Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195253,
        author = {VUNA VENKATA VIDYASAGAR and M. SRI PRANATHI and P. ALEKHYA and P. KARTHEEK and M. LEPAKSHI KUMAR},
        title = {AUTONMOUS CRIME ACTIVITY PATTERN PREDICTION USING ML ALGORITHMS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {7653-7664},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195253},
        abstract = {Crime detection and prevention have become critical concerns in modern society, requiring innovative technological solutions to enhance public safety. This project presents an Autonomous Crime Activity Pattern Prediction System using Machine Learning Algorithms, designed to automatically detect and classify criminal activities from image data in real-time. The system employs sophisticated dual-model architecture combining state-of-the-art deep learning techniques. The primary component utilizes YOLOv8 (You Only Look Once version 8) for object detection, capable of identifying 19+ crime-related objects including weapons (guns, knives, crowbars), violence indicators (blood, fights, injured persons), crime scene evidence (dead bodies, broken glass), and suspicious activities (masked individuals, vandalism). The secondary component implements EfficientNet-B0 for scene classification, categorizing images into six distinct contexts: violence, robbery, animal attacks, accidents, vandalism, and safe environments. Gray Level Co-occurrence Matrix (GLCM) for texture- based pattern recognition. A novel risk assessment algorithm integrates the outputs from both models to generate comprehensive threat analysis, assigning risk levels from 0 (Safe) to 4 (Emergency) based on detected objects, scene context, and predefined alert rules.},
        keywords = {YoloV8, Efficient-Net, GLCM, Django, DMU},
        month = {March},
        }