Pub Date : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298125
Jiadao Zou, Qingxue Zhang, Kyle Frick
Smart health big data is quickly driving the healthcare field and bringing numerous new opportunities. Cardiac disease is a leading cause of death worldwide, and the personalized cardiac big data is expected to offer new strategies and possibilities for cardiac health management. The standard 12-lead electrocardiogram (ECG) has been a gold standard of cardiac health measurement for decades. However, there is still lack of effective ways to monitor 12-lead ECG in our daily lives, which is a critical obstacle towards personalized cardiac big data. In this study, we have proposed and validated a mobile 3-lead ECG monitoring system that can reconstruct the standard 12-lead ECG, offering a much greater usability for daily ECG tracking compared with the traditional 12-lead ECG system. Moreover, the system is able to deal with severe motion artifacts during daily physical exercises and yield high-fidelity ECG reconstruction, leveraging a deep recurrent neural network. A multi-stage long short-term memory network has been proposed to reconstruct the robust 12-lead ECG from the noisy 3-lead ECG. This motion artifacts-tolerant ability is highly important, considering that users may perform diverse and random physical activities, which will inevitably contaminate or even corrupt the ECG signal. The reconstruction error is as low as 0.069, and the correlation coefficient is as high as 0.84. This unobtrusive and motion-tolerant mobile ECG monitoring system has been validated on human data and demonstrated the feasibility to continuously establish the personalized cardiac big data. This research is highly encouraging and is expected to be able to significantly advance big data-driven cardiac health management.
{"title":"Intelligent Mobile Electrocardiogram Monitor-empowered Personalized Cardiac Big Data*","authors":"Jiadao Zou, Qingxue Zhang, Kyle Frick","doi":"10.1109/UEMCON51285.2020.9298125","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298125","url":null,"abstract":"Smart health big data is quickly driving the healthcare field and bringing numerous new opportunities. Cardiac disease is a leading cause of death worldwide, and the personalized cardiac big data is expected to offer new strategies and possibilities for cardiac health management. The standard 12-lead electrocardiogram (ECG) has been a gold standard of cardiac health measurement for decades. However, there is still lack of effective ways to monitor 12-lead ECG in our daily lives, which is a critical obstacle towards personalized cardiac big data. In this study, we have proposed and validated a mobile 3-lead ECG monitoring system that can reconstruct the standard 12-lead ECG, offering a much greater usability for daily ECG tracking compared with the traditional 12-lead ECG system. Moreover, the system is able to deal with severe motion artifacts during daily physical exercises and yield high-fidelity ECG reconstruction, leveraging a deep recurrent neural network. A multi-stage long short-term memory network has been proposed to reconstruct the robust 12-lead ECG from the noisy 3-lead ECG. This motion artifacts-tolerant ability is highly important, considering that users may perform diverse and random physical activities, which will inevitably contaminate or even corrupt the ECG signal. The reconstruction error is as low as 0.069, and the correlation coefficient is as high as 0.84. This unobtrusive and motion-tolerant mobile ECG monitoring system has been validated on human data and demonstrated the feasibility to continuously establish the personalized cardiac big data. This research is highly encouraging and is expected to be able to significantly advance big data-driven cardiac health management.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128531939","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298113
A. Ornatelli, A. Tortorelli, A. Giuseppi
Multi-Access Heterogeneous Networks introduced a step forward in modern communication networks allowing the provision of reliable and efficient broadband services. However, heterogeneous networks imply a burden of complexity in the integration, coordination and QoS management processes thus complicating the satisfaction of users’ requirements. The aim of the present work is to address the above-mentioned issues by developing a mathematical framework for optimizing resource usage in 5G heterogeneous networks. More in detail, the optimization will take into account both the network’s load and energy consumption simultaneously. The proposed approach, based on Model Predictive Control, will be compared with other control strategies for validation and performance comparison.
