Pub Date : 2015-04-22DOI: 10.1109/NER.2015.7146582
Xujiong Dong, Haofei Wang, Zhaokang Chen, Bertram E. Shi
We describe a hybrid brain computer interface that integrates information from a four-class motor imagery based EEG classifier with information about gaze trajectories from an eye tracker. The novel aspect of this system is that no explicit gaze behavior is required of the user. Rather, the natural gaze behavior of the user integrated probabilistically to smooth the noisy classification results from the motor imagery based EEG. The goal is to provide for a more natural interaction with the BCI system than if gaze were used as an explicit command signal, as is commonly done. Our results on a 2D cursor control task show that integration of gaze information significantly improves task completion accuracy and reduces task completion time. In particular, our system achieves over 80% target completion accuracy on a cursor control task requiring guidance to one of 12 targets.
{"title":"Hybrid Brain Computer Interface via Bayesian integration of EEG and eye gaze","authors":"Xujiong Dong, Haofei Wang, Zhaokang Chen, Bertram E. Shi","doi":"10.1109/NER.2015.7146582","DOIUrl":"https://doi.org/10.1109/NER.2015.7146582","url":null,"abstract":"We describe a hybrid brain computer interface that integrates information from a four-class motor imagery based EEG classifier with information about gaze trajectories from an eye tracker. The novel aspect of this system is that no explicit gaze behavior is required of the user. Rather, the natural gaze behavior of the user integrated probabilistically to smooth the noisy classification results from the motor imagery based EEG. The goal is to provide for a more natural interaction with the BCI system than if gaze were used as an explicit command signal, as is commonly done. Our results on a 2D cursor control task show that integration of gaze information significantly improves task completion accuracy and reduces task completion time. In particular, our system achieves over 80% target completion accuracy on a cursor control task requiring guidance to one of 12 targets.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131469777","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 : 2015-04-22DOI: 10.1109/NER.2015.7146633
Maruan Al-Shedivat, R. Naous, E. Neftci, G. Cauwenberghs, K. Salama
Neuromorphic engineering aims to design hardware that efficiently mimics neural circuitry and provides the means for emulating and studying neural systems. In this paper, we propose a new memristor-based neuron circuit that uniquely complements the scope of neuron implementations and follows the stochastic spike response model (SRM), which plays a cornerstone role in spike-based probabilistic algorithms. We demonstrate that the switching of the memristor is akin to the stochastic firing of the SRM. Our analysis and simulations show that the proposed neuron circuit satisfies a neural computability condition that enables probabilistic neural sampling and spike-based Bayesian learning and inference. Our findings constitute an important step towards memristive, scalable and efficient stochastic neuromorphic platforms.
{"title":"Inherently stochastic spiking neurons for probabilistic neural computation","authors":"Maruan Al-Shedivat, R. Naous, E. Neftci, G. Cauwenberghs, K. Salama","doi":"10.1109/NER.2015.7146633","DOIUrl":"https://doi.org/10.1109/NER.2015.7146633","url":null,"abstract":"Neuromorphic engineering aims to design hardware that efficiently mimics neural circuitry and provides the means for emulating and studying neural systems. In this paper, we propose a new memristor-based neuron circuit that uniquely complements the scope of neuron implementations and follows the stochastic spike response model (SRM), which plays a cornerstone role in spike-based probabilistic algorithms. We demonstrate that the switching of the memristor is akin to the stochastic firing of the SRM. Our analysis and simulations show that the proposed neuron circuit satisfies a neural computability condition that enables probabilistic neural sampling and spike-based Bayesian learning and inference. Our findings constitute an important step towards memristive, scalable and efficient stochastic neuromorphic platforms.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130197723","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 : 2015-04-22DOI: 10.1109/NER.2015.7146729
Linda Xu, S. Loh, C. Taswell
Clinical telegaming integrates telecare and videogaming to enable a more convenient and enjoyable experience for patients when providers diagnose, monitor, and treat a variety of health problems via web-enabled telecommunications. In recent years, clinical telegaming systems have been applied to physical therapy and rehabilitation, evaluation of mental health, and prevention and management of obesity and diabetes. Parkinson's disease (PD) is suitable for development of new clinical telegaming applications because PD patients are known to experience motor symptoms that can be improved by physical therapy. Recent research suggests that sensory processing deficits may also play an important role in these motor impairments because successful motor function requires multisensory integration. In this paper, we describe a new web-enabled software system that uses clinical telegaming to evaluate and improve multisensory integration ability in users. This software has the potential to be used in diagnostic and therapeutic telegaming for PD patients.
