DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignals
cs.AI
Submitted: 2025-12-09
Updated: 2026-09-14
Code: https://github.com/Mobile-Sensing-and-UbiComp-Laboratory/NormWear
Project page: https://facebookresearch.github.io/Kats
License: http://creativecommons.org/licenses/by/4.0/
The gist: Biosignals collected from wearable devices are widely utilized in healthcare applications.
Terminology
Abstract
Biosignals collected from wearable devices are widely utilized in healthcare applications. Machine learning models used in these applications often rely on features extracted from biosignals due to their effectiveness, lower data dimensionality, and wide compatibility across various model architectures. However, existing feature extraction methods often lack task-specific contextual knowledge, struggle to identify optimal features in high-dimensional combinatorial feature space, and are prone to automated code generation and execution errors. In this paper, we propose DeepFeature, the first LLM-empowered, context-aware feature generation framework for wearable biosignals. DeepFeature introduces a multi-source feature generation mechanism that integrates the inherent ability of LLMs, expert knowledge and inter-feature interactions. It also employs an iterative feature refinement process that uses feature assessment-based feedback for feature re-selection. Additionally, DeepFeature utilizes a robust multi-layer filtering and verification approach for feature description-to-code translation to ensure that the feature extraction functions run without crashing. Experimental evaluation results show that DeepFeature achieves the highest average AUROC across eight tasks under both sample-level and subject-level settings, outperforming the best baselines by 4.60% and 4.61%, respectively. DeepFeature achieves the most pronounced gains on the PPG-BP tasks, while remaining competitive with the best-performing baselines on Epilepsy, WESAD, and our self-collected SEN dataset.
Sources
- Language Models are Symbolic Learners in Arithmetic
- OpenTCM: A GraphRAG-Empowered LLM-based System for Traditional Chinese Medicine Knowledge Retrieval and Diagnosis
- LLM-Select: Feature Selection with Large Language Models
- SMARTFEAT: Efficient Feature Construction through Feature-Level Foundation Model Interactions
- DeepSeek-V3 Technical Report
- Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals
- Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
- Kimi K2: Open Agentic Intelligence
- Qwen2 Technical Report
- Dynamic and Adaptive Feature Generation with LLM
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection