Pub Date : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941320
Xinshun Ma, Qi An
A robust two-stage stochastic convex programming model is proposed in this paper with the second stage of which is quadratic programming. A formula is obtained to calculate the subdifferential of the recourse function, under the assumption that linear partial information is observed for the probability distribution. A subgradient algorithm based on deflected subgradients and exponential decay step sizes is proposed to solve the robust stochastic convex programming problem. The convergence of the algorithm is proved, and the effectiveness is demonstrated by the numerical examples.
{"title":"Solution to Robust Two-Stage Stochastic Convex Programming Using Subgradient Method","authors":"Xinshun Ma, Qi An","doi":"10.1109/ICMLC56445.2022.9941320","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941320","url":null,"abstract":"A robust two-stage stochastic convex programming model is proposed in this paper with the second stage of which is quadratic programming. A formula is obtained to calculate the subdifferential of the recourse function, under the assumption that linear partial information is observed for the probability distribution. A subgradient algorithm based on deflected subgradients and exponential decay step sizes is proposed to solve the robust stochastic convex programming problem. The convergence of the algorithm is proved, and the effectiveness is demonstrated by the numerical examples.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124011865","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941301
H. P. Fordson, Katherine Gardhouse, Nicholas G. Cicero, J. Chikazoe, A. Anderson, Eve Derosa
Emotions are central to physical and mental health and general well being. There is a great need to affordably and non invasively track moment to moment changes in emotional states and their conversion into chronic conditions. Blood Volume Pulse (BVP) is a widely used sensor for measuring blood volume changes, heart rate, and is embedded in numerous biofeedback systems and applications. Nonetheless, the role of BVP features relating to emotion detection is lacking in current studies. While engineers have become more interested in the analysis of heart rate variability (HRV) and its regulation by the autonomic nervous system, there is a need to design systems that can investigate their variations due to real life stressors and how people respond to emotions differently. The study employs the database for emotion analysis using physiological signals (DEAP) in assessing emotional responses of subjects according to valence arousal scale to music videos. We demonstrate a novel approach to augmenting original features and normalized features of blood volume in peripheral vessels. The features of HRV include tachogram, multi-scale entropy (MSE), power spectral density (PSD), and statistical moments derived from BVP. We further propose embedding age and gender of participants as a weight to the augmented features. We finally used multilayer perceptron (MLP) as classifier to evaluate our approach. Obtained results show an 8.4% and 7.3% improvement in F1-score in the valence and arousal dimension respectively. Such advances may aid in building closed-loop emotion detection and intervention systems.
{"title":"A Novel Deep Learning Based Emotion Recognition Approach to well Being from Fingertip Blood Volume Pulse","authors":"H. P. Fordson, Katherine Gardhouse, Nicholas G. Cicero, J. Chikazoe, A. Anderson, Eve Derosa","doi":"10.1109/ICMLC56445.2022.9941301","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941301","url":null,"abstract":"Emotions are central to physical and mental health and general well being. There is a great need to affordably and non invasively track moment to moment changes in emotional states and their conversion into chronic conditions. Blood Volume Pulse (BVP) is a widely used sensor for measuring blood volume changes, heart rate, and is embedded in numerous biofeedback systems and applications. Nonetheless, the role of BVP features relating to emotion detection is lacking in current studies. While engineers have become more interested in the analysis of heart rate variability (HRV) and its regulation by the autonomic nervous system, there is a need to design systems that can investigate their variations due to real life stressors and how people respond to emotions differently. The study employs the database for emotion analysis using physiological signals (DEAP) in assessing emotional responses of subjects according to valence arousal scale to music videos. We demonstrate a novel approach to augmenting original features and normalized features of blood volume in peripheral vessels. The features of HRV include tachogram, multi-scale entropy (MSE), power spectral density (PSD), and statistical moments derived from BVP. We further propose embedding age and gender of participants as a weight to the augmented features. We finally used multilayer perceptron (MLP) as classifier to evaluate our approach. Obtained results show an 8.4% and 7.3% improvement in F1-score in the valence and arousal dimension respectively. Such advances may aid in building closed-loop emotion detection and intervention systems.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124146127","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941312
Yuma Iwabuchi, T. Motoyoshi, Noboru Takagi, H. Masuta, K. Sawai
In this study, we aimed to develop a system that can present object shapes to visually impaired people. We developed and evaluated a prototype system that can present height information using linear actuators, and can also re-edit the presented information in the same system. In a verification experiment using the prototype system, it was found that the recognition rate for small objects about 10 mm square was low. Therefore, we added a marker function to the prototype to discriminate between unsearched and searched areas to improve the search accuracy for users, and verified the usefulness of this function. Although, the use of the marker function did not decrease the search time, it may improve the recognition rate for small objects.
