Designing an Intelligent Parcel Management System using IoT & Machine Learning
Mohit Gupta, Nitesh Garg, Jai Garg, Vansh Gupta, Devraj Gautam
TL;DR
The paper tackles safe and efficient parcel handling in railways by proposing an IoT-enabled two-phase system that combines scanning (RFID entry, metal detection, X-ray imaging, and IR-based explosive detection) with ML-driven interpretation and a sorting phase guided by weight, dimensions, and destination. A CNN-based image analysis component processes X-ray data, while IR thermography aids explosive/drug detection; QR codes and RFID tags enable robust tracking and routing. Real-time parcel tracking is supported via a web interface and Firebase, with Blender-based simulation used for validation. The results show favorable per-class detection metrics and an overall accuracy near 0.891, suggesting meaningful improvements over prior methods in reducing manual inspection and increasing throughput. The integrated solution promises safer, faster, and more cost-effective parcel management in large-scale rail networks and related applications.
Abstract
Parcels delivery is a critical activity in railways. More importantly, each parcel must be thoroughly checked and sorted according to its destination address. We require an efficient and robust IoT system capable of doing all of these tasks with great precision and minimal human interaction. This paper discusses, We created a fully-fledged solution using IoT and machine learning to assist trains in performing this operation efficiently. In this study, we covered the product, which consists mostly of two phases. Scanning is the first step, followed by sorting. During the scanning process, the parcel will be passed through three scanners that will look for explosives, drugs, and any dangerous materials in the parcel and will trash it if any of the tests fail. When the scanning step is over, the parcel moves on to the sorting phase, where we use QR codes to retrieve the details of the parcels and sort them properly. The simulation of the system is done using the blender software. Our research shows that our procedure significantly improves accuracy as well as the assessment of cutting-edge technology and existing techniques.