表面肌电信号检测和处理中若干关键技术研究
|
摘要
表面肌电(sEMG)信号是一种伴随肌肉活动的电生理信号。基于表面肌电的人体动作识别、表而肌电信号的分解是当前这个领域研究的两大热点。其中,前者旨在提供一种更自然、便捷、有效的人机交互方式,在假肢控制、移动设备操控、手语识别、运动电子产品、游戏娱乐产品、作战指挥等领域具有重要的应用价值；后者旨在从表而肌电信号中提取神经肌肉运动单位募集、发放信息和MUAP波形信息,研究神经肌肉系统的控制机理,并为神经肌肉疾病的诊断提供依据。
与插入式肌电信号(iEMG)相比,sEMG信号具有检测无创性的优点,因此应用范围更广。但由于是从皮肤表面检测信号且电极面积较大,同时受到肌肉、脂肪和皮肤组织的低通滤波效应影响,其信噪比较低,波形变异性较大,对其检测和处理的难度也相应增大。目前在基于sEMG信号的动作识别与人机交互研究以及在sEMG信号分解研究中,仍存在一些技术问题需要解决,例如：具有特定应用场合的sEMG电极：电极的噪声、阻抗和环境适应能力；抑制工频干扰的方法；适合人机交互的低噪声、低功耗、可穿戴sEMG信号采集系统；实时、高效率、可结构化的动作识别方法：连续手势动作的识别方法：有效获取sEMG时空信息的高密度、高性能、低噪声电极阵列的研制。本文即是围绕上述问题展开研究,主要工作和创新点归纳如下：
1.高质量表面肌电检测电极的研制和性能分析。紧密围绕sEMG信号检测的应用场合,研制了具有便捷性和耐用性的各类干电极。其中线形电极结构简单、便捷耐用,印制电极外形灵活、佩戴舒适,弹簧探针电极接触良好、时空分辨力高。通过实验对各种自制电极的噪声进行了测定分析：研制矢量导纳测试装置,并利用该装置研究了各种电极阻抗的时变规律、频率响应以及压强、皮肤处理方式对阻抗的影响；改进放大电路的结构,有效的滤除了运动伪迹。这北方法和结果对sEMG信号检测工作具有普遍意义。
2.微弱表而肌电信号检测中的工频干扰及消除方法。提出了基于锁相环同步时钟的时域分组滤波法以抑制工频干扰,与传统的工频消除算法不同,这是一种软硬件相结合的方法,具有快速、有效、可结构化的特点。设计和研制了一种新颖的、具有双变压器结构的工频隔离电源,通过互补抵消的作用,巧妙地实现了使输入、输出达到低噪声、低共模干扰的目标。另外,采用金属板屏蔽、全电池供电隔离采集等方法,有效的实现了工频抑制。
3.多种不同应用的表面肌电信号采集系统研制。针对不同应用场合,设计和研制了多种高信噪比、高共模抑制能力的sEMG信号采集系统,包括配置有源电极的sEMG采集系统、调频无线sEMG采集系统、2.4GHz无线数字传输sEMG与加速度采集系统和基于蓝牙的无线sEMG与加速度采集系统。采用多项技术和措施提高传感器和系统的性能,以减小其体积、重量和功耗,增强其便携性和可穿戴性,从而可为穿戴式计算机和移动手持设备提供若干种全新的交互方式。
4.基于表面肌电信号的实时手势识别及FPGA实现。适应基于sEMG的人机交互设备微型化、芯片化的要求,采用一系列可靠、快速、结构化的方法进行实时手势识别,并将其应用于FPGA平台。其中,提出了三级缓存控制方法、基于循环队列的快速活动段检测方法：提取各通道绝对值均值与AR模型系数作为特征；采用加权欧式空间距离和LDC贝叶斯分类器进行分类。另外构建了实时手势识别平台并对手势识别的速度、准确率、多用户适应能力进行了实验分析。
5.基于表面肌电信号的连续手势识别。提出一种基于短时能量特征的连续手势识别方法。这种方法根据测得信号的能量大小及其与标准动作模板的匹配程度进行识别,具有每一次采样随即识别一次的高速度,可以不依赖于活动段,获得连续的手势识别结果。
6.获取表面肌电时空信息的高密度电极研究。运用双差分电极进行手势sEMG信号研究,实验证实该电极具有较高的位置分辨能力和位置敏感程度。设计和研制了带有前级放大器的集成sEMG电极阵列传感器,这种集成方式可以很大程度的减少外界干扰,降低噪声。运用该传感器进行了肌纤维传导速度测定；采用自相关主峰宽度近似表达MUAP时限,用此方法评估了印制电极与弹簧探针电极的MUAP时限特性；以空间滤波方式提高了电极对MUAP的分辨能力。
本论文研究得到国家863项目“基于肌电传感器和加速计的手势交互设备研究”(2009AAO1Z322)和国家自然科学基金项目“基于线性变化力采集和多通道时空信息的表面肌电信号分解”(30870656)的资助。
Surface electromyographic signal (sEMG) is the electrophysiological signal concomitant with musculations. There're two research focuses about sEMG:Human action recognition based on sEMG and sEMG decomposition. The former aims for providing a more natural, more convenient and more effective way of computer human interaction (CHI), which could be widely applied in artificial limb controlling, mobile device handling, gesture language recognition, sport electronics, games/ entertainments, tactical commanding, etc. The latter aims for extracting information about motor unit recruitment/firing and MUAP waveforms, so as to studying the control mechanism of neuromuscular system, and providing evidences for diagnosing neuromuscular diseases.
Compared with intramuscular EMG (iEMG) signal, the sEMG signal detection can be widely applied for the advantage of non-invasive. However, for detected from skin surface with bigger sized electrodes, and influenced by low-pass-filter effect of muscle, hypoderm and skin, the sEMG signal has a lower signal noise ratio, a higher waveform dissimilation, and a higher difficulty in detections and processes. As a result, in the fields of sEMG decomposition, and human action recognition/CHI based on sEMG, there're still several issues of technologies to solve, for example: Designs of sEMG electrodes in special applications; The noises, impedances and adaptabilities of electrodes; Ways of reducing power frequency interferences; Designs of low noise, low power and wearable sEMG signal acquisition systems for CHI; High efficiency, real time and structurized method for action recognition; Recognizing method for continuous gesture actions; High density, high performance and low noise electrodes array for acquiring temporal and spacial information from sEMG; etc. Focus on these issues, the main work and achievement of the dissertation could be presented as follows:
1. Designs and analysis of high performance electrodes for sEMG detection. Revolving closely around the applications of sEMG signal, many kinds of convenient and durable dry electrodes were developed, including line-shaped electrodes which are simple, convenient and durable; printed electrodes which have devisable shapes and can be comfortably wore; spring probe electrodes which have good temporal/ spacial resolutions and can be well contacted. The noises of these electrodes were tested and analyzed by experiments; The impedance characteristics of these electrodes including time-varying behavior, frequency response, effect of pressure and skin pretreatment, were studied using home-developed vector admittance instrument; Motion artifacts of the electrodes were filtered out by improving the instrumentation amplifier circuits. All these methods and results could provide universal meanings for works of sEMG signal detection.
