Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608977
Ali Sheikh, J. Mir
Drowsiness-a state before the onset of sleep- resulting from insufficient s leep i s recognized a s a g lobal problem due to associated health and safety risks for the individuals involved in activities requiring constant attention. Therefore, several computer vision-based non-invasive techniques have been proposed for the timely detection of drowsiness. However, these methods are generally based on drowsy behavior indicators like yawning and excessive eye blinking. Moreover, the results are generally reported for databases with very few subjects or acted drowsy data. This paper proposes a drowsiness detection technique based on hybrid features using comprehensive and challenging real drowsy data. Primarily, eye state and body motion analysis is performed to determine drowsiness. Towards ameliorating this, the eye region is selected from each frame using facial landmarks and is described using a histogram of oriented gradients (HoG) descriptors. For body motion description, frame difference is computed and parameterized using HoG descriptors. Then, the hybrid feature set, i.e., the combination of eye and body motion features, is subjected to dimensionality reduction through principal component analysis. Finally, SVM is trained and tested on the hybrid feature set to detect drowsiness. The detection accuracy of 90% is achieved through our proposed technique.
{"title":"Machine Learning Inspired Vision-based Drowsiness Detection using Eye and Body Motion Features","authors":"Ali Sheikh, J. Mir","doi":"10.1109/ICTS52701.2021.9608977","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608977","url":null,"abstract":"Drowsiness-a state before the onset of sleep- resulting from insufficient s leep i s recognized a s a g lobal problem due to associated health and safety risks for the individuals involved in activities requiring constant attention. Therefore, several computer vision-based non-invasive techniques have been proposed for the timely detection of drowsiness. However, these methods are generally based on drowsy behavior indicators like yawning and excessive eye blinking. Moreover, the results are generally reported for databases with very few subjects or acted drowsy data. This paper proposes a drowsiness detection technique based on hybrid features using comprehensive and challenging real drowsy data. Primarily, eye state and body motion analysis is performed to determine drowsiness. Towards ameliorating this, the eye region is selected from each frame using facial landmarks and is described using a histogram of oriented gradients (HoG) descriptors. For body motion description, frame difference is computed and parameterized using HoG descriptors. Then, the hybrid feature set, i.e., the combination of eye and body motion features, is subjected to dimensionality reduction through principal component analysis. Finally, SVM is trained and tested on the hybrid feature set to detect drowsiness. The detection accuracy of 90% is achieved through our proposed technique.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"94 1","pages":"146-150"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73406413","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9609044
Ranjit P. Kolkar, V. Geetha
To understand the human activities and anticipate his intentions Human Activity Recognition(HAR) research is rapidly developing in tandem with the widespread availability of sensors. Various applications like elderly care and health monitoring systems in smart homes use smartphones and wearable devices. This paper proposes an effective HAR framework that uses deep learning methodology like Convolution Neural Networks(CNN), variations of LSTM(Long Short term Memory) and Gated Recurrent Units(GRU) Networks to recognize the activities based on smartphone sensors. The hybrid use of CNN-LSTM eliminates the handcrafted feature engineering and uses spatial and temporal data deep. The experiments are carried on UCI HAR and WISDM data sets, and the comparison results are obtained. The result shows a better 96.83 % and 98.00% for the UCI-HAR and WISDM datasets, respectively.
