Pub Date : 2022-06-16DOI: 10.1109/CyberneticsCom55287.2022.9865477
Anubhuti Singh, Arun C. S. Kumar
After a prolonged use of a faulty bearing, cracks are created on more than one parts of the bearing, which is a compound fault condition. This situation is tougher than the single fault condition. This combined faulty bearing creates a complex vibration signal with significant amount of noise, where it becomes very difficult to identify the fault frequencies by signal processing methods. This paper deals with a novel machine learning method for the compound fault diagnosis of Rolling bearing, where compound fault signals are decomposed into Intrinsic Mode Functions (IMF) by Ensemble Empirical Mode Decomposition (EEMD). The proposed method uses Convolution NeuralNetwork (CNN) based technique, which receives the decomposed signals of compound fault signal as input to CNN. These IMFs consists of groups of different frequencies. When these IMFs are given as input to CNN it classifies it effectively into different faults existing on bearing. CNN yields almost 96% accuracy which is better than any other previous performance for compound faultclassification.
{"title":"EEMD-CNN based Method for Compound Fault Diagnosis of Bearing","authors":"Anubhuti Singh, Arun C. S. Kumar","doi":"10.1109/CyberneticsCom55287.2022.9865477","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865477","url":null,"abstract":"After a prolonged use of a faulty bearing, cracks are created on more than one parts of the bearing, which is a compound fault condition. This situation is tougher than the single fault condition. This combined faulty bearing creates a complex vibration signal with significant amount of noise, where it becomes very difficult to identify the fault frequencies by signal processing methods. This paper deals with a novel machine learning method for the compound fault diagnosis of Rolling bearing, where compound fault signals are decomposed into Intrinsic Mode Functions (IMF) by Ensemble Empirical Mode Decomposition (EEMD). The proposed method uses Convolution NeuralNetwork (CNN) based technique, which receives the decomposed signals of compound fault signal as input to CNN. These IMFs consists of groups of different frequencies. When these IMFs are given as input to CNN it classifies it effectively into different faults existing on bearing. CNN yields almost 96% accuracy which is better than any other previous performance for compound faultclassification.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"48 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120822133","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/CyberneticsCom55287.2022.9865427
Havinda Rosita Faradina, Tenia Wahyuningrum, Novian Adi Prasetyo, Iqsyahiro Kresna A
Usability is the level of ease of users in using the interface on a system. Usability can be measured using expert judgment or user testing. One of the techniques in usability measurement that can be is Heuristic Evaluation (measured by the expert) and Usability Metric for User Experience or as known as UMUX (measured by user). Heuristic Evaluation is an interface evaluation process that aims to measure an interface's usability, efficiency, and effectiveness based on ten heuristic rules. Meanwhile, UMUX is a short-level instrument method or rating level used to collect quantitative user data about the usability of an application. Therefore, the combination of expert judgment and user assessment will provide rich and complementary findings. In this study, we used “CARDS” as the research object. “CARDS” is a digital card application or e-wallet used to pay bills, top-up card balances, online stores, and Payment Point Online Banks. This study aims to improve the quality of service to users of the “CARDS” application by testing the user experience. The result shows that the UMUX score is not equal to 74, so it is necessary to make improvements, with recommendations from experts by the Heuristic Evaluation method based on the lowest assessment score, namely the Consistency and Standards category.
