Clustering-Based Segmentation of Off-Road Vehicle Activity into Productive and Non-Productive States from GPS Data

Accurate identification of Productive and Non-Productive States or Off-Road vehicle duty cycles—comprising working, idle, and transport states—is critical for performance analysis, fuel optimization, and emissions modeling in agriculture machinery and fleet operations. This study explores the application of unsupervised machine learning techniques to classify duty cycles using GPS-derived parameters such as speed, location variance, and temporal patterns. Unlike supervised approaches, the proposed method does not rely on labeled datasets, making it scalable and adaptable across diverse operational contexts. Clustering algorithms, including K-means and DBSCAN, are employed to segment GPS data into distinct behavioral states. Feature engineering focuses on extracting motion signatures and spatial-temporal features that correlate with operational modes. Validation against manually annotated datasets demonstrates high accuracy in distinguishing idle, working, and transport phases. The present methodology is also compared with other methods including ML algorithms of finding duty cycle. The framework offers a robust, data-driven solution for real-time duty cycle monitoring and can be integrated into telematics systems for predictive maintenance and operational efficiency for Off-Road vehicles. Keywords: Duty Cycle, Agriculture machinery, Machine Learning, DBSCAN