首页--医药、卫生论文--基础医学论文--医用一般科学论文--生物医学工程论文--人工脏器与器官论文--运动器官论文

Optimization of Myoelectric Pattern Recognition System of Multifunction Upper-limb Prosthesis

Acknowledgement第6-7页
Abstract第7页
This dissertation is divided into eight Chapters第9-10页
Abbreviations第10-13页
Chapter 1第13-17页
    1-Overview第14-17页
        1.1 Motivation and problem description第14-15页
        1.2 Suggested solution第15-17页
Chapter 2:Theoretical Background and Previous Work第17-54页
    Part 1: Theory第18-44页
        2.1 Human's muscles第18-24页
            2.1.1 Anatomy of human forearm第19-24页
        2.2 Electromyographic EMG signal第24-35页
            2.2.1 Introduction第24-25页
            2.2.2 EMG-History第25-26页
            2.2.3 EMG-Signal processing: EMG recording-Noise effect第26-28页
            2.2.4 Feature extraction第28-32页
            2.2.5 Wavelet analysis第32-35页
        2.3 Pattern recognition第35-44页
            2.3.1 Neural network-Historical overviews第36-37页
            2.3.2 Supervised and unsupervised learning第37-38页
            2.3.3 Classification methods第38-44页
    Part 2:Myoelectric Pattern Recognition System Using Different ClassificationApproaches:A Review第44-54页
        2.1 Literature review-Myoelectric pattern recognition第44-53页
        2.2 Conclusion第53-54页
Chapter 3:Recognition of Five Hand Motions Patterns Using RBF Neural NetworkBased on Surface Electromyography Signal第54-64页
    3.1 Introduction第55页
    3.2 Subjects-Material-Experimental protocol第55-59页
        3.2.1 Subjects第55-56页
        3.2.2 Material第56-57页
        3.2.3 Experimental protocol第57-59页
    3.3 Feature selection and classification step第59-60页
    3.4 Result and discussion第60-62页
    3.5 Conclusion,limitaiton and future work第62-64页
Chapter 4:An Investigation of Myoelectric Pattern Recognition Based on WaveletAnalysis第64-75页
    4.1 Introduction第65页
    4.2 Wavelet analysis in myoelectric pattern recognition system第65-67页
    4.3 The proposed myoelectric PR system based on wavelet coefficients第67-69页
    4.4 Results and discussion第69-73页
    4.5 Conclusion第73页
    4.6 Limitations and future work第73-75页
Chapter 5:Pattern Recognition of Eight Hand Motions Using FeatureExtraction of Forearm EMG Signal Based on Statistical Analysis第75-95页
    5.1 Introduction第76-77页
    5.2 Experimental protocol第77-81页
    5.3 Feature weighing the proposed pattern recognition system第81-83页
    5.4 Results and discussions第83-94页
        5.4.1 Part One:Feature weighting第83-87页
        5.4.2 Part Two:Feature combination第87-88页
        5.4.3 Part Three:Select the kernels functions of support vector machine (SVM)第88-90页
        5.4.4 Part Four:Selecting best wavelet family第90-93页
        5.4.5 Part Five:Optimization of K-nearest neighbor (K-NN) algorithm based on k-value第93-94页
    5.5 Conclusion第94-95页
Chapter 6:Different Dimensionality Reduction Methods for ClassificationEleven Hand Motions Using Wavelet Packet Multilayer Neural Network andArtificial Bee Colony Algorithm第95-101页
    6.1 Introduction第96-97页
    6.2 Multilayer perceptron back propagation neural network第97-98页
    6.3 Result and discussion第98-99页
    6.4 Proposed ABC-MLPNN algorithm第99-100页
    6.5 Conclusion第100-101页
Chapter 7:A Novel Pattern Recognition Approach Using GA-LibSVM HybridModel for Classification Eleven Hand Motions第101-107页
    7.1 Introduction第102-103页
    7.2 Block diagram of the proposed myoelectric pattern recognition system第103-105页
        7.2.1 Data acquisition第103页
        7.2.2 Dimensionality reduction第103页
        7.2.3 Feature extraction第103-104页
        7.2.4 The proposed hybrid GA-LibSVM pattern recognition model第104-105页
    7.3 Results and discussion第105-106页
    7.4 Conclusion第106-107页
Chapter 8:Conclusion, Future Work and Limitations第107-110页
Academic Publications第110-111页
Reference第111-128页

论文共128页,点击 下载论文
上一篇:产业集群竞争优势研究
下一篇:哈尔滨市社区体育发展现状及发展趋势的研究