{"title":"Iterative MPC for Energy Management and Load Balancing in 5G Heterogeneous Networks","authors":"A. Ornatelli, A. Tortorelli, A. Giuseppi","doi":"10.1109/UEMCON51285.2020.9298113","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298113","url":null,"abstract":"Multi-Access Heterogeneous Networks introduced a step forward in modern communication networks allowing the provision of reliable and efficient broadband services. However, heterogeneous networks imply a burden of complexity in the integration, coordination and QoS management processes thus complicating the satisfaction of users’ requirements. The aim of the present work is to address the above-mentioned issues by developing a mathematical framework for optimizing resource usage in 5G heterogeneous networks. More in detail, the optimization will take into account both the network’s load and energy consumption simultaneously. The proposed approach, based on Model Predictive Control, will be compared with other control strategies for validation and performance comparison.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129580545","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298063
Gregory J. Larrick, Yun Tian, U. Rogers, Halim Acosta, Fangyang Shen
This paper explores recent trends in field of big data visualization based on cloud computing via the use of virtual machine hosted servers. Specifically, the visualization of terrain data acquired from several major open data sets using a graphics library for browser based rendering will be explored. It will be shown that three dimensional terrain information may be viewed and interacted with by many remote clients within a browser when using modern graphics libraries, and a collection of Amazon EC-2 machines for fetching and decoding of the terrain data. Data pre-fetching and a parallel implementation of each server further improves performance. Results from this study are expected to enable and expedite existing and future research in the terrain data visualization field.
{"title":"Interactive Visualization of 3D Terrain Data Stored in the Cloud","authors":"Gregory J. Larrick, Yun Tian, U. Rogers, Halim Acosta, Fangyang Shen","doi":"10.1109/UEMCON51285.2020.9298063","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298063","url":null,"abstract":"This paper explores recent trends in field of big data visualization based on cloud computing via the use of virtual machine hosted servers. Specifically, the visualization of terrain data acquired from several major open data sets using a graphics library for browser based rendering will be explored. It will be shown that three dimensional terrain information may be viewed and interacted with by many remote clients within a browser when using modern graphics libraries, and a collection of Amazon EC-2 machines for fetching and decoding of the terrain data. Data pre-fetching and a parallel implementation of each server further improves performance. Results from this study are expected to enable and expedite existing and future research in the terrain data visualization field.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129582778","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298062
C. Arnold, Jason Brown
Recent instances of malicious Unmanned Aerial Vehicles (UAVs) causing service disruption or damage to critical infrastructure has prompted research into methods of mitigating and deterring such nefarious activities. One such countermeasure is to use a swarm of UAVs to track the malicious UAV back to its origin. In this paper, we evaluate different methods of swarm formation for the purposes of malicious UAV tracking via a bespoke OMNeT++ simulation. The simulation also evaluates the effect of the number of UAVs in the swarm, as well as the evasiveness of the malicious UAV in terms of its flight capabilities and flight path. The results demonstrate that encirclement type swarm formations such as Surround and Cone, in which the malicious UAV is surrounded by the swarm, perform better than a follow type swarm formation in their ability to continue to track the malicious UAV.
{"title":"Performance Evaluation for Tracking a Malicious UAV using an Autonomous UAV Swarm","authors":"C. Arnold, Jason Brown","doi":"10.1109/UEMCON51285.2020.9298062","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298062","url":null,"abstract":"Recent instances of malicious Unmanned Aerial Vehicles (UAVs) causing service disruption or damage to critical infrastructure has prompted research into methods of mitigating and deterring such nefarious activities. One such countermeasure is to use a swarm of UAVs to track the malicious UAV back to its origin. In this paper, we evaluate different methods of swarm formation for the purposes of malicious UAV tracking via a bespoke OMNeT++ simulation. The simulation also evaluates the effect of the number of UAVs in the swarm, as well as the evasiveness of the malicious UAV in terms of its flight capabilities and flight path. The results demonstrate that encirclement type swarm formations such as Surround and Cone, in which the malicious UAV is surrounded by the swarm, perform better than a follow type swarm formation in their ability to continue to track the malicious UAV.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131025386","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298083
Randy Krauss, Matthew Vaysfeld, Murad Arslaner, Gregg Vesonder
Due to the coronavirus pandemic, there have been growing concerns over the safety of various highly populated areas such as universities, stores, and gyms. For this project, our team created an app using the react native framework in order to help people understand which areas are safe to occupy. The app uses environmental sensors attached to a Raspberry Pi to gather data in various locations to determine whether the area is safe or not. With the app, the goal is to create a streamlined way to relay information to the general public that could aid in the wellbeing of citizens during this pandemic and any future ones.
