Passive Sensor Data Based Future Mood, Health, and Stress Prediction: User Adaptation Using Deep Learning

Passive Sensor Data Based Future Mood, Health, and Stress Prediction: User Adaptation Using Deep Learning
复制标题

基于被动传感器数据的未来情绪、健康和压力预测:使用深度学习进行用户适应

DOI:
10.1109/embc44109.2020.9176242
复制
发表时间:
2020
期刊:
IEEE Engineering Medicine Biology Conference 2020
影响因子:
--
通讯作者:
Sano, Akane
Sano, Akane
中科院分区:
--
文献类型:
--
作者:
Yu, Han;Sano, Akane

文献摘要

参考文献

被引文献

相似文献

预测一个人未来的情绪、健康和压力可能会在与健康相关的问题变得严重之前提供有用的反馈。此前,研究人员使用移动的和可穿戴传感器开发了依赖于参与者的健康预测模型,这些模型是用同一组人训练和测试的。然而,在实际应用中,必须考虑所开发的模型对新用户的适应性,以便立即准确地预测新用户的健康状况。在本文中,我们使用来自可穿戴传感器、移动的手机和天气API的被动感知数据以及深度学习方法构建了健康预测模型,并使用新用户的数据对模型进行了评估。我们比较了深度长短期记忆(LSTM)网络和卷积神经网络(CNN)与LSTM模型的组合。我们发现,我们的深度LSTM模型在预测新用户自我报告的情绪、健康和压力方面的平均绝对误差(MAE)分别为15.7、15.6和16.8。此外,我们应用了一种基于深度LSTM模型的微调迁移学习方法,为新参与者提供了更准确的预测,特别是当新参与者的数据量有限时。迁移学习模型将情绪、健康和压力的MAE表现分别提高到13.5、13.2和14.4分。
Predicting one's mood, health, and stress in the future may provide useful feedback before wellbeing related problems become severe. Previously, researchers developed participant-dependent wellbeing prediction models using mobile and wearable sensors, where the models were trained and tested with the same group of people. However, in real-world applications, it is essential to consider the adaptability of the developed models to new users for predicting new users' wellbeing immediately and accurately. In this paper, we built wellbeing prediction models using passively sensed data from wearable sensors, mobile phones, and weather API, and deep learning methods, and evaluated the models with the data from new users. We compared deep long short-term memory (LSTM) network and the combination of convolutional neural network (CNN) and the LSTM model. We found that our deep LSTM model provided performances, in mean absolute error (MAE), as 15.7, 15.6, and 16.8 out of 100 in predicting self-reported mood, health, and stress respectively for new users. Furthermore, we applied a fine-tuning transfer learning method based on our deep LSTM model, which provided new participants with more accurate predictions, especially when the volume of new participants' data was limited. The transfer learning model improved the MAE performances to 13.5, 13.2, and 14.4 out of 100 for mood, health, and stress, respectively.
使用 LSTM 神经网络改进学生日常生活压力预测
DOI: --
发表时间: 2019
期刊: IEEE-EMBS Biomedical and Health Informatics 2019
影响因子: --
作者:
Umematsu, T;Sano, A;Taylor, S;Picard, R.
通讯作者: Picard, R.
情绪健康及其与健康的关系
DOI: --
发表时间: 1998
影响因子: --
作者:
S. Stewart
通讯作者: S. Stewart
DOI: --
发表时间: 2015-02
期刊: --
影响因子: --
作者:
Ke Xu;Jimmy Ba;Ryan Kiros;Kyunghyun Cho;Aaron C. Courville;R. Salakhutdinov;R. Zemel;Yoshua Bengio-Yoshua-Ben
通讯作者: Ke Xu;Jimmy Ba;Ryan Kiros;Kyunghyun Cho;Aaron C. Courville;R. Salakhutdinov;R. Zemel;Yoshua Bengio-Yoshua-Ben
感知的压力水平可能会影响接受乳腺癌治疗的女性的上肢功能
DOI: --
发表时间: 2017
影响因子: 2.9
作者:
M. Fisher;A. Fleischer;K. Parent;R. Roberts;M. McClure;L. Hendricks
通讯作者: L. Hendricks
能够使用深度学习从面部照片中区分阿尔茨海默病
DOI: --
发表时间: 2020
期刊:
影响因子: --
作者:
Manabu Kokubo;Akihiro Hirashiki;Takahiro Kamihara;Atsuya Shimizu;Hidenori Arai;亀山祐美,亀山征史,深澤誠,飯塚友道,飯島勝矢,田中友規,矢可部満隆,小島太郎,小川純人,秋下雅弘
通讯作者: 亀山祐美,亀山征史,深澤誠,飯塚友道,飯島勝矢,田中友規,矢可部満隆,小島太郎,小川純人,秋下雅弘