{"title":"User Experience Analysis on e-Wallet Using a Combination of Heuristic Evaluation and UMUX","authors":"Havinda Rosita Faradina, Tenia Wahyuningrum, Novian Adi Prasetyo, Iqsyahiro Kresna A","doi":"10.1109/CyberneticsCom55287.2022.9865427","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865427","url":null,"abstract":"Usability is the level of ease of users in using the interface on a system. Usability can be measured using expert judgment or user testing. One of the techniques in usability measurement that can be is Heuristic Evaluation (measured by the expert) and Usability Metric for User Experience or as known as UMUX (measured by user). Heuristic Evaluation is an interface evaluation process that aims to measure an interface's usability, efficiency, and effectiveness based on ten heuristic rules. Meanwhile, UMUX is a short-level instrument method or rating level used to collect quantitative user data about the usability of an application. Therefore, the combination of expert judgment and user assessment will provide rich and complementary findings. In this study, we used “CARDS” as the research object. “CARDS” is a digital card application or e-wallet used to pay bills, top-up card balances, online stores, and Payment Point Online Banks. This study aims to improve the quality of service to users of the “CARDS” application by testing the user experience. The result shows that the UMUX score is not equal to 74, so it is necessary to make improvements, with recommendations from experts by the Heuristic Evaluation method based on the lowest assessment score, namely the Consistency and Standards category.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"11 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120849544","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/CyberneticsCom55287.2022.9865604
Jakkaphan Whasphuttisit, Watchareewan Jitsakul
This research aims to study the suitable time series analysis to forecast the automobile and parts product export values over the next 12 months. The time series data source gathers from the Government Open Data of Thailand official website during January 2013 to December 2021, 108 months in total. The experiment starts with creation, comparison, selection, verification, and forecasting. Time series analysis has considered five methods: Trend Analysis, Moving Average, Decomposition, Single Exponential Smoothing, and Double Exponential Smoothing. We use mean absolute present error (MAPE), mean absolute deviation (MAD), and mean squared deviation (MSD) to compare and select the least value. The result showed that Moving Average had the best performance. Then we used the Moving Average to verify and forecast over the next 12 months. However, it was found that the forecast values obtained were constant for the entire 12 months, so the moving average is unused for forecasting. The Moving Average has the least mean absolute present error (MAPE) at 0.2420. Therefore, we have used Decomposition which is a suitable performance in the second order of forecasting. It is forecast and has a trend value. Moreover, the Decomposition method has the least mean absolute present error (MAPE) at 0.1832.
本研究旨在研究适合的时间序列分析，以预测未来12个月的汽车及零部件产品出口价值。时间序列数据源来自泰国官方网站Government Open data，时间为2013年1月至2021年12月，共108个月。实验从创造、比较、选择、验证和预测开始。时间序列分析考虑了五种方法:趋势分析、移动平均、分解、单指数平滑和双指数平滑。我们使用平均绝对当前误差(MAPE)，平均绝对偏差(MAD)和均方偏差(MSD)来比较和选择最小值。结果表明，移动平均线的表现最好。然后我们使用移动平均线来验证和预测未来12个月的走势。然而，我们发现，整个12个月的预测值是不变的，所以移动平均线不用于预测。移动平均线的平均绝对当前误差(MAPE)最小，为0.2420。因此，我们使用了分解，这是一种适合于二级预测的性能。它是预测的，具有趋势值。此外，分解方法的平均绝对当前误差(MAPE)最小，为0.1832。
{"title":"Forecasting the Automobile and Parts Product Export Values using Time Series Analysis","authors":"Jakkaphan Whasphuttisit, Watchareewan Jitsakul","doi":"10.1109/CyberneticsCom55287.2022.9865604","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865604","url":null,"abstract":"This research aims to study the suitable time series analysis to forecast the automobile and parts product export values over the next 12 months. The time series data source gathers from the Government Open Data of Thailand official website during January 2013 to December 2021, 108 months in total. The experiment starts with creation, comparison, selection, verification, and forecasting. Time series analysis has considered five methods: Trend Analysis, Moving Average, Decomposition, Single Exponential Smoothing, and Double Exponential Smoothing. We use mean absolute present error (MAPE), mean absolute deviation (MAD), and mean squared deviation (MSD) to compare and select the least value. The result showed that Moving Average had the best performance. Then we used the Moving Average to verify and forecast over the next 12 months. However, it was found that the forecast values obtained were constant for the entire 12 months, so the moving average is unused for forecasting. The Moving Average has the least mean absolute present error (MAPE) at 0.2420. Therefore, we have used Decomposition which is a suitable performance in the second order of forecasting. It is forecast and has a trend value. Moreover, the Decomposition method has the least mean absolute present error (MAPE) at 0.1832.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"74 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":"124431942","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/CyberneticsCom55287.2022.9865509
Satria Hidayat, Aviv Yuniar Rahman, Istiadi
Betta fish also known as battling fish, is a type of freshwater fish that is well known among ornamental fish lovers. For this reason, the analyst proposes Betta Fish Picture Grouping Utilizing Artificial Neural Networks with the Color Gabor feature. The test results have 3 parameters, namely precision, recall, and accuracy. The level in comparison using a comparator between 50:50. The results obtained starting from the Gabor feature with CMYK precision color have test results reaching 37.94%. Then the recall has a value of 30.40% and accuracy in the existing accuracy reaches 56.71%. From the results of testing the Gabor feature with HSV precision color, reached 38.69%. Then the recall has value of 34.92% and accuracy in the existing accuracy reaches 54.69%. The Gabor feature with RGB precision reaching 39.40% at a 50:50. Then the recall has a value of 32.28% at a 50:50. The level of accuracy in the existing accuracy reaches 58.85% with a ratio of 50:50. From this it can be concluded that the Gabor feature with GRB color has the best accuracy value at a ratio of 50:50. The Gabor feature with RGB color is the best result in betta fish classification using Artificial Neural Networks.
