ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2019, Vol. 56 ›› Issue (3): 611-622.doi: 10.7544/issn1000-1239.2019.20170809

• 人工智能 • 上一篇    下一篇



  1. 1(高可信软件技术教育部重点实验室(北京大学) 北京 100871); 2(北京大学信息科学技术学院 北京 100871); 3(北京大学软件工程国家工程研究中心 北京 100871); 4(密苏里科技大学计算机科学系 美国密苏里州罗拉 65409); 5(计算机网络和信息集成教育部重点实验室(东南大学) 南京 210018) (
  • 出版日期: 2019-03-01
  • 基金资助: 

Mental Stress Assessment Approach Based on Smartphone Sensing Data

Wang Feng1,2,5, Wang Yasha1,3, Wang Jiangtao1,2, Xiong Haoyi4, Zhao Junfeng1,2, Zhang Daqing1,2   

  1. 1(Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing 100871); 2(School of Electronics Engineering and Computer Science, Peking University, Beijing 100871); 3(National Research Center of Software Engineering, Peking University, Beijing 100871); 4(Department of Computer Science, Missouri University of Science and Technology, Rolla, MO, USA 65409); 5(Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, Nanjing 210018)
  • Online: 2019-03-01

摘要: 较大的心理压力对大学生的心理和生理均会产生危害.心理压力往往在前期容易被人忽视,从而导致严重的问题.因此,如果能较早发现心理压力,并进行合理干预,有益于人的身心健康.传统心理压力检测方法以问卷调查和借助专业设备的评估为主,但都存在成本较高,且对被评估对象侵扰较大等不足.另一方面,随着智能手机的快速普及,通过手机中内置的位置、声音、加速度等多种传感器感知用户的行为习惯,并基于感知数据评估用户心理压力成为一种低成本、低侵扰的心理压力评估手段.在此背景下,针对基于智能手机感知数据分析,对评估大学生心理压力的方法展开了研究,从感知数据中提取合理的特征,提出了一种更高效的心理压力评估方法.首先,讨论了如何从原始的手机感知数据提取出合理的特征;其次,介绍将心理压力评估转化为分类问题,并使用半监督学习方法构造分类模型;最后,在开放数据集StudentLife上对上述模型进行实验验证.实现结果表明:该方法在心理压力检测精确度和召回率等方面均优于基线方法.

关键词: 心理压力, 情境感知, 特征工程, 自动评估, 机器学习

Abstract: Mental stress is harmful on individuals’ physical and mental well-being. It is often easy to be overlooked in the early stage, leading to serious problems. Therefore, it is crucial to detect stress before it evolves into severe problems. Traditional stress detection methods are based on either questionnaires or professional devices, which are time-consuming, costly and intrusive. With the popularity of smartphones with various embedded sensors, which can capture users’ context data contains movement, sound, location and so on, it is an alternative way to access users’ behavior by smartphones, which is less intrusive. This paper proposes an automatic and non-intrusive stress detection approach based on mobile sensing data captured by smartphones. By extracting reasonable features from the perceived data, a more efficient psychological stress assessment method is proposed. First, we generate lots of features represent users’ behavior and explore the correlation between mobile sensing data and stress, then identify discriminative features. Second, we further develop a semi-supervised learning based stress detection model. Specifically, we use techniques such as co-training and random forest to deal with insufficient data. Finally, we evaluate our model based on the StudentLife dataset, and the experimental results verify the advantages of our approach over other baselines.

Key words: mental stress, context awareness, feature engineering, automatic detection, machine learning