基于改进隐马尔科夫模型的鲁棒用户行为识别
|
摘要
提出了一种基于改进隐马尔科夫模型的用户行为识别方法.采用遗传算法用于优化隐马尔科夫模型的初始参数,将混沌算子代替遗传算法中高斯变异算子,以避免传统遗传算法在收敛过程中的停滞和早熟问题,并有效解决传统隐马尔科夫模型中Baum-Welch算法对初始参数敏感的问题.此外,采用UCI中ADLs数据对用户行为进行识别,实验结果表明该方法具有很高的识别率和可靠性.
An improved Hidden Markov Models(HMM)was proposed to recognize the user's behavior.In order to improve the learning efficiency of Baum-Welch algorithm in HMM,and to solve the problem of initial sensitivity,the improved GA s used to optimize the initial parameters of HMM,in which the Chaos operator is utilized to avoid the problem of stagnation and premature convergence of the traditional GA in the convergence process.Finally,the experiment results based on ADLs data in UCI show the algorithm's availability and reliability for user's behavior recognition.
An improved Hidden Markov Models(HMM)was proposed to recognize the user's behavior.In order to improve the learning efficiency of Baum-Welch algorithm in HMM,and to solve the problem of initial sensitivity,the improved GA s used to optimize the initial parameters of HMM,in which the Chaos operator is utilized to avoid the problem of stagnation and premature convergence of the traditional GA in the convergence process.Finally,the experiment results based on ADLs data in UCI show the algorithm's availability and reliability for user's behavior recognition.
引文
[1]LI M,LIN H.Design and implementation of smart home control systems based on wireless sensor networks and power line communications[J].IEEE Transactions on Industrial Electronics,2015,62(7):4430-4442.
[2]ORDEZ F J,ENGLEBIENNE G,TOLEDO P D,et al.In-home activity recognition:Bayesian inference for hidden Markov models[J].IEEE Pervasive Computing,2014,13(3):67-75.
[3]HOSEINI-TABATABAEI S A,GLUHAK A,TAFAZOLLI R.A survey on smart phone-based systems for opportunistic user context recognition[J].ACM Computing Surveys(CSUR),2013,45(3):1-33.
[4]BULLING A,BLANKE U,SCHIELE B.A tutorial on human activity recognition using body-worn inertial sensors[J].ACM Computing Surveys(CSUR),2014,46(3):57-76.
[5]CHIANG J H,YANG P C,TU H.Pattern analysis in daily physical activity data for personal health management[J].Journal Pervasive and Mobile Computing,2014,13(4):13-25.
[6]ZHOU B,LI Q,MAO Q,et al.Activity sequence-based indoor pedestrian localization using smart phones[J].IEEE Transactions on Human-Machine Systems,2015,45(5):562-574.
[7]MARTIN H,BERNARDOS A M,IGLESIAS J,et al.Activity logging using lightweight classification techniques in mobile devices[J].Personal and Ubiquitous Computing,2013,17(4):675-695.
[8]王忠民,韩帅,宋辉.一种位置无关的多模型移动用户行为识别方法[J].计算机应用研究,2017,34(4):1060-1062,1066.WANG Z M,HAN S,SONG H.A location-independent multi-model mobile user behavior recognition method[J].Application Research of Computers,2017,34(4):1060-1062,1066.(In Chinese)
[9]宋相法,张延锋,郑逢斌.基于L(2,1)范数稀疏特征选择和超法向量的深度图像序列行为识别[J].计算机科学,2017,44(2):306-308,323.SONG X F,ZHANG Y F,ZHENG F B.Activity recognition from depth image sequences based on L(2,1)norm sparse feature selection and super normal vector[J].Computer Science,2017,44(2):306-308,323.(In Chinese)
[10]贺炎,王斌,王忠民.小波分解在移动用户行为识别中的应用[J].北京邮电大学学报,2016,39(4):67-70.HE Y,WANG B,WANG Z M.Application of wavelet decomposition in mobile user behavior recognition[J].Journal of Beijing University of Posts and Telecom,2016,39(4):67-70.(In Chinese)
[11]朱煜,赵江坤,王逸宁,等.基于深度学习的人体行为识别算法综述[J].自动化学报,2016,42(6):848-857.ZHU Y,ZHAO J K,WANG Y N,et al.Summarization of human behavior recognition algorithm based on deep learning[J].Journal of Automation,2016,42(6):848-857.(In Chinese)
[12]王昌海,张建忠,徐敬东,等.基于HMM的动作识别结果可信度计算方法[J].通信学报,2016,37(5):143-151.WANG C H,ZHANG J Z,XU J D,et al.Identifying the confidence level of activity recognition via HMM[J].Journal on Communications,2016,37(5):143-151.(In Chinese)
[13]HASSAN M R,NATH B.Stock market forecasting using Hidden Markov Model:a new approach[C]//International Conference on Intelligent Systems Design and Applications.2005:192-196.