{"title":"Betta Fish Image Classification Using Artificial Neural Networks with Gabor Extraction Features","authors":"Satria Hidayat, Aviv Yuniar Rahman, Istiadi","doi":"10.1109/CyberneticsCom55287.2022.9865509","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865509","url":null,"abstract":"Betta fish also known as battling fish, is a type of freshwater fish that is well known among ornamental fish lovers. For this reason, the analyst proposes Betta Fish Picture Grouping Utilizing Artificial Neural Networks with the Color Gabor feature. The test results have 3 parameters, namely precision, recall, and accuracy. The level in comparison using a comparator between 50:50. The results obtained starting from the Gabor feature with CMYK precision color have test results reaching 37.94%. Then the recall has a value of 30.40% and accuracy in the existing accuracy reaches 56.71%. From the results of testing the Gabor feature with HSV precision color, reached 38.69%. Then the recall has value of 34.92% and accuracy in the existing accuracy reaches 54.69%. The Gabor feature with RGB precision reaching 39.40% at a 50:50. Then the recall has a value of 32.28% at a 50:50. The level of accuracy in the existing accuracy reaches 58.85% with a ratio of 50:50. From this it can be concluded that the Gabor feature with GRB color has the best accuracy value at a ratio of 50:50. The Gabor feature with RGB color is the best result in betta fish classification using Artificial Neural Networks.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"14 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":"130593454","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/CyberneticsCom55287.2022.9865543
Y. Jusman, Anna Widyaningrum, Sartika Puspita
A number of patients with untreated caries only seek treatment at late stages when serious complications might have already developed and can lead to significant acute and chronic conditions with high cost of treatment. The purpose of this research is to be able to find out the level of caries based on X ray images by using image processing and machine learning methods. The image processing algorithm namely Gray Level Co-occurrence Matrix (GLCM) has been used to extract texture features and Multilayer Perceptron (MLP) methods to classify the X ray caries images. Lavenberg Marquard and Backpropagation Bayesian Regularization are used in this study. The conclusion obtained in this study is that the algorithm of classification using Multilayer Perceptron (MLP) based texture features can classify dental caries images in four classes. The best performance result is achieved the training accuracy of 99.20% and the testing accuracy of 98.30% by using Lavenberg Marquardt (LM) model with hidden layer 10. In Backpropagation Bayesian Regularization (BR), the best results are found in hidden layer 10 as well (Training: 100%, Testing: 100%).
