Human Behaviour Classification in Emergency Situations UsingMachine Learning withMultimodal Data: A Systematic Review (2020–2025)

MirzaMurad Baig¹, Muhammad Rehan Faheem^2,*, LalKhan^3,*, Hannan Adeel² and Syed Asim Ali Shah⁴
1 Department of Computer Science, Faculty of Computing,The Islamia University of Bahawalpur, Bahawalpur, 63100, Pakistan
2 Fakulti Kecerdasan Buatan dan Keselamatan Siber, Universiti Teknikal Malaysia, Melaka, 76100, Malaysia
3 Department of AI and SW, Gachon University, Seongnam, 13557, Republic of Korea
4 Fakulti Pengurusan Teknologi Dan Teknousahawanan, Universiti Teknikal Malaysia Melaka, Kampus Teknologi, Melaka, 76100, Malaysia
* Corresponding Author:Muhammad Rehan Faheem. Email: email ; Lal Khan. Email: email

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2025.073172

Received 12 September 2025; Accepted 13 November 2025; Published online 28 November 2025

Abstract

With growing urban areas, the climate continues to change as a result of growing populations, and hence, the demand for better emergency response systems has become more important than ever. Human Behaviour Classification (HBC) systems have started to play a vital role by analysing data from different sources to detect signs of emergencies. These systems are being used inmany critical areas like healthcare, public safety, and disastermanagement to improve response time and to prepare ahead of time. But detecting human behaviour in such stressful conditions is not simple; it often comes with noisy data, missing information, and the need to react in real time. This review takes a deeper look atHBCresearch published between 2020 and 2025 and aims to answer five specific research questions.These questions cover the types of emergencies discussed in the literature, the datasets and sensors used, the effectiveness of machine learning (ML) and deep learning (DL) models, and the limitations that still exist in this field.We explored 120 papers that used different types of datasets, some were based on sensor data, others on social media, and a few used hybrid approaches. Commonly used models included CNNs, LSTMs, and reinforcement learning methods to identify behaviours.Though a lot of progress has been made, the review found ongoing issues in combining sensors properly, reacting fast enough, and using more diverse datasets. Overall, from the findings we observed, the focus should be on building systems that use multiple sensors together, gather real-time data on a large scale, and produce results that are easier to interpret. Proper attention to privacy and ethical concerns needs to be addressed as well.