检索结果-南通市图书馆

Learning Data Correction for Myoelectric Hand Based on“Survival of the Fittest”

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cyborg and Bionic Systems 2021年第1期2021卷 234-245页

作者： Yusuke Yamanoi Shunta Togo yinlai jiang Hiroshi Yokoi Faculty of Informatics and Engineering The University of Electro-CommunicationsTokyoJapan Center for Neuroscience and Biomedical Engineering The University of Electro-CommunicationsTokyoJapan Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of TechnologyChina

In recent years,myoelectric hands have become multi-degree-of-freedom(DOF)devices,which are controlled via machine learning ***,currently,learning data for myoelectric hands are gathered manually and thus tend to be of low ***,in the case of infants,gathering accurate learning data is nearly impossible because of the difficulty of communicating with ***,a method that automatically corrects errors in the learning data is *** hands are wearable robots and thus have volumetric and weight constraints that make it infeasible to store large amounts of data or apply complex processing *** with general machine learning methods such as image processing,those for myoelectric hands have limitations on the data storage,although the amount of data to be processed is quite *** we can use this huge amount of processing data to correct the learning data without storing the processing data,the machine learning performance is expected to *** then propose a method for correcting the learning data through utilisation of the signals acquired during the use of the myoelectric *** proposed method is inspired by“survival of the fittest.”The effectiveness of the method was verified through offline *** method reduced the amount of learning data and learning time by approximately a factor of 10 while maintaining classification *** classification rates improved for one participant but slightly deteriorated on average among all *** solve this problem,verifying the method via interactive learning will be necessary in the future.

关键词： gathering apply hands

Coevolution of Myoelectric Hand Control under the Tactile Interaction among Fingers and Objects

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cyborg and Bionic Systems 2022年第1期2022卷 285-302页

作者： Yuki Kuroda Yusuke Yamanoi Shunta Togo yinlai jiang Hiroshi Yokoi Joint Doctoral Program for Sustainability Research Graduate School of Informatics and Engineering The University of Electro-CommunicationsTokyoJapan Department of Mechan ical and Intelligent System Engineering Graduate School of Informatics and Engineering The University of Electro Communications TokyoJapan Center for Neuroscience and Biomedical Engineering The University of Electro Communications TokyoJapan Bejing Innovation Center for Inelligent Robots and Systems BeijingChina

The usability of a prosthetic hand difers significantly from that of a real ***,the complexity of manipulation increases as the number of degrees of freedom to be controlled increases,making manipulation with biological signals extremely *** overcome this problem,users need to select a grasping posture that is adaptive to the object and a stable grasping method that prevents the object from *** previous studies,these have been left to the operating skills of the user,which is extremely difficult to *** this study,we demonstrate how stable and adaptive grasping can be achieved according to the object regardless of the user's operation *** required grasping technique is achieved by determining the correlation bet ween the motor output and each sensor through the interaction between the prosthetic hand and the surrounding stimuli,such as myoelectricity,sense of touch,and grasping *** agents of the 16 DOF robot hand were trained with the myoelectric signals of six participants,including one child with a congenital forearm ***,each agent could open and close the hand in response to the myoeletric stimuli and could accomplish the object pickup *** the tasks,the agents successfully identified grasping patterns suitable for practical and stable positioning of the *** addition,the agents were able to pick up the object in a similar posture regardless of the partiipant,suggesting that the hand was optimized by evolutionary computation to a posture that prevents the object from being dropped.

关键词： robot Objects overcome

An Online sEMG Motion Classification Framework for Tele-operating the Robotic Hand

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An Online sEMG Motion Classification Framework for Tele-oper...