{"title":"Streamlining Smart Cities to Create Safer Spaces","authors":"Randy Krauss, Matthew Vaysfeld, Murad Arslaner, Gregg Vesonder","doi":"10.1109/UEMCON51285.2020.9298083","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298083","url":null,"abstract":"Due to the coronavirus pandemic, there have been growing concerns over the safety of various highly populated areas such as universities, stores, and gyms. For this project, our team created an app using the react native framework in order to help people understand which areas are safe to occupy. The app uses environmental sensors attached to a Raspberry Pi to gather data in various locations to determine whether the area is safe or not. With the app, the goal is to create a streamlined way to relay information to the general public that could aid in the wellbeing of citizens during this pandemic and any future ones.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132036286","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298108
Murad Mehrab Abrar, Raian Islam, Md. Azad Hossen Shanto
Due to the coronavirus situation around the world, safe and contactless home delivery services have become substantial concerns for the people while they are forced to stay at home. In this context, we have proposed a prototype robot that can be very helpful to reduce the risk of infectious disease transmission in the product delivery system during the extreme strain on healthcare and hygiene. The design and development of a cost effective autonomous mobile robot prototype have been presented that can deliver packages safely to a desired destination using Global Positioning System (GPS). The robot ensures a secure and human-contactless delivery by using a password protected container to carry the delivery package. The four wheel drive robot can successfully navigate to a preset location by receiving GPS coordinates from satellites and correcting its direction using a digital compass. After the robot arrives at its destination, it waits for the customer to unlock the container. The customer will have to use a password upon delivery to unlock the container and retrieve the ordered product. This password can be sent to the customer with the order confirmation message. After completing the delivery, the robot can autonomously return to its starting location. Heading angle accuracy test and trajectory completion accuracy test have been performed to ascertain the accuracy of the robot. Alongside an infection risk-free product delivery, our robot can be an effective technological solution of the last mile problem which will reduce the last mile delivery cost significantly.
{"title":"An Autonomous Delivery Robot to Prevent the Spread of Coronavirus in Product Delivery System","authors":"Murad Mehrab Abrar, Raian Islam, Md. Azad Hossen Shanto","doi":"10.1109/UEMCON51285.2020.9298108","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298108","url":null,"abstract":"Due to the coronavirus situation around the world, safe and contactless home delivery services have become substantial concerns for the people while they are forced to stay at home. In this context, we have proposed a prototype robot that can be very helpful to reduce the risk of infectious disease transmission in the product delivery system during the extreme strain on healthcare and hygiene. The design and development of a cost effective autonomous mobile robot prototype have been presented that can deliver packages safely to a desired destination using Global Positioning System (GPS). The robot ensures a secure and human-contactless delivery by using a password protected container to carry the delivery package. The four wheel drive robot can successfully navigate to a preset location by receiving GPS coordinates from satellites and correcting its direction using a digital compass. After the robot arrives at its destination, it waits for the customer to unlock the container. The customer will have to use a password upon delivery to unlock the container and retrieve the ordered product. This password can be sent to the customer with the order confirmation message. After completing the delivery, the robot can autonomously return to its starting location. Heading angle accuracy test and trajectory completion accuracy test have been performed to ascertain the accuracy of the robot. Alongside an infection risk-free product delivery, our robot can be an effective technological solution of the last mile problem which will reduce the last mile delivery cost significantly.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130438491","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298090
A. Drebee, A. Topcu, Yasamin Alagrash
Healthcare-related costs still pose problems despite the availability of large quantities of healthcare information. In this paper we propose reducing health-related costs while not violating the privacy of information related to the patients, and we also address the authentication of the blockchain. This study makes use of raw data by processing it in a reasonable way to provide effective and less costly healthcare services along with the needed privacy and ease of accessibility of information to the relevant providers. The current paper utilizes the properties of the logistic map as SHA-256 calculates the hash value for the plain text, with the results being applied to change the initial keys for the logistic map. For expansion of the chaotic region of the logistic map and for making it better suited for the generation key, a mixture of multiple parameters of the logistic map key generation is proposed. Algorithm 2 shows how to generate a new key for the hash function for the new block. A key generator based on logistic map theory can be applied. The key generator is not meant to regenerate, which means that it is not possible to regenerate the same key. Therefore, the authentication is strengthened.
{"title":"Healthcare Security Based on Blockchain within Multi-parameter Chaotic Map","authors":"A. Drebee, A. Topcu, Yasamin Alagrash","doi":"10.1109/UEMCON51285.2020.9298090","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298090","url":null,"abstract":"Healthcare-related costs still pose problems despite the availability of large quantities of healthcare information. In this paper we propose reducing health-related costs while not violating the privacy of information related to the patients, and we also address the authentication of the blockchain. This study makes use of raw data by processing it in a reasonable way to provide effective and less costly healthcare services along with the needed privacy and ease of accessibility of information to the relevant providers. The current paper utilizes the properties of the logistic map as SHA-256 calculates the hash value for the plain text, with the results being applied to change the initial keys for the logistic map. For expansion of the chaotic region of the logistic map and for making it better suited for the generation key, a mixture of multiple parameters of the logistic map key generation is proposed. Algorithm 2 shows how to generate a new key for the hash function for the new block. A key generator based on logistic map theory can be applied. The key generator is not meant to regenerate, which means that it is not possible to regenerate the same key. Therefore, the authentication is strengthened.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126198706","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298119
Bijal Patel, Haiyang Ji, S. Nayak, Ting Ding, Yue Pan, Michal Aibin
Elastic Optical Networks are based on the Orthogonal frequency-division multiplexing (OFDM), thus providing a more efficient and flexible data-transferring network than fixed-grid WDM networks. In this paper we solve the Routing, Modulation and Spectrum Assignment (RMSA) problem. For this purpose, we design a new, highly efficient Adaptive Dynamic Routing Algorithm (ADRA). Our results show that it outperforms other methods from the literature.