2. The power frequency interference reduction (PFIR) in the weak signal detection of sEMG. Compared with traditional PFIR algorithms, the time-domain grouped filtering based on PLL synchronized clock which presented as a novel software-hardware combined PFIR method, has the advantage of fast, efficient and structurized. A novel isolated power supply with the structure of double transformers was developed for lower input/output noises and lower common mode interferences, capitalizing on the effects of complemental counteraction. In addition, metal plate shielding and battery supplied acquisition also achieved satisfying PFIR effects.
3. Designs of sEMG signal acquisition systems (SAS) for multiple applications. Several kinds of sEMG signal acquisition systems with high signal noise ratios and high common mode rejection ratios were developed, including sEMG SAS with active electrodes, FM wireless sEMG SAS,2.4GHz wireless digital sEMG/ Acceleration SAS and Bluetooth sEMG/Acceleration SAS. With improved performances, miniaturized sizes, lightened weights, reduced power dissipations, enhanced portabilities and wearabilities by multiple ways and techniques, the sensors and systems are able to provide several novel ways of interaction for wearable computers and mobile hand-held devices.
4. Real-time gesture recognition based on sEMG and its realization on FPGA. For the demands of miniaturized and integrated interaction devices, some reliable, fast and structurized algorithms were used for real-time gesture recognition, and realized on an FPGA platform.3 stage cache controlling method, fast action detection method based on looped queue, feature extraction method based on mean absolute value and AR coefficients, classifiers based on weighted Euclidean distance or Bayes method (LDC) were used in the real-time gesture recognition. A platform for real-time gesture recognition was also built, by which the recognition speeds, success rates and user adaptabilities of the methods were tested and analyzed.
5. Continuous gesture recognition based on sEMG. Based on the feature of short time energy, a method of gesture recognition that judges by signal energy's magnitude and similarity to patterns was presented for continuous gesture recognition. In this way, recognition is immediately proceeded within each data sample duration, and the continuous recognition is independent of "action segment"
6. Research on high density electrodes for acquiring temporal and spacial information of sEMG. Double differential electrodes (DDE) were introduced in studies about sEMG of hand gestures. It was proved in the experiments that the positional resolution was improved by the DDE, at the same time, the DDE was more sensitive to positional deviations. A kind of integrated sEMG electrodes array sensor with a first stage amplifier was developed, which managed to reduce interferences and noises by the integrated way. Several studies was carried out with the sensor:The measurement of muscle fiber conduction velocity (MFCV); The MUAP durations of printed electrodes and spring probe electrodes, approximate evaluated by the main peak width of signal's autocorrelation; The improvement of MUAP resolution by spacial filtering.
The research is supported by the National "863" Project "Research on EMG sensors and accelerometers based hand gesture interaction devices" (2009AA01Z322) and the National Natural Science Foundation of China "Surface EMG decomposition based on linear varied force and temporal/spacial information from multiple channels" (30870656).
与插入式肌电信号(iEMG)相比,sEMG信号具有检测无创性的优点,因此应用范围更广。但由于是从皮肤表面检测信号且电极面积较大,同时受到肌肉、脂肪和皮肤组织的低通滤波效应影响,其信噪比较低,波形变异性较大,对其检测和处理的难度也相应增大。目前在基于sEMG信号的动作识别与人机交互研究以及在sEMG信号分解研究中,仍存在一些技术问题需要解决,例如：具有特定应用场合的sEMG电极：电极的噪声、阻抗和环境适应能力；抑制工频干扰的方法；适合人机交互的低噪声、低功耗、可穿戴sEMG信号采集系统；实时、高效率、可结构化的动作识别方法：连续手势动作的识别方法：有效获取sEMG时空信息的高密度、高性能、低噪声电极阵列的研制。本文即是围绕上述问题展开研究,主要工作和创新点归纳如下：
1.高质量表面肌电检测电极的研制和性能分析。紧密围绕sEMG信号检测的应用场合,研制了具有便捷性和耐用性的各类干电极。其中线形电极结构简单、便捷耐用,印制电极外形灵活、佩戴舒适,弹簧探针电极接触良好、时空分辨力高。通过实验对各种自制电极的噪声进行了测定分析：研制矢量导纳测试装置,并利用该装置研究了各种电极阻抗的时变规律、频率响应以及压强、皮肤处理方式对阻抗的影响；改进放大电路的结构,有效的滤除了运动伪迹。这北方法和结果对sEMG信号检测工作具有普遍意义。
2.微弱表而肌电信号检测中的工频干扰及消除方法。提出了基于锁相环同步时钟的时域分组滤波法以抑制工频干扰,与传统的工频消除算法不同,这是一种软硬件相结合的方法,具有快速、有效、可结构化的特点。设计和研制了一种新颖的、具有双变压器结构的工频隔离电源,通过互补抵消的作用,巧妙地实现了使输入、输出达到低噪声、低共模干扰的目标。另外,采用金属板屏蔽、全电池供电隔离采集等方法,有效的实现了工频抑制。
3.多种不同应用的表面肌电信号采集系统研制。针对不同应用场合,设计和研制了多种高信噪比、高共模抑制能力的sEMG信号采集系统,包括配置有源电极的sEMG采集系统、调频无线sEMG采集系统、2.4GHz无线数字传输sEMG与加速度采集系统和基于蓝牙的无线sEMG与加速度采集系统。采用多项技术和措施提高传感器和系统的性能,以减小其体积、重量和功耗,增强其便携性和可穿戴性,从而可为穿戴式计算机和移动手持设备提供若干种全新的交互方式。
4.基于表面肌电信号的实时手势识别及FPGA实现。适应基于sEMG的人机交互设备微型化、芯片化的要求,采用一系列可靠、快速、结构化的方法进行实时手势识别,并将其应用于FPGA平台。其中,提出了三级缓存控制方法、基于循环队列的快速活动段检测方法：提取各通道绝对值均值与AR模型系数作为特征；采用加权欧式空间距离和LDC贝叶斯分类器进行分类。另外构建了实时手势识别平台并对手势识别的速度、准确率、多用户适应能力进行了实验分析。
5.基于表面肌电信号的连续手势识别。提出一种基于短时能量特征的连续手势识别方法。这种方法根据测得信号的能量大小及其与标准动作模板的匹配程度进行识别,具有每一次采样随即识别一次的高速度,可以不依赖于活动段,获得连续的手势识别结果。
6.获取表面肌电时空信息的高密度电极研究。运用双差分电极进行手势sEMG信号研究,实验证实该电极具有较高的位置分辨能力和位置敏感程度。设计和研制了带有前级放大器的集成sEMG电极阵列传感器,这种集成方式可以很大程度的减少外界干扰,降低噪声。运用该传感器进行了肌纤维传导速度测定；采用自相关主峰宽度近似表达MUAP时限,用此方法评估了印制电极与弹簧探针电极的MUAP时限特性；以空间滤波方式提高了电极对MUAP的分辨能力。
本论文研究得到国家863项目“基于肌电传感器和加速计的手势交互设备研究”(2009AAO1Z322)和国家自然科学基金项目“基于线性变化力采集和多通道时空信息的表面肌电信号分解”(30870656)的资助。
Surface electromyographic signal (sEMG) is the electrophysiological signal concomitant with musculations. There're two research focuses about sEMG:Human action recognition based on sEMG and sEMG decomposition. The former aims for providing a more natural, more convenient and more effective way of computer human interaction (CHI), which could be widely applied in artificial limb controlling, mobile device handling, gesture language recognition, sport electronics, games/ entertainments, tactical commanding, etc. The latter aims for extracting information about motor unit recruitment/firing and MUAP waveforms, so as to studying the control mechanism of neuromuscular system, and providing evidences for diagnosing neuromuscular diseases.
