Weighted Fusion of Multiple Classifiers for Human Activity Recognition

EasyChair Preprint 10371

Abstract

Human Activity Recognition (HAR) based on wearable device has become as a hot topic of research due to its wide range of applications in health-care, fitness and smart homes. However, the classification of some activities with similar sensor readings, such as standing and sitting, is usually more challenging for the design of efficient activity recognition algorithms. Considering the inconsistent performance of different classifiers, which can provide information complementary for individual classifier, we propose a novel multi-classifier fusion method based on belief functions (BFs) theory for HAR. Specifically, at first, four classifiers are trained using time-domain and frequency-domain features to obtain basic belief assignments (BBA) of activity, respectively. Then, three assessment criteria are utilized to evaluate the reliability of the classifiers and a scoring matrix is constructed. Next, the algorithm of Belief Function based the Technique for Order Preference by Similarity to Ideal Solution (BF-TOPSIS) is employed to calculate the weighting coefficients for each classifier. Finally, the discounting and Dempster’s rules are adopted to combine the multiple classifiers and further decision making. Several experiments were conducted to illustrate the performance of the proposed method using the UCI smartphone dataset, and the results show that the proposed method is more accurate than the state-of-art methods.

Keyphrases: BF-TOPSIS, Human Activity Recognition, Multiple Classifiers Fusion, belief functions theory

@booklet{EasyChair:10371,
  author    = {Kezhu Zuo and Xinde Li and Jean Dezert and Yilin Dong},
  title     = {Weighted Fusion of Multiple Classifiers for Human Activity Recognition},
  howpublished = {EasyChair Preprint 10371},
  year      = {EasyChair, 2023}}