超越Lux阈值:从可穿戴数据中系统性分类生物相关光照情境的管道
Beyond Lux thresholds: a systematic pipeline for classifying biologically relevant light contexts from wearable data
AI总结:
本文提出了一种可复现的流程和设计规则,用于从可穿戴数据中区分自然光与人工光,通过光谱-时间建模超越传统照度阈值。
摘要:
背景:可穿戴光谱仪能够实现野外对生物相关光照的量化测量,但可复现的上下文分类流程仍缺乏明确的规范。目标:建立并验证一个经过受试者评估的、可复现的流程和可操作的设计规则,用于从可穿戴光谱数据中区分自然光与人工光。方法:我们分析了26名参与者的数据,每人至少连续监测7天,采样间隔为10秒,同时配对每日暴露日记。该流程固定了以下步骤:领域选择、以10为底的对数变换、L2归一化(排除总强度以避免亮度捷径)、小时级的中位数聚合、正弦/余弦小时编码以及MLP分类器,并在受试者层面进行交叉验证。结果:所提出的流程在主要任务上始终表现出高性能,代表性配置在保留的受试者分割上达到AUC=0.938(准确率88%)用于自然光与人工光的分类。相比之下,室内与户外分类仍处于可行性水平,由于光谱重叠和类别不平衡(最佳AUC约为0.75;多数类崩溃无上下文传感器)。阈值基线在我们的数据上表现不足,支持了在照度截止值之外需要光谱-时间建模的必要性。结论:我们提供了一个可复现、可审计的基线流程和设计规则,用于在受试者层面的上下文光分类。所有代码、配置文件和衍生成果将被公开存档(GitHub + Zenodo DOI)以支持重用和基准测试。
英文摘要:
Background: Wearable spectrometers enable field quantification of biologically relevant light, yet reproducible pipelines for contextual classification remain under-specified. Objective: To establish and validate a subject-wise evaluated, reproducible pipeline and actionable design rules for classifying natural vs. artificial light from wearable spectral data. Methods: We analysed ActLumus recordings from 26 participants, each monitored for at least 7 days at 10-second sampling, paired with daily exposure diaries. The pipeline fixes the sequence: domain selection, log-base-10 transform, L2 normalisation excluding total intensity (to avoid brightness shortcuts), hour-level medoid aggregation, sine/cosine hour encoding, and MLP classifier, evaluated under participant-wise cross-validation. Results: The proposed sequence consistently achieved high performance on the primary task, with representative configurations reaching AUC = 0.938 (accuracy 88%) for natural vs. artificial classification on the held-out subject split. In contrast, indoor vs. outdoor classification remained at feasibility level due to spectral overlap and class imbalance (best AUC approximately 0.75; majority-class collapse without contextual sensors). Threshold baselines were insufficient on our data, supporting the need for spectral-temporal modelling beyond illuminance cut-offs. Conclusions: We provide a reproducible, auditable baseline pipeline and design rules for contextual light classification under subject-wise generalisation. All code, configuration files, and derived artefacts will be openly archived (GitHub + Zenodo DOI) to support reuse and benchmarking.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。