{"title":"Web-enabled software for clinical telegaming evaluation of multisensory integration and response to auditory and visual stimuli","authors":"Linda Xu, S. Loh, C. Taswell","doi":"10.1109/NER.2015.7146729","DOIUrl":"https://doi.org/10.1109/NER.2015.7146729","url":null,"abstract":"Clinical telegaming integrates telecare and videogaming to enable a more convenient and enjoyable experience for patients when providers diagnose, monitor, and treat a variety of health problems via web-enabled telecommunications. In recent years, clinical telegaming systems have been applied to physical therapy and rehabilitation, evaluation of mental health, and prevention and management of obesity and diabetes. Parkinson's disease (PD) is suitable for development of new clinical telegaming applications because PD patients are known to experience motor symptoms that can be improved by physical therapy. Recent research suggests that sensory processing deficits may also play an important role in these motor impairments because successful motor function requires multisensory integration. In this paper, we describe a new web-enabled software system that uses clinical telegaming to evaluate and improve multisensory integration ability in users. This software has the potential to be used in diagnostic and therapeutic telegaming for PD patients.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121763163","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 : 2015-04-22DOI: 10.1109/NER.2015.7146606
H. Lorach, Georges A. Goetz, Y. Mandel, R. Smith, David Boinagrov, X. Lei, R. Dalal, P. Huie, T. Kamins, J. Harris, K. Mathieson, A. Sher, D. Palanker
Patients with retinal degeneration lose sight due to gradual demise of photoreceptors. Electrical stimulation of the surviving retinal neurons provides an alternative route for delivery of visual information. We developed subretinal photovoltaic arrays to convert pulsed light into bi-phasic pulses of current to stimulate the nearby inner retinal neurons. Bright pulsed illumination is provided by image projection from video goggles and avoids photophobic effects by using near-infrared (NIR, 880-915nm) light. Experiments in-vitro and in-vivo demonstrate that the network-mediated retinal stimulation preserves many features of natural vision, such as flicker fusion, adaptation to static images, and most importantly, high spatial resolution. Our implants with 70μm pixels restored visual acuity to half of the normal level in rats with retinal degeneration. Ease of implantation and tiling of these wireless arrays to cover a large visual field, combined with their high resolution opens the door to highly functional restoration of sight.
{"title":"Photovoltaic restoration of high visual acuity in rats with retinal degeneration","authors":"H. Lorach, Georges A. Goetz, Y. Mandel, R. Smith, David Boinagrov, X. Lei, R. Dalal, P. Huie, T. Kamins, J. Harris, K. Mathieson, A. Sher, D. Palanker","doi":"10.1109/NER.2015.7146606","DOIUrl":"https://doi.org/10.1109/NER.2015.7146606","url":null,"abstract":"Patients with retinal degeneration lose sight due to gradual demise of photoreceptors. Electrical stimulation of the surviving retinal neurons provides an alternative route for delivery of visual information. We developed subretinal photovoltaic arrays to convert pulsed light into bi-phasic pulses of current to stimulate the nearby inner retinal neurons. Bright pulsed illumination is provided by image projection from video goggles and avoids photophobic effects by using near-infrared (NIR, 880-915nm) light. Experiments in-vitro and in-vivo demonstrate that the network-mediated retinal stimulation preserves many features of natural vision, such as flicker fusion, adaptation to static images, and most importantly, high spatial resolution. Our implants with 70μm pixels restored visual acuity to half of the normal level in rats with retinal degeneration. Ease of implantation and tiling of these wireless arrays to cover a large visual field, combined with their high resolution opens the door to highly functional restoration of sight.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133679585","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 : 2015-04-22DOI: 10.1109/NER.2015.7146745
Tommaso Proietti, N. Jarrassé, A. Roby-Brami, G. Morel
Neurorehabilitation efficiency increases with therapy intensity and subject's involvement during physical exercises. Robotic exoskeletons could bring both features, if they could adapt the level of assistance to patient's motor capacities. To this aim, we developed an exoskeleton controller, based on adaptive techniques, that can actively modulate the stiffness of the robotic device in function of the subject's activity. We tested this control law on one healthy subject with an upper-limb exoskeleton. The experiment consisted in learning a trajectory imposed by the robot. The early results show the different features allowed by our controller with respect to controllers commonly used for neurorehabilitation with exoskeletons.
