Pub Date : 2019-12-01DOI: 10.1109/SSCI44817.2019.9002658
Jinhui Hu, Yifan Zhu, Huaqing Li, Zheng Wang
In this paper, we study distributed optimization problem over multi-agent networks where the goal is to find the global optimal of a sum of convex functions over strongly connected and directed graphs. A novel distributed algorithm is proposed where both row and column-stochastic matrices are utilized to bypass the limits of the implementation of doubly-stochastic matrices or eigenvector estimation in related work. Besides, it has an evident expression and accelerated convergence by introducing the momentum term. Combining the Generalized Small Gain Theorem with Linear Time Invariant (LTI) system inequality, the algorithm is proved to be able to linearly converge to the exact optimal solution. Furthermore, the ranges of stepsize and momentum paramater are characterized, respectively. Finally, simulation results illustrate effectiveness of the method and correctness of theoretical analysis.
{"title":"Accelerated Distributed Optimization over Directed Graphs with Row and Column-Stochastic Matrices","authors":"Jinhui Hu, Yifan Zhu, Huaqing Li, Zheng Wang","doi":"10.1109/SSCI44817.2019.9002658","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9002658","url":null,"abstract":"In this paper, we study distributed optimization problem over multi-agent networks where the goal is to find the global optimal of a sum of convex functions over strongly connected and directed graphs. A novel distributed algorithm is proposed where both row and column-stochastic matrices are utilized to bypass the limits of the implementation of doubly-stochastic matrices or eigenvector estimation in related work. Besides, it has an evident expression and accelerated convergence by introducing the momentum term. Combining the Generalized Small Gain Theorem with Linear Time Invariant (LTI) system inequality, the algorithm is proved to be able to linearly converge to the exact optimal solution. Furthermore, the ranges of stepsize and momentum paramater are characterized, respectively. Finally, simulation results illustrate effectiveness of the method and correctness of theoretical analysis.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"193 1","pages":"1299-1305"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83729977","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9002946
Junjie Shen, Xiao Li, Hong Zeng, Aiguo Song
Brain responses to visual stimulus can provide information about cognitive process or intentions. Several studies show that it is feasible to use stimulus-dependent modulation of the evoked brain responses after gaze movements (i.e., Fixation Related Potential, FRP) to predict the interested object of human. However, the performance of the state-of the-art shallow models for FRP classification is still far from satisfactory. Recent years, Riemannian geometry based on deep learning has gained its popularity in many image and video processing tasks, thanks to their ability to learn appropriate statistical representations while respecting Riemannian geometry of the data in such fields. In this paper, we have investigated a Riemannian network for classifying FRP in guided visual search task. Experiment results showed that the Riemannian network improved classification performance significantly in comparison to the shallow methods.
{"title":"Single-trial Classification of Fixation-related Potentials in Guided Visual Search Tasks using A Riemannian Network","authors":"Junjie Shen, Xiao Li, Hong Zeng, Aiguo Song","doi":"10.1109/SSCI44817.2019.9002946","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9002946","url":null,"abstract":"Brain responses to visual stimulus can provide information about cognitive process or intentions. Several studies show that it is feasible to use stimulus-dependent modulation of the evoked brain responses after gaze movements (i.e., Fixation Related Potential, FRP) to predict the interested object of human. However, the performance of the state-of the-art shallow models for FRP classification is still far from satisfactory. Recent years, Riemannian geometry based on deep learning has gained its popularity in many image and video processing tasks, thanks to their ability to learn appropriate statistical representations while respecting Riemannian geometry of the data in such fields. In this paper, we have investigated a Riemannian network for classifying FRP in guided visual search task. Experiment results showed that the Riemannian network improved classification performance significantly in comparison to the shallow methods.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"28 1","pages":"375-379"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83754074","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9003039
Kouhei Yamamoto, Shuai Shao, N. Kubota
In recent years, the demand for nursing services in Japan has been increasing. However, due to the work pressure and significant responsibility to the patient, people are not willing to engage in related work, and the labor shortage has become a severe problem. By our work, we propose a sensor-based monitoring system to reduce the burden on the caregiver. We put a set of air pressure sensor on the bed. When people are lying on the bed, air pressure signal changes. Using spiking neural networks, we can analyze the data and estimate the inactive state. In this paper, we mainly discuss how to get a person's heartbeat state while sleeping, which is useful for assessing sleep state.