Compared with intramuscular EMG (iEMG) signal, the sEMG signal detection can be widely applied for the advantage of non-invasive. However, for detected from skin surface with bigger sized electrodes, and influenced by low-pass-filter effect of muscle, hypoderm and skin, the sEMG signal has a lower signal noise ratio, a higher waveform dissimilation, and a higher difficulty in detections and processes. As a result, in the fields of sEMG decomposition, and human action recognition/CHI based on sEMG, there're still several issues of technologies to solve, for example: Designs of sEMG electrodes in special applications; The noises, impedances and adaptabilities of electrodes; Ways of reducing power frequency interferences; Designs of low noise, low power and wearable sEMG signal acquisition systems for CHI; High efficiency, real time and structurized method for action recognition; Recognizing method for continuous gesture actions; High density, high performance and low noise electrodes array for acquiring temporal and spacial information from sEMG; etc. Focus on these issues, the main work and achievement of the dissertation could be presented as follows:
1. Designs and analysis of high performance electrodes for sEMG detection. Revolving closely around the applications of sEMG signal, many kinds of convenient and durable dry electrodes were developed, including line-shaped electrodes which are simple, convenient and durable; printed electrodes which have devisable shapes and can be comfortably wore; spring probe electrodes which have good temporal/ spacial resolutions and can be well contacted. The noises of these electrodes were tested and analyzed by experiments; The impedance characteristics of these electrodes including time-varying behavior, frequency response, effect of pressure and skin pretreatment, were studied using home-developed vector admittance instrument; Motion artifacts of the electrodes were filtered out by improving the instrumentation amplifier circuits. All these methods and results could provide universal meanings for works of sEMG signal detection.
2. The power frequency interference reduction (PFIR) in the weak signal detection of sEMG. Compared with traditional PFIR algorithms, the time-domain grouped filtering based on PLL synchronized clock which presented as a novel software-hardware combined PFIR method, has the advantage of fast, efficient and structurized. A novel isolated power supply with the structure of double transformers was developed for lower input/output noises and lower common mode interferences, capitalizing on the effects of complemental counteraction. In addition, metal plate shielding and battery supplied acquisition also achieved satisfying PFIR effects.
3. Designs of sEMG signal acquisition systems (SAS) for multiple applications. Several kinds of sEMG signal acquisition systems with high signal noise ratios and high common mode rejection ratios were developed, including sEMG SAS with active electrodes, FM wireless sEMG SAS,2.4GHz wireless digital sEMG/ Acceleration SAS and Bluetooth sEMG/Acceleration SAS. With improved performances, miniaturized sizes, lightened weights, reduced power dissipations, enhanced portabilities and wearabilities by multiple ways and techniques, the sensors and systems are able to provide several novel ways of interaction for wearable computers and mobile hand-held devices.
4. Real-time gesture recognition based on sEMG and its realization on FPGA. For the demands of miniaturized and integrated interaction devices, some reliable, fast and structurized algorithms were used for real-time gesture recognition, and realized on an FPGA platform.3 stage cache controlling method, fast action detection method based on looped queue, feature extraction method based on mean absolute value and AR coefficients, classifiers based on weighted Euclidean distance or Bayes method (LDC) were used in the real-time gesture recognition. A platform for real-time gesture recognition was also built, by which the recognition speeds, success rates and user adaptabilities of the methods were tested and analyzed.
5. Continuous gesture recognition based on sEMG. Based on the feature of short time energy, a method of gesture recognition that judges by signal energy's magnitude and similarity to patterns was presented for continuous gesture recognition. In this way, recognition is immediately proceeded within each data sample duration, and the continuous recognition is independent of "action segment"
6. Research on high density electrodes for acquiring temporal and spacial information of sEMG. Double differential electrodes (DDE) were introduced in studies about sEMG of hand gestures. It was proved in the experiments that the positional resolution was improved by the DDE, at the same time, the DDE was more sensitive to positional deviations. A kind of integrated sEMG electrodes array sensor with a first stage amplifier was developed, which managed to reduce interferences and noises by the integrated way. Several studies was carried out with the sensor:The measurement of muscle fiber conduction velocity (MFCV); The MUAP durations of printed electrodes and spring probe electrodes, approximate evaluated by the main peak width of signal's autocorrelation; The improvement of MUAP resolution by spacial filtering.
The research is supported by the National "863" Project "Research on EMG sensors and accelerometers based hand gesture interaction devices" (2009AA01Z322) and the National Natural Science Foundation of China "Surface EMG decomposition based on linear varied force and temporal/spacial information from multiple channels" (30870656).
