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{198801,
        author = {Tejas Gadge and Anisha Shankar and Ganesh Shelar and Deepak Kumbhar and Vedant Mhatre and Niraj Chaudhari and Mrs. Mannat Doultani},
        title = {Suraksha_Sakey - A Smart Keychain ensuring Safety for all ages},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {11629-11636},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198801},
        abstract = {Women’s safety is a significant global concern, with increasing cases of harassment and gender-based violence. Traditional safety solutions, such as mobile SOS applications and CCTV surveillance, rely on user intervention or passive monitoring, making them inefficient in real-time threat detection [1]. This paper presents Suraksha_Sakey, an AI-driven women’s safety system that integrates real-time anomaly detection, gesture-based SOS alerts, and crime hotspot mapping.  The system utilizes YOLOv3 for person detection [2], a CNN model for gender classification [3], and MobileNetV2 for gesture recognition. Additionally, an IoT-enabled smart keychain with GPS tracking extends safety measures to non-surveillance areas. The system has been tested on a dataset of over 10,000 images and real-world surveillance footage, achieving 92.5% accuracy in gesture recognition and 89% in gender classification by leveraging AI and predictive analytics, Suraksha_Sakey enhances proactive crime prevention and emergency response, ensuring swift action in distress situations [7].},
        keywords = {Women Safety, Convolutional Neural Networks, Smart Keychain,AI-based Surveillance, Gesture Recognition, Anomaly Detection},
        month = {April},
        }