基于节点迭代模糊Petri网的非接触异常步态识别方法

第三十九届中国控制会议

作者： Haosi Zheng Hiroshi Yokoi yinlai jiang Feng Duan College of Artificial Intelligence Nankai University The Brain Science Inspired Life Support Research Center The University of Electro-Communication

Seamless communication between human intended motions and robot actions is essential for Human-Robot Interaction（HRI）. When tele-operating a robotic hand, it is a natural and effective way via surface electromyography（sEMG）signals. This paper proposes an online sEMG motion classification framework for tele-operating the robotic hand. The whole framework consists of offline training and online recognition phases. In the offline training phase, three features were selected from four candidates and Artificial Neural Network（ANN） won the election among three classifiers. In the online recognition phase, two-thresholds data segmentation and majority voting techniques were designed, and three subjects participated in online experiment to verify the feasibility of this framework. The online experimental results show that the average total accuracy is73.56% and the average vote accuracy is 91.67%. The outcomes of this study have shown the promising potential of sEMG-based HRI.

关键词： Human-Robot Interaction(HRI) surface electromyography signal(sEMG) online classification

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

仪器仪表学报 2019年第4期40卷 255-264页

作者：赵东辉杨俊友白殿春姜银来沈阳工业大学电气工程学院沈阳110870 日本电气通信大学机械工程与智能系统学院东京182-8585

为了准确识别下肢功能障碍患者辅助行走中的跌倒、拖拽式异常步态,从多种用户群体的普适性与便捷性出发,提出了一种基于节点迭代型模糊Petri网的非接触式异常步态识别方法。首先,论述了康复训练机器人结构及辅助行走过程中跌倒与拖拽式... 详细信息

为了准确识别下肢功能障碍患者辅助行走中的跌倒、拖拽式异常步态,从多种用户群体的普适性与便捷性出发,提出了一种基于节点迭代型模糊Petri网的非接触式异常步态识别方法。首先,论述了康复训练机器人结构及辅助行走过程中跌倒与拖拽式异常步态的行为特征;然后研发了一种多通道近距离传感器阵列实时检测步态信息,并融合了步行方向意图向量提出采用步态偏离度、频率和躯干倾斜角度作为检测系统输入参数;基于模糊隶属度函数生成网络点燃机制,并建立节点迭代型模糊Petri网系统识别异常步态;最后进行了异常步态算子推理与多模态行走跌倒检测实验,表明该算法对使用步行康复机器人过程中异常步态识别率达到91. 2%并提高了辅助行走的安全性与舒适性。所提方法可以应用于下肢行动不便人群使用类似助行器的日常起居与康复训练场景。

关键词：异常步态识别多通道近距离传感器阵列模糊Petri网节点迭代

在线全文

学校读者我要写书评

暂无评论

基于简约模糊系统的多福祉机器人移乘方法

机器人 2019年第6期41卷 813-822页

作者：赵东辉杨俊友白殿春姜银来沈阳工业大学电气工程学院辽宁沈阳110870 日本电气通信大学信息与工程学院日本东京1820021

针对行动不便者在日常生活中起床、站立、排泄等移乘行为的辅助,基于自主研发的5台福祉机器人与传感器网络搭建了智能助老助残房间.该系统为移乘行为提供服务平台,并提出了兼具安全性与舒适性的移乘推理算法和移乘规划方法.首先论述了... 详细信息

针对行动不便者在日常生活中起床、站立、排泄等移乘行为的辅助,基于自主研发的5台福祉机器人与传感器网络搭建了智能助老助残房间.该系统为移乘行为提供服务平台,并提出了兼具安全性与舒适性的移乘推理算法和移乘规划方法.首先论述了多福祉机器人的功能与日常自主行为的局限性.针对多种不同行动能力的用户群体,提出了一种基于简约粗糙集的移乘方式推理算法.在使用者对自己行动能力不确定、病情信息不完备的情况下,制订对应的移乘方案.然后,以使用者行为的安全性与舒适性为出发点,提出了起床移乘规划与站立移乘规划.最后进行了移乘方法推理及移乘实验.实验表明,该移乘推理算法可以为不同行动能力的使用者制订合适的移乘方法.站立移乘状态下,可以分别减小患侧与健侧足底压强39.9%和19.5%,起床移乘状态下可以分别减小背部与臀部的压强5.05%和3.95%.该基于多福祉机器人的移乘推理系统可以应用于家庭、养老院与康复中心等场合.

