Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9282888
A. Mosqueda-Herrera, D. Martinez-Peon, L. Gomez-Sanchez, M. I. Ramirez-Sosa, S. Delfin-Prieto, F. Benavides-Bravo
Kinesthetic Motor Imagery (MKI) has been demonstrated to be a robust paradigm for Brain-Computer Interfaces (BCI). In this paper we present the characterization of KMI paradigm of three tasks of wrist and forearm of the right arm using Hurst exponent and variogram, preceding for ICA to map signals into source space. The results show high persistency an average of 0.76 ± 0.07 for KMI Pronation/Supination (PS), 0.82 ± 0.05 for KMI Flexion-Extension). (FE), and 0.90 ± 0.02 for KMI Abduction-Adduction (AA We found a significant difference between the three KMI tasks, useful for multimodal command in BCI.
{"title":"Characterization of Kinesthetic Motor Imagery paradigm for wrist and forearm using an algorithm based on the Hurst Exponent and Variogram","authors":"A. Mosqueda-Herrera, D. Martinez-Peon, L. Gomez-Sanchez, M. I. Ramirez-Sosa, S. Delfin-Prieto, F. Benavides-Bravo","doi":"10.1109/SMC42975.2020.9282888","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9282888","url":null,"abstract":"Kinesthetic Motor Imagery (MKI) has been demonstrated to be a robust paradigm for Brain-Computer Interfaces (BCI). In this paper we present the characterization of KMI paradigm of three tasks of wrist and forearm of the right arm using Hurst exponent and variogram, preceding for ICA to map signals into source space. The results show high persistency an average of 0.76 ± 0.07 for KMI Pronation/Supination (PS), 0.82 ± 0.05 for KMI Flexion-Extension). (FE), and 0.90 ± 0.02 for KMI Abduction-Adduction (AA We found a significant difference between the three KMI tasks, useful for multimodal command in BCI.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"27 20 1","pages":"3683-3688"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78134945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9283071
V. Marík, V. Gorodetsky, P. Skobelev
Multi-agent systems (MAS) have been an area of high expectations of the industrial IT community. However, in reality, these expectations are still not met and, in practice, the industry very rarely uses the MAS design methodologies, technologies, and software tools despite the appearance of many new classes of applications for which the MAS paradigm could be the perfect match. This paper analyzes the barriers and trends of the mismatch between the recent industrial anticipations and the real state of the practical use of MAS. It identifies engineering problems with very little re-use of code that currently stops economics of scale and impedes the extensive industrial MAS deployment and the ways to overcome them.
{"title":"Multi-Agent Technology for Industrial Applications: Barriers and Trends","authors":"V. Marík, V. Gorodetsky, P. Skobelev","doi":"10.1109/SMC42975.2020.9283071","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283071","url":null,"abstract":"Multi-agent systems (MAS) have been an area of high expectations of the industrial IT community. However, in reality, these expectations are still not met and, in practice, the industry very rarely uses the MAS design methodologies, technologies, and software tools despite the appearance of many new classes of applications for which the MAS paradigm could be the perfect match. This paper analyzes the barriers and trends of the mismatch between the recent industrial anticipations and the real state of the practical use of MAS. It identifies engineering problems with very little re-use of code that currently stops economics of scale and impedes the extensive industrial MAS deployment and the ways to overcome them.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"64 1","pages":"1980-1987"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80327628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9283349
Fahdah Alalyan, Nuha Zamzami, N. Bouguila
In the last decades, the development of generative/discriminative approaches for classifying different kinds of data has attracted scholars’ attention. Considering the strengths and weaknesses of both approaches, several hybrid learning approaches which combined the desirable properties of both have been developed. Our goal in this paper is to combine Support Vector Machines (SVMs), as a powerful classification tool, and Bernoulli mixture model in order to classify binary data. We propose using Bernoulli mixture model for generating probabilistic kernels for SVM based on information divergence. These kernels make intelligent use of unlabeled binary data to achieve good data discrimination. We demonstrate the merits of the proposed hybrid learning approach for the problem of classifying binary and texture images.
