Personalized Fall Detection by Balancing Data with Selective Feedback Using Contrastive Learning

2026-03-17

AI Summary

This work addresses the challenge of insufficient sensitivity in personalized fall detection models, primarily caused by the scarcity of real-world fall data and the overwhelming dominance of non-fall samples. To mitigate this issue, the authors propose a selective feedback mechanism that integrates contrastive learning with semi-supervised clustering to identify high-informative samples from user interactions and achieve class balance. The framework supports efficient model adaptation across three learning paradigms: training from scratch, transfer learning, and few-shot learning. In real-time experiments involving ten participants, the approach substantially improves performance—boosting accuracy by up to 25% over baseline methods in from-scratch training and by 7% in few-shot scenarios—effectively alleviating extreme class imbalance and enhancing personalized fall detection capabilities.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Personalized fall detection models can significantly improve accuracy by adapting to individual motion patterns, yet their effectiveness is often limited by the scarcity of real-world fall data and the dominance of non-fall feedback samples. This imbalance biases the model toward routine activities and weakens its sensitivity to true fall events. To address this challenge, we propose a personalization framework that combines semi-supervised clustering with contrastive learning to identify and balance the most informative user feedback samples. The framework is evaluated under three retraining strategies, including Training from Scratch (TFS), Transfer Learning (TL), and Few-Shot Learning (FSL), to assess adaptability across learning paradigms. Real-time experiments with ten participants show that the TFS approach achieves the highest performance, with up to a 25% improvement over the baseline, while FSL achieves the second-highest performance with a 7% improvement, demonstrating the effectiveness of selective personalization for real-world deployment.

Problem

• personalized fall detection
• data imbalance
• fall data scarcity
• non-fall dominance
• model bias

Innovation

• contrastive learning
• personalized fall detection
• semi-supervised clustering
• selective feedback
• data imbalance