AI-Based Mobile Application for Real-Time Criminal Event Recognition and Classification
Engineering, Technology & Applied Science Research · 2026-06-06 · 16 (3) · 35950-35961
DOI: 10.48084/etasr.17841 ↗At a glance
Journal article in Engineering, Technology & Applied Science Research, published online on 2026-06-06. Written by Rafael Cachique and 5 co-authors. 37 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
This paper proposes an Artificial Intelligence (AI)-based mobile application that identifies and categorizes crime and emergency events utilizing an acoustic and linguistic signals mechanism. The system combines Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) models with sound event detection architectures to process emergency call recordings and identify incidents such as robberies, assaults, and riots. Data training consisted of preprocessing more than 530 audio recordings of emergency calls made by the Peruvian National Police (PNP), in anonymized formats, and training deep learning models based on convolutional and transformer-based networks. The performance was evaluated using metrics such as precision, accuracy, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (AUC-ROC). The multimodal fusion model achieved high performance, demonstrating an accuracy of 86.79% and an AUC-ROC of 87.14%, strongly distinguishing between emergency and non-emergency conditions in various fields and noisy environments. The results of the study show that the proposed solution is highly reliable and responsive, presenting an opportunity to enhance urban security and inform public safety system decision-making.
Cite
APA
Cachique, R., Gutierrez, D., Castaneda, P., Wong-Durand, S., Acosta, R. C. S. C., & Garcia-Nunez, A. D. (2026). AI-Based Mobile Application for Real-Time Criminal Event Recognition and Classification. Engineering, Technology & Applied Science Research, 16(3), 35950-35961. https://doi.org/10.48084/etasr.17841
Vancouver
Cachique R, Gutierrez D, Castaneda P, Wong-Durand S, Acosta RCSC, Garcia-Nunez AD. AI-Based Mobile Application for Real-Time Criminal Event Recognition and Classification. Engineering, Technology & Applied Science Research. 2026;16(3):35950-35961. doi:10.48084/etasr.17841
BibTeX
@article{Cachique2026,
author = {Cachique, Rafael and Gutierrez, Diego and Castaneda, Pedro and Wong-Durand, Sandra and Acosta, Roberto Carlos Santa Cruz and Garcia-Nunez, Alberto Daniel},
title = {AI-Based Mobile Application for Real-Time Criminal Event Recognition and Classification},
journal = {Engineering, Technology & Applied Science Research},
year = {2026},
volume = {16},
number = {3},
pages = {35950--35961},
doi = {10.48084/etasr.17841}
}
EUVIMED