关键词：福祉机器人移乘粗糙集距离型模糊推理

7自由度仿人机械臂工作空间求解的降密蒙特卡洛法

在线全文

学校读者我要写书评

暂无评论

西南交通大学学报 2023年第6期58卷 1328-1338页

作者：窦汝桐于慎波孙凤夏鹏澎横井浩史姜银来沈阳工业大学机械工程学院辽宁沈阳110870 电气通信大学机械与智能系统工程学院东京182-8585

针对蒙特卡洛法和改进蒙特卡洛法在求解机械臂工作空间时存在精度不够准确和加密点云浪费的问题,提出一种降密蒙特卡洛法.首先,基于蒙特卡洛法中随机点分布不均的特性,对机械臂初始工作空间进行均匀加密,使空间的内部与边界区域分明;然... 详细信息

针对蒙特卡洛法和改进蒙特卡洛法在求解机械臂工作空间时存在精度不够准确和加密点云浪费的问题,提出一种降密蒙特卡洛法.首先,基于蒙特卡洛法中随机点分布不均的特性,对机械臂初始工作空间进行均匀加密,使空间的内部与边界区域分明;然后,采用扩展关节角度和循环加密随机点的方式,只对边界区域进行加密,达到降低工作空间随机点云密度的目的;同时,还研究了该方法中初始点云数量、各轴向分割体素数量、精度阈值、扩展关节角度和循环次数等参数对工作空间精度的影响;最后,通过仿真分析对降密蒙特卡洛法的有效性进行验证.结果表明:相比于蒙特卡洛法,降密蒙特卡洛法在工作空间平均误差率为0.022 42%时,总随机点云数量降幅为93.89%;相比于改进蒙特卡洛法,在循环次数为2次和4次时,降密蒙特卡洛法工作空间的平均误差率分别降低0.138 53%和0.113 29%,总随机点云数量降幅分别为44.83%和64.52%.

关键词： 7自由度仿人机械臂工作空间蒙特卡洛法体素网格法降密蒙特卡洛法

多电机耦合驱动式仿人机械臂设计与传动特性分析

在线全文

学校读者我要写书评

暂无评论

机床与液压 2023年第21期51卷 23-30页

作者：窦汝桐于慎波翟凤晨夏鹏澎李文扬横井浩史姜银来沈阳工业大学机械工程学院辽宁沈阳110870 电气通信大学机械与智能系统工程学院东京182-8585

针对传统仿人机械臂载荷与自重比低的问题,提出一种多电机耦合驱动式仿人机械臂。根据人臂的运动特性,确定串联结构下的仿人机械臂构型,并将机械臂划分为肩关节模块、肘关节模块和腕关节模块。分析单电机驱动单关节的绳索传动特性,推导... 详细信息

针对传统仿人机械臂载荷与自重比低的问题,提出一种多电机耦合驱动式仿人机械臂。根据人臂的运动特性,确定串联结构下的仿人机械臂构型,并将机械臂划分为肩关节模块、肘关节模块和腕关节模块。分析单电机驱动单关节的绳索传动特性,推导该模型下电机与关节的扭矩映射关系和转角映射关系。研究各模块中多电机耦合驱动多关节的电机布局和绳索绕线方式,解释各模块中多电机耦合后的工作原理,推导各模块中电机与关节的扭矩映射关系和转角映射关系。并通过实验验证各模块中映射关系的正确性,以及各模块关节的承载能力。结果表明:多电机耦合驱动方式在保证质量的前提下,可以有效提高各关节的承载力,为仿人机械臂的设计提供理论依据。

