An evolving machine learning method for human activity recognition systems

作者：Andreu Javier^*; Angelov Plamen

来源：Journal of Ambient Intelligence and Humanized Computing, 2013, 4(2): 195-206.

DOI：10.1007/s12652-011-0068-9

• Human activity recognition
• Machine learning
• Fuzzy rule-based classifiers
• Evolving systems
• Wearable sensors
• Business-oriented applications

In this paper is presented a novel approach for human activity recognition (HAR) through complex data provided from wearable sensors. This approach considers the development of a more realistic system which takes into account the diversity of the population. It aims to define a general HAR model for any type of individuals. To achieve this much-needed processing capacity, this novel approach makes use of customizable, self-adaptive, selfdevelopment capacities of the so-called machine learning technique named evolving intelligent systems. An online pre-processing model to suit real-time capacities has been developed and is also explained in detail in this paper. Additionally, this paper provides valuable information on sensor analysis, online feature extraction, and evolving classifiers used for the attainment of this purpose.

• 出版日期2013-4