International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 2

Research Paper | Computer Science | Volume 15 Issue 4, April 2026 | Pages: 1609 - 1613 | India


SensAI: Intelligent Human Behaviour Analytics and Prediction System Using Activity Sequences, Machine Learning, and Temporal Modeling

Midhun T Manoj, Preethi Thomas

Abstract: SensAI is an intelligent human behaviour analytics and prediction system designed to analyze human activity patterns and predict future activities using machine learning and temporal sequence modeling. The system processes human activity data obtained from activity recognition datasets and applies machine learning algorithms such as Random Forest for activity classification. Sequential activity patterns are analyzed using transition probability matrices based on Markov Chain models to predict the next activity. The system also generates behavioural insights such as productivity score, routine stability, and inactivity index. Developed using Python, Django, Scikit-learn, and SQLite, the system provides a web-based platform for activity analysis, behaviour prediction, and visualization. The proposed system demonstrates how activity recognition and temporal modeling can be integrated to build intelligent behaviour analysis systems. Experimental results show that the system achieves an accuracy of 90% and an AUC of 0.91, demonstrating strong performance in both classification and prediction tasks.

Keywords: Human Activity Recognition, Behaviour Prediction, Machine Learning, Markov Chain, Activity Analytics

How to Cite?: Midhun T Manoj, Preethi Thomas, "SensAI: Intelligent Human Behaviour Analytics and Prediction System Using Activity Sequences, Machine Learning, and Temporal Modeling", Volume 15 Issue 4, April 2026, International Journal of Science and Research (IJSR), Pages: 1609-1613, https://www.ijsr.net/getabstract.php?paperid=SR26421231500, DOI: https://dx.dx.doi.org/10.21275/SR26421231500

Download Citation: APA | MLA | BibTeX | EndNote | RefMan


Download Article PDF


Rate This Article!


Top