IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

A Hybrid Approach for Smart Home Activity Recognition Using Sensor Data and Deep Learning Techniques

A Hybrid Approach for Smart Home Activity Recognition Using Sensor Data and Deep Learning Techniques
View Sample PDF
Author(s): K. Kavitha (Vellore Institute of Technology, Chennai, India), Shashank Pandey (Vellore Institute of Technology, Chennai, India), Piyali Saha (Vellore Institute of Technology, Chennai, India)and Atul R. Patel (Vellore Institute of Technology, Chennai, India)
Copyright: 2025
Pages: 22
Source title: Enhancing Data-Driven Electronics Through IoT
Source Author(s)/Editor(s): Bhagwan Das (Centre for Artificial Intelligence Research and Optimization (AIRO), Torrens University Australia, Australia), Muhammad Zakir Shaikh (Universidad de Málaga, Spain), Samreen Hussain (Dawood University of Engineering and Technology, Pakistan)and Enrique Nava Baro (Universidad de Málaga, Spain)
DOI: 10.4018/979-8-3693-5448-3.ch007

Purchase

View A Hybrid Approach for Smart Home Activity Recognition Using Sensor Data and Deep Learning Techniques on the publisher's website for pricing and purchasing information.

Abstract

Recognizing human activities in smart homes poses challenges due to environmental variability, sensor systems, and sparse signals. Deep learning models struggle to extract meaningful features autonomously, necessitating additional context. This study proposes a novel hybrid approach merging natural language processing and time series classification techniques to address feature extraction for activity recognition. Sensor events are encoded into frequency-based terms, generating embeddings capturing semantic relationships. Evaluation on two smart home datasets demonstrates the effectiveness of encoding-based embeddings for improving automatic feature learning. Comparisons with Cascade LSTM and other models show the superiority of the proposed approach. The hybrid technique, centered around Cascade LSTM, effectively leverages contextual information from sensor event sequences for recognizing complex human activities in smart homes.

Related Content

P. V. Naveen, A. Poongodi. © 2026. 24 pages.
Sathya Selvaraj Sinnasamy, S. Kamaleswari, U. Surendar, Biswaranjan Senapati, B. Vaidianathan, M. Gandhi. © 2026. 14 pages.
B. Aarthi, A. Smruthi, Pamireddy Thanishka, G. Sakthi Prasanna, P. Mahendran. © 2026. 18 pages.
R. Radhika, A. Muthukumaravel. © 2026. 24 pages.
R. Regin, K. Lalith Reddy, R. Sanjay Narayanan, Y. Likhith Srinivas, R. Steffi, S. Saranya, S. R. Saranya. © 2026. 26 pages.
R. Saranya, S. Silvia Priscila. © 2026. 20 pages.
Manjunath Singh H., R. Tanuja. © 2026. 28 pages.
Body Bottom