引文
曹楚南,张鉴清.2002.电化学阻抗谱导论[M].北京：科学出版社,26-32.
褚雪忠,杨基海,李强,陈香.2006.电极配置对MUAP检测影响的仿真研究[J].生物医学工程研究,25(3)：137-140.
崔丽英.2006.简明肌电图学手册[M].北京：科学出版社,26-27.
丁祥峰,孙怡宁,孙启枉.2006.表面肌电检测中消除工频干扰的方法[J].北京生物医学工程,25(1)：63-66.
段晏文,李献红,肖文杰等.2007.新型的银／氯化银粉末医用电极[C].中国生物医学工程联合学术年会,西安,89-92.
菲利普·J·拉希,洛奇·K·柏克.1985.运动学和应用解剖学[M].胡勣,廖咸锐,译.北京：人民体育出版社,238-246.
高晋占.2004.微弱信号检测[M].北京：清华大学出版社,141-149,51-53.
何庆华,彭承琳,吴宝明,王禾.2003.有源电极用于表面肌电信号的检测[J].生物医学工程学杂志,20(3)：488-490.
胡大雷,刘珩.2005.高噪声环境下的语音活动检测技术[J].中国农业大学学报,10(3)：65-68.
姜海远,霍纪文,尹立志.1997.医用传感器[M].北京：科学出版社,285-287,296-300.
雷敏,王志中.2001.肌电假肢控制中的表面肌电信号的研究进展与展望[J].中国医疗器械杂志,25(3)：156-160.
李强.2008.表面肌电信号的运动单位动作电位检测[D]:[博士].合肥：中国科学技术大学.
梁政.2004.表面肌电信号分解方法研究[D]：[博士].合肥：中国科学技术大学.
梁政,杨基海,叶硃,等.2004.基于高阶谱的肌纤维传导速度谱坑法检测[J].北京生物医学工程,23(2)：126-131.
路凯,李小坚,周金祥.2006.基于肤色和边缘轮廓检测的手势识别[J].北方工业大学学报,18(3)：12-15.
罗志增,任晓亮.2005.表面肌电信号测试中工频干扰的抑制[J].仪器仪表学报,26(2)：193-195.
吕江波,虞露.2002.S/PDIF数字音频接口和接收机中的数据译码实现[J].电声技术,207(9)：15-20.
孙丽娟,张立材,郭彩龙.2008.基于视觉的手势识别技术[J].计算机技术与发展,18(10)：214-216,221.
汤晓芙.2002.神经病学——神经系统临床电生理学(下)(肌电图学及其他)[M].北京：人民军 医出版社,1-87,317-383.
王人成,郑双喜,蔡付文,等.2008.基于表面肌电信号的手指运模式识别系统[J].中国康复医学杂志,23(5)：410-412.
吴江琴,高文.2000.基于DGMM的中国手语识别系统[J].计算机研究与发展,37(5)：551-558.
吴江琴,高文,陈熙霖.1999.基于数据手套输入的汉语手指字母的识别[J].模式识别与人工智能,12(1)：74-78.
杨福生,高上凯.1989.生物医学信号处理[M].北京：高等教育出版社,109-139,607-643.
杨玉星,2005.生物医学传感器与检测技术[M].北京：化学工业出版社,318-321,344-346.
杨玉星,束美霞,罗洁,周黎明.2006.基于小型电极的新型阻抗血流图测量系统的研究[J].航天医学与医学工程,19(3)：208-211.
余洪俊,刘宏亮,陈蕾.2002.表面肌电图的发展与应用[J].中国临床康复,6(5)：720-721.
周士枋,丁伯坦.2004.运动学[M].北京：华夏出版社,172-179,17-18.
Analog Device.2007. AD8220, JFET Input Instrumentation Amplifier with Rail-to-Rail Output in MSOP Package[EB/OL]. Norwood, USA:ADI, [2007-05]. http://www.analog.com/en/ ampl ifiers-and-comparators/i nstrumentation-amplifiers/ad8220/products/product. html.
Antonio Piccoli, Giordano Pastori, Marta Guizzo, et al.2005. Equivalence of information from single versus multiple frequency bioimpedance vector analysis in hemodialysis[J]. Kidney International,67:301-313.
Baratta RV, Solomonow M, Zhou BH, et al.1998. Methods to reduce the variability of EMG power spectrum estimates[J]. Journal of Electromyography and Kinesiology,8(5):279-285.
Blok JH, van Dijk JP, Drost G, et al.2002. A high-density multichannel surface electromyography system for the characterization of single motor units[J]. Review of Scientific Instruments, 73(4):1887-1897.
Chan A, Kevin B.2005. Continuous myoelectric control for powered protheses using hidden markov models[J]. IEEE Transactions on Biomedical Engineer,52:123-134.
Chauvet E, Fokapu O, Hogrel JY, et al.2001. A method of EMG decomposition based on fuzzy logic[C]. Proceedings of the 23rd IEEE EMBS annual international conference, Istanbul, Turkey,1948-1950.
Chauvet E, Fokapu O, Hogrel JY, et al.2003. Automatic identification of motor unit action potential trains from electromyographic signals using fuzzy techniques[J]. Medical & Biological Engineering & Computing,41(6):646-653.
Daniel Dumitru, John C King, William E Rogers.1999. Motor unit action potential components and physiologic duration[J]. Muscle Nerve,22:733-741.
De Luca CJ, Adam A, Wotiz R, et al.2006. Decomposition of surface EMG signals[J]. Journal of Neurophysiology,96(3):1646-1657.
Delsys Inc.2009. Myomonitor Wireless EMG Systems[EB/OL]. Boston, USA:Delsys Inc, [2009],http://www.delsys.com/Products/Wireless.html.
Disselhorst-Klug C., Bahm J., Ramaekers V., et.al.2000. Non-invasive approach of motor unit recording during muscle contractions in humans[J]. Eur J Appl Physiol,83:144-150.
Drost Gea, Stegeman F Dick, van Engelen Baziel GM, Zwarts Machiel J.2006. Clinical applications of high-density surface EMG:A systematic review[J]. Journal of Electromyography and Kinesiology,16:586-602.
Englehart K, Hudgins B, Parker PA, et al.1999. Classification of the myoelectric signal using time-frequency based representations[J]. Medical Engineering & Physics,21:431-438.
Enrico Costanza, Samuel A lnversol, Rebecca Allen.2005. Toward subtle intimate interfaces for mobile devices using an EMG controller[C]. CHI2005, Portland, Oregon, USA,481-489.
