Study on modeling and recognition of human behaviors by If-Then-Rules with HMM
Study on modeling and recognition of human behaviors by If-Then-Rules with HMM
复制标题
基于If-Then-Rules和HMM的人类行为建模与识别研究
DOI：
10.1109/iecon.2009.5415391
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
S. Okuma
中科院分区：
文献类型：
--
作者：
K. Hashimoto;K. Doki;S. Doki;S. Okuma
传统的智能系统要求人类获得有关系统的知识和技术，以便人类获得其好处。这意味着人类必须适应这些系统。对于这个问题，有必要实现这样的系统，可以支持人类，换句话说，通过考虑人类的行为来适应人类的系统。为了实现这一思想，本文提出了一种人类行为的建模与识别方法。在这种方法中，我们假设一个人会随着周围环境的变化而改变他的行为，这个概念是通过如果-那么-规则来表达的。在规则中，为了考虑人的时空冗余性，用隐马尔可夫模型(HMM)来描述人周围环境的变化。为了识别人类行为的变化，根据当前的人类行为和与传感器获得的态势时间序列数据的相似性来选择最优的IF-THEN规则。本文以人的驾驶行为为例，构建了人的驾驶行为识别系统。通过所构建系统的实验结果，验证了该方法的有效性。
Conventional intelligent systems require humans to acquire knowledge and technique about the systems in order that humans receive their benefits. This means that humans must adapt to the systems. For this problem, it is necessary to realize such systems that can support humans, in other words, the systems that adapt to humans by considering human behaviors. In order to realize this idea, we propose a modeling and recognition method of human behaviors in this paper. In this method, we suppose that a human changes his behavior according to the change of the situation around him, and this concept is expressed by If-Then-Rules. In the rules, the change of the situation around a human is described by HMM(Hidden Markov Model) in order to consider its temporal and spatial redundancy. To recognize the change of human behaviors, the optimal If-Then-Rule is chosen based on the current human behavior and similarity to the time series data of the situation obtained by sensors. In this paper, human driving behaviors are considered as an example of human behaviors, and a recognition system of human driving behaviors is constructed. The usefulness of the proposed method is examined through some experimental results with the constructed system.