AI-Driven Personal Item & Crime Pattern Tracker for Bangladeshi Consumers

DOI

10.2991/978-94-6239-664-7_68How to use a DOI?

Keywords

AI-driven Item Tracking; IoT-enabled Crime Detection; Bluetooth Low Energy (BLE); GPS-based Localization; Machine Learning for Theft Prediction

Abstract

Theft and loss of personal belongings continue to be a grievous problem in Bangladesh, more so in heavily populated cities like Dhaka and Chittagong. Most of the tracking solutions are either expensive, fragmented, or poorly suited to the local infrastructure and user behaviors of this region. This paper proposes an AI-driven personal item and crime-pattern tracking framework that integrates low-cost IoT devices with machine learning-based recovery prediction and hotspot analysis. A unified data preprocessing and annotation pipeline was developed by combining user-reported incidents, crowdsourced validations, and police-record data. Multiple models have been trained and tested: K-Nearest Neighbors, Support Vector Machine, Multi-Layer Perceptron, Decision Tree, Random Forest, and XGBoost. Ensemble methods yielded accuracy of more than 93% across accuracy, precision, recall, F1-score, and ROC-AUC metrics. The system is complemented by an economical IoT tracker card integrated with BLE, GPS, motion sensing, and mobile connectivity for real-time alerts, geofencing, and last seen location tracking. Overall, the proposed AIoT solution provides a cost-effective, scalable, and privacy-aware framework suitable for enhancing personal security and facilitating data-driven crime prevention in Bangladesh.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nushrat Jahan Mila
AU  - Abdullah Al Noman
AU  - Tanvirul Islam
AU  - Dipta Chandra Banik
AU  - Abrar Hameem Bornil
AU  - Faria Khan
PY  - 2026
DA  - 2026/06/08
TI  - AI-Driven Personal Item & Crime Pattern Tracker for Bangladeshi Consumers
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 994
EP  - 1008
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_68
DO  - 10.2991/978-94-6239-664-7_68
ID  - Mila2026
ER  -