A hybrid FMM-CART model for human activity recognition

Author

Seera, Manjeevan ; Chu Kiong Loo ; Chee Peng Lim

Author_Institution

Fac. of Comput. Sci. & Inf. Technol., Univ. of Malaya, Kuala Lumpur, Malaysia

fYear

2014

fDate

5-8 Oct. 2014

Firstpage

182

Lastpage

187

Abstract

In this paper, the application of a hybrid model combining the fuzzy min-max (FMM) neural network and the classification and regression tree (CART) to human activity recognition is presented. The hybrid FMM-CART model capitalizes the merits of both FMM and CART in data classification and rule extraction. To evaluate the effectiveness of FMM-CART, two data sets related to human activity recognition problems are conducted. The results obtained are higher than those reported in the literature. More importantly, practical rules in the form of a decision tree are extracted to provide explanation and justification for the predictions from FMM-CART. This outcome positively indicates the potential of FMM-CART in undertaking human activity recognition tasks.

Keywords

decision trees; fuzzy set theory; minimax techniques; neural nets; pattern classification; regression analysis; CART; classification and regression tree; decision tree; fuzzy min-max neural network; human activity recognition; hybrid FMM-CART model; Accelerometers; Accuracy; Complexity theory; Computational modeling; Decision trees; Legged locomotion; Training; classification and regression tree; fuzzy min-max neural network; human activity recognition; rule extraction;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics (SMC), 2014 IEEE International Conference on

Conference_Location

San Diego, CA

Type

conf

DOI

10.1109/SMC.2014.6973904

Filename

6973904