{"title":"Algorithm of Caries Level Image Classification Using Multilayer Perceptron Based Texture Features","authors":"Y. Jusman, Anna Widyaningrum, Sartika Puspita","doi":"10.1109/CyberneticsCom55287.2022.9865543","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865543","url":null,"abstract":"A number of patients with untreated caries only seek treatment at late stages when serious complications might have already developed and can lead to significant acute and chronic conditions with high cost of treatment. The purpose of this research is to be able to find out the level of caries based on X ray images by using image processing and machine learning methods. The image processing algorithm namely Gray Level Co-occurrence Matrix (GLCM) has been used to extract texture features and Multilayer Perceptron (MLP) methods to classify the X ray caries images. Lavenberg Marquard and Backpropagation Bayesian Regularization are used in this study. The conclusion obtained in this study is that the algorithm of classification using Multilayer Perceptron (MLP) based texture features can classify dental caries images in four classes. The best performance result is achieved the training accuracy of 99.20% and the testing accuracy of 98.30% by using Lavenberg Marquardt (LM) model with hidden layer 10. In Backpropagation Bayesian Regularization (BR), the best results are found in hidden layer 10 as well (Training: 100%, Testing: 100%).","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"30 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":"121622510","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/CyberneticsCom55287.2022.9865498
Anindita Septiarini, Ferda Maulana, H. Hamdani, Rizqi Saputra, Tenia Wahyuningrum, Indra
Swallow Nest is a valuable export commodity, particularly in Indonesia. It is produced when a swallow's saliva hardens and is frequently encountered in high-rise buildings. Swallow nests can be utilized to treat various ailments in the medical sector. The price of a swallow nest varies according to its quality, which is commonly classified into three grades: quality 1 (Q1), quality 2 (Q2), and quality 3 (Q3). Q1 is of the highest quality, while Q3 is of the lowest. Each grade has a different physical appearance. Currently, many people lack knowledge regarding the grade of a swallow nest. Therefore, a method is needed to automatically classify the quality of swallow nests based on computer vision. The proposed method consists of several main processes, including image acquisition, ROI detection, pre-processing, segmentation, feature extraction, and classification. The feature extraction was applied based on shapes, followed by the Support Vector Machine (SVM) implementation in the classification process. This process was performed with cross-validation using the k-fold values of 5. The performance evaluation was done using three parameters: precision, recall, and accuracy, by achieving the value of 90.6%, 89.3%, and 89.3%, respectively.
{"title":"Classifying the Swallow Nest Quality Using Support Vector Machine Based on Computer Vision","authors":"Anindita Septiarini, Ferda Maulana, H. Hamdani, Rizqi Saputra, Tenia Wahyuningrum, Indra","doi":"10.1109/CyberneticsCom55287.2022.9865498","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865498","url":null,"abstract":"Swallow Nest is a valuable export commodity, particularly in Indonesia. It is produced when a swallow's saliva hardens and is frequently encountered in high-rise buildings. Swallow nests can be utilized to treat various ailments in the medical sector. The price of a swallow nest varies according to its quality, which is commonly classified into three grades: quality 1 (Q1), quality 2 (Q2), and quality 3 (Q3). Q1 is of the highest quality, while Q3 is of the lowest. Each grade has a different physical appearance. Currently, many people lack knowledge regarding the grade of a swallow nest. Therefore, a method is needed to automatically classify the quality of swallow nests based on computer vision. The proposed method consists of several main processes, including image acquisition, ROI detection, pre-processing, segmentation, feature extraction, and classification. The feature extraction was applied based on shapes, followed by the Support Vector Machine (SVM) implementation in the classification process. This process was performed with cross-validation using the k-fold values of 5. The performance evaluation was done using three parameters: precision, recall, and accuracy, by achieving the value of 90.6%, 89.3%, and 89.3%, respectively.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"17 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":"131413592","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/CyberneticsCom55287.2022.9865290
Mohammad Dwipa Furqan, A. Achmad, Wardi, M. Niswar
During COVID19 pandemic, people are encouraged to practice physical distancing at least 1 meter when interacting with other people to prevent the spread of the COVID19. This study aims to develop a system that can monitor the physical distancing and track physical contact in a room using internet of things (IoT) and artificial intelligent technology. The system consists of a small single-board computer (Raspberry Pi), webcam, and web application displaying physical contact information. The system uses YOLO algorithms to detect the human object and euclidean distance formula to determine the distance between human objects. We evaluated the performance of YOLOv3 and YOLOv3-tiny running on Raspberry Pi. The evaluation result shows that YOLOv3 consumes more CPU resources than YOLOv3-tiny but has better accuracy in detecting human objects. YOLOv3-tiny can process images and detect objects faster than YOLOv3.
