Sensor-Based Spatio-Temporal Human Activity Recognition: A
Systematic Review of Advancements, Challenges, and Future
Directions
Asmaa Badran1, Ahmad Salah2,3 , A. A. Soliman4, Dina A. Elmanakhly5, Ahmed Fathalla5,∗
1Department of computer science, Faculty of Computers and Information, Arish University, Arish, Egypt
2College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri,
Sultanate of Oman
3Department of Computer Science, Faculty of Computers and Informatics, Zagazig University, Zagazig,
Sharkeya, Egypt
4Department of Mathematics, Faculty of Science, Arish University, Arish, 45111, Egypt
5Department of Mathematics, Faculty of Science,Suez Canal University, Ismailia, Egypt
Emails: asmaa.ahmedbadran@gmail.com; ahmad.salah@utas.edu.om; asoliman 99@yahoo.com;
dina almnakhly@science.suez.edu.eg; fathalla sci@science.suez.edu.eg
Abstract
Spatio-temporal human activity recognition (HAR) is an emerging field that uses spatial and tem-
poral data to identify and classify human activities accurately. It has been effectively applied in
areas like healthcare for monitoring daily activities, detecting anomalies, and aiding rehabilitation
with real-time feedback. However, there is a gap in research specifically focusing on integrating
spatio-temporal data with advanced machine and deep learning techniques for HAR based on sensor
data. Existing reviews do not comprehensively cover spatio-temporal HAR based on sensor data,
resulting in a lack of summaries on recent models, datasets, sensor technologies, applications, and
machine/deep learning techniques used in this field. This systematic review provides a comprehen-
sive overview of spatio-temporal HAR based on sensor data, tracing its development from the origin
of sensor-based spatio-temporal HAR field to the present. It highlights the main challenges in spatio-
temporal HAR. The review also examines model trends over the years, including the distribution
of models used in HAR and the identification of those frequently combined to form hybrid models.
Additionally, it analyzes accuracy trends of the commonly used datasets and identifies the datasets
that are widely used in spatio-temporal HAR research. Furthermore, various application domains and
sensor technologies used in spatio-temporal HAR are identified.
Received: January 17, 2025 Revised: February 12, 2025 Accepted: March 10, 2025
Keywords: Deep learning; Human activity recognition; Machine learning; Systematic review; Spatio-temporal;
Wearable sensors