{"title":"Human Activity Recognition in Smart Home using Deep Learning Techniques","authors":"Ranjit P. Kolkar, V. Geetha","doi":"10.1109/ICTS52701.2021.9609044","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9609044","url":null,"abstract":"To understand the human activities and anticipate his intentions Human Activity Recognition(HAR) research is rapidly developing in tandem with the widespread availability of sensors. Various applications like elderly care and health monitoring systems in smart homes use smartphones and wearable devices. This paper proposes an effective HAR framework that uses deep learning methodology like Convolution Neural Networks(CNN), variations of LSTM(Long Short term Memory) and Gated Recurrent Units(GRU) Networks to recognize the activities based on smartphone sensors. The hybrid use of CNN-LSTM eliminates the handcrafted feature engineering and uses spatial and temporal data deep. The experiments are carried on UCI HAR and WISDM data sets, and the comparison results are obtained. The result shows a better 96.83 % and 98.00% for the UCI-HAR and WISDM datasets, respectively.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"2 1","pages":"230-234"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80243539","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608519
Apriantoni, Hazna At Thooriqoh, C. Fatichah, D. Purwitasari
During the COVID-19 situation, discussions about the effect of COVID-19 increase on Twitter. Not only affecting the health sector, but the COVID-19 pandemic has also affected other fields, such as economic activities. Issues related to the economy become an essential discussion on Twitter because this sector has close links with other sectors in public activities. It makes twitter relevant as a knowledge extraction medium to identify users' opini comparisons. The contribution of this research is to find the effect of the COVID-19 pandemic on the comparison of sentiment and emotion in three different locations in Surabaya. Based on the results of emotion detection, at the beginning of the COVID-19 pandemic, topics related to economic activities and personal activities were dominated by anger emotion in the ITS campus and the TP mall area. Then, despite the gradual decrease in the intensity of tweets, the dominance of anger emotion tends to be stable. On economics topics, 40% of tweets in the ITS campus area and 84% of tweets in the TP mall area were dominated by anger emotion. Then 37% of tweets in the ITS campus area and 32% tweets in the Tunjungan Plaza mall area based on personal activities were dominated by anger. The economics topic is related to buying-selling and shopping activities, while personal activity is related to lifestyle and daily activities. These results indicate that during the COVID-19 pandemic, anger became the most dominant sentiment related to local economic activity from Twitter users in Surabaya.
{"title":"Topic Detection in Sentiment Analysis of Twitter Texts for Understanding The COVID-19 Effect in Local Economic Activities","authors":"Apriantoni, Hazna At Thooriqoh, C. Fatichah, D. Purwitasari","doi":"10.1109/ICTS52701.2021.9608519","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608519","url":null,"abstract":"During the COVID-19 situation, discussions about the effect of COVID-19 increase on Twitter. Not only affecting the health sector, but the COVID-19 pandemic has also affected other fields, such as economic activities. Issues related to the economy become an essential discussion on Twitter because this sector has close links with other sectors in public activities. It makes twitter relevant as a knowledge extraction medium to identify users' opini comparisons. The contribution of this research is to find the effect of the COVID-19 pandemic on the comparison of sentiment and emotion in three different locations in Surabaya. Based on the results of emotion detection, at the beginning of the COVID-19 pandemic, topics related to economic activities and personal activities were dominated by anger emotion in the ITS campus and the TP mall area. Then, despite the gradual decrease in the intensity of tweets, the dominance of anger emotion tends to be stable. On economics topics, 40% of tweets in the ITS campus area and 84% of tweets in the TP mall area were dominated by anger emotion. Then 37% of tweets in the ITS campus area and 32% tweets in the Tunjungan Plaza mall area based on personal activities were dominated by anger. The economics topic is related to buying-selling and shopping activities, while personal activity is related to lifestyle and daily activities. These results indicate that during the COVID-19 pandemic, anger became the most dominant sentiment related to local economic activity from Twitter users in Surabaya.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"635 1","pages":"354-359"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85550503","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608014
Salsabiil Hasanah, Aulia Teaku Nururrahmah, D. Herumurti
Computer and mouse are two devices that inseparable from each other. Because mouse movement will control cursor movement to do any task that occurs on the computer, our research will also replace the role of the mouse in controlling cursor movement, using facial tracking by HOG and Haarcascade. Using facial movements instead of the mouse to move the cursor, users can minimize hand movements so users with impaired hands can operate the computer without a mouse. It is called hands-free. We use the HOG and Haarcascade method to determine the difference in time required by each method to control user movement. Here we experiment with 12 participants to find out the difference in time and accuracy. We use ANOVA analysis to produce a significant time difference and accuracy between those two methods. The accuracy shows that HOG has better accuracy than Haarcascade. HOG's accuracy is about 95.79%. In addition, age category analysis also affects the time generated. From this age category, it turns out that it produces a significant difference.
