基于智能手机感知数据的心理压力评估方法
|
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.
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.
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.
引文
[1]America College Health Association. Fall 2015 reference group executive summary[EB/OL]. 2015 [2017-01-23]. https://www.acha.org/documents/ncha/NCHA-II_FALL_2017_REFERENCE_GROUP_EXECUTIVE_SUMMARY.pdf
[2]Kirsten S. Statistics on college student stress[EB/OL]. 2015 [2017-01-23]. http://stress.lovetoknow.com/Statistics_on_College_Student_Stress
[3]Selye H. Stress in Health and Disease[M]. Oxford: Butterworth-Heinemann, 1974
[4]Kahneman D, Tursky B, Shapiro D, et al. Pupillary, heart rate, and skin resistance changes during a mental task[J]. Journal of Experimental Psychology, 1969, 79(1): 164- 167
[5]Wang Rui, Chen Fanglin, Chen Zhenyu, et al. StudentLife: Assessing mental health, academic performance and behavioral trends of college students using smartphones[C] //Proc of the 2014 ACM Conf on Ubiquitous Computing. NewYork: ACM, 2014: 3- 14
[6]Hetz C, Martinon F, Rodriguez D, et al. The unfolded protein response: Integrating stress signals through the stress sensor IRE1α[J]. Physiological Reviews, 2011, 91(4): 1219- 1243
[7]Healey J A, Picard R W. Detecting stress during real-world driving tasks using physiological sensors[J]. IEEE Transactions on Intelligent Transportation Systems, 2005, 6(2): 156- 166
[8]Mozos M, Sandulescu V, Andrews S. Stress detection using wearable physiological and sociometric sensors[J]. International Journal of Neural Systems, 2017, 27(2): 1- 17
[9]Lu Hong, Frauendorfer D, Rabbi M, et al. StressSense: Detecting stress in unconstrained acoustic environments using smartphones[C] //Proc of the 2012 ACM Conf on Ubiquitous Computing. New York: ACM, 2012: 351- 360
[10]Lin Huijie, Jia Jia, Guo Quan, et al. Psychological stress detection from cross-media microblog data using deep sparse neural network[C] //Proc of the 2014 IEEE Int Conf on Multimedia and Expo. Piscataway, NJ: IEEE, 2014: 1- 6
[11]Lin Huijie, Jia Jia, Guo Quan, et al. User-level psychological stress detection from social media using deep neural network[C] //Proc of the 22nd ACM Int Conf on Multimedia. New York: ACM, 2014: 507- 516
[12]Xue Yuanyuan, Li Qi, Jin Li, et al. Detecting adolescent psychological pressures from micro-blog[G] //LNCS 8423: Proc of the 3rd Int Conf on Health Information Science. Berlin: Springer, 2014: 83- 94
[13]Jin Li, Xue Yuanyuan, Li Qi, et al. Integrating human mobility and social media for adolescent psychological stress detection[G] //LNCS 9643: Proc of the 21st Int Conf on Database Systems for Advanced Applications. Berlin: Springer, 2016: 367- 382
[14]Chen Longbiao, Li Shijian, Pan Gang. Smartphone:Pervasive sensing and applications[J]. Chinese Journal of Computers, 2015, 38(2): 423- 438 (in Chinese)(陈龙彪, 李石坚, 潘纲. 智能手机:普适感知与应用[J]. 计算机学报, 2015, 38(2): 423- 438)
[15]Mehrotra A, Pejovic V, Vermeulen J, et al. My phone and me: Understanding people’s receptivity to mobile notifi-cations[C] //Proc of the 2016 CHI Conf on Human Factors in Computing Systems. New York: ACM, 2016: 1021- 1032
[16]Xiong Haoyi, Huang Yu, Barnes L E, et al. Sensus: A cross-platform, general-purpose system for mobile crowd-sensing in human-subject studies[C] //Proc of the 2016 ACM Int Joint Conf on Pervasive and Ubiquitous Computing. New York: ACM, 2016: 415- 426
[17]Canzian L, Musolesi M. Trajectories of depression: Unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis[C] //Proc of the 2015 ACM Int Joint Conf on Pervasive and Ubiquitous Computing. New York: ACM, 2015: 1293- 1304
[18]Lu Hong, Frauendorfer D, Rabbi M, et al. StressSense: Detecting stress in unconstrained acoustic environments using smartphones[C] //Proc of the 2012 ACM Conf on Ubiquitous Computing. New York: ACM, 2012: 351- 360
[19]Bogomolov A, Lepri B, Ferron M, et al. Daily stress recognition from mobile phone data, weather conditions and individual traits[C] //Proc of the 22nd ACM Int Conf on Multimedia. New York: ACM, 2014: 477- 486
[20]Wang Rui, Harari G, Hao Peilin, et al. SmartGPA: How smartphones can assess and predict academic performance of college students[C] //Proc of the 2015 ACM Int Joint Conf on Pervasive and Ubiquitous Computing. New York: ACM, 2015: 295- 306