关键词：仿人机械臂绳索驱动多电机耦合驱动模块化设计

yinlai decoction alleviates lipopolysaccharide-induced pneumonia by changing the immune status of juvenile rats:A study based on network pharmacology

在线全文

学校读者我要写书评

暂无评论

Journal of Traditional Chinese Medical Sciences 2019年第1期6卷 44-58页

作者： Chen Bai Jingnan Xu Kaiyue Ma Ling Huang Shaoyang Liu Xin jiang He Yu Tiegang Liu Xiaohong Gu School of Traditional Chinese Medicine Beijing University of Chinese Medicine Beijing 100029 China

Objective:Pediatric pneumonia is a common respiratory disease and yinlai Decoction (YLD) is a commonly used treatment in *** explored the anti-inflammatory mechanism of action of this traditional Chinese medicine for ***:We studied,by experimentation,the mechanism of action of YLD in treating pneumonia according to network *** comparing YLD with dexamethasone (DXMS),we investigated the efficacy of YLD in treating pneumonia induced by lipopolysaccharide (LPS) in juvenile ***:In an aqueous extract of YLD,22 chemical compounds were identified,among which 10 were related to inflammation,involving 78 target genes and 16 signaling *** them,45 core target proteins were related to biologic processes and functions,such as response to stimuli,biologic regulation,cell communication and protein *** experiments showed that YLD relieved pulmonary inflammation and demonstrated no significant damage to the liver,spleen or kidneys of *** could regulate expression of inflammatory cytokines in serum and inflammation-related proteins in lung tissues to some extent,but its effect is less significant than that of ***:YLD protected juvenile rats against LPS-induced pneumonia,and showed fewer side effects in comparison with *** could be efficacious treatment for pediatric respiratory infections and even pneumonia.

关键词： Pediatric pneumonia yinlai decoction Traditional Chinese medicine Network pharmacology Immunity

针刺大椎、百会、人中穴对脑缺血再灌注损伤大鼠脑组织p-VEGF蛋白表达的影响

在线全文

学校读者我要写书评

暂无评论

湖南中医药大学学报 2018年第11期38卷 1262-1266页

作者：蒋素容武姿含高音来陈芯仪何灏龙陈楚淘田浩梅湖南中医药大学湖南长沙410208

目的观察针刺大椎、百会、人中穴对脑缺血再灌注损伤大鼠脑组织p-VEGF蛋白表达的影响,探讨针刺对脑缺血再灌注损伤的部分作用机制。方法从60只大鼠中随机选择24只,再将之随机分成正常组和假手术组,12只/组,其余36只大鼠参照Zea Longa线... 详细信息

目的观察针刺大椎、百会、人中穴对脑缺血再灌注损伤大鼠脑组织p-VEGF蛋白表达的影响,探讨针刺对脑缺血再灌注损伤的部分作用机制。方法从60只大鼠中随机选择24只,再将之随机分成正常组和假手术组,12只/组,其余36只大鼠参照Zea Longa线栓法制备大脑中动脉栓塞模型,造模成功后再随机分为模型组、针刺组、依达拉奉组,12只/组。造模大鼠生命体征平稳后,正常组、假手术组及模型组大鼠只捆绑不针刺;针刺组大鼠针刺大椎、百会、人中三穴,留针30 min;依达拉奉组大鼠按3 mg/kg(稀释至1mL)腹腔注射依达拉奉,均为每12小时1次;首次治疗前及末次治疗后,对大鼠进行神经功能缺损评分;6次治疗完成后处死大鼠,行TTC染色观察脑梗死面积比,采用Western blot法检测p-VEGF蛋白表达水平。结果与正常组及假手术组比较,模型组大鼠神经功能缺损评分及脑梗死面积比显著上升(P0.05)。结论针刺大椎、百会、人中穴能明显减轻脑缺血再灌注损伤,且其机制可能与上调VEGF蛋白磷酸化表达,进而促进血管新生有关。

关键词：针刺脑缺血再灌注损伤血管内皮生长因子大椎百会人中