Farina D, Fortunato E, Merletti R.2000. Noninvasive estimation of motor unit conduction velocity distribution using linear electrode arrays[J]. IEEE Transactions on Biomedical Engineering, 47(3):380-388.
Farina D, Schulte E, Merletti R, et al.2003. Single motor unit analysis from spatially filtered surface electromyogram signals[J]. Med Biol Eng Comput,41:330-345.
Gazzoni M, Farina D, Merletti R.2004. A new method for the extraction and classification of single motor unit action potentials from surface EMG signals[J]. Journal of Neuroscience Methods,136(2):165-177.
Graupe D, Vern B, Gruener G, et al.1989. Decomposition of surface EMG signals into single fiber action potentials by means of neural networks[C]. IEEE international symposium on circuits and systems,1008-1011.
Hermens HJ, Boon KL, Zilvold G.1984. The clinical use of surface EMG[J]. Electromyogr. Clin. Neurophysiol,24:243-65.
Holobar A, Zazula D.2003. Surface EMG decomposition using a novel approach for blind source separation[J]. Informatica Medica Slovenica,8(1):2-14.
Holobar A, Zazula D.2004a. Blind deconvolution of close-to-orthogonal pulse sources applied to surface electromyograms[C].ICA2004, Lecture Notes in Computer Science,1056-1063.
Holobar A, Zazula D.2004b. Correlation-based decomposition of surface electromyograms at low contraction forces[J]. Medical & Biological Engineering & Computing,42(4):487-495.
Jin Lee, Alexander Adam, De Luca CJ.2008. A simulation study for a surface EMG sensor that detects distinguishable motor unit action potentials[J]. J Neuroscience Methods,168:54-63.
Jong-Sung Kim, Huyk Jeong, Wookho Son.2004. A new means of HCI:EMG-MOUSE[C]. IEEE International Conference on Systems, Man and Cybernetics,1:100-104.
Jong Wom Shin, Joon-Hyuk, Nam Soo Kim.2007. Voice activity detection based on a family of parametric distributions[J]. Pattern Recognition Letters,28:1295-1299.
Jun-Uk Chu, Inhyuk Moon, Museong Mun.2005. A real-time pattern recognition for multifunction myoelectric hand control[C]. ICCAS2005, Kintex, Korea.
Klasser GD, Okeson JP.2006. The clinical usefulness of surface electromyography in the diagnosis and treatment of temporomandibular disorders[J]. J Am Dent Assoc, 137:763-771.
Kleine BU, Blok JH, Oostenveld R.2000. Magnetic stimulation-induced modulations of motor unit firings extracted from multi-channel surface EMG[J]. Muscle & Nerve,23(7): 1005-1015.
Kleine BU, van Dijk JP, Lapatki BG, et.al.2007. Using two-dimensional spatial information in decomposition of surface EMG signals[J]. Journal of Electromyography and Kinesiology, 17(5):535-548.
Lapatki BG, van Dijk JP, Jonas IE, et. al.2004. A thin, flexible multielectrode grid for high-density surface EMG[J]. J Appl Physiol,96:327-336.
Liu RW, Huang Q, Graupe D.1990. A neural network for noninvasive decomposition of surface EMG signals using Gaussian nodes[C]. IEEE international symposium on circuits and systems,2053-2056.
Mello RGT, Oliveira LF, Nadal J.2007. Digital butterworth filter for subtracting noise from low magnitude surface electromyogram[J]. Computer Medthods and Programs in Biomedicine, 87(1):28-35.
Merletti R, Parker P.2004. Electromyography:physiology, engineering, and noninvasive application[M]. Wiley-IEEE Press.
Mewett DT, Reynolds KJ, Nazeran H.2004. Reducing power line interference in digitised electromyogram recordings by spectrum interpolation[J]. Medical & Biological Engineering & Computing,42(4):524-531.
Michael R Neuman.2010. Biopotential electrodes[M]. Medical instrumentation(4th edition), USA: John Wiley & Sons, Inc:189-240
Naik GR, Kumar DK, Palaniswami M.2008. Multi run ICA and surface EMG based signal processing system for recognising hand gestures[C].8th IEEE International Conference on Computer and Information Technology, CIT,700-705.
Nakamura H, Yoshida M, Kotani M, et al.2004a. The application of independent component analysis to the multi-channel surface electromyographic signals for separation of motor unit action potential trains:part Ⅰ-measuring techniques[J]. Journal of Electromyography and Kinesiology,14(4):423-432.
Nakamura H, Yoshida M, Kotani M, et al.2004b. The application of independent component analysis to the multi-channel surface electromyographic signals for separation of motor unit action potential trains:part Ⅱ-modelling interpretation[J]. Journal of Electromyography and Kinesiology,14(4):433-441.
Nakamura H, Nahai K, Yoshida M.2005. Application of independent component analysis and expansion matching filter for automatic detection of motor unit action potential trains[C]. Proc of the 27th IEEE EMBS annual international conference, Shanhai, China,5013-5016.
Nishikawa D, Yu W, Yokoi H, et al.1999. EMG prosthetic hand controller discriminating ten motions using real-time learning method[C]. The IEEE RSJ International Conference on Intelligent Robots and Systems,153-158.
Ortolan RL, Mori RN, Pereira RR, et al.2003. Evaluation of adaptive/nonadaptive filtering and wavelet transform techniques for noise reduction in EMG mobile acquisition equipment[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering,11(1):60-69.
Osamah A Alsayegh.2000. EMG-based human-machine interface system[C]. IEEE International Conference on Multimedia and Expo, New York,2:925-928.
Ostlund N, Yu J, Roeleveld K, Karlsson JS.2004. Adaptive spatial filtering of multichannel surface electromyogram signals[J]. Med Biol Eng Comput,42:825-831.
Patrick Griss, Heli K.Tolvanen-Laakso, et.al.2002. Characterization of micromachined spiked biopotential electrodes[J]. IEEE Trans. Biomedical Engineering,49(6):597-604.
Peter K.2005. The ABC of EMG-A practical introduction to kinesiological electromyography [EB/OL]. Noraxon INC. USA. http://www.noraxon.com/downloads/educational.php3.
Ren XM, Yan ZG, Wang ZZ, et al.2006. Noise reduction based on ICA decomposition and wavelet transform for the extraction of motor unit action potentials[J]. Journal of Neuroscience Methods,158(2):313-322.