{"title":"On Efficient Candidate Path Selection for Dynamic Routing in Elastic Optical Networks","authors":"Bijal Patel, Haiyang Ji, S. Nayak, Ting Ding, Yue Pan, Michal Aibin","doi":"10.1109/UEMCON51285.2020.9298119","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298119","url":null,"abstract":"Elastic Optical Networks are based on the Orthogonal frequency-division multiplexing (OFDM), thus providing a more efficient and flexible data-transferring network than fixed-grid WDM networks. In this paper we solve the Routing, Modulation and Spectrum Assignment (RMSA) problem. For this purpose, we design a new, highly efficient Adaptive Dynamic Routing Algorithm (ADRA). Our results show that it outperforms other methods from the literature.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122240778","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298123
Yash Parikh, Eman Abdelfattah
This paper investigates how clustering algorithms and Recency, Frequency, and Monetary value (RFM) analysis can be performed on online transactions to provide strategies for customer purchasing behaviors. Along with performing RFM analysis on the retail dataset, clustering algorithms such as Mean-shift, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Agglomerative Clustering, and K-Means were utilized. By comparing these clustering algorithms, we have found valuable customer groups based on RFM values.
{"title":"Clustering Algorithms and RFM Analysis Performed on Retail Transactions","authors":"Yash Parikh, Eman Abdelfattah","doi":"10.1109/UEMCON51285.2020.9298123","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298123","url":null,"abstract":"This paper investigates how clustering algorithms and Recency, Frequency, and Monetary value (RFM) analysis can be performed on online transactions to provide strategies for customer purchasing behaviors. Along with performing RFM analysis on the retail dataset, clustering algorithms such as Mean-shift, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Agglomerative Clustering, and K-Means were utilized. By comparing these clustering algorithms, we have found valuable customer groups based on RFM values.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121383516","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298064
Qi Wang, Xianping Wang
sEMG is a promising human computer interaction approach, which has been widely used in myriads of areas. To perform sEMG classification, more and more sophisticated machine learning strategies have been developed. However, the deep neural network still has limited applications on sEMG decoding, though it has got a great success in the computer vision area. In this study, we propose a new deep learning framework to classify hand gestures based on sEMG, especially we perform convolutional neural network (CNN) on multiple-session sEMG, which is more challenging because of the time-varying biodynamics of the subjects. So we also investigate the topologies of CNN, expecting to get an optimized architecture to effectively detect the hidden features in the signals. It is shown that the proposed CNN framework in this study has a high classification accuracy for sEMG-based hand gesture recognition, and the difference of topologies has great impact on the performance of CNN. This study lays a promising foundation for multiple-session sEMG signal pattern recognition by CNN.
{"title":"Deep Convolutional Neural Network for Decoding EMG for Human Computer Interaction","authors":"Qi Wang, Xianping Wang","doi":"10.1109/UEMCON51285.2020.9298064","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298064","url":null,"abstract":"sEMG is a promising human computer interaction approach, which has been widely used in myriads of areas. To perform sEMG classification, more and more sophisticated machine learning strategies have been developed. However, the deep neural network still has limited applications on sEMG decoding, though it has got a great success in the computer vision area. In this study, we propose a new deep learning framework to classify hand gestures based on sEMG, especially we perform convolutional neural network (CNN) on multiple-session sEMG, which is more challenging because of the time-varying biodynamics of the subjects. So we also investigate the topologies of CNN, expecting to get an optimized architecture to effectively detect the hidden features in the signals. It is shown that the proposed CNN framework in this study has a high classification accuracy for sEMG-based hand gesture recognition, and the difference of topologies has great impact on the performance of CNN. This study lays a promising foundation for multiple-session sEMG signal pattern recognition by CNN.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125665980","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：