{"title":"Comparative Analysis of Hands-free Mouse Controlling based on Face Tracking","authors":"Salsabiil Hasanah, Aulia Teaku Nururrahmah, D. Herumurti","doi":"10.1109/ICTS52701.2021.9608014","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608014","url":null,"abstract":"Computer and mouse are two devices that inseparable from each other. Because mouse movement will control cursor movement to do any task that occurs on the computer, our research will also replace the role of the mouse in controlling cursor movement, using facial tracking by HOG and Haarcascade. Using facial movements instead of the mouse to move the cursor, users can minimize hand movements so users with impaired hands can operate the computer without a mouse. It is called hands-free. We use the HOG and Haarcascade method to determine the difference in time required by each method to control user movement. Here we experiment with 12 participants to find out the difference in time and accuracy. We use ANOVA analysis to produce a significant time difference and accuracy between those two methods. The accuracy shows that HOG has better accuracy than Haarcascade. HOG's accuracy is about 95.79%. In addition, age category analysis also affects the time generated. From this age category, it turns out that it produces a significant difference.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"44 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86012171","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608217
Hatma Suryotrisongko, Y. Musashi
In the DNS query-based botnet domain generation algorithm (DGA) detection, one might argue that domain names in DNS query data might disclose sensitive information related to browsing histories. User privacy preservation is important in the current personal data protection (PDP) era. This paper proposed implementing the differential privacy approach to the hybrid quantum deep learning model for botnet DGA detection. The proposed model consists of traditional deep learning layers and a quantum layer by combining angle embedding and random layer circuits from the Pennylane framework. We used ten botnet DGA datasets: Conficker, Cryptolocker, Goz, Matsnu, New_Goz, Pushdo, Ramdo, and Rovnix. We conducted experiments with considering noise models of eight IBM quantum devices: (ibmq_5_yorktown, ibmq_armonk, ibmq_athens, ibmq_belem, ibmq_lima, ibmq_quito, ibmq_santiago, and ibmqx2). We found that our proposed hybrid quantum model delivers a satisfactory performance (92.4% of maximum accuracy), superior to the classical deep learning counterpart. However, the hyperparameters of the differential privacy implementations (l2_norm_clip, noise_multiplier, microbatches, and learning_rate) still need to be tuned to improve the privacy guarantee of our proposed models.
{"title":"Hybrid Quantum Deep Learning with Differential Privacy for Botnet DGA Detection","authors":"Hatma Suryotrisongko, Y. Musashi","doi":"10.1109/ICTS52701.2021.9608217","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608217","url":null,"abstract":"In the DNS query-based botnet domain generation algorithm (DGA) detection, one might argue that domain names in DNS query data might disclose sensitive information related to browsing histories. User privacy preservation is important in the current personal data protection (PDP) era. This paper proposed implementing the differential privacy approach to the hybrid quantum deep learning model for botnet DGA detection. The proposed model consists of traditional deep learning layers and a quantum layer by combining angle embedding and random layer circuits from the Pennylane framework. We used ten botnet DGA datasets: Conficker, Cryptolocker, Goz, Matsnu, New_Goz, Pushdo, Ramdo, and Rovnix. We conducted experiments with considering noise models of eight IBM quantum devices: (ibmq_5_yorktown, ibmq_armonk, ibmq_athens, ibmq_belem, ibmq_lima, ibmq_quito, ibmq_santiago, and ibmqx2). We found that our proposed hybrid quantum model delivers a satisfactory performance (92.4% of maximum accuracy), superior to the classical deep learning counterpart. However, the hyperparameters of the differential privacy implementations (l2_norm_clip, noise_multiplier, microbatches, and learning_rate) still need to be tuned to improve the privacy guarantee of our proposed models.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"5 1","pages":"68-72"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78427216","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608469
Mikhael Ming Khosasih, D. Herumurti
There are media which can help people to learn such as website, augmented reality (AR), and virtual reality (VR). A previous study explained that AR can increase learning motivation for the student. Up until now, there is a limited study to compare learning motivation on website, AR, and VR. The purpose of this research was to compare learning motivation on the website, AR, and VR. This research using the ARCS (attention, relevance confidence, and satisfaction) model to compare learning motivation in website, AR, and VR. A total of 34 participant's data will be analyzed using one-way ANOVA within subjects. Participant will try three media and answer online questionnaire. The result of this study explained that VR is the higher media for learning motivation on attention, relevance, and confidence than AR and website. But AR has higher satisfaction mean values than VR. AR has 4.50 VR has 4.30 for the maen value of satisfaction.