{"title":"A Hybrid Approach Based on SVM and Bernoulli Mixture Model for Binary Vectors Classification","authors":"Fahdah Alalyan, Nuha Zamzami, N. Bouguila","doi":"10.1109/SMC42975.2020.9283349","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283349","url":null,"abstract":"In the last decades, the development of generative/discriminative approaches for classifying different kinds of data has attracted scholars’ attention. Considering the strengths and weaknesses of both approaches, several hybrid learning approaches which combined the desirable properties of both have been developed. Our goal in this paper is to combine Support Vector Machines (SVMs), as a powerful classification tool, and Bernoulli mixture model in order to classify binary data. We propose using Bernoulli mixture model for generating probabilistic kernels for SVM based on information divergence. These kernels make intelligent use of unlabeled binary data to achieve good data discrimination. We demonstrate the merits of the proposed hybrid learning approach for the problem of classifying binary and texture images.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"89 1","pages":"1155-1160"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77184352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9283064
Abdulrahman Al-Abassi, Jacob Sakhnini, H. Karimipour
Smart Cyber Physical Grids are the new wave of power system technology that integrates networks of sensors with power stations for more efficient power generation and distribution. While utilizing communication networks is accompanied with tremendous advantages, it also increases the vulnerability of power systems to cyber attacks. Many methods for security and attack detection have been proposed in literature; however, most papers do not consider the imbalance of data in real power systems. In this paper, we propose a deep learning based method, referred to as Ensemble Stacked AutoEncoder (ESAE), aimed at tackling the problem of data imbalance. This method achieves superior performance on imbalanced data by developing a deep representation learning model to construct new balanced representations. The detection accuracy and model performance is improved by utilizing an ensemble architecture based on Stacked Autoencoders and Random Forest classifiers to detect attacks from the new representations. The proposed method is tested on all degrees of data imbalance using test cases of IEEE 14-bus, 30-bus, and 57-bus systems. Comparisons are made to several classifiers to demonstrate the effectiveness of the proposed algorithm
{"title":"Unsupervised Stacked Autoencoders for Anomaly Detection on Smart Cyber-physical Grids","authors":"Abdulrahman Al-Abassi, Jacob Sakhnini, H. Karimipour","doi":"10.1109/SMC42975.2020.9283064","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283064","url":null,"abstract":"Smart Cyber Physical Grids are the new wave of power system technology that integrates networks of sensors with power stations for more efficient power generation and distribution. While utilizing communication networks is accompanied with tremendous advantages, it also increases the vulnerability of power systems to cyber attacks. Many methods for security and attack detection have been proposed in literature; however, most papers do not consider the imbalance of data in real power systems. In this paper, we propose a deep learning based method, referred to as Ensemble Stacked AutoEncoder (ESAE), aimed at tackling the problem of data imbalance. This method achieves superior performance on imbalanced data by developing a deep representation learning model to construct new balanced representations. The detection accuracy and model performance is improved by utilizing an ensemble architecture based on Stacked Autoencoders and Random Forest classifiers to detect attacks from the new representations. The proposed method is tested on all degrees of data imbalance using test cases of IEEE 14-bus, 30-bus, and 57-bus systems. Comparisons are made to several classifiers to demonstrate the effectiveness of the proposed algorithm","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"94 1","pages":"3123-3129"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87670731","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}
There is a growing concern in recycling plants for minimizing the negative environmental impacts (such as carbon emissions) of disassembling end-of-life products. Uncertainty caused by their different usage stages exists when disassembling them. In this paper, we propose a stochastic multi-objective disassembly sequencing and line balancing problem based on an AND/OR graph. By considering disassembly failure risk, we construct objectives of maximizing profit and minimizing carbon emission and energy consumption to help sustain economic development. Then, we propose a novel multi-objective discrete grey wolf optimizer to solve it. We show its effectiveness via a product example. The results show the superiority of the proposed algorithm over classical non-dominated sorting genetic algorithm II and multi-objective evolutionary algorithm based on decomposition.
{"title":"Multi-objective Discrete Grey Wolf Optimizer for Solving Stochastic Multi-objective Disassembly Sequencing and Line Balancing Problem","authors":"Zhiwei Zhang, Xiwang Guo, Mengchu Zhou, Shixin Liu, Liang Qi","doi":"10.1109/SMC42975.2020.9283184","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283184","url":null,"abstract":"There is a growing concern in recycling plants for minimizing the negative environmental impacts (such as carbon emissions) of disassembling end-of-life products. Uncertainty caused by their different usage stages exists when disassembling them. In this paper, we propose a stochastic multi-objective disassembly sequencing and line balancing problem based on an AND/OR graph. By considering disassembly failure risk, we construct objectives of maximizing profit and minimizing carbon emission and energy consumption to help sustain economic development. Then, we propose a novel multi-objective discrete grey wolf optimizer to solve it. We show its effectiveness via a product example. The results show the superiority of the proposed algorithm over classical non-dominated sorting genetic algorithm II and multi-objective evolutionary algorithm based on decomposition.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"10 1","pages":"682-687"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87826636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9283275
Yanting Li, Junwei Jin, Huaiguang Wu, Lijun Sun, C. L. P. Chen
Sparse representation, collaborative representation, and other kinds of representation based classifiers have been extensively applied to face recognition. Specially, lots of experiments demonstrate that collaborative representation exhibits great potential. These existing classifiers generally focus on the single resolution. They do not work well for multiple resolution issues. However, images taken by different cameras in the real world have different resolutions. To deal with multi-resolution issues, this paper proposes a multi-resolution collaborative representation method. It builds multi-resolution training sample matrices and combines the collaborative representation to solve the multi-resolution recognition problem. Comparison experiments show that the proposed method exhibits the best comprehensive performance between all the tested methods.