{"title":"Improvement and Evaluation of Object Shape Presentation System Using Linear Actuators","authors":"Yuma Iwabuchi, T. Motoyoshi, Noboru Takagi, H. Masuta, K. Sawai","doi":"10.1109/ICMLC56445.2022.9941312","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941312","url":null,"abstract":"In this study, we aimed to develop a system that can present object shapes to visually impaired people. We developed and evaluated a prototype system that can present height information using linear actuators, and can also re-edit the presented information in the same system. In a verification experiment using the prototype system, it was found that the recognition rate for small objects about 10 mm square was low. Therefore, we added a marker function to the prototype to discriminate between unsearched and searched areas to improve the search accuracy for users, and verified the usefulness of this function. Although, the use of the marker function did not decrease the search time, it may improve the recognition rate for small objects.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115258252","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941319
Yuki Kitahara, Masaki Nakamura, K. Sakakibara
A multi-car elevator (MCE) system has more than two cars in a single shaft. For MCE, both safety avoiding collision of cars and efficiency obtaining high performance of passengers satisfaction are expected. Uppaal is a statistical model checking tool based on stochastic timed automata that can handle time constraints and stochastic transitions, and performs both formal verification for the safety property and symbolic simulation based statistical analysis to obtain efficient passengers assignments. In this study, we investigate the use of Uppaal tool to obtain safety and efficient control laws of MCE.
{"title":"An Investigation of Formal Verification of Control Policy of Multi-Car Elevator Systems Using Statistical Model Checking","authors":"Yuki Kitahara, Masaki Nakamura, K. Sakakibara","doi":"10.1109/ICMLC56445.2022.9941319","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941319","url":null,"abstract":"A multi-car elevator (MCE) system has more than two cars in a single shaft. For MCE, both safety avoiding collision of cars and efficiency obtaining high performance of passengers satisfaction are expected. Uppaal is a statistical model checking tool based on stochastic timed automata that can handle time constraints and stochastic transitions, and performs both formal verification for the safety property and symbolic simulation based statistical analysis to obtain efficient passengers assignments. In this study, we investigate the use of Uppaal tool to obtain safety and efficient control laws of MCE.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116854140","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941322
Kodai Suzuki, K. Sakakibara, Masaki Nakamura, Suguru Shinoda, Y. Asano
The proteins that have the function of catalysis, called enzymes, can be used in many different ways in the chemical industry. The catalysis function of enzymes works by solubilizing. Enzymes can be used in the chemical industry, but in the recombinant production of enzymes, some enzymes aggregate during production. In- solubilized enzymes that has lost its catalysis function cannot be used in industry. Therefore, the search for new enzymes that can be used for industrial purposes is one of the important strategies. However, the search for new enzymes takes time and costs money. In previous research, a model for predicting protein solubility from the amino add sequence of a protein was constructed using machine learning. This has made it possible to predict the solubility of a protein before it is produced. In this study, a model is constructed to predict protein solubility not only from the amino acid sequence but also from the amino acid sequence and the secondary structure information of the protein. We attempt to improve the prediction accuracy of the model by providing the model with information that is thought to influence solubility.
{"title":"Machine Learning for Protein Solubility Prediction","authors":"Kodai Suzuki, K. Sakakibara, Masaki Nakamura, Suguru Shinoda, Y. Asano","doi":"10.1109/ICMLC56445.2022.9941322","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941322","url":null,"abstract":"The proteins that have the function of catalysis, called enzymes, can be used in many different ways in the chemical industry. The catalysis function of enzymes works by solubilizing. Enzymes can be used in the chemical industry, but in the recombinant production of enzymes, some enzymes aggregate during production. In- solubilized enzymes that has lost its catalysis function cannot be used in industry. Therefore, the search for new enzymes that can be used for industrial purposes is one of the important strategies. However, the search for new enzymes takes time and costs money. In previous research, a model for predicting protein solubility from the amino add sequence of a protein was constructed using machine learning. This has made it possible to predict the solubility of a protein before it is produced. In this study, a model is constructed to predict protein solubility not only from the amino acid sequence but also from the amino acid sequence and the secondary structure information of the protein. We attempt to improve the prediction accuracy of the model by providing the model with information that is thought to influence solubility.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124849620","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941328
Da Meng, Yanze Zheng
As we all know, the difficulty of automatic placement and routing is proportional to the size of the circuit. Through Printed circuit board (PCB) netlist partition algorithms, PCB circuits can be divided into different sub-modules, and the problem scale can be effectively reduced in order to obtain the optimal automatic layout and routing. It is observed that when engineers design circuits, they usually mark important nets by annotation, called net attributes. This paper proposes a PCB netlist partition approach based on net attributes. Our partition approach takes the netlist as input, and module partition set as output. Firstly, the modules are pre-partitioned using net attributes. Further, the special patterns in circuits are discovered, and the scattered resistors, capacitors and other components caused by pre-partitioning according to net attributes would be allocated to initial modules by classifying and module matching rules. Our method is evaluated on 11 PCB netlists, and experimental results show that our proposed netlist partition approach outperforms the state of the arts, which can achieve 80%–96% partition accuracy.
