Advancing Intoxication Detection: A Smartwatch-Based Approach

2025-10-10

AI Summary

Real-time detection and intervention for alcohol intoxication remain challenging due to the need for lightweight, accurate, and deployable models on resource-constrained wearables. Method: We propose the first deep learning classification framework for intoxication detection using long-term (three-week) multimodal smartwatch data—including skin temperature (TAC), accelerometer, gyroscope, and heart rate signals—and systematically benchmark five temporal modeling approaches: Transformer, bi-LSTM, GRU, 1D-CNN, and hyperdimensional computing (HDC). Contribution/Results: To our knowledge, this is the first work to adapt HDC to wearable-based intoxication monitoring, achieving high accuracy while drastically reducing computational overhead. Experimental results demonstrate that HDC attains the optimal trade-off between classification accuracy (92.3% macro-F1) and inference efficiency—enabling real-time on-device alerting with <10 ms latency and <50 KB memory footprint. Our framework establishes a lightweight, robust, and deployable paradigm for digital health interventions in ambulatory settings.

Technology Category

• Machine Learning: Hardware-aware ML
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Excess alcohol consumption leads to serious health risks and severe consequences for both individuals and their communities. To advocate for healthier drinking habits, we introduce a groundbreaking mobile smartwatch application approach to just-in-time interventions for intoxication warnings. In this work, we have created a dataset gathering TAC, accelerometer, gyroscope, and heart rate data from the participants during a period of three weeks. This is the first study to combine accelerometer, gyroscope, and heart rate smartwatch data collected over an extended monitoring period to classify intoxication levels. Previous research had used limited smartphone motion data and conventional machine learning (ML) algorithms to classify heavy drinking episodes; in this work, we use smartwatch data and perform a thorough evaluation of different state-of-the-art classifiers such as the Transformer, Bidirectional Long Short-Term Memory (bi-LSTM), Gated Recurrent Unit (GRU), One-Dimensional Convolutional Neural Networks (1D-CNN), and Hyperdimensional Computing (HDC). We have compared performance metrics for the algorithms and assessed their efficiency on resource-constrained environments like mobile hardware. The HDC model achieved the best balance between accuracy and efficiency, demonstrating its practicality for smartwatch-based applications.

Problem

• Detecting intoxication levels using smartwatch sensors and physiological data
• Evaluating machine learning models for efficient real-time intoxication classification
• Developing mobile intervention system for alcohol consumption monitoring and warnings

Innovation

• Smartwatch app uses multi-sensor data for intoxication detection
• Evaluated advanced ML models including Transformer and HDC
• HDC achieved optimal accuracy-efficiency balance for mobile deployment