{"title":"Adaptive control of a robotic exoskeleton for neurorehabilitation","authors":"Tommaso Proietti, N. Jarrassé, A. Roby-Brami, G. Morel","doi":"10.1109/NER.2015.7146745","DOIUrl":"https://doi.org/10.1109/NER.2015.7146745","url":null,"abstract":"Neurorehabilitation efficiency increases with therapy intensity and subject's involvement during physical exercises. Robotic exoskeletons could bring both features, if they could adapt the level of assistance to patient's motor capacities. To this aim, we developed an exoskeleton controller, based on adaptive techniques, that can actively modulate the stiffness of the robotic device in function of the subject's activity. We tested this control law on one healthy subject with an upper-limb exoskeleton. The experiment consisted in learning a trajectory imposed by the robot. The early results show the different features allowed by our controller with respect to controllers commonly used for neurorehabilitation with exoskeletons.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132117089","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 : 2015-04-22DOI: 10.1109/NER.2015.7146791
Tiaotiao Liu, X. Tian
Working memory (WM) provides temporary information storage for performance of cognitive tasks. Neural signals in hippocampus-prefrontal cortex (HPC-PFC) circuit interact and construct a network. The question raised here is how the neural signals connect and transfer in the HPC-PFC network to perform a WM task? In this study, 32-channel local field potentials (LFPs) were recorded with two electrode arrays respectively implanted in HPC and PFC during a rat Y-maze working memory task. The principle frequency band of LFPs during the task was theta, determined via short-time Fourier transform. Functional connectivity strength was further calculated quantitatively and a causal network was defined by directed transfer function (DTF). The information transfer in the network was described by information flow. The results show that (1)the DTF curve peaked before the choice point. (2) The information flow in working memory was from HPC to PFC. These findings suggest that the functional connectivity strengthens at WM state and HPC is the WM information source in the HPC- PFC network.
{"title":"LFPs network of hippocampal-prefrontal circuit during working memory task","authors":"Tiaotiao Liu, X. Tian","doi":"10.1109/NER.2015.7146791","DOIUrl":"https://doi.org/10.1109/NER.2015.7146791","url":null,"abstract":"Working memory (WM) provides temporary information storage for performance of cognitive tasks. Neural signals in hippocampus-prefrontal cortex (HPC-PFC) circuit interact and construct a network. The question raised here is how the neural signals connect and transfer in the HPC-PFC network to perform a WM task? In this study, 32-channel local field potentials (LFPs) were recorded with two electrode arrays respectively implanted in HPC and PFC during a rat Y-maze working memory task. The principle frequency band of LFPs during the task was theta, determined via short-time Fourier transform. Functional connectivity strength was further calculated quantitatively and a causal network was defined by directed transfer function (DTF). The information transfer in the network was described by information flow. The results show that (1)the DTF curve peaked before the choice point. (2) The information flow in working memory was from HPC to PFC. These findings suggest that the functional connectivity strengthens at WM state and HPC is the WM information source in the HPC- PFC network.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134551374","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 : 2015-04-22DOI: 10.1109/NER.2015.7146601
R. So, Zhiming Xu, C. Libedinsky, Kyaw Kyar Toe, K. Ang, S. Yen, Cuntai Guan
Using a brain-machine interface (BMI), a non-human primate (NHP) was trained to control a mobile robotic platform in real time using spike activity from the motor cortex, enabling self-motion through brain-control. The decoding model was initially trained using neural signals recorded when the NHP controlled the platform using a joystick. Using this decoding model, we compared the performance of the BMI during brain control with and without the use of a dummy joystick, and found that the success ratio dropped by 40% and time taken increased by 45% when the dummy joystick was removed. Performance during full brain control was only restored after a recalibration of the decoding model. We aimed to understand the differences in the underlying neural representations of movement intentions with and without the use of a dummy joystick, and showed that there were significant changes in both directional tuning, as well as global firing rates. These results indicate that the strategies used by the NHP for self-motion were different depending on whether a dummy joystick was present. We propose that a recalibration of the decoding model is an important step during the implementation of a BMI system for self-motion.
