 signals. Nine different classification experiments were conducted using four performance evaluation indicators: accuracy, precision, recall, and F1-Score. Based on the test results, the model with the best performance is the SVM method with 100% accuracy, 100% precision, 100% recall, and 100% f1-score.
{"title":"Epileptic Seizure Detection Using Machine Learning and Deep Learning Method","authors":"A. Eviyanti, Ahmad Saikhu, C. Fatichah","doi":"10.1109/CyberneticsCom55287.2022.9865313","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865313","url":null,"abstract":"Seizures are a common symptom of epilepsy, a nervous system disease. Epilepsy can be detected with an Electroencephalogram (EEG) signal that records brain nerve activity. Visual observations cannot be done on a routine basis because the EEG signal has a large volume and high dimensions, so a method for dimension reduction is needed to maintain signal information. Appropriate features should be selected to reduce computational complexity and classification time in detecting epileptic seizures. This study compares the performance of Machine Learning and Deep Learning models to detect epileptic seizures to get the best performing model. The feature extraction process using Discrete Wavelet Transform (DWT) taking feature values, namely maximum, minimum, standard deviation, mean, median, and energy. Furthermore, feature selection uses correlation variables, namely removing uncorrelated variables using threshold variations. The improvement of this study is to use six features, namely the maximum, minimum, standard deviation, mean, median, and energy values, as input values in the classification process. Non-seizure signals and epileptic seizures were classified using Machine Learning: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Decision Tree (DT), and Deep Learning: Long Short-Term Memory (LSTM). The trials used three variations of datasets, namely dataset 1: 96 signals, dataset 134 signals, and dataset 3: 182 signals. Nine different classification experiments were conducted using four performance evaluation indicators: accuracy, precision, recall, and F1-Score. Based on the test results, the model with the best performance is the SVM method with 100% accuracy, 100% precision, 100% recall, and 100% f1-score.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129972001","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 : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865354
Agung Suhendar, Tri Ayuningsih, S. Suyanto
Human activity recognition (HAR) is critical for determining human interactions and interpersonal relationships. Among the various classification techniques, two things become the main focus of HAR, namely the type of activity and its localization. Most of the tasks in HAR involve identifying a human scene from a series of frames in a video, where the subject being monitored is free to perform an activity. For some of the current HAR approaches, 3D sensors are used as input extractors for the skeleton/body pose of the subject being monitored. It is much more precise than using only 2D information obtained from conventional cameras. Of course, the use of 3D sensors is a significant limitation for implementing video-based surveillance systems. In this research, we use the Deep learning OpenPose 3D method as a substitute for 3D sensors that can estimate the 3D frame/pose of the subject's body identified from conventional camera 2D input sources. It is then combined with other machine learning methods for the activity classification process from the obtained 3D framework. Classifiers that can be used include Support Vector Machine (SVM), Neural Network (NN), Long short-term memory (LSTM), and Transformer. Thus, HAR can be applied flexibly in various scopes of supervision without the help of 3D sensors. The experiment results inform that Transformer is the best in accuracy while SVM is in speed.
{"title":"Skeletal-based Classification for Human Activity Recognition","authors":"Agung Suhendar, Tri Ayuningsih, S. Suyanto","doi":"10.1109/CyberneticsCom55287.2022.9865354","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865354","url":null,"abstract":"Human activity recognition (HAR) is critical for determining human interactions and interpersonal relationships. Among the various classification techniques, two things become the main focus of HAR, namely the type of activity and its localization. Most of the tasks in HAR involve identifying a human scene from a series of frames in a video, where the subject being monitored is free to perform an activity. For some of the current HAR approaches, 3D sensors are used as input extractors for the skeleton/body pose of the subject being monitored. It is much more precise than using only 2D information obtained from conventional cameras. Of course, the use of 3D sensors is a significant limitation for implementing video-based surveillance systems. In this research, we use the Deep learning OpenPose 3D method as a substitute for 3D sensors that can estimate the 3D frame/pose of the subject's body identified from conventional camera 2D input sources. It is then combined with other machine learning methods for the activity classification process from the obtained 3D framework. Classifiers that can be used include Support Vector Machine (SVM), Neural Network (NN), Long short-term memory (LSTM), and Transformer. Thus, HAR can be applied flexibly in various scopes of supervision without the help of 3D sensors. The experiment results inform that Transformer is the best in accuracy while SVM is in speed.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132061874","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：