Reucher H, Rau Gunter, Silny Jiri.1987. Spatial filtering of noninvasive multielectrode EMG:part I-introduction to measuring technique and applications[J]. IEEE Transactions on Biomedical Engineering,34(2):98-105.
Robert Allen, Stanley Huang, William Tam.2004-11-18. Electromyographic force measuring system and method. USA, WO2004/098406 A1[P].
Ron Lenk.2005. Practical design of power supplies[M].王正仕,张军明,译.北京：人民邮电出版社,203-207.
Rosell J, Colominas J, Riu P, et al. 1988. Skin impedance from 1 Hz to 1 MHz [J]. IEEE Transactions on Biomedical Engineering,35(8):649-651.
Shinichi Aso, Akinori Sasaki, Hiroshi Hashimoto, et al.2006. Driving electric car by using EMG interface[C]. IEEE conference on Cybernetics and Intelligent Systems, Bangkok,1-5.
Suzushi Nishimura, Yutaka Tomita, Toshio Horiuchi.1992. Clinical application of an active electrode using an operational amplifier[J]. IEEE Trans. Biomedical Engineering,39(10): 1096-1099.
Swee Mok, Di-an Hong, Thomas S Babin, Sanjar Ghaem.2004-1-22. Wireless electromyography sensor and system. USA, US2004/0015096 A1[P].
Taylor D, Finley F.1971. Multiple axis prosthesis control by muscle synergies[C]. Int Symp Control Upper Extremity Prostheses Orthoses, Goteborg, Sweden.
Texas Instruments.2009. Passive low frequency interface device (PaLFI) with EEPROM and 134.2 kHz transponder interface[EB/OL]. USA:TI, [2009-11-05]. http://www.ti.com/palfi.
Todd A Kuiken, Laura A Miller, Robert D Lipschutz, et al.2007. Targeted reinnervation for enhanced prosthetic arm function in a woman with a proximal amputation:a case study[J]. The Lancet,369(9559):371-380.
Tsenov G, Zeghbib AH, Palis F, et al.2006. Neural networks for online classification of hand and finger movements using surface EMG signals[C].8th Seminar Neural Network Applications in Electrical Engineering, NEUREL,167-171.
Tsuji T, Bu N, Fukuda O, Kaneko M.2003. A recurrent log-linearized gaussian mixture network[J]. IEEE Transactions on Neural Network,14(2):304-316.
Van Vugt JP, van Dijk JG.2001. A convenient method to reduce crosstalk in surface EMG[J]. Clinical Neurophysiology 112:583-592,
Wang Wenhui, Chen Xiang, Wang Kongqiao, et al.2009. Dynamic gesture recognition based on multiple sensors fusion technology[C].31st Annual International Conference of the IEEE EMBS, Minneapolis, USA:7014-7017.
Xu Zhang, Xiang Chen, et al.2007. Research on gesture definition and electrode placement in pattern recognition of hand gesture action sEMG[C]. ICMB, LNCS4901:33-40.
Yi-Hung Liu, Han-Pang Huang, Chang-Hsin Weng.2007. Recognition of electromyographic signals using cascaded kernel learning machine[J]. IEEE Trans on Mechatronics,12(3): 253-264.
Zazula D.1999. Higher-order statistics used for decomposition of SEMGs[C]. Proceedings of the 12th IEEE symposium on Computer-Based Medical Systems,12-11.
褚雪忠,杨基海,李强,陈香.2006.电极配置对MUAP检测影响的仿真研究[J].生物医学工程研究,25(3)：137-140.
崔丽英.2006.简明肌电图学手册[M].北京：科学出版社,26-27.
丁祥峰,孙怡宁,孙启枉.2006.表面肌电检测中消除工频干扰的方法[J].北京生物医学工程,25(1)：63-66.
段晏文,李献红,肖文杰等.2007.新型的银／氯化银粉末医用电极[C].中国生物医学工程联合学术年会,西安,89-92.
菲利普·J·拉希,洛奇·K·柏克.1985.运动学和应用解剖学[M].胡勣,廖咸锐,译.北京：人民体育出版社,238-246.
高晋占.2004.微弱信号检测[M].北京：清华大学出版社,141-149,51-53.
何庆华,彭承琳,吴宝明,王禾.2003.有源电极用于表面肌电信号的检测[J].生物医学工程学杂志,20(3)：488-490.
胡大雷,刘珩.2005.高噪声环境下的语音活动检测技术[J].中国农业大学学报,10(3)：65-68.
姜海远,霍纪文,尹立志.1997.医用传感器[M].北京：科学出版社,285-287,296-300.
雷敏,王志中.2001.肌电假肢控制中的表面肌电信号的研究进展与展望[J].中国医疗器械杂志,25(3)：156-160.
李强.2008.表面肌电信号的运动单位动作电位检测[D]:[博士].合肥：中国科学技术大学.
梁政.2004.表面肌电信号分解方法研究[D]：[博士].合肥：中国科学技术大学.
梁政,杨基海,叶硃,等.2004.基于高阶谱的肌纤维传导速度谱坑法检测[J].北京生物医学工程,23(2)：126-131.
路凯,李小坚,周金祥.2006.基于肤色和边缘轮廓检测的手势识别[J].北方工业大学学报,18(3)：12-15.
罗志增,任晓亮.2005.表面肌电信号测试中工频干扰的抑制[J].仪器仪表学报,26(2)：193-195.
吕江波,虞露.2002.S/PDIF数字音频接口和接收机中的数据译码实现[J].电声技术,207(9)：15-20.
孙丽娟,张立材,郭彩龙.2008.基于视觉的手势识别技术[J].计算机技术与发展,18(10)：214-216,221.
汤晓芙.2002.神经病学——神经系统临床电生理学(下)(肌电图学及其他)[M].北京：人民军 医出版社,1-87,317-383.
王人成,郑双喜,蔡付文,等.2008.基于表面肌电信号的手指运模式识别系统[J].中国康复医学杂志,23(5)：410-412.
吴江琴,高文.2000.基于DGMM的中国手语识别系统[J].计算机研究与发展,37(5)：551-558.
吴江琴,高文,陈熙霖.1999.基于数据手套输入的汉语手指字母的识别[J].模式识别与人工智能,12(1)：74-78.
杨福生,高上凯.1989.生物医学信号处理[M].北京：高等教育出版社,109-139,607-643.
杨玉星,2005.生物医学传感器与检测技术[M].北京：化学工业出版社,318-321,344-346.