{"title":"Heart Rate Measurement Using Air Pressure Sensor for Elderly Caring System","authors":"Kouhei Yamamoto, Shuai Shao, N. Kubota","doi":"10.1109/SSCI44817.2019.9003039","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9003039","url":null,"abstract":"In recent years, the demand for nursing services in Japan has been increasing. However, due to the work pressure and significant responsibility to the patient, people are not willing to engage in related work, and the labor shortage has become a severe problem. By our work, we propose a sensor-based monitoring system to reduce the burden on the caregiver. We put a set of air pressure sensor on the bed. When people are lying on the bed, air pressure signal changes. Using spiking neural networks, we can analyze the data and estimate the inactive state. In this paper, we mainly discuss how to get a person's heartbeat state while sleeping, which is useful for assessing sleep state.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"216 1","pages":"1440-1444"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79638300","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9003132
Chongchong Guan, Hui Lu
Maintenance support resource scheduling (MSRS) problem has attracted increasing attention in modern battle. It aims to allocate resources from multi-supply points to multi-tasks with the shortest time. However, there exists various constraints which are difficult to satisfy at the same time, such as limited resource reserves, different resource requirements, complex route conditions and strict task timing. As a result, we first obtain the shortest routes and task sequence with route planning and topological sorting algorithms separately. Then, with these information, an integrated meta-heuristic algorithm (IMHA) is designed to solve all the constraints. Furthermore, two improved algorithms, CMHA and GMHA are generated with classical and greedy scheduling strategies respectively. Experiment results show the feasibility of IMHA in solving the MSRS problem with timing constraint. Besides, compared with the IMHA, the GMHA and CMHA can generate scheduling schemes with lower cost and time in the whole 24 instances. In addition, as the increase of proportion of timing tasks, the advantages of GMHA in cost and time are more evident.
{"title":"Scheduling method of maintenance support resource with task timing constraint","authors":"Chongchong Guan, Hui Lu","doi":"10.1109/SSCI44817.2019.9003132","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9003132","url":null,"abstract":"Maintenance support resource scheduling (MSRS) problem has attracted increasing attention in modern battle. It aims to allocate resources from multi-supply points to multi-tasks with the shortest time. However, there exists various constraints which are difficult to satisfy at the same time, such as limited resource reserves, different resource requirements, complex route conditions and strict task timing. As a result, we first obtain the shortest routes and task sequence with route planning and topological sorting algorithms separately. Then, with these information, an integrated meta-heuristic algorithm (IMHA) is designed to solve all the constraints. Furthermore, two improved algorithms, CMHA and GMHA are generated with classical and greedy scheduling strategies respectively. Experiment results show the feasibility of IMHA in solving the MSRS problem with timing constraint. Besides, compared with the IMHA, the GMHA and CMHA can generate scheduling schemes with lower cost and time in the whole 24 instances. In addition, as the increase of proportion of timing tasks, the advantages of GMHA in cost and time are more evident.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"154 1","pages":"2698-2705"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79729343","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9002897
Tengfei Zhan, M. Ye, Wen-Wen Jiang, Yongjie Li, Kaifu Yang
Previous works suggest that scene contours play important roles in guiding visual attention. In this study, a computational model is proposed to improve the performance in visual saliency prediction by integrating the low- and mid-level visual cues and evaluate the contribution of scene contours in guiding visual attention. Firstly, we define three kinds of Gestalt principles based on mid-level cues, including contour density, closure, and symmetry to characterize the potential salient regions. In addition, we employ the classical bottom-up methods to generate low-level saliency maps. Finally, the proposed method combines the low-level cues from natural images and the mid-level cues from the corresponding contours to improve the fixation prediction. Experimental results show that the contour-based midlevel cues can remarkably improve the performance of the bottomup models in fixation prediction.
{"title":"Fixation Prediction based on Scene Contours","authors":"Tengfei Zhan, M. Ye, Wen-Wen Jiang, Yongjie Li, Kaifu Yang","doi":"10.1109/SSCI44817.2019.9002897","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9002897","url":null,"abstract":"Previous works suggest that scene contours play important roles in guiding visual attention. In this study, a computational model is proposed to improve the performance in visual saliency prediction by integrating the low- and mid-level visual cues and evaluate the contribution of scene contours in guiding visual attention. Firstly, we define three kinds of Gestalt principles based on mid-level cues, including contour density, closure, and symmetry to characterize the potential salient regions. In addition, we employ the classical bottom-up methods to generate low-level saliency maps. Finally, the proposed method combines the low-level cues from natural images and the mid-level cues from the corresponding contours to improve the fixation prediction. Experimental results show that the contour-based midlevel cues can remarkably improve the performance of the bottomup models in fixation prediction.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"12 1","pages":"2548-2554"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84682464","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9002971
Wen-Wen Jiang, Kai-Fu Yang, Yongjie Li
Neurobiology researches suggest that the motion information attracts more attention of human visual system than other low-level features such as brightness, color and texture. Consequently, video saliency detection methods not only consider the spatial saliency caused by the underlying features of images, but also the motion information in temporal domain. In this study, we proposes a model of video salient object detection based on a two-pathway framework that the spatio-temporal contrast guides the search for salient targets. Firstly, along the non-selective pathway, which is computed with the intra-frame and inter-frame maps of the color contrast and motion contrast, combining with the previous saliency map, to represent the prior information of the possible target locations. In contrast, the low-level features such as brightness, color and motion features are extracted in the selective pathway to search target accurately. Finally, the Bayesian inference is used to further obtain the optimal results. Experimental results show that our algorithm improves the performance of salient object detection on video compared to the representative method of Contour Guided Visual Search.
