International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Real‑Time Victim Audio Detection System using Machine Learning and Deep Learning |
|---|---|
| ABSTRACT | The increasing rise in violent crimes and emergency situations has emphasized the need for intelligent, automated safety systems capable of detecting distress in real time. This paper presents a Real‑Time Victim Audio Detection System that uses Machine Learning (ML) and Deep Learning (DL) methodologies to identify distress signals—particularly human screams—under varying environmental conditions. Audio features such as Mel‑Frequency Cepstral Coefficients (MFCC), Zero‑Crossing Rate (ZCR), and spectrogram representations are extracted from input audio streams and classified using a hybrid SVM–MLP architecture. Further, the system integrates automated alert mechanisms including SMS, email, and WhatsApp notifications with GPS-based location tracking. Experimental evaluation demonstrates a detection accuracy of 95.8%, precision of 96.3%, and an F1-score of 95.5%, confirming the robustness of the proposed model. The system provides an efficient, low-latency, real-time alerting framework that can significantly reduce response time during emergencies |
| AUTHOR | G.SIVA NAGA MALLESWARI, CH.NIROSHA |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311103 |
| pdf/103_Real‑Time Victim Audio Detection System using Machine Learning and Deep Learning.pdf | |
| KEYWORDS |
