计算机科学 ›› 2019, Vol. 46 ›› Issue (4): 274-279.doi: 10.11896/j.issn.1002-137X.2019.04.043
李愚1, 柴国钟2, 卢纯福1, 唐智川1
LI Yu1, CHAI Guo-zhong2, LU Chun-fu1, TANG Zhi-chuan1
摘要: 表面肌电信号由于个体差异性,在作为外设的控制源时,往往需要针对个体进行长时间的前期训练以获得精准分类辨识模型。针对该问题,在原有的KKT-SVM增量学习方法的基础上,提出了一种基于DBSCAN密度聚类的SVM增量学习算法(D-ISVM),并将该算法应用于在线肌电手势识别。首先,考虑新增样本和原非SV样本对新SV集的影响,通过DBSCAN对样本分布的紧密程度进行分析聚类,筛选出原SV集附近的新增样本以及原非SV样本;其次,结合核心对象以及各样本到超平面的距离进行二次筛选;最后,将筛选出的样本与原SV集一起训练以获得新SV集。实验结果表明,与传统算法相比,提出的D-ISVM增量学习算法能保持更高的识别准确率,同时进一步提高分类模型的学习速度,并有效解决了在线手势识别中表面肌电个体差异性的问题。
中图分类号:
[1]AL-TIMEMY A H,KHUSHABA R N,BUGMANN G,et al. Improving the performance against force variation of EMG controlled multifunctional upper-limb prostheses for transradial amputees[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2016,24(6):650-661. [2]YOUNG A J,KUIKEN T A,HARGROVE L J.Analysis of using EMG and mechanical sensors to enhance intent recognition in powered lower limb prostheses[J].Journal of Neural Engineering,2014,11(5):1-12. [3]FARINA D,VUJAKLIJA I,SARTORI M,et al.Man/machine interface based on the discharge timings of spinal motor neurons after targeted muscle reinnervation[J].Nature Biomedical Engineering,2017,1(2):1-12. [4]ZHAO Y N,ZHANG H S,XU L S,et al.A study of different linear discriminant analysis methods in myoelectric prosthesis control[J].Journal of Integration Technology,2013,2(4):20-26.(in Chinese) 赵曜楠,张浩诗,徐礼胜,等.几种自适应线性判别分析方法在肌电假肢控制中的应用研究[J].集成技术,2013,2(4):20-26. [5]GU Y,YANG D,HUANG Q,et al.Robust EMG pattern recognition in the presence of confounding factors:features,classifiers and adaptive learning[J].Expert Systems with Applications,2018,96:208-217. [6]HENDERSON J,TITOV I.Incremental Sigmoid Belief Net- works for Grammar Learning[J].Journal of Machine Learning Research,2010,11(11):3541-3570. [7]LASKOV P,GEHL C,KRUEGER S,et al.Incremental support vector learning:analysis,implementation and applications[J].Journal of Machine Learning Research,2006,7(3):1909-1936. [8]ZHANG Y,ZHU X,LUO Y.An SVM algorithm for overcoming the influence of muscle fatigue in sEMG based human machine interaction[J].Control Engineering of China,2014,21(4):467-471.(in Chinese) 张毅,祝翔,罗元.一种克服 sEMG 人机交互中肌肉疲劳的 SVM 算法[J].控制工程,2014,21(4):467-471. [9]SENSINGER J W,LOCK B A,KUIKEN T A.Adaptive pattern recognition of myoelectric signals:exploration of conceptual framework and practical algorithms[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2009,17(3):270-278. [10]HUANG Q,YANG D,JIANG L,et al.A Novel Unsupervised Adaptive Learning Method for Long-Term Electromyography (EMG) Pattern Recognition[J].Sensors,2017,17(6):1-28. [11]DIEHL C P,CAUWENBERGHS G.SVM incremental learning,adaptation and optimization[C]∥Proceedings of the International Joint Conference on Neural Networks.IEEE,2003.IEEE,2003:2685-2690. [12]RISTIN M,GUILLAUMIN M,GALL J,et al.Incremental Learning of Random Forests for Large-Scale Image Classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(3):490-503. [13]MITRA P,MURTHY C A,PAL S K.A probabilistic active support vector learning algorithm[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(3):413-418. [14]SYED N A,LIU H,SUNG K K.Handling concept drifts in incremental learning with support vector machines[C]∥Procee-dings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,1999:317-321. [15]YAO M H,LIN X M,WANG X B.Fast incremental learning al- gorithm of svm with locality sensitive hashing[J].Computer Science,2017,44(S2):88-91.(in Chinese) 姚明海,林宣民,王宪保.一种基于局部敏感哈希的SVM快速增量学习算法[J].计算机科学,2017,44(S2):88-91. [16]SHILTON A,PALANISWAMI M,RALPH D,et al.Incremental training of support vector machines[J].IEEE transactions on Neural Networks,2005,16(1):114-131. [17]LI Y F,SU B,LIU G S.An incremental learning algorithm for SVM based on combined reserved set[J].Journal of Shanghai Jiao Tong University,2016,50(7):1054-1059.