Title: Impacts of feature selection on classification of individual activity recognitions for prediction of crowd disasters

Authors: Fatai Idowu Sadiq; Ali Selamat; Ondrej Krejcar; Roliana Ibrahim

Addresses: School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia (UTM), 81310 UTM Johor Bahru, Johor, Malaysia; Faculty of Physical Sciences, Ambrose Alli University, Ekpoma, Nigeria ' School of Computing, Faculty of Engineering, Media and Games Centre of Excellence (MagicX), Universiti Teknologi Malaysia (UTM), 81310 UTM Johor Bahru, Johor, Malaysia; Malaysia Japan International Institute of Technology (MJIIT), Universiti Teknologi Malaysia Kuala Lumpur, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia; Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 500-03 Hradec Kralove, Czech Republic ' Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 500-03 Hradec Kralove, Czech Republic ' School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia (UTM), 81310 UTM Johor Bahru, Johor, Malaysia

Abstract: We examined the possibility of feature selection using statistical based time frequency domain (SBTFD) extracted features for human activity recognition. This is to reduce the dimensionality of features on monitoring devices to improve accuracy and minimize false negative alarm for crowd disasters. We analysed 54 SBTFD features obtained from 22,350 instances comprising of a climb down, climb up, peak shake while standing, standing, still, and walking; as classes V1, V2, to V8. Also, the benchmark dataset of 274,214 instances from nine users for accelerometer signals. Both datasets were subjected to minimum redundancy maximum relevance with information gain (MRMR-IG), correlation and chi-square techniques to select the relevant SBTFD features. We applied ten-fold cross validation using WEKA with four classifiers to classify individual behaviour classes V1 to V8. We achieved 97.8% accuracy and false negative rate of 9.5% to save human lives from crowd disasters with seven features of MRMR-IG using RF.

Keywords: statistical-based time frequency domain; SBTFD; human activity recognition; HAR; minimum redundancy maximum relevance; MRMR; chi-square; dimensionality reduction.

DOI: 10.1504/IJIIDS.2019.102920

International Journal of Intelligent Information and Database Systems, 2019 Vol.12 No.3, pp.179 - 198

Received: 18 May 2018
Accepted: 19 Aug 2018
Published online: 11 Oct 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article