{"title":"Multi-resolution Collaborative Representation for Face Recognition","authors":"Yanting Li, Junwei Jin, Huaiguang Wu, Lijun Sun, C. L. P. Chen","doi":"10.1109/SMC42975.2020.9283275","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283275","url":null,"abstract":"Sparse representation, collaborative representation, and other kinds of representation based classifiers have been extensively applied to face recognition. Specially, lots of experiments demonstrate that collaborative representation exhibits great potential. These existing classifiers generally focus on the single resolution. They do not work well for multiple resolution issues. However, images taken by different cameras in the real world have different resolutions. To deal with multi-resolution issues, this paper proposes a multi-resolution collaborative representation method. It builds multi-resolution training sample matrices and combines the collaborative representation to solve the multi-resolution recognition problem. Comparison experiments show that the proposed method exhibits the best comprehensive performance between all the tested methods.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"80 1","pages":"128-133"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87143635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9283379
Li-Tao Tan, Wei-neng Chen, Xiao-Min Hu
The virtual machine (VM) placement problem with the objective to save energy consumption and improve machine utility has been studied extensively in Cloud computing. However, the connection information among VMs during the execution of scientific workflows is seldom considered in existing studies. Therefore, this paper intends to build a novel connection-aware model for VM placement in scientific workflows. Different from existing studies, as the connection information of VMs is considered following the topology of workflows, not only the CPU capacity and memory capacity but also the transmission bandwidth among machines should be considered. An energy- aware, traffic-aware, connection-aware ant colony optimization (ETCACO) approach is developed. The proposed ETCACO combines Ant Colony Optimization (ACO) with a scheduler, namely greedy placeman. Experiments are performed to compare the proposed model with the traditional approach. It is discovered that by taking the connection information into consideration, the proposed approach can reduce energy consumption by 7%.
{"title":"An Ant Colony Optimization Approach to Connection-Aware Virtual Machine Placement for Scientific Workflows","authors":"Li-Tao Tan, Wei-neng Chen, Xiao-Min Hu","doi":"10.1109/SMC42975.2020.9283379","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283379","url":null,"abstract":"The virtual machine (VM) placement problem with the objective to save energy consumption and improve machine utility has been studied extensively in Cloud computing. However, the connection information among VMs during the execution of scientific workflows is seldom considered in existing studies. Therefore, this paper intends to build a novel connection-aware model for VM placement in scientific workflows. Different from existing studies, as the connection information of VMs is considered following the topology of workflows, not only the CPU capacity and memory capacity but also the transmission bandwidth among machines should be considered. An energy- aware, traffic-aware, connection-aware ant colony optimization (ETCACO) approach is developed. The proposed ETCACO combines Ant Colony Optimization (ACO) with a scheduler, namely greedy placeman. Experiments are performed to compare the proposed model with the traditional approach. It is discovered that by taking the connection information into consideration, the proposed approach can reduce energy consumption by 7%.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"61 1","pages":"3515-3522"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87526179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9283480
V. Schweizer, A. Lazurko
Social scientists apply cybernetic thought in subfields such as sociocybernetics; however, their applications are qualitatively inclined, limiting their ability to provide predictions useful for decision support. The quasi-qualitative method of cross-impact balances (CIB) offers a potential bridge between social scientific applications of cybernetics and cybernetic research that is more mechanistic, such as expert systems. This paper introduces the method of cross-impact balances (CIB) and serves as an invitation to systems scientists, systems engineers, and cyberneticians with shared interests in decision support for social system modeling and control. The problem of deep uncertainty in risk and policy research, as well as the potential for advances in second-order cybernetics through interdisciplinary research, are also discussed.