{"title":"Neural representations of movement intentions during brain-controlled self-motion","authors":"R. So, Zhiming Xu, C. Libedinsky, Kyaw Kyar Toe, K. Ang, S. Yen, Cuntai Guan","doi":"10.1109/NER.2015.7146601","DOIUrl":"https://doi.org/10.1109/NER.2015.7146601","url":null,"abstract":"Using a brain-machine interface (BMI), a non-human primate (NHP) was trained to control a mobile robotic platform in real time using spike activity from the motor cortex, enabling self-motion through brain-control. The decoding model was initially trained using neural signals recorded when the NHP controlled the platform using a joystick. Using this decoding model, we compared the performance of the BMI during brain control with and without the use of a dummy joystick, and found that the success ratio dropped by 40% and time taken increased by 45% when the dummy joystick was removed. Performance during full brain control was only restored after a recalibration of the decoding model. We aimed to understand the differences in the underlying neural representations of movement intentions with and without the use of a dummy joystick, and showed that there were significant changes in both directional tuning, as well as global firing rates. These results indicate that the strategies used by the NHP for self-motion were different depending on whether a dummy joystick was present. We propose that a recalibration of the decoding model is an important step during the implementation of a BMI system for self-motion.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134561706","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 : 2015-04-22DOI: 10.1109/NER.2015.7146695
G. Lanzani, M. Antognazza, N. Martino, D. Ghezzi, F. Benfenati
The capability to selectively affect vital functions in cell networks and sub-cell compartments in vitro or in vivo is a mission critical tool in neuroscience and medicine. Optical excitation is one of the main strategies used to achieve high spatial and temporal resolution. In the following we describe recent results and future approaches of cell photostimulation mediated by organic semiconducting polymers.
{"title":"Controlling cell functions by light","authors":"G. Lanzani, M. Antognazza, N. Martino, D. Ghezzi, F. Benfenati","doi":"10.1109/NER.2015.7146695","DOIUrl":"https://doi.org/10.1109/NER.2015.7146695","url":null,"abstract":"The capability to selectively affect vital functions in cell networks and sub-cell compartments in vitro or in vivo is a mission critical tool in neuroscience and medicine. Optical excitation is one of the main strategies used to achieve high spatial and temporal resolution. In the following we describe recent results and future approaches of cell photostimulation mediated by organic semiconducting polymers.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115214627","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 : 2015-04-22DOI: 10.1109/NER.2015.7146551
D. Valeriani, R. Poli, C. Cinel
Detecting a target in a complex environment can be a difficult task, both for a single individual and a group, especially if the scene is very rich of structure and there are strict time constraints. In recent research, we have demonstrated that collaborative Brain-Computer Interfaces (cBCIs) can use neural signals and response times to estimate the decision confidence of participants and use this to improve group decisions in visual-matching and visual-search tasks with artificial stimuli. This paper extends that work in two ways. Firstly, we use a much harder target detection task where observers are presented with complex natural scenes where targets are very difficult to identify. Secondly, we complement the neural and behavioural information used in our previous cBCIs with physiological features representing eye movements and eye blinks of participants in the period preceding their decisions. Results obtained with 10 participants indicate that the proposed cBCI improves decision errors by up to 3.4% (depending on group size) over group decisions made by a majority vote. Furthermore, results show that providing the system with information about eye movements and blinks further significantly improves performance over our best previously reported method.
