Copyright © 2025 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{171566,
        author = {Adithi D J and Ms. Sonia K P and Alfaz Hamad Razak and Deeksha B Devadiga and Kavitha V Poojary},
        title = {VIOLENCE DETECTION USING MACHINE LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {547-550},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171566},
        abstract = {The increasing prevalence of violence in public and private spaces necessitates the development of efficient, automated detection systems to ensure safety and timely intervention. This research explores the use of machine learning techniques for detecting violent behavior in video feeds, with applications in security and surveillance systems. A comprehensive dataset comprising diverse real-world scenarios is utilized to train and evaluate models. The proposed system utilizes a combination of deep learning architectures, which include CNNs for spatial feature extraction and RNNs for temporal behavior analysis. Data augmentation and transfer learning are used to mitigate the effects of data scarcity and variability. Experimental results demonstrate high accuracy in distinguishing violent from non-violent activities with promising real-time performance. The system is adaptable and scalable, so it is robust for smart cities, public safety, and private security systems' deployment. This research contribution advances the state-of-the-art in violence detection, pointing out the importance of applying machine learning in practical life-saving applications.},
        keywords = {Violence detection, machine learning, deep learning, Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), spatial feature extraction, temporal behavior analysis, data augmentation, transfer learning, real-time performance, security and surveillance, smart cities, public safety.},
        month = {January},
        }