Real-time Recognition of Interleaved Activities Based on Ensemble Classifier of Long Short-Term Memory with Fuzzy Temporal Windows

Proceedings

Nugent, Chris¹  Zang, Shuai²  Quero, Javier Medina³  Salguero, Alberto⁴  Orr, Claire⁵ 

[1] Author to whom correspondence should be addressed.;Department of Computer Science, University of Cádiz, Calle Ancha 16, 11001 Cádiz, Spain;Department of Computer Science, University of Jaén, Campus Las Lagunillas, 23071 Jaén, Spain;Presented at the 12th International Conference on Ubiquitous Computing and Ambient Intelligence (UCAmI 2018), Punta Cana, Dominican Republic, 4–7 December 2018;School of Computing, Ulster University, Newtownabbey, Co. Antrim, Northern Ireland BT15 1ED, UK

关键词: real-time activity recognition;    interleaved activities;    fuzzy temporal windows;    long short-term memory;   

DOI  :  10.3390/proceedings2191225

学科分类：社会科学、人文和艺术（综合）

来源: mdpi

【 摘 要 】

In this paper, we present a methodology for Real-Time Activity Recognition of Interleaved Activities based on Fuzzy Logic and Recurrent Neural Networks. Firstly, we propose a representation of binary-sensor activations based on multiple Fuzzy Temporal Windows. Secondly, an ensemble of activity-based classifiers for balanced training and selection of relevant sensors is proposed. Each classifier is configured as a Long Short-Term Memory with self-reliant detection of interleaved activities. The proposed approach was evaluated using well-known interleaved binary-sensor datasets comprised of activities of daily living.

【 授权许可】

CC BY