A Hybrid Deep Learning Model for Human Activity Recognition Using Multimodal Body Sensing Data

TLDR

Human activity recognition from multimodal body sensor data is key for elderly care, yet most machine learning approaches rely on single modalities, prompting a shift toward robust multimodal techniques for smart healthcare. This study proposes a hybrid deep learning framework that fuses SRUs and GRUs for multimodal sensor‑based human activity recognition. The framework employs deep SRUs to capture temporal patterns and deep GRUs to mitigate vanishing gradients, and is evaluated against conventional methods on a standard public dataset. Experiments demonstrate that the hybrid model surpasses existing state‑of‑the‑art methods.

Abstract

Human activity recognition from multimodal body sensor data has proven to be an effective approach for the care of elderly or physically impaired people in a smart healthcare environment. However, traditional machine learning techniques are mostly focused on a single sensing modality, which is not practical for robust healthcare applications. Therefore, recently increasing attention is being given by the researchers on the development of robust machine learning techniques that can exploit multimodal body sensor data and provide important decision making in Smart healthcare. In this paper, we propose an effective multi-sensors-based framework for human activity recognition using a hybrid deep learning model, which combines the simple recurrent units (SRUs) with the gated recurrent units (GRUs) of neural networks. We use the deep SRUs to process the sequences of multimodal input data by using the capability of their internal memory states. Moreover, we use the deep GRUs to store and learn how much of the past information is passed to the future state for solving fluctuations or instability in accuracy and vanishing gradient problems. The system has been compared against the conventional approaches on a publicly available standard dataset. The experimental results show that the proposed approach outperforms the available state-of-the-art methods.