{"title":"Circuit Partitioning for PCB Netlist Based on Net Attributes","authors":"Da Meng, Yanze Zheng","doi":"10.1109/ICMLC56445.2022.9941328","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941328","url":null,"abstract":"As we all know, the difficulty of automatic placement and routing is proportional to the size of the circuit. Through Printed circuit board (PCB) netlist partition algorithms, PCB circuits can be divided into different sub-modules, and the problem scale can be effectively reduced in order to obtain the optimal automatic layout and routing. It is observed that when engineers design circuits, they usually mark important nets by annotation, called net attributes. This paper proposes a PCB netlist partition approach based on net attributes. Our partition approach takes the netlist as input, and module partition set as output. Firstly, the modules are pre-partitioned using net attributes. Further, the special patterns in circuits are discovered, and the scattered resistors, capacitors and other components caused by pre-partitioning according to net attributes would be allocated to initial modules by classifying and module matching rules. Our method is evaluated on 11 PCB netlists, and experimental results show that our proposed netlist partition approach outperforms the state of the arts, which can achieve 80%–96% partition accuracy.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129630600","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941316
Tomoaki Hirose, Kazuma Yamaguchi, H. Takano
With the rapid development of artificial intelligence, automatic facial expression recognition has been intensively investigated. However, it cannot maintain high accuracy of facial expression recognition due to face’s partial occlusion because most of facial expression recognition methods are designed based on the assumption that the entire face is visible. Therefore, the purpose of this study is to develop a method that does not degrade the accuracy of facial expression recognition even if a part of the face is occluded. In this paper, we investigate the accuracy of the facial expression recognition for only the region around the eyes using the CK+ dataset. The 3-D CNN and 2-D CNN with synthetic or subtracted eye images as the input image were adopted in the experiment The experimental results showed that the accuracy of facial expression recognition using the 3-D CNN or 2-D CNN with subtracted eye images were improved. Therefore, the temporal variations of facial expression are effective for the facial expression recognition using only the region around the eyes.
{"title":"Recognition Performance of Facial Expression for the Face’s Partial Regions","authors":"Tomoaki Hirose, Kazuma Yamaguchi, H. Takano","doi":"10.1109/ICMLC56445.2022.9941316","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941316","url":null,"abstract":"With the rapid development of artificial intelligence, automatic facial expression recognition has been intensively investigated. However, it cannot maintain high accuracy of facial expression recognition due to face’s partial occlusion because most of facial expression recognition methods are designed based on the assumption that the entire face is visible. Therefore, the purpose of this study is to develop a method that does not degrade the accuracy of facial expression recognition even if a part of the face is occluded. In this paper, we investigate the accuracy of the facial expression recognition for only the region around the eyes using the CK+ dataset. The 3-D CNN and 2-D CNN with synthetic or subtracted eye images as the input image were adopted in the experiment The experimental results showed that the accuracy of facial expression recognition using the 3-D CNN or 2-D CNN with subtracted eye images were improved. Therefore, the temporal variations of facial expression are effective for the facial expression recognition using only the region around the eyes.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129060802","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941324
Yanqin Xie, K. Nagamune
In this study, the cardiothoracic ratio is automatically measured by extracting lung and heart regions in a chest X-ray image and measuring their widths. The proposed method uses a deep learning model based on U-Net++ with VGG19_bn encoders. The results of cardiothoracic enlargement detection using the cardiothoracic ratio measured by the proposed method showed a high degree of agreement with the judgment made by a physician. As a result, the automatic cardiothoracic ratio measurement system using the proposed method contributes to a significant reduction in the time and labor of physicians.