{"title":"Cross-impact Balances: A Method for Bridging Social Systems and Cybernetics","authors":"V. Schweizer, A. Lazurko","doi":"10.1109/SMC42975.2020.9283480","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283480","url":null,"abstract":"Social scientists apply cybernetic thought in subfields such as sociocybernetics; however, their applications are qualitatively inclined, limiting their ability to provide predictions useful for decision support. The quasi-qualitative method of cross-impact balances (CIB) offers a potential bridge between social scientific applications of cybernetics and cybernetic research that is more mechanistic, such as expert systems. This paper introduces the method of cross-impact balances (CIB) and serves as an invitation to systems scientists, systems engineers, and cyberneticians with shared interests in decision support for social system modeling and control. The problem of deep uncertainty in risk and policy research, as well as the potential for advances in second-order cybernetics through interdisciplinary research, are also discussed.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"21 1","pages":"4486-4492"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88105016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9282883
Alfredo Ibias, M. Núñez
Mutation Testing is an effective testing technique that relies in the generation of mutants from the system under test. The main limitation of this technique is that the potential number of mutants is usually huge. Therefore, it is important to classify and select mutants in order to avoid repetitive, useless or excessive computations, and biased results. In this paper we focus on avoiding too many executions and/or biased results by classifying mutants into two categories: hard-to-kill and easy-to-kill mutants. We propose a new swarm intelligence algorithm to classify a set of mutants between those two classes and we show how our algorithm compares to other approaches.
{"title":"Using a swarm to detect hard-to-kill mutants","authors":"Alfredo Ibias, M. Núñez","doi":"10.1109/SMC42975.2020.9282883","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9282883","url":null,"abstract":"Mutation Testing is an effective testing technique that relies in the generation of mutants from the system under test. The main limitation of this technique is that the potential number of mutants is usually huge. Therefore, it is important to classify and select mutants in order to avoid repetitive, useless or excessive computations, and biased results. In this paper we focus on avoiding too many executions and/or biased results by classifying mutants into two categories: hard-to-kill and easy-to-kill mutants. We propose a new swarm intelligence algorithm to classify a set of mutants between those two classes and we show how our algorithm compares to other approaches.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"21 1","pages":"2190-2195"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86253968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-11DOI: 10.1109/SMC42975.2020.9283310
Hong Jing Khok, Victor Teck Chang Koh, Cuntai Guan
Glaucoma is an eye disease that occurs without the onset of symptoms at initial, and late diagnosis results in irreversible degeneration of retinal ganglion cells. Standard automated perimetry is the gold standard for assessing glaucoma; however, the examination is subjective, where responses can fluctuate each time the test is performed, significantly confounding the test’s interpretation. In this study, we present our approach that aims to provide a rapid point-of-care diagnostics for glaucoma patients by eliminating the cognitive aspect in existing visual field assessment. Unlike existing methods that mostly report the foveal target detection’s accuracy, we employed a multi-task learning architecture that efficiently captures signals simultaneously from the fovea and the neighboring targets in the peripheral vision, generating a visual response map. Furthermore, we designed a multi-task learning module that learns multiple tasks in parallel efficiently. We evaluated our model classification on a 40-classes dataset, with yields 92% and 95% in accuracy and F1 score respectively. Our model is able to perform on a calibration-free user-independent scenario, which is desirable for clinical diagnostics. Our proposed approach could be a stepping stone for an objective assessment of glaucoma patients’ visual field.
{"title":"Deep Multi-Task Learning for SSVEP Detection and Visual Response Mapping","authors":"Hong Jing Khok, Victor Teck Chang Koh, Cuntai Guan","doi":"10.1109/SMC42975.2020.9283310","DOIUrl":"https://doi.org/10.1109/SMC42975.2020.9283310","url":null,"abstract":"Glaucoma is an eye disease that occurs without the onset of symptoms at initial, and late diagnosis results in irreversible degeneration of retinal ganglion cells. Standard automated perimetry is the gold standard for assessing glaucoma; however, the examination is subjective, where responses can fluctuate each time the test is performed, significantly confounding the test’s interpretation. In this study, we present our approach that aims to provide a rapid point-of-care diagnostics for glaucoma patients by eliminating the cognitive aspect in existing visual field assessment. Unlike existing methods that mostly report the foveal target detection’s accuracy, we employed a multi-task learning architecture that efficiently captures signals simultaneously from the fovea and the neighboring targets in the peripheral vision, generating a visual response map. Furthermore, we designed a multi-task learning module that learns multiple tasks in parallel efficiently. We evaluated our model classification on a 40-classes dataset, with yields 92% and 95% in accuracy and F1 score respectively. Our model is able to perform on a calibration-free user-independent scenario, which is desirable for clinical diagnostics. Our proposed approach could be a stepping stone for an objective assessment of glaucoma patients’ visual field.","PeriodicalId":6718,"journal":{"name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","volume":"91 1","pages":"1280-1285"},"PeriodicalIF":0.0,"publicationDate":"2020-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86192295","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：