PixleepFlow: A Pixel-Based Lifelog Framework for Predicting Sleep Quality and Stress Level
Younghoon Na, Seunghun Oh, Seongji Ko, Hyunkyung Lee
TL;DR
PixleepFlow tackles predicting sleep quality and stress level from everyday lifelog data by converting synchronized multimodal sensor streams into composite images for joint multi-label classification of seven life-quality indicators. The approach is evaluated against raw and spectrogram representations, with image-based inputs (especially 11-channel composites) achieving the highest F1 scores (e.g., ≈0.746), while Full-CAM-based XAI provides visual explanations of which sensors drive predictions. The study highlights the importance of data synchronization, channel selection, and image-based representations for robust, interpretable health monitoring, though it is limited by small sample sizes and overfitting risk, prompting future work on broader sensor sets and real-world validation.
Abstract
The analysis of lifelogs can yield valuable insights into an individual's daily life, particularly with regard to their health and well-being. The accurate assessment of quality of life is necessitated by the use of diverse sensors and precise synchronization. To rectify this issue, this study proposes the image-based sleep quality and stress level estimation flow (PixleepFlow). PixleepFlow employs a conversion methodology into composite image data to examine sleep patterns and their impact on overall health. Experiments were conducted using lifelog datasets to ascertain the optimal combination of data formats. In addition, we identified which sensor information has the greatest influence on the quality of life through Explainable Artificial Intelligence(XAI). As a result, PixleepFlow produced more significant results than various data formats. This study was part of a written-based competition, and the additional findings from the lifelog dataset are detailed in Section Section IV. More information about PixleepFlow can be found at https://github.com/seongjiko/Pixleep.