有一些媒体可以帮助人们学习，如网站，增强现实(AR)，虚拟现实(VR)。先前的一项研究解释说，AR可以增加学生的学习动机。到目前为止，比较网站、AR和VR学习动机的研究有限。本研究的目的是比较网站、AR和VR的学习动机。本研究采用ARCS (attention, relevance confidence, and satisfaction)模型比较网站、AR和VR的学习动机。共有34名参与者的数据将在受试者中使用单向方差分析进行分析。参与者将尝试三种媒体并回答在线问卷。本研究的结果解释了VR是比AR和网站在注意力、相关性和信心方面的学习动机更高的媒体。但AR的满意度均值高于VR。AR满意度为4.50,VR满意度为4.30。
{"title":"Website, AR, VR: Comparison for Learning Motivation","authors":"Mikhael Ming Khosasih, D. Herumurti","doi":"10.1109/ICTS52701.2021.9608469","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608469","url":null,"abstract":"There are media which can help people to learn such as website, augmented reality (AR), and virtual reality (VR). A previous study explained that AR can increase learning motivation for the student. Up until now, there is a limited study to compare learning motivation on website, AR, and VR. The purpose of this research was to compare learning motivation on the website, AR, and VR. This research using the ARCS (attention, relevance confidence, and satisfaction) model to compare learning motivation in website, AR, and VR. A total of 34 participant's data will be analyzed using one-way ANOVA within subjects. Participant will try three media and answer online questionnaire. The result of this study explained that VR is the higher media for learning motivation on attention, relevance, and confidence than AR and website. But AR has higher satisfaction mean values than VR. AR has 4.50 VR has 4.30 for the maen value of satisfaction.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"44 1","pages":"7-11"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78633903","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608932
Riya Singh, Shivani Wadkar, Semil Jain, Manisha Dodeja
COVID-19 is a contagious and highly infectious disease which has led to an ongoing pandemic. Researchers and scientists across the world, across various fields, are exploring new methods and approaches to fight against the disease since its outbreak. A study of the COVID-19 infected patients suggests that these patients are affected with the lung infection. In this paper, we have leveraged several deep learning models using the concept of transfer learning. We have also designed a custom convolutional neural network for the purpose of feature extraction and then for effective categorization into pneumonia, covid and normal classes, several classification methods from the machine learning domain such as SVM, Random Forest and softmax regression were utilised. The custom convolutional neural network with the final layer as the dense layer with three units employing softmax activation function achieved a significant accuracy of 94.6 % which was comparable to the accuracy achieved by the transfer learning models. In order to ensure the results are not biased in favour of one class we have utilized a balanced dataset containing 1345 X-ray images for each class - pneumonia, covid, normal in order to demonstrate these experiments.