[14]温加睿,刘丽娜,芮玲,等.基于自学习特征与HMM的人体动作识别[J].系统仿真学报,2015,27(8):1782-1789,1795.WEN J R,LIU L N,RUI L,et al.Human action recognition based on self-learning feature and HMM[J].Journal of System Simulation,2015,27(8):1782-1789,1795.(In Chinese)
[15]ALEMDAR H,KASTEREN T L M V,NIESSEN M E,et al.A unified model for human behavior modeling using a hierarchy with a variable number of states[J].International Conference on Pattern Recognition,2014,29(2):3804-3809.
[16]PATTERSON D J,FOX D,KAUTZ H,et al.Fine-grained activity recognition by aggregating abstract object usage[C]//IEEE International symposium on Wearable Computers.2005:44-51.
[17]CRANDALL A S,COOK D J.Using a Hidden Markov Model for resident identification[C]//Sixth International Conference on Intelligent Environments.IEEE Xplore,2010:74-79.
[18]YANG L J,CHEN T L.Application of chaos in genetic algorithms[J].Journal of Communications in Theoretical Physics,2002,38(8):168-172.
[19]HALALAI R,LEMNARU C,POTOLEA R.Distributed community detection in social networks with genetic algorithms[C]//IEEE International Conference on Intelligent Computer Communication and Processing.2010:35-41.
[20]LIAO L,FOX D,KAUTZ H.Location-based activity recognition using relational Markov networks[C]//International Joint Conference on Artificial Intelligence.2005:773-778.
[21]刘振军,杨迪雄.面向工程全局优化的混沌优化算法研究进展[J].计算力学学报,2016,33(3):269-286.LIU Z J,YANG D X.Research advances of chaos optimization algorithms for engineering global optimization[J].Journal of Computational Mechanics,2016,33(3):269-286.(In Chinese)
[22]ORDONEZ F J,De TOLEDO P,SANCHIS A.Activity recognition using hybrid generative/discriminative models on home environments using binary sensors[DB/OL].Sensors.https://archive.ics.uci.edu/ml/datasets/Activities+of+Daily+Living+(ADLs)+Recognition+Using+Binary+Sensors,2013-13,5460-5477/2017-5.
[23]吴刚,邱煜晶,王国仁,等.基于隐尔可夫模型和遗传算法的地图匹配算法[J].东北大学学报(自然科学版),2017,38(4):472-475.WU G,QIU Y J,WANG G R,et al.Map matching algorithm based on Hidden Markov model and Gennetic algorithm[J].Journal of Northeastern University(Natural Science),2017,38(4):472-475.(In Chinese)
[24]BILMES J A.A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian Mixture and Hidden Markov models[M].U.C.Berkeley:International Computer Science Institute,1998:120-126.
[2]ORDEZ F J,ENGLEBIENNE G,TOLEDO P D,et al.In-home activity recognition:Bayesian inference for hidden Markov models[J].IEEE Pervasive Computing,2014,13(3):67-75.
[3]HOSEINI-TABATABAEI S A,GLUHAK A,TAFAZOLLI R.A survey on smart phone-based systems for opportunistic user context recognition[J].ACM Computing Surveys(CSUR),2013,45(3):1-33.
[4]BULLING A,BLANKE U,SCHIELE B.A tutorial on human activity recognition using body-worn inertial sensors[J].ACM Computing Surveys(CSUR),2014,46(3):57-76.
[5]CHIANG J H,YANG P C,TU H.Pattern analysis in daily physical activity data for personal health management[J].Journal Pervasive and Mobile Computing,2014,13(4):13-25.
[6]ZHOU B,LI Q,MAO Q,et al.Activity sequence-based indoor pedestrian localization using smart phones[J].IEEE Transactions on Human-Machine Systems,2015,45(5):562-574.
[7]MARTIN H,BERNARDOS A M,IGLESIAS J,et al.Activity logging using lightweight classification techniques in mobile devices[J].Personal and Ubiquitous Computing,2013,17(4):675-695.