[21]Shiffman S, Stone A, Hufford R. Ecological momentary assessment[J]. Annual Review of Clinical Psychology, 2008, 4: 1- 32
[22]Lu Hong, Yang Jun, Liu Zhigang, et al. The Jigsaw continuous sensing engine for mobile phone applications[C] //Proc of the 8th ACM Conf on Embedded Networked Sensor Systems. New York: ACM, 2010: 71- 84
[23]Zheng Yu, Liu Furui, Hsieh P. U-air: When urban air quality inference meets big data[C] //Proc of the 19th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2013: 1436- 1444
[24]Blum A, Mitchell T. Combining labeled and unlabeled data with co-training[C] //Proc of the 11th Annual Conf on Computational Learning Theory. New York: ACM, 1998: 92- 100
[2]Kirsten S. Statistics on college student stress[EB/OL]. 2015 [2017-01-23]. http://stress.lovetoknow.com/Statistics_on_College_Student_Stress
[3]Selye H. Stress in Health and Disease[M]. Oxford: Butterworth-Heinemann, 1974
[4]Kahneman D, Tursky B, Shapiro D, et al. Pupillary, heart rate, and skin resistance changes during a mental task[J]. Journal of Experimental Psychology, 1969, 79(1): 164- 167
[5]Wang Rui, Chen Fanglin, Chen Zhenyu, et al. StudentLife: Assessing mental health, academic performance and behavioral trends of college students using smartphones[C] //Proc of the 2014 ACM Conf on Ubiquitous Computing. NewYork: ACM, 2014: 3- 14
[6]Hetz C, Martinon F, Rodriguez D, et al. The unfolded protein response: Integrating stress signals through the stress sensor IRE1α[J]. Physiological Reviews, 2011, 91(4): 1219- 1243
[7]Healey J A, Picard R W. Detecting stress during real-world driving tasks using physiological sensors[J]. IEEE Transactions on Intelligent Transportation Systems, 2005, 6(2): 156- 166
[8]Mozos M, Sandulescu V, Andrews S. Stress detection using wearable physiological and sociometric sensors[J]. International Journal of Neural Systems, 2017, 27(2): 1- 17
[9]Lu Hong, Frauendorfer D, Rabbi M, et al. StressSense: Detecting stress in unconstrained acoustic environments using smartphones[C] //Proc of the 2012 ACM Conf on Ubiquitous Computing. New York: ACM, 2012: 351- 360
[10]Lin Huijie, Jia Jia, Guo Quan, et al. Psychological stress detection from cross-media microblog data using deep sparse neural network[C] //Proc of the 2014 IEEE Int Conf on Multimedia and Expo. Piscataway, NJ: IEEE, 2014: 1- 6
[11]Lin Huijie, Jia Jia, Guo Quan, et al. User-level psychological stress detection from social media using deep neural network[C] //Proc of the 22nd ACM Int Conf on Multimedia. New York: ACM, 2014: 507- 516
[12]Xue Yuanyuan, Li Qi, Jin Li, et al. Detecting adolescent psychological pressures from micro-blog[G] //LNCS 8423: Proc of the 3rd Int Conf on Health Information Science. Berlin: Springer, 2014: 83- 94
[13]Jin Li, Xue Yuanyuan, Li Qi, et al. Integrating human mobility and social media for adolescent psychological stress detection[G] //LNCS 9643: Proc of the 21st Int Conf on Database Systems for Advanced Applications. Berlin: Springer, 2016: 367- 382
[14]Chen Longbiao, Li Shijian, Pan Gang. Smartphone:Pervasive sensing and applications[J]. Chinese Journal of Computers, 2015, 38(2): 423- 438 (in Chinese)(陈龙彪, 李石坚, 潘纲. 智能手机:普适感知与应用[J]. 计算机学报, 2015, 38(2): 423- 438)
[15]Mehrotra A, Pejovic V, Vermeulen J, et al. My phone and me: Understanding people’s receptivity to mobile notifi-cations[C] //Proc of the 2016 CHI Conf on Human Factors in Computing Systems. New York: ACM, 2016: 1021- 1032
[16]Xiong Haoyi, Huang Yu, Barnes L E, et al. Sensus: A cross-platform, general-purpose system for mobile crowd-sensing in human-subject studies[C] //Proc of the 2016 ACM Int Joint Conf on Pervasive and Ubiquitous Computing. New York: ACM, 2016: 415- 426
[17]Canzian L, Musolesi M. Trajectories of depression: Unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis[C] //Proc of the 2015 ACM Int Joint Conf on Pervasive and Ubiquitous Computing. New York: ACM, 2015: 1293- 1304
[18]Lu Hong, Frauendorfer D, Rabbi M, et al. StressSense: Detecting stress in unconstrained acoustic environments using smartphones[C] //Proc of the 2012 ACM Conf on Ubiquitous Computing. New York: ACM, 2012: 351- 360
[19]Bogomolov A, Lepri B, Ferron M, et al. Daily stress recognition from mobile phone data, weather conditions and individual traits[C] //Proc of the 22nd ACM Int Conf on Multimedia. New York: ACM, 2014: 477- 486
[20