COVID-19是一种传染性和高度传染性疾病，已导致持续的大流行。自疫情爆发以来，世界各地各个领域的研究人员和科学家都在探索新的方法和途径来对抗这种疾病。一项对COVID-19感染患者的研究表明，这些患者患有肺部感染。在本文中，我们利用迁移学习的概念利用了几个深度学习模型。我们还设计了一个自定义的卷积神经网络，用于特征提取，然后有效地分类为肺炎，covid和正常类，使用了机器学习领域的几种分类方法，如SVM, Random Forest和softmax回归。自定义卷积神经网络以最后一层为密集层，采用softmax激活函数的三个单元，达到了94.6%的显著准确率，与迁移学习模型的准确率相当。为了确保结果不偏向于某一类，我们使用了一个平衡的数据集，其中包含每个类别的1345张x射线图像-肺炎，covid，正常，以演示这些实验。
{"title":"AI Driven Solution for the Detection of COVID-19 Using X-ray images","authors":"Riya Singh, Shivani Wadkar, Semil Jain, Manisha Dodeja","doi":"10.1109/ICTS52701.2021.9608932","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608932","url":null,"abstract":"COVID-19 is a contagious and highly infectious disease which has led to an ongoing pandemic. Researchers and scientists across the world, across various fields, are exploring new methods and approaches to fight against the disease since its outbreak. A study of the COVID-19 infected patients suggests that these patients are affected with the lung infection. In this paper, we have leveraged several deep learning models using the concept of transfer learning. We have also designed a custom convolutional neural network for the purpose of feature extraction and then for effective categorization into pneumonia, covid and normal classes, several classification methods from the machine learning domain such as SVM, Random Forest and softmax regression were utilised. The custom convolutional neural network with the final layer as the dense layer with three units employing softmax activation function achieved a significant accuracy of 94.6 % which was comparable to the accuracy achieved by the transfer learning models. In order to ensure the results are not biased in favour of one class we have utilized a balanced dataset containing 1345 X-ray images for each class - pneumonia, covid, normal in order to demonstrate these experiments.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"46 1","pages":"123-128"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82582926","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608043
A. Abdillah, Mohammad Zaenuddin Hamidi, Ratih Nur Esti Anggraeni, R. Sarno
Research protocol is an important document to be scrutinized by the ethical committee. As the research proposal is growing, the necessity for quick and concise protocol review is rising. This study undergoes a comparative study of multi-task learning (MTL) and single-task learning (STL) to classify research protocol documents. We try to carry out the classification process from the summary of health research. We represent research documents as multi-label classification problems and develop a deep learning model based on MTL and STL strategies. In our evaluation, multi-task learning achieved a better result with 0.125 loss and 0.785 Jaccard score than 0.182 and 0.720 in single-task learning. In consequence, MTL has a 27% slower computation time than STL.
{"title":"Comparative Study of Single-task and Multi-task Learning on Research Protocol Document Classification","authors":"A. Abdillah, Mohammad Zaenuddin Hamidi, Ratih Nur Esti Anggraeni, R. Sarno","doi":"10.1109/ICTS52701.2021.9608043","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608043","url":null,"abstract":"Research protocol is an important document to be scrutinized by the ethical committee. As the research proposal is growing, the necessity for quick and concise protocol review is rising. This study undergoes a comparative study of multi-task learning (MTL) and single-task learning (STL) to classify research protocol documents. We try to carry out the classification process from the summary of health research. We represent research documents as multi-label classification problems and develop a deep learning model based on MTL and STL strategies. In our evaluation, multi-task learning achieved a better result with 0.125 loss and 0.785 Jaccard score than 0.182 and 0.720 in single-task learning. In consequence, MTL has a 27% slower computation time than STL.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"298 1","pages":"213-217"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75458246","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608810
Hunain Altaf, S. Ibrahim, Nor F. M. Azmin, A. L. Asnawi, Balqis Hanisah Binti Walid, N.H. Harun
The contribution to stress detection and classification is far beyond demand as the statistics show that the health and mental illness of society have kept on deteriorating. Electroencephalogram (EEG) signals have the potential to detect stress levels reliably due to their high accuracy. Majority of studies of stress detection are based on alpha and beta waves and the corresponding ratio of the two waves and there are hardly any based-on theta waves. This work explores the impact of bandpower of alpha/beta and theta/beta ratios when combined with other features to classify two-levels of human stress based on EEG signals using five commonly used machine learning algorithms. A classification model is developed from the clustering model gained and Naïve Bayes shows the highest accuracy which is 95% in compared to the other four common machine learning algorithms (i.e., SVM, Logistic, IBk, and SGD) by using WEKA. The proposed framework recommends that both ratios are reliable features, and theta/beta appears to give a huge impact compared to alpha/beta. This study will ultimately contribute to society's development with improved robust machine learning algorithm for binary classification.
