NapTune：利用前一晚睡眠指标与可穿戴时间序列进行情绪分类的高效模型微调
NapTune: Efficient Model Tuning for Mood Classification using Previous Night's Sleep Measures along with Wearable Time-series
AI总结：
提出 NapTune 提示微调框架，将前一晚睡眠指标注入冻结的可穿戴时间序列 Transformer 编码器，在 ECG、PPG、EDA 情绪分类中显著提升性能与样本效率。
摘要：
众所周知，睡眠是情绪调节和整体心理健康的关键因素。在本研究中，我们探索将前一晚的睡眠指标整合到基于可穿戴设备的情绪识别中。为此，我们提出了 NapTune，这是一种新颖的提示微调框架，通过向每个 Transformer 层添加并训练轻量级提示参数，将睡眠相关指标作为冻结的预训练可穿戴时间序列编码器的额外输入。通过严格的实证评估，我们证明使用 NapTune 纳入睡眠数据，不仅提升了 ECG、PPG 和 EDA 等不同可穿戴时间序列上的情绪识别性能，还提高了样本效率。我们的方法相较最佳基线和单模态变体表现出显著改进。此外，我们分析了加入睡眠相关指标对识别不同情绪的影响，以及各项睡眠相关指标的作用。
英文摘要：
Sleep is known to be a key factor in emotional regulation and overall mental health. In this study, we explore the integration of sleep measures from the previous night into wearable-based mood recognition. To this end, we propose NapTune, a novel prompt-tuning framework that utilizes sleep-related measures as additional inputs to a frozen pre-trained wearable time-series encoder by adding and training lightweight prompt parameters to each Transformer layer. Through rigorous empirical evaluation, we demonstrate that the inclusion of sleep data using NapTune not only improves mood recognition performance across different wearable time-series namely ECG, PPG, and EDA, but also makes it more sample-efficient. Our method demonstrates significant improvements over the best baselines and unimodal variants. Furthermore, we analyze the impact of adding sleep-related measures on recognizing different moods as well as the influence of individual sleep-related measures.
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。