杨玉星,束美霞,罗洁,周黎明.2006.基于小型电极的新型阻抗血流图测量系统的研究[J].航天医学与医学工程,19(3)：208-211.
余洪俊,刘宏亮,陈蕾.2002.表面肌电图的发展与应用[J].中国临床康复,6(5)：720-721.
周士枋,丁伯坦.2004.运动学[M].北京：华夏出版社,172-179,17-18.
Analog Device.2007. AD8220, JFET Input Instrumentation Amplifier with Rail-to-Rail Output in MSOP Package[EB/OL]. Norwood, USA:ADI, [2007-05]. http://www.analog.com/en/ ampl ifiers-and-comparators/i nstrumentation-amplifiers/ad8220/products/product. html.
Antonio Piccoli, Giordano Pastori, Marta Guizzo, et al.2005. Equivalence of information from single versus multiple frequency bioimpedance vector analysis in hemodialysis[J]. Kidney International,67:301-313.
Baratta RV, Solomonow M, Zhou BH, et al.1998. Methods to reduce the variability of EMG power spectrum estimates[J]. Journal of Electromyography and Kinesiology,8(5):279-285.
Blok JH, van Dijk JP, Drost G, et al.2002. A high-density multichannel surface electromyography system for the characterization of single motor units[J]. Review of Scientific Instruments, 73(4):1887-1897.
Chan A, Kevin B.2005. Continuous myoelectric control for powered protheses using hidden markov models[J]. IEEE Transactions on Biomedical Engineer,52:123-134.
Chauvet E, Fokapu O, Hogrel JY, et al.2001. A method of EMG decomposition based on fuzzy logic[C]. Proceedings of the 23rd IEEE EMBS annual international conference, Istanbul, Turkey,1948-1950.
Chauvet E, Fokapu O, Hogrel JY, et al.2003. Automatic identification of motor unit action potential trains from electromyographic signals using fuzzy techniques[J]. Medical & Biological Engineering & Computing,41(6):646-653.
Daniel Dumitru, John C King, William E Rogers.1999. Motor unit action potential components and physiologic duration[J]. Muscle Nerve,22:733-741.
De Luca CJ, Adam A, Wotiz R, et al.2006. Decomposition of surface EMG signals[J]. Journal of Neurophysiology,96(3):1646-1657.
Delsys Inc.2009. Myomonitor Wireless EMG Systems[EB/OL]. Boston, USA:Delsys Inc, [2009],http://www.delsys.com/Products/Wireless.html.
Disselhorst-Klug C., Bahm J., Ramaekers V., et.al.2000. Non-invasive approach of motor unit recording during muscle contractions in humans[J]. Eur J Appl Physiol,83:144-150.
Drost Gea, Stegeman F Dick, van Engelen Baziel GM, Zwarts Machiel J.2006. Clinical applications of high-density surface EMG:A systematic review[J]. Journal of Electromyography and Kinesiology,16:586-602.
Englehart K, Hudgins B, Parker PA, et al.1999. Classification of the myoelectric signal using time-frequency based representations[J]. Medical Engineering & Physics,21:431-438.
Enrico Costanza, Samuel A lnversol, Rebecca Allen.2005. Toward subtle intimate interfaces for mobile devices using an EMG controller[C]. CHI2005, Portland, Oregon, USA,481-489.
Farina D, Fortunato E, Merletti R.2000. Noninvasive estimation of motor unit conduction velocity distribution using linear electrode arrays[J]. IEEE Transactions on Biomedical Engineering, 47(3):380-388.
Farina D, Schulte E, Merletti R, et al.2003. Single motor unit analysis from spatially filtered surface electromyogram signals[J]. Med Biol Eng Comput,41:330-345.
Gazzoni M, Farina D, Merletti R.2004. A new method for the extraction and classification of single motor unit action potentials from surface EMG signals[J]. Journal of Neuroscience Methods,136(2):165-177.
Graupe D, Vern B, Gruener G, et al.1989. Decomposition of surface EMG signals into single fiber action potentials by means of neural networks[C]. IEEE international symposium on circuits and systems,1008-1011.
Hermens HJ, Boon KL, Zilvold G.1984. The clinical use of surface EMG[J]. Electromyogr. Clin. Neurophysiol,24:243-65.
Holobar A, Zazula D.2003. Surface EMG decomposition using a novel approach for blind source separation[J]. Informatica Medica Slovenica,8(1):2-14.
Holobar A, Zazula D.2004a. Blind deconvolution of close-to-orthogonal pulse sources applied to surface electromyograms[C].ICA2004, Lecture Notes in Computer Science,1056-1063.
Holobar A, Zazula D.2004b. Correlation-based decomposition of surface electromyograms at low contraction forces[J]. Medical & Biological Engineering & Computing,42(4):487-495.
Jin Lee, Alexander Adam, De Luca CJ.2008. A simulation study for a surface EMG sensor that detects distinguishable motor unit action potentials[J]. J Neuroscience Methods,168:54-63.
Jong-Sung Kim, Huyk Jeong, Wookho Son.2004. A new means of HCI:EMG-MOUSE[C]. IEEE International Conference on Systems, Man and Cybernetics,1:100-104.
Jong Wom Shin, Joon-Hyuk, Nam Soo Kim.2007. Voice activity detection based on a family of parametric distributions[J]. Pattern Recognition Letters,28:1295-1299.
Jun-Uk Chu, Inhyuk Moon, Museong Mun.2005. A real-time pattern recognition for multifunction myoelectric hand control[C]. ICCAS2005, Kintex, Korea.
Klasser GD, Okeson JP.2006. The clinical usefulness of surface electromyography in the diagnosis and treatment of temporomandibular disorders[J]. J Am Dent Assoc, 137:763-771.
Kleine BU, Blok JH, Oostenveld R.2000. Magnetic stimulation-induced modulations of motor unit firings extracted from multi-channel surface EMG[J]. Muscle & Nerve,23(7): 1005-1015.
Kleine BU, van Dijk JP, Lapatki BG, et.al.2007. Using two-dimensional spatial information in decomposition of surface EMG signals[J]. Journal of Electromyography and Kinesiology, 17(5):535-548.
Lapatki BG, van Dijk JP, Jonas IE, et. al.2004. A thin, flexible multielectrode grid for high-density surface EMG[J]. J Appl Physiol,96:327-336.
Liu RW, Huang Q, Graupe D.1990. A neural network for noninvasive decomposition of surface EMG signals using Gaussian nodes[C]. IEEE international symposium on circuits and systems,2053-2056.