{"title":"A collaborative Brain-Computer Interface for improving group detection of visual targets in complex natural environments","authors":"D. Valeriani, R. Poli, C. Cinel","doi":"10.1109/NER.2015.7146551","DOIUrl":"https://doi.org/10.1109/NER.2015.7146551","url":null,"abstract":"Detecting a target in a complex environment can be a difficult task, both for a single individual and a group, especially if the scene is very rich of structure and there are strict time constraints. In recent research, we have demonstrated that collaborative Brain-Computer Interfaces (cBCIs) can use neural signals and response times to estimate the decision confidence of participants and use this to improve group decisions in visual-matching and visual-search tasks with artificial stimuli. This paper extends that work in two ways. Firstly, we use a much harder target detection task where observers are presented with complex natural scenes where targets are very difficult to identify. Secondly, we complement the neural and behavioural information used in our previous cBCIs with physiological features representing eye movements and eye blinks of participants in the period preceding their decisions. Results obtained with 10 participants indicate that the proposed cBCI improves decision errors by up to 3.4% (depending on group size) over group decisions made by a majority vote. Furthermore, results show that providing the system with information about eye movements and blinks further significantly improves performance over our best previously reported method.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116871754","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 : 2015-04-22DOI: 10.1109/NER.2015.7146753
Qin Zhang, C. Xiong, Chengfei Zheng
Surface Electromyography (EMG) has been considered as a viable human-machine interface in the context of human-centered robotics. In order to interpret human muscle activities into motion intentions, various pattern classification methods was proposed for human motion/gesture classification, which provided binary command for myoelectric control. To obtain complex motions coordinated by multiple DoFs, single DoF was usually sequentially classified and activated, which is not intuitive and efficient comparing with the natural motor strategy of the human. In this work, we investigated the motion classification methods from EMG for intuitive and simultaneous activation of multiple DoFs during 3-D arm motions. In the experiments, all motions were performed naturally rather than under the condition of maximum muscle contractions or other kinematic constraints. The combination of two EMG time-domain features after principal component analysis (PCA) processing is considered as the suitable choice considering both the classification accuracy and feasibility for robot control. For the motion classification method, least-square support vector machine (LS-SVM) represents higher classification accuracy for five arm motion classification across eight subjects with respect to other four methods which were popularly used in the previous works. The proposed method is hopefully applied in a EMG-driven simultaneous and proportional kinematics estimation systems for decoding model selection according to the motion intention.
表面肌电图(EMG)已被认为是在以人为中心的机器人环境下可行的人机界面。为了将人体肌肉活动解释为运动意图，提出了多种模式分类方法进行人体运动/手势分类，为肌电控制提供了二进制指令。为了获得由多个自由度协调的复杂运动，通常对单个自由度进行顺序分类和激活，与人类的自然运动策略相比，这种方法并不直观和高效。在这项工作中，我们研究了基于肌电图的运动分类方法，以直观地同时激活三维手臂运动中的多个DoFs。在实验中，所有的运动都是自然进行的，而不是在最大肌肉收缩或其他运动学约束的条件下进行的。考虑到分类精度和机器人控制的可行性，结合主成分分析(PCA)处理后的两种肌电信号时域特征是比较合适的选择。对于运动分类方法，最小二乘支持向量机(least-square support vector machine, LS-SVM)相对于以往常用的4种方法，在8个受试者的5个手臂运动分类中具有更高的分类精度。该方法有望应用于肌电驱动的同步和比例运动估计系统中，用于根据运动意图选择解码模型。
{"title":"Intuitive motion classification from EMG for the 3-D arm motions coordinated by multiple DoFs","authors":"Qin Zhang, C. Xiong, Chengfei Zheng","doi":"10.1109/NER.2015.7146753","DOIUrl":"https://doi.org/10.1109/NER.2015.7146753","url":null,"abstract":"Surface Electromyography (EMG) has been considered as a viable human-machine interface in the context of human-centered robotics. In order to interpret human muscle activities into motion intentions, various pattern classification methods was proposed for human motion/gesture classification, which provided binary command for myoelectric control. To obtain complex motions coordinated by multiple DoFs, single DoF was usually sequentially classified and activated, which is not intuitive and efficient comparing with the natural motor strategy of the human. In this work, we investigated the motion classification methods from EMG for intuitive and simultaneous activation of multiple DoFs during 3-D arm motions. In the experiments, all motions were performed naturally rather than under the condition of maximum muscle contractions or other kinematic constraints. The combination of two EMG time-domain features after principal component analysis (PCA) processing is considered as the suitable choice considering both the classification accuracy and feasibility for robot control. For the motion classification method, least-square support vector machine (LS-SVM) represents higher classification accuracy for five arm motion classification across eight subjects with respect to other four methods which were popularly used in the previous works. The proposed method is hopefully applied in a EMG-driven simultaneous and proportional kinematics estimation systems for decoding model selection according to the motion intention.","PeriodicalId":137451,"journal":{"name":"2015 7th International IEEE/EMBS Conference on Neural Engineering (NER)","volume":"10 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116962189","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：