Human activity recognition based on HMM by improved PSO and event probability sequence

• 作 者: Hanju Li Yang Yi Xiaoxing Li Z
• 机 构: DepartmentofComputerScience,InformationCentre,XinhuaCollege
• 出 处: 系统工程与电子技术：英文版
• 发表日期: 2013年3期
• 关键词: 事件概率 人类活动 序列识别 HMM PSO 隐马尔可夫模型 参数学习算法 有效性评价 human activity recognition hidden M
• 基金项目: This work was supported by the National Natural Science Foundation of China （60573159） and the Guangdong High Technique Project （201100000514）.

This paper proposes a hybrid approach for recognizing human activities from trajectories.First,an improved hidden Markov model(HMM) parameter learning algorithm,HMM-PSO,is proposed,which achieves a better balance between the global and local exploitation