Mello RGT, Oliveira LF, Nadal J.2007. Digital butterworth filter for subtracting noise from low magnitude surface electromyogram[J]. Computer Medthods and Programs in Biomedicine, 87(1):28-35.
Merletti R, Parker P.2004. Electromyography:physiology, engineering, and noninvasive application[M]. Wiley-IEEE Press.
Mewett DT, Reynolds KJ, Nazeran H.2004. Reducing power line interference in digitised electromyogram recordings by spectrum interpolation[J]. Medical & Biological Engineering & Computing,42(4):524-531.
Michael R Neuman.2010. Biopotential electrodes[M]. Medical instrumentation(4th edition), USA: John Wiley & Sons, Inc:189-240
Naik GR, Kumar DK, Palaniswami M.2008. Multi run ICA and surface EMG based signal processing system for recognising hand gestures[C].8th IEEE International Conference on Computer and Information Technology, CIT,700-705.
Nakamura H, Yoshida M, Kotani M, et al.2004a. The application of independent component analysis to the multi-channel surface electromyographic signals for separation of motor unit action potential trains:part Ⅰ-measuring techniques[J]. Journal of Electromyography and Kinesiology,14(4):423-432.
Nakamura H, Yoshida M, Kotani M, et al.2004b. The application of independent component analysis to the multi-channel surface electromyographic signals for separation of motor unit action potential trains:part Ⅱ-modelling interpretation[J]. Journal of Electromyography and Kinesiology,14(4):433-441.
Nakamura H, Nahai K, Yoshida M.2005. Application of independent component analysis and expansion matching filter for automatic detection of motor unit action potential trains[C]. Proc of the 27th IEEE EMBS annual international conference, Shanhai, China,5013-5016.
Nishikawa D, Yu W, Yokoi H, et al.1999. EMG prosthetic hand controller discriminating ten motions using real-time learning method[C]. The IEEE RSJ International Conference on Intelligent Robots and Systems,153-158.
Ortolan RL, Mori RN, Pereira RR, et al.2003. Evaluation of adaptive/nonadaptive filtering and wavelet transform techniques for noise reduction in EMG mobile acquisition equipment[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering,11(1):60-69.
Osamah A Alsayegh.2000. EMG-based human-machine interface system[C]. IEEE International Conference on Multimedia and Expo, New York,2:925-928.
Ostlund N, Yu J, Roeleveld K, Karlsson JS.2004. Adaptive spatial filtering of multichannel surface electromyogram signals[J]. Med Biol Eng Comput,42:825-831.
Patrick Griss, Heli K.Tolvanen-Laakso, et.al.2002. Characterization of micromachined spiked biopotential electrodes[J]. IEEE Trans. Biomedical Engineering,49(6):597-604.
Peter K.2005. The ABC of EMG-A practical introduction to kinesiological electromyography [EB/OL]. Noraxon INC. USA. http://www.noraxon.com/downloads/educational.php3.
Ren XM, Yan ZG, Wang ZZ, et al.2006. Noise reduction based on ICA decomposition and wavelet transform for the extraction of motor unit action potentials[J]. Journal of Neuroscience Methods,158(2):313-322.
Reucher H, Rau Gunter, Silny Jiri.1987. Spatial filtering of noninvasive multielectrode EMG:part I-introduction to measuring technique and applications[J]. IEEE Transactions on Biomedical Engineering,34(2):98-105.
Robert Allen, Stanley Huang, William Tam.2004-11-18. Electromyographic force measuring system and method. USA, WO2004/098406 A1[P].
Ron Lenk.2005. Practical design of power supplies[M].王正仕,张军明,译.北京：人民邮电出版社,203-207.
Rosell J, Colominas J, Riu P, et al. 1988. Skin impedance from 1 Hz to 1 MHz [J]. IEEE Transactions on Biomedical Engineering,35(8):649-651.
Shinichi Aso, Akinori Sasaki, Hiroshi Hashimoto, et al.2006. Driving electric car by using EMG interface[C]. IEEE conference on Cybernetics and Intelligent Systems, Bangkok,1-5.
Suzushi Nishimura, Yutaka Tomita, Toshio Horiuchi.1992. Clinical application of an active electrode using an operational amplifier[J]. IEEE Trans. Biomedical Engineering,39(10): 1096-1099.
Swee Mok, Di-an Hong, Thomas S Babin, Sanjar Ghaem.2004-1-22. Wireless electromyography sensor and system. USA, US2004/0015096 A1[P].
Taylor D, Finley F.1971. Multiple axis prosthesis control by muscle synergies[C]. Int Symp Control Upper Extremity Prostheses Orthoses, Goteborg, Sweden.
Texas Instruments.2009. Passive low frequency interface device (PaLFI) with EEPROM and 134.2 kHz transponder interface[EB/OL]. USA:TI, [2009-11-05]. http://www.ti.com/palfi.
Todd A Kuiken, Laura A Miller, Robert D Lipschutz, et al.2007. Targeted reinnervation for enhanced prosthetic arm function in a woman with a proximal amputation:a case study[J]. The Lancet,369(9559):371-380.
Tsenov G, Zeghbib AH, Palis F, et al.2006. Neural networks for online classification of hand and finger movements using surface EMG signals[C].8th Seminar Neural Network Applications in Electrical Engineering, NEUREL,167-171.
Tsuji T, Bu N, Fukuda O, Kaneko M.2003. A recurrent log-linearized gaussian mixture network[J]. IEEE Transactions on Neural Network,14(2):304-316.
Van Vugt JP, van Dijk JG.2001. A convenient method to reduce crosstalk in surface EMG[J]. Clinical Neurophysiology 112:583-592,
Wang Wenhui, Chen Xiang, Wang Kongqiao, et al.2009. Dynamic gesture recognition based on multiple sensors fusion technology[C].31st Annual International Conference of the IEEE EMBS, Minneapolis, USA:7014-7017.
Xu Zhang, Xiang Chen, et al.2007. Research on gesture definition and electrode placement in pattern recognition of hand gesture action sEMG[C]. ICMB, LNCS4901:33-40.
Yi-Hung Liu, Han-Pang Huang, Chang-Hsin Weng.2007. Recognition of electromyographic signals using cascaded kernel learning machine[J]. IEEE Trans on Mechatronics,12(3): 253-264.
Zazula D.1999. Higher-order statistics used for decomposition of SEMGs[C]. Proceedings of the 12th IEEE symposium on Computer-Based Medical Systems,12-11.