• Mrs.R.Dhanalakshmi
• Dinesh kumar, C
• Kalanithi, V
• Prashanth ,E
• G.Varadharaja Perumal

The conventional methods utilizing Graph Convolutional Network (GCN) and 3D Convolutional Neural Network (3DCNN) algorithms have been instrumental, but their limitations impede their efficacy in dealing with the nuanced complexities of real-world scenarios. Our proposed system introduces Transfer Learning, leveraging pre-trained models to adapt efficiently to limited data, crucial in abnormal behaviour detection. Combining this with the YOLO algorithm revolutionizes object detection, processing entire images in one go for enhanced speed and accuracy. This integration significantly improves real-time abnormal behaviour detection in public spaces, crucial for the safety of individuals with mental disorders and those around them. By mitigating potential harm through precise detection, our system contributes to robust public safety solutions. Its implementation marks a milestone in addressing complex challenges associated with abnormal behaviour, promising more effective and adaptive solutions for public safety.

Transfers Learning (TL), Convolutional Networks and YOLO.

"ARTIFICIAL INTELLIGENCE USAGE IN ANAYSIS OF ANOMALIES IN CROWD INVOLVING INDIVIDUAL WITH MENTAL DISORDER", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 7, page no.h252-h256, July-2022, Available :http://www.jetir.org/papers/JETIR2207740.pdf

"ARTIFICIAL INTELLIGENCE USAGE IN ANAYSIS OF ANOMALIES IN CROWD INVOLVING INDIVIDUAL WITH MENTAL DISORDER", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 7, page no. pph252-h256, July-2022, Available at : http://www.jetir.org/papers/JETIR2207740.pdf