Sagar Dakua, Alamgir Kabir Rusad, N. Sakib, Md. Ahsan-Ul Kabir Shawon, Md Kafiul Islam
{"title":"面向孟加拉等发展中国家假肢控制的低成本肌电信号记录仪的设计与实现","authors":"Sagar Dakua, Alamgir Kabir Rusad, N. Sakib, Md. Ahsan-Ul Kabir Shawon, Md Kafiul Islam","doi":"10.1109/ICCITECHN.2018.8631965","DOIUrl":null,"url":null,"abstract":"Recently, Human Machine Interface (HMI) has become an important part of medical technology where different bio-signals such as EOG, EMG, and EEG can be deployed to develop a closed-loop control system for physically disabled and elderly people to improve their quality of life. On the other hand, as the road and industrial accidents are increasing in countries like Bangladesh, more and more people are losing body parts and are not able to treat their condition properly due to the financial burden and lack in technological advancement. In this research, we have preliminarily designed, implemented and tested a low-cost EMG recording and monitoring system that can detect and process EMG signals from different kinds of muscle contraction. The recorded signals can be interfaced with the computer through Arduino UNO and then the EMG signals can be analyzed further in MATLAB platform. We have also developed an algorithm to detect muscle contraction and expansion from raw EMG recordings and then converted them into command signals that can control a robotic arm. In order to demonstrate the efficacy of the proposed system, lab experiments are performed by recording of EMG signals from 5 subjects by attaching electrodes on their shoulders and calculated the accuracy of detecting muscle contraction based on four ROC parameters, known as True Positives (TP) False Positives (FP), True Negatives (TN) and False Negatives (FN); which results in 83% accuracy on an average. Then based on the detected muscle contraction, we successfully demonstrated to control a robotic arm by opening and closing of its fingers which can later be replaced with a prosthetic arm for those disabled persons who lost their arms. This research will help not only to diagnose any neuromuscular disease by comparing it with any healthy subject's EMG signal, but also these EMG recordings can be processed and decoded to control prosthetic arm for those people who lost their arm but cannot afford commercially available expensive prosthetic systems in a developing country like Bangladesh.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Towards Design and Implementation of a Low-Cost EMG Signal Recorder for Application in Prosthetic Arm Control for Developing Countries Like Bangladesh\",\"authors\":\"Sagar Dakua, Alamgir Kabir Rusad, N. Sakib, Md. Ahsan-Ul Kabir Shawon, Md Kafiul Islam\",\"doi\":\"10.1109/ICCITECHN.2018.8631965\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, Human Machine Interface (HMI) has become an important part of medical technology where different bio-signals such as EOG, EMG, and EEG can be deployed to develop a closed-loop control system for physically disabled and elderly people to improve their quality of life. On the other hand, as the road and industrial accidents are increasing in countries like Bangladesh, more and more people are losing body parts and are not able to treat their condition properly due to the financial burden and lack in technological advancement. In this research, we have preliminarily designed, implemented and tested a low-cost EMG recording and monitoring system that can detect and process EMG signals from different kinds of muscle contraction. The recorded signals can be interfaced with the computer through Arduino UNO and then the EMG signals can be analyzed further in MATLAB platform. We have also developed an algorithm to detect muscle contraction and expansion from raw EMG recordings and then converted them into command signals that can control a robotic arm. In order to demonstrate the efficacy of the proposed system, lab experiments are performed by recording of EMG signals from 5 subjects by attaching electrodes on their shoulders and calculated the accuracy of detecting muscle contraction based on four ROC parameters, known as True Positives (TP) False Positives (FP), True Negatives (TN) and False Negatives (FN); which results in 83% accuracy on an average. Then based on the detected muscle contraction, we successfully demonstrated to control a robotic arm by opening and closing of its fingers which can later be replaced with a prosthetic arm for those disabled persons who lost their arms. This research will help not only to diagnose any neuromuscular disease by comparing it with any healthy subject's EMG signal, but also these EMG recordings can be processed and decoded to control prosthetic arm for those people who lost their arm but cannot afford commercially available expensive prosthetic systems in a developing country like Bangladesh.\",\"PeriodicalId\":355984,\"journal\":{\"name\":\"2018 21st International Conference of Computer and Information Technology (ICCIT)\",\"volume\":\"14 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 21st International Conference of Computer and Information Technology (ICCIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCITECHN.2018.8631965\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 21st International Conference of Computer and Information Technology (ICCIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCITECHN.2018.8631965","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Towards Design and Implementation of a Low-Cost EMG Signal Recorder for Application in Prosthetic Arm Control for Developing Countries Like Bangladesh
Recently, Human Machine Interface (HMI) has become an important part of medical technology where different bio-signals such as EOG, EMG, and EEG can be deployed to develop a closed-loop control system for physically disabled and elderly people to improve their quality of life. On the other hand, as the road and industrial accidents are increasing in countries like Bangladesh, more and more people are losing body parts and are not able to treat their condition properly due to the financial burden and lack in technological advancement. In this research, we have preliminarily designed, implemented and tested a low-cost EMG recording and monitoring system that can detect and process EMG signals from different kinds of muscle contraction. The recorded signals can be interfaced with the computer through Arduino UNO and then the EMG signals can be analyzed further in MATLAB platform. We have also developed an algorithm to detect muscle contraction and expansion from raw EMG recordings and then converted them into command signals that can control a robotic arm. In order to demonstrate the efficacy of the proposed system, lab experiments are performed by recording of EMG signals from 5 subjects by attaching electrodes on their shoulders and calculated the accuracy of detecting muscle contraction based on four ROC parameters, known as True Positives (TP) False Positives (FP), True Negatives (TN) and False Negatives (FN); which results in 83% accuracy on an average. Then based on the detected muscle contraction, we successfully demonstrated to control a robotic arm by opening and closing of its fingers which can later be replaced with a prosthetic arm for those disabled persons who lost their arms. This research will help not only to diagnose any neuromuscular disease by comparing it with any healthy subject's EMG signal, but also these EMG recordings can be processed and decoded to control prosthetic arm for those people who lost their arm but cannot afford commercially available expensive prosthetic systems in a developing country like Bangladesh.