{"title":"Machine Learning Approach for Stress Detection based on Alpha-Beta and Theta-Beta Ratios of EEG Signals","authors":"Hunain Altaf, S. Ibrahim, Nor F. M. Azmin, A. L. Asnawi, Balqis Hanisah Binti Walid, N.H. Harun","doi":"10.1109/ICTS52701.2021.9608810","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608810","url":null,"abstract":"The contribution to stress detection and classification is far beyond demand as the statistics show that the health and mental illness of society have kept on deteriorating. Electroencephalogram (EEG) signals have the potential to detect stress levels reliably due to their high accuracy. Majority of studies of stress detection are based on alpha and beta waves and the corresponding ratio of the two waves and there are hardly any based-on theta waves. This work explores the impact of bandpower of alpha/beta and theta/beta ratios when combined with other features to classify two-levels of human stress based on EEG signals using five commonly used machine learning algorithms. A classification model is developed from the clustering model gained and Naïve Bayes shows the highest accuracy which is 95% in compared to the other four common machine learning algorithms (i.e., SVM, Logistic, IBk, and SGD) by using WEKA. The proposed framework recommends that both ratios are reliable features, and theta/beta appears to give a huge impact compared to alpha/beta. This study will ultimately contribute to society's development with improved robust machine learning algorithm for binary classification.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"2 1","pages":"201-206"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79409205","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608963
A. F. Septiyanto, R. Sarno, K. R. Sungkono
Business processes are experiencing increasingly complex developments; therefore, an extensive business process must cover all existing process flows. Applied business process collaboration between organizations can complete a complex business process. The additional information which shows the collaboration of activities is called messages. Process discovery is currently focused on a series of activities in a single process model, so the process discovery cannot depict the messages in the business process collaboration. In addition, there are several problems in describing the condition of activities, e.g., an Invisible Task. The Invisible Task is a condition of additional tasks that appear not in the event logs but in the process models. The Invisible Task must be described in the process model; therefore, it can be analyzed further. Several conditions which need the Invisible Task are redo, switch, and skip conditions. In this research, the proposed method is to obtain information about the event log of all activities of the business process collaboration and discover any Invisible Task to describe in the process model. The proposed method, named the Modified Alpha algorithm, builds several rules for adding messages and the Invisible Task in the event log before executing the Alpha algorithm. The results of this study indicate that the Modified Alpha algorithm can describe the collaboration process model. Based on the comparison results, the Modified Alpha algorithm gets the best results than other algorithms, namely Alpha# and Inductive Miner. Modified Alpha received 1.00, 1.00, 1.00, 0.82 for the fitness, precision, simplicity, and generalization. Alpha# Miner earned 0.74 and 0.70 for the simplicity and generalization, and Inductive Miner gained 0.55 simplicity value and 0.72 generalization value. Alpha# Miner and Inductive Miner got 0.00 for the fitness and the precision.
{"title":"Mining Collaboration Business Process Containing Invisible Task by Using Modified Alpha","authors":"A. F. Septiyanto, R. Sarno, K. R. Sungkono","doi":"10.1109/ICTS52701.2021.9608963","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608963","url":null,"abstract":"Business processes are experiencing increasingly complex developments; therefore, an extensive business process must cover all existing process flows. Applied business process collaboration between organizations can complete a complex business process. The additional information which shows the collaboration of activities is called messages. Process discovery is currently focused on a series of activities in a single process model, so the process discovery cannot depict the messages in the business process collaboration. In addition, there are several problems in describing the condition of activities, e.g., an Invisible Task. The Invisible Task is a condition of additional tasks that appear not in the event logs but in the process models. The Invisible Task must be described in the process model; therefore, it can be analyzed further. Several conditions which need the Invisible Task are redo, switch, and skip conditions. In this research, the proposed method is to obtain information about the event log of all activities of the business process collaboration and discover any Invisible Task to describe in the process model. The proposed method, named the Modified Alpha algorithm, builds several rules for adding messages and the Invisible Task in the event log before executing the Alpha algorithm. The results of this study indicate that the Modified Alpha algorithm can describe the collaboration process model. Based on the comparison results, the Modified Alpha algorithm gets the best results than other algorithms, namely Alpha# and Inductive Miner. Modified Alpha received 1.00, 1.00, 1.00, 0.82 for the fitness, precision, simplicity, and generalization. Alpha# Miner earned 0.74 and 0.70 for the simplicity and generalization, and Inductive Miner gained 0.55 simplicity value and 0.72 generalization value. Alpha# Miner and Inductive Miner got 0.00 for the fitness and the precision.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"31 1","pages":"90-95"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80353730","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：