A Comparative Analysis of Hybrid Deep Learning Models for Human Activity Recognition

Sensors

Ali Sedaghatbaf¹  Faranak Fotouhi²  Hossein Fotouhi³  Saedeh Abbaspour⁴  Maria Linden⁴  Maryam Vahabi⁴ 

[1] 3 RISE Research Institutes of Sweden, 72212 Västerås, Sweden;Engineering Department, University of Qom, Qom 3716146611, Iran;RISE Research Institutes of Sweden, 72212 Västerås, Sweden;School of Innovation, Design, and Engineering, Mälardalen University, 72220 Västerås, Sweden;

关键词: human activity recognition;    deep learning;    convolutional neural nets;    long short-term memory;    gated recurrent unit;   

DOI  :  10.3390/s20195707

来源: DOAJ

【 摘 要 】

Recent advances in artificial intelligence and machine learning (ML) led to effective methods and tools for analyzing the human behavior. Human Activity Recognition (HAR) is one of the fields that has seen an explosive research interest among the ML community due to its wide range of applications. HAR is one of the most helpful technology tools to support the elderly’s daily life and to help people suffering from cognitive disorders, Parkinson’s disease, dementia, etc. It is also very useful in areas such as transportation, robotics and sports. Deep learning (DL) is a branch of ML based on complex Artificial Neural Networks (ANNs) that has demonstrated a high level of accuracy and performance in HAR. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are two types of DL models widely used in the recent years to address the HAR problem. The purpose of this paper is to investigate the effectiveness of their integration in recognizing daily activities, e.g., walking. We analyze four hybrid models that integrate CNNs with four powerful RNNs, i.e., LSTMs, BiLSTMs, GRUs and BiGRUs. The outcomes of our experiments on the PAMAP2 dataset indicate that our proposed hybrid models achieve an outstanding level of performance with respect to several indicative measures, e.g., F-score, accuracy, sensitivity, and specificity.

【 授权许可】

Unknown