{"title":"IoT and AI-enabled Physical Distance Monitoring Application to Prevent COVID19 Transmission","authors":"Mohammad Dwipa Furqan, A. Achmad, Wardi, M. Niswar","doi":"10.1109/CyberneticsCom55287.2022.9865290","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865290","url":null,"abstract":"During COVID19 pandemic, people are encouraged to practice physical distancing at least 1 meter when interacting with other people to prevent the spread of the COVID19. This study aims to develop a system that can monitor the physical distancing and track physical contact in a room using internet of things (IoT) and artificial intelligent technology. The system consists of a small single-board computer (Raspberry Pi), webcam, and web application displaying physical contact information. The system uses YOLO algorithms to detect the human object and euclidean distance formula to determine the distance between human objects. We evaluated the performance of YOLOv3 and YOLOv3-tiny running on Raspberry Pi. The evaluation result shows that YOLOv3 consumes more CPU resources than YOLOv3-tiny but has better accuracy in detecting human objects. YOLOv3-tiny can process images and detect objects faster than YOLOv3.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"69 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":"132608271","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}
Sinovi (Innovation Center Innovation System) is a website developed to manage the collection of innovation and HAKI owned by the ITTP academic community. Based on the results of initial observations made by interviewing the Center for Innovation and HAKI, although it has been done twice socialization of website use, there are still complaints and obstacles experienced by users. Based on these problems, the researchers conducted research on evaluating the user experience (UX) of the Sinovi website. This study aims to determine the system's performance based on user experience. The UX evaluation process uses methods moderated remote usability testing and user experience questionnaire (UEQ). The study's results using moderated usability testing showed a significant difference in completion rate between the two groups of users, with each group having values of 0.9560 and 0.8235. While the results of time-based efficiency tests showed that the average time-based efficiency between group A and group B has similarities with the values obtained, respectively are 0.1652 and 0.1259. The test results using UEQ show that the Sinovi website has managed to get a positive evaluation. Several categories were successfully obtained, including the “Attractiveness” category with a score of 1.967, the “Perspicuity” category with a score of 1.850, the “Efficiency” category with a score of 2.042, the “Dependability” category with a score of 1.825, and the “Stimulation” category with a score of 1,742. The overall user experience evaluation results show that Sinovi's website is already at a good user experience level but needs to improve to reduce the number of problems.
{"title":"User Experience Evaluation Using Integration of Remote Usability Testing and Usability Evaluation Questionnaire Method","authors":"Ajeng Fitria Rahmawati, Tenia Wahyuningrum, Ariq Cahya Wardhana, Anindita Septiari, Lasmedi Afuan","doi":"10.1109/CyberneticsCom55287.2022.9865664","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865664","url":null,"abstract":"Sinovi (Innovation Center Innovation System) is a website developed to manage the collection of innovation and HAKI owned by the ITTP academic community. Based on the results of initial observations made by interviewing the Center for Innovation and HAKI, although it has been done twice socialization of website use, there are still complaints and obstacles experienced by users. Based on these problems, the researchers conducted research on evaluating the user experience (UX) of the Sinovi website. This study aims to determine the system's performance based on user experience. The UX evaluation process uses methods moderated remote usability testing and user experience questionnaire (UEQ). The study's results using moderated usability testing showed a significant difference in completion rate between the two groups of users, with each group having values of 0.9560 and 0.8235. While the results of time-based efficiency tests showed that the average time-based efficiency between group A and group B has similarities with the values obtained, respectively are 0.1652 and 0.1259. The test results using UEQ show that the Sinovi website has managed to get a positive evaluation. Several categories were successfully obtained, including the “Attractiveness” category with a score of 1.967, the “Perspicuity” category with a score of 1.850, the “Efficiency” category with a score of 2.042, the “Dependability” category with a score of 1.825, and the “Stimulation” category with a score of 1,742. The overall user experience evaluation results show that Sinovi's website is already at a good user experience level but needs to improve to reduce the number of problems.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"7 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":"133179864","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/CyberneticsCom55287.2022.9865450
Y. Heryadi, B. Wijanarko, D. F. Murad, C. Tho, Kiyota Hashimoto
This paper presents an empiric results of aspectbased sentiment analysis in education to extract and classify opinions, sentiments, evaluations, attitudes, and emotions from newly graduates of an online learning program. As part of continuous education monitoring system, the sentiment analysis process produces valuable input to leverage service quality of online learning program. In this study, the aspect-based sentiment analysis is implemented to analyze a set of feedbacks from 162 newly graduate from Binus Online Program majoring in Accounting, Management, Information System, and Computer Science. The important qualitative results of this study are confirmation that the main benefits of online learning from student perspective are mainly: the knowledge they gained from the program, learning guidance, reliable student team to work on thesis, quality of education support system, and learning happiness.