{"title":"A Video Salient Object Detection Model Guided by Spatio-Temporal Prior","authors":"Wen-Wen Jiang, Kai-Fu Yang, Yongjie Li","doi":"10.1109/SSCI44817.2019.9002971","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9002971","url":null,"abstract":"Neurobiology researches suggest that the motion information attracts more attention of human visual system than other low-level features such as brightness, color and texture. Consequently, video saliency detection methods not only consider the spatial saliency caused by the underlying features of images, but also the motion information in temporal domain. In this study, we proposes a model of video salient object detection based on a two-pathway framework that the spatio-temporal contrast guides the search for salient targets. Firstly, along the non-selective pathway, which is computed with the intra-frame and inter-frame maps of the color contrast and motion contrast, combining with the previous saliency map, to represent the prior information of the possible target locations. In contrast, the low-level features such as brightness, color and motion features are extracted in the selective pathway to search target accurately. Finally, the Bayesian inference is used to further obtain the optimal results. Experimental results show that our algorithm improves the performance of salient object detection on video compared to the representative method of Contour Guided Visual Search.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"24 1","pages":"2555-2562"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88773281","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9003101
Hao Tong, Shuyi Zhang, Changwu Huang, X. Yao
Evolutionary algorithms’ performance can be enhanced significantly by using suitable parameter configurations when solving optimization problems. Most existing parametertuning methods are inefficient, which tune algorithm’s parameters using whole benchmark function set and only obtain one parameter configuration. Moreover, the only obtained parameter configuration is likely to fail when solving different problems. In this paper, we propose a framework that applying portfolio for parameter-tuned algorithm (PPTA) to address these challenges. PPTA uses the parameter-tuned algorithm to tune algorithm’s parameters on one instance of each problem category, but not to all functions in the benchmark. As a result, it can obtain one parameter configuration for each problem category. Then, PPTA combines several instantiations of the same algorithms with different tuned parameters by portfolio method to decrease the risk of solving unknown problems. In order to analyse the performance of PPTA framework, we embed several test algorithms (i.e. GA, DE and PSO) into PPTA framework constructing algorithm instances. And the PPTA instances are compared with default test algorithms on BBOB2009 and CEC2005 benchmark functions. The experimental results has shown PPTA framework can significantly enhance the basic algorithm’s performance and reduce its optimization risk as well as the algorithm’s parametertuning time.
{"title":"Algorithm Portfolio for Parameter Tuned Evolutionary Algorithms","authors":"Hao Tong, Shuyi Zhang, Changwu Huang, X. Yao","doi":"10.1109/SSCI44817.2019.9003101","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9003101","url":null,"abstract":"Evolutionary algorithms’ performance can be enhanced significantly by using suitable parameter configurations when solving optimization problems. Most existing parametertuning methods are inefficient, which tune algorithm’s parameters using whole benchmark function set and only obtain one parameter configuration. Moreover, the only obtained parameter configuration is likely to fail when solving different problems. In this paper, we propose a framework that applying portfolio for parameter-tuned algorithm (PPTA) to address these challenges. PPTA uses the parameter-tuned algorithm to tune algorithm’s parameters on one instance of each problem category, but not to all functions in the benchmark. As a result, it can obtain one parameter configuration for each problem category. Then, PPTA combines several instantiations of the same algorithms with different tuned parameters by portfolio method to decrease the risk of solving unknown problems. In order to analyse the performance of PPTA framework, we embed several test algorithms (i.e. GA, DE and PSO) into PPTA framework constructing algorithm instances. And the PPTA instances are compared with default test algorithms on BBOB2009 and CEC2005 benchmark functions. The experimental results has shown PPTA framework can significantly enhance the basic algorithm’s performance and reduce its optimization risk as well as the algorithm’s parametertuning time.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"7 1","pages":"1849-1856"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79555534","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9003147
Julie L. Harvey, S. Kumar
Predicting classifiers can be used to analyze data in K-12 education. Creating a classification model to accurately identify factors affecting student performance can be challenging. Much research has been conducted to predict student performance in higher education, but there is limited research in using data science to predict student performance in K-12 education. Predictive models are developed and examined in this review to analyze a K-12 education dataset. Three classifiers are used to develop these predictive models, including linear regression, decision tree, and Naive Bayes techniques. The Naive Bayes techniques showed the highest accuracy when predicting SAT Math scores for high school students. The results from this review of current research and the models presented in this paper can be used by stakeholders of K-12 education to make predictions of student performance and be able to implement intervention strategies for students in a timely manner.
