Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Container damage during maritime transportation remains a critical challenge in global logistics, with over 10,000 containers lost or damaged annually resulting in billions of dollars in economic losses. Traditional threshold-based monitoring systems exhibit high false-positive rates and inability to classify impact severity, leading to alarm fatigue among maritime crews. This paper presents an end-to-end Machine Learning-based Container Crash Detection System that identifies and classifies crash events in real-time using synthetic accelerometer signal analysis. The proposed pipeline comprises five sequential stages: (i) physics-based signal generation with realistic sensor artifacts, (ii) time-domain feature extraction computing six statistical metrics, (iii) Random Forest ensemble classification into four ordinal impact classes, (iv) confidence-adjusted severity assessment with uncertainty modeling, and (v) interactive Streamlit dashboard with persistent event logging. The system achieves a weighted F1-score of 96.9% with 100% recall on Severe Crash events, inference latency under 10ms per window, and a modular architecture enabling future hardware integration. Unlike existing threshold-based approaches that yield ~70% accuracy with 8.5% false-positive rates, our ML-driven approach reduces false positives by 75% while providing multi-class severity classification.
Keywords:
Container Crash Detection, Maritime Safety, Random Forest, Internet of Things, Real-Time Monitoring, Structural Health Monitoring, Time-Domain Feature Engineering
Cite Article:
"Real-Time Container Crash Detection in Maritime Logistics Using Machine Learning and IoT Sensor Fusion", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 6, page no.a358-a364, June-2026, Available :http://www.ijrti.org/papers/IJRTI2606037.pdf
Downloads:
000122
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator