Leveraging multi-source and heterogeneous signals for fatigue detection

2025-07-21

AI Summary

To address poor generalization and deployment challenges in real-world fatigue detection—caused by sensor heterogeneity and resource constraints—this paper proposes an adaptive cross-domain fusion framework for multi-source heterogeneous signals. Unlike conventional approaches, it requires neither modality alignment nor predefined sensor configurations; instead, it employs a learnable modality selection mechanism to dynamically adapt to available signals in the target domain and leverages cross-domain knowledge transfer to effectively exploit source-domain data collected under diverse sensor setups. Experiments on both real-world deployment environments and public benchmarks demonstrate that the method maintains high robustness under resource-constrained conditions (e.g., low power consumption, few signal channels), achieving an average 6.2% improvement in detection accuracy. Consequently, it significantly reduces reliance on expensive hardware and controlled laboratory settings, thereby enhancing practicality and generalizability of fatigue detection in automotive and wearable applications.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Fatigue detection plays a critical role in safety-critical applications such as aviation, mining, and long-haul transport. However, most existing methods rely on high-end sensors and controlled environments, limiting their applicability in real world settings. This paper formally defines a practical yet underexplored problem setting for real world fatigue detection, where systems operating with context-appropriate sensors aim to leverage knowledge from differently instrumented sources including those using impractical sensors deployed in controlled environments. To tackle this challenge, we propose a heterogeneous and multi-source fatigue detection framework that adaptively utilizes the available modalities in the target domain while benefiting from the diverse configurations present in source domains. Our experiments, conducted using a realistic field-deployed sensor setup and two publicly available datasets, demonstrate the practicality, robustness, and improved generalization of our approach, paving the practical way for effective fatigue monitoring in sensor-constrained scenarios.

Problem

• Detecting fatigue in real-world settings with limited sensors
• Leveraging multi-source data from varied sensor configurations
• Improving generalization for fatigue monitoring in constrained scenarios

Innovation

• Heterogeneous multi-source fatigue detection framework
• Adaptive utilization of available target modalities
• Improved generalization in sensor-constrained scenarios