(in Chinese) 李妍坊,苏波,刘功申.一种基于组合保留集的 SVM 增量学习算法[J].上海交通大学学报,2016,50(7):1054-1059. [18]BIRANT D,KUT A.ST-DBSCAN:An algorithm for clustering spatial-temporal data[J].Data & Knowledge Engineering,2007,60(1):208-221. [19]CHEN Y,TANG S,PEI S,et al.DHeat:A Density Heat-Based Algorithm for Clustering With Effective Radius[J].IEEE Transactions on Systems Man Cybernetics-Systems,2018,48(4):649-660. [20]HSU C W,LIN C J.A comparison of methods for multiclass support vector machines[J].IEEE Transactions on Neural Networks,2002,13(2):415-425. [21]ZHANG Z L,LUO X G,GONZALEZ S,et al.DRCW-ASEG:One-versus-One distance-based relative competence weighting with adaptive synthetic example generation for multi-class imbalanced datasets[J].Neurocomputing,2018,285:176-187. |
[1] | 刘冬梅, 徐洋, 吴泽彬, 刘倩, 宋斌, 韦志辉. 基于边框距离度量的增量目标检测方法 Incremental Object Detection Method Based on Border Distance Measurement 计算机科学, 2022, 49(8): 136-142. https://doi.org/10.11896/jsjkx.220100132 |
[2] | 刘卫明, 安冉, 毛伊敏. 基于聚类和WOA的并行支持向量机算法 Parallel Support Vector Machine Algorithm Based on Clustering and WOA 计算机科学, 2022, 49(7): 64-72. https://doi.org/10.11896/jsjkx.210500040 |
[3] | 周志豪, 陈磊, 伍翔, 丘东亮, 梁广升, 曾凡巧. 基于SMOTE-SDSAE-SVM的车载CAN总线入侵检测算法 SMOTE-SDSAE-SVM Based Vehicle CAN Bus Intrusion Detection Algorithm 计算机科学, 2022, 49(6A): 562-570. https://doi.org/10.11896/jsjkx.210700106 |
[4] | 胡聪, 何晓晖, 邵发明, 张艳武, 卢冠林, 王金康. 基于极大极稳定区域及SVM的交通标志检测 Traffic Sign Detection Based on MSERs and SVM 计算机科学, 2022, 49(6A): 325-330. https://doi.org/10.11896/jsjkx.210300117 |
[5] | 沈少朋, 马洪江, 张智恒, 周相兵, 朱春满, 温佐承. 多元时序上状态转移模式的三支漂移检测 Three-way Drift Detection for State Transition Pattern on Multivariate Time Series 计算机科学, 2022, 49(4): 144-151. https://doi.org/10.11896/jsjkx.210600045 |
[6] | 王炽, 常俊. 基于3D卷积神经网络的CSI跨场景手势识别方法 CSI Cross-domain Gesture Recognition Method Based on 3D Convolutional Neural Network 计算机科学, 2021, 48(8): 322-327. https://doi.org/10.11896/jsjkx.200600122 |
[7] | 刘亮, 蒲浩洋. 基于LSTM的多维度特征手势实时识别 Real-time LSTM-based Multi-dimensional Features Gesture Recognition 计算机科学, 2021, 48(8): 328-333. https://doi.org/10.11896/jsjkx.210300079 |
[8] | 郭福民, 张华, 胡瑢华, 宋岩. 一种基于表面肌电信号的腕部肌力估计方法研究 Study on Method for Estimating Wrist Muscle Force Based on Surface EMG Signals 计算机科学, 2021, 48(6A): 317-320. https://doi.org/10.11896/jsjkx.200600021 |
[9] | 李梦荷, 许宏吉, 石磊鑫, 赵文杰, 李娟. 基于骨骼关键点检测的多人行为识别 Multi-person Activity Recognition Based on Bone Keypoints Detection 计算机科学, 2021, 48(4): 138-143. https://doi.org/10.11896/jsjkx.200300042 |
[10] | 宋一言, 唐东林, 吴续龙, 周立, 秦北轩. 改进穿线法与HOG+SVM结合的数码管图像读数研究 Study on Digital Tube Image Reading Combining Improved Threading Method with HOG+SVM Method 计算机科学, 2021, 48(11A): 396-399. https://doi.org/10.11896/jsjkx.210100123 |
[11] | 桑彬彬, 杨留中, 陈红梅, 王生武. 优势关系粗糙集增量属性约简算法 Incremental Attribute Reduction Algorithm in Dominance-based Rough Set 计算机科学, 2020, 47(8): 137-143. https://doi.org/10.11896/jsjkx.190700188 |
[12] | 刘凌云, 钱辉, 邢红杰, 董春茹, 张峰. 一种基于Q-学习算法的增量分类模型 Incremental Classification Model Based on Q-learning Algorithm 计算机科学, 2020, 47(8): 171-177. https://doi.org/10.11896/jsjkx.190600150 |
[13] | 刘肖, 袁冠, 张艳梅, 闫秋艳, 王志晓. 基于自适应多分类器融合的手势识别 Hand Gesture Recognition Based on Self-adaptive Multi-classifiers Fusion 计算机科学, 2020, 47(7): 103-110. https://doi.org/10.11896/jsjkx.200100073 |
[14] | 宋岩, 胡瑢华, 郭福民, 袁新亮, 熊睿洋. 基于sEMG的改进SVM+BP肌力预测分层算法 Improved SVM+BP Algorithm for Muscle Force Prediction Based on sEMG 计算机科学, 2020, 47(6A): 75-78. https://doi.org/10.11896/JsJkx.190900143 |
[15] | 景雨, 祁瑞华, 刘建鑫, 刘朝霞. 基于改进多尺度深度卷积网络的手势识别算法 Gesture Recognition Algorithm Based on Improved Multiscale Deep Convolutional Neural Network 计算机科学, 2020, 47(6): 180-183. https://doi.org/10.11896/jsjkx.200200030 |
|