{"title":"A Practical Model for Educators to Predict Student Performance in K-12 Education using Machine Learning","authors":"Julie L. Harvey, S. Kumar","doi":"10.1109/SSCI44817.2019.9003147","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9003147","url":null,"abstract":"Predicting classifiers can be used to analyze data in K-12 education. Creating a classification model to accurately identify factors affecting student performance can be challenging. Much research has been conducted to predict student performance in higher education, but there is limited research in using data science to predict student performance in K-12 education. Predictive models are developed and examined in this review to analyze a K-12 education dataset. Three classifiers are used to develop these predictive models, including linear regression, decision tree, and Naive Bayes techniques. The Naive Bayes techniques showed the highest accuracy when predicting SAT Math scores for high school students. The results from this review of current research and the models presented in this paper can be used by stakeholders of K-12 education to make predictions of student performance and be able to implement intervention strategies for students in a timely manner.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"18 1","pages":"3004-3011"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86586733","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9003135
Xiumei Cai, Jingwei Bian, Yan Wang, Y. Ning
Aiming at the problems of static parameters and dynamic parameter testing of IGBT (Insulated Gate Bipolar Transistor), the error is large, the efficiency is low, and the test structure is poorly mixed. This paper proposes to use LabVIEWbased test system to measure the parameters. Using NI ELVIS as the measuring instrument platform, the ADC0809 single-chip microcomputer and the hardware circuit corresponding to the series voltage equalization are used as the execution process of the measurement process, making the measurement data more precise and stable. The stability and function of the IGBT are evaluated by measuring the saturation voltage drop, the off current and the switching off time as the measurement parameters.
{"title":"Design of IGBT Parameter Automatic Test System Based on LabVIEW","authors":"Xiumei Cai, Jingwei Bian, Yan Wang, Y. Ning","doi":"10.1109/SSCI44817.2019.9003135","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9003135","url":null,"abstract":"Aiming at the problems of static parameters and dynamic parameter testing of IGBT (Insulated Gate Bipolar Transistor), the error is large, the efficiency is low, and the test structure is poorly mixed. This paper proposes to use LabVIEWbased test system to measure the parameters. Using NI ELVIS as the measuring instrument platform, the ADC0809 single-chip microcomputer and the hardware circuit corresponding to the series voltage equalization are used as the execution process of the measurement process, making the measurement data more precise and stable. The stability and function of the IGBT are evaluated by measuring the saturation voltage drop, the off current and the switching off time as the measurement parameters.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"23 1","pages":"2807-2812"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90790322","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 : 2019-12-01DOI: 10.1109/SSCI44817.2019.9002720
Natabara Máté Gyöngyössy, Márk Domonkos, J. Botzheim, P. Korondi
This paper proposes a novel supervised learning algorithm for spiking neural networks. The algorithm combines Hebbian learning and least mean squares method and it works well for small training datasets and short training cycles. The proposed method is applied in human-robot interaction for recognizing musical hand gestures based on the work of Zoltán Kodaly. The MNIST dataset is also used as a benchmark test to´ verify the proposed algorithm’s capability to outperform shallow ANN architectures. Experiments with the robot also provided promising results by recognizing the human hand signs correctly.
{"title":"Supervised Learning with Small Training Set for Gesture Recognition by Spiking Neural Networks","authors":"Natabara Máté Gyöngyössy, Márk Domonkos, J. Botzheim, P. Korondi","doi":"10.1109/SSCI44817.2019.9002720","DOIUrl":"https://doi.org/10.1109/SSCI44817.2019.9002720","url":null,"abstract":"This paper proposes a novel supervised learning algorithm for spiking neural networks. The algorithm combines Hebbian learning and least mean squares method and it works well for small training datasets and short training cycles. The proposed method is applied in human-robot interaction for recognizing musical hand gestures based on the work of Zoltán Kodaly. The MNIST dataset is also used as a benchmark test to´ verify the proposed algorithm’s capability to outperform shallow ANN architectures. Experiments with the robot also provided promising results by recognizing the human hand signs correctly.","PeriodicalId":6729,"journal":{"name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"49 1","pages":"2201-2206"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89868851","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：