Citation

Suliman, Khairul Rizuan and Abeykoon, Abeykoon Mudiyanselage Akila Thenuka (2026) Detecting Rough Handling Events in Parcel Transportation using Unsupervised Learning. Journal of Engineering Technology and Applied Physics, 8 (2). p. 134. ISSN 2682-8383

Text View of Detecting Rough Handling Events in Parcel Transportation using Unsupervised Learning.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

The growth of e-commerce has intensified the impact of parcel damage caused by mishandling during transit. The study proposes an unsupervised anomaly detection to identify real time abnormal events during parcel transit using low cost inertial sensor data from a consumer grade smartphone embedded within a parcel. Data was collected for manual parcel handling, motorcycle, and vehicular transport under ‘normal’ and ‘rough’ handling conditions. Data collected in ‘normal’conditions were used to train IForest and LSTM Autoencoder unsupervised models, and they were evaluated on parcel handling data collected on ‘rough’ conditions. Precision, recall, F1-Score, and False Positives Rate (FPR) metrics were used to assess model performance, and results indicated that both models effectively detect anomalies for manual and motorcycle handling, but report lower performance in vehicular transportation. The study contributes to the body of knowledge by demonstrating the feasibility of using smartphone-based inertial sensing for parcel monitoring and byproviding a comparative evaluation of classical (IForest) and deep learning (LSTM Autoencoder) anomaly detection approaches across multiple transport modes.Overall, IForest reported more robust and consistent performance across heterogeneous transport modes, while LSTM Autoencoder achieved a lower FPR in contexts with sustained temporal irregularities. Both highlight the feasibility of utilizing unsupervised anomaly detection for parcel monitoring in complex freight transportationenvironments.

Item Type:	Article
Uncontrolled Keywords:	Parcel handling, unsupervised anomaly detection
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	12 Oct 2026 03:28
Last Modified:	12 Oct 2026 03:28
URII:	http://shdl.mmu.edu.my/id/eprint/16903

Downloads

Edit (login required)