本研究通过提取胸部 X 光图像中的肺部和心脏区域并测量其宽度，自动测量心胸比例。所提出的方法使用了基于 U-Net++ 和 VGG19_bn 编码器的深度学习模型。利用所提方法测量的心胸比例进行心胸扩大检测的结果显示，与医生的判断高度一致。因此，使用所提方法的心胸比例自动测量系统有助于大大减少医生的时间和劳动。
{"title":"Measurement of Cardiothoracic Ratio and Detection of Cardiomegaly in X-Ray Images Using Deep Learning","authors":"Yanqin Xie, K. Nagamune","doi":"10.1109/ICMLC56445.2022.9941324","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941324","url":null,"abstract":"In this study, the cardiothoracic ratio is automatically measured by extracting lung and heart regions in a chest X-ray image and measuring their widths. The proposed method uses a deep learning model based on U-Net++ with VGG19_bn encoders. The results of cardiothoracic enlargement detection using the cardiothoracic ratio measured by the proposed method showed a high degree of agreement with the judgment made by a physician. As a result, the automatic cardiothoracic ratio measurement system using the proposed method contributes to a significant reduction in the time and labor of physicians.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127842126","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941295
C. Fahn, Tzu-Chin Wu
In this paper, the deep learning-based method for forgery image detection is presented. First, we respectively do discrete Fourier transform for both real images and the forgery images generated from the generative adversarial networks. Then the obtained Fourier spectrums are fed to deep neural networks for model training. In order to enhance the detection capability of the model, we incorporate contrastive learning to make the model directly learns the difference between real and forgery images. Four kinds of generative adversarial networks (GANs), namely DCGAN, CycleGAN, AutoGAN, and Mixed GAN, are chosen to generate forgery images for testing our proposed method. The experimental results reveal that the average accuracy rate reaches 99.5% using our proposed method to detect the four kinds of GAN-generated images. Compared with the state-of-the-art forgery image detection method, our proposed method can more widely detect forgery images derived from different sources.
{"title":"A Deep-Neural-Network-Based Approach To Detecting Forgery Images Generated From Various Generative Adversarial Networks","authors":"C. Fahn, Tzu-Chin Wu","doi":"10.1109/ICMLC56445.2022.9941295","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941295","url":null,"abstract":"In this paper, the deep learning-based method for forgery image detection is presented. First, we respectively do discrete Fourier transform for both real images and the forgery images generated from the generative adversarial networks. Then the obtained Fourier spectrums are fed to deep neural networks for model training. In order to enhance the detection capability of the model, we incorporate contrastive learning to make the model directly learns the difference between real and forgery images. Four kinds of generative adversarial networks (GANs), namely DCGAN, CycleGAN, AutoGAN, and Mixed GAN, are chosen to generate forgery images for testing our proposed method. The experimental results reveal that the average accuracy rate reaches 99.5% using our proposed method to detect the four kinds of GAN-generated images. Compared with the state-of-the-art forgery image detection method, our proposed method can more widely detect forgery images derived from different sources.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116107605","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 : 2022-09-09DOI: 10.1109/ICMLC56445.2022.9941314
Shinnosuke Yoshiiwa, H. Takano, Keisuke Ido, Ken-ichi Morishige
Electroencephalography studies of working memory have demonstrated cortical activities and oscillatory representations without clarifying what kind of information is stored in memory representations. To answer this question, we measured scalp EEG and fMRI data while participants performed a N-back working memory task. We calculated the current intensities from the estimated cortical currents. To investigate the representation of working memory in the cortical regions, we classified information about its contents using the power spectrum during a retention period. These results indicate that our method classified (to some extent) the oscillatory representations of EEG cortical currents over multiple regions.
{"title":"Estimation Of Cortical Currents From Eeg Signals During N-Back Working Memory Tasks","authors":"Shinnosuke Yoshiiwa, H. Takano, Keisuke Ido, Ken-ichi Morishige","doi":"10.1109/ICMLC56445.2022.9941314","DOIUrl":"https://doi.org/10.1109/ICMLC56445.2022.9941314","url":null,"abstract":"Electroencephalography studies of working memory have demonstrated cortical activities and oscillatory representations without clarifying what kind of information is stored in memory representations. To answer this question, we measured scalp EEG and fMRI data while participants performed a N-back working memory task. We calculated the current intensities from the estimated cortical currents. To investigate the representation of working memory in the cortical regions, we classified information about its contents using the power spectrum during a retention period. These results indicate that our method classified (to some extent) the oscillatory representations of EEG cortical currents over multiple regions.","PeriodicalId":117829,"journal":{"name":"2022 International Conference on Machine Learning and Cybernetics (ICMLC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129495619","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：