<![CDATA[The rapid emergence of digital technologies and the increased of using intelligent devices have led to a significant increase in crime incidents. Therefore, there is an emerging need to develop highly accurate and efficient detection frameworks. Hence, this work introduces an intelligent drone-assisted crime-detection system based on a novel Puma Multilayer Perceptron Detection Framework. The images are collected from a Kaggle dataset. The image dataset is pre-processed in a Python environment, with image quality improved by removing noise and normalizing the images. Further, discriminative image features are selected by the Puma Optimization Algorithm. It efficiently selects the optimal features by balancing between detection accuracy and dimensionality reduction. The optimized feature set is then classified using a multilayer perceptron. All these processes aim to accurately detect criminal activities. The efficiency of the proposed model is evaluated using standard metrics, including accuracy, precision, recall, F-score, and error rate, and the results are compared with those of traditional detection approaches. The experimental results show that the proposed framework improves detection accuracy and reliability, making it effective for intelligent drone-based crime monitoring.]]>
Copyrights © 2026