[8]王忠民,韩帅,宋辉.一种位置无关的多模型移动用户行为识别方法[J].计算机应用研究,2017,34(4):1060-1062,1066.WANG Z M,HAN S,SONG H.A location-independent multi-model mobile user behavior recognition method[J].Application Research of Computers,2017,34(4):1060-1062,1066.(In Chinese)
[9]宋相法,张延锋,郑逢斌.基于L(2,1)范数稀疏特征选择和超法向量的深度图像序列行为识别[J].计算机科学,2017,44(2):306-308,323.SONG X F,ZHANG Y F,ZHENG F B.Activity recognition from depth image sequences based on L(2,1)norm sparse feature selection and super normal vector[J].Computer Science,2017,44(2):306-308,323.(In Chinese)
[10]贺炎,王斌,王忠民.小波分解在移动用户行为识别中的应用[J].北京邮电大学学报,2016,39(4):67-70.HE Y,WANG B,WANG Z M.Application of wavelet decomposition in mobile user behavior recognition[J].Journal of Beijing University of Posts and Telecom,2016,39(4):67-70.(In Chinese)
[11]朱煜,赵江坤,王逸宁,等.基于深度学习的人体行为识别算法综述[J].自动化学报,2016,42(6):848-857.ZHU Y,ZHAO J K,WANG Y N,et al.Summarization of human behavior recognition algorithm based on deep learning[J].Journal of Automation,2016,42(6):848-857.(In Chinese)
[12]王昌海,张建忠,徐敬东,等.基于HMM的动作识别结果可信度计算方法[J].通信学报,2016,37(5):143-151.WANG C H,ZHANG J Z,XU J D,et al.Identifying the confidence level of activity recognition via HMM[J].Journal on Communications,2016,37(5):143-151.(In Chinese)
[13]HASSAN M R,NATH B.Stock market forecasting using Hidden Markov Model:a new approach[C]//International Conference on Intelligent Systems Design and Applications.2005:192-196.
[14]温加睿,刘丽娜,芮玲,等.基于自学习特征与HMM的人体动作识别[J].系统仿真学报,2015,27(8):1782-1789,1795.WEN J R,LIU L N,RUI L,et al.Human action recognition based on self-learning feature and HMM[J].Journal of System Simulation,2015,27(8):1782-1789,1795.(In Chinese)
[15]ALEMDAR H,KASTEREN T L M V,NIESSEN M E,et al.A unified model for human behavior modeling using a hierarchy with a variable number of states[J].International Conference on Pattern Recognition,2014,29(2):3804-3809.
[16]PATTERSON D J,FOX D,KAUTZ H,et al.Fine-grained activity recognition by aggregating abstract object usage[C]//IEEE International symposium on Wearable Computers.2005:44-51.
[17]CRANDALL A S,COOK D J.Using a Hidden Markov Model for resident identification[C]//Sixth International Conference on Intelligent Environments.IEEE Xplore,2010:74-79.
[18]YANG L J,CHEN T L.Application of chaos in genetic algorithms[J].Journal of Communications in Theoretical Physics,2002,38(8):168-172.
[19]HALALAI R,LEMNARU C,POTOLEA R.Distributed community detection in social networks with genetic algorithms[C]//IEEE International Conference on Intelligent Computer Communication and Processing.2010:35-41.
[20]LIAO L,FOX D,KAUTZ H.Location-based activity recognition using relational Markov networks[C]//International Joint Conference on Artificial Intelligence.2005:773-778.
[21]刘振军,杨迪雄.面向工程全局优化的混沌优化算法研究进展[J].计算力学学报,2016,33(3):269-286.LIU Z J,YANG D X.Research advances of chaos optimization algorithms for engineering global optimization[J].Journal of Computational Mechanics,2016,33(3):269-286.(In Chinese)
[22]ORDONEZ F J,De TOLEDO P,SANCHIS A.Activity recognition using hybrid generative/discriminative models on home environments using binary sensors[DB/OL].Sensors.https://archive.ics.uci.edu/ml/datasets/Activities+of+Daily+Living+(ADLs)+Recognition+Using+Binary+Sensors,2013-13,5460-5477/2017-5.
[23]吴刚,邱煜晶,王国仁,等.基于隐尔可夫模型和遗传算法的地图匹配算法[J].东北大学学报(自然科学版),2017,38(4):472-475.WU G,QIU Y J,WANG G R,et al.Map matching algorithm based on Hidden Markov model and Gennetic algorithm[J].Journal of Northeastern University(Natural Science),2017,38(4):472-475.(In Chinese)
[24]BILMES J A.A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian Mixture and Hidden Markov models[M].U.C.Berkeley:International Computer Science Institute,1998:120-126.