{"title":"Aspect-based Sentiment Analysis for Improving Online Learning Program Based on Student Feedback","authors":"Y. Heryadi, B. Wijanarko, D. F. Murad, C. Tho, Kiyota Hashimoto","doi":"10.1109/CyberneticsCom55287.2022.9865450","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865450","url":null,"abstract":"This paper presents an empiric results of aspectbased sentiment analysis in education to extract and classify opinions, sentiments, evaluations, attitudes, and emotions from newly graduates of an online learning program. As part of continuous education monitoring system, the sentiment analysis process produces valuable input to leverage service quality of online learning program. In this study, the aspect-based sentiment analysis is implemented to analyze a set of feedbacks from 162 newly graduate from Binus Online Program majoring in Accounting, Management, Information System, and Computer Science. The important qualitative results of this study are confirmation that the main benefits of online learning from student perspective are mainly: the knowledge they gained from the program, learning guidance, reliable student team to work on thesis, quality of education support system, and learning happiness.","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":"114163529","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/CyberneticsCom55287.2022.9865320
Rico S. Santos, E. Festijo
Despite the extensive use of malware technologies, malware detection is still a challenge today, especially with the daily cyber-attack barrage. Data analysis coupled with machine learning techniques is gaining popularity as one of the approaches deployed to address this issue. This paper proposed a new technique for classifying malware from a large Portable Executable file (PEFile) using a deep neural decision tree. Every node in a hybrid approach represents a neural network trained to identify a single output category using binary classification as a decision tree. The dataset used in this study includes both benign (7,196) and malicious (16,698) PE files with 14 features extracted from the PEFile headers. Precision is 0.88, Recall is 0.32, Matthew Coefficient Correlation (MCC) is 0.302, Area Under the Curve (AUC) Receiving Operating Characteristic (ROC) with an AUC value of 0.63, and Average Precision score of 0.69 was used to evaluate the classifier. The result shows that binary classifier can distinguish between two classes: (1) malware and (2) benign.
{"title":"Classifying Portable Executable Malware Using Deep Neural Decision Tree","authors":"Rico S. Santos, E. Festijo","doi":"10.1109/CyberneticsCom55287.2022.9865320","DOIUrl":"https://doi.org/10.1109/CyberneticsCom55287.2022.9865320","url":null,"abstract":"Despite the extensive use of malware technologies, malware detection is still a challenge today, especially with the daily cyber-attack barrage. Data analysis coupled with machine learning techniques is gaining popularity as one of the approaches deployed to address this issue. This paper proposed a new technique for classifying malware from a large Portable Executable file (PEFile) using a deep neural decision tree. Every node in a hybrid approach represents a neural network trained to identify a single output category using binary classification as a decision tree. The dataset used in this study includes both benign (7,196) and malicious (16,698) PE files with 14 features extracted from the PEFile headers. Precision is 0.88, Recall is 0.32, Matthew Coefficient Correlation (MCC) is 0.302, Area Under the Curve (AUC) Receiving Operating Characteristic (ROC) with an AUC value of 0.63, and Average Precision score of 0.69 was used to evaluate the classifier. The result shows that binary classifier can distinguish between two classes: (1) malware and (2) benign.","PeriodicalId":178279,"journal":{"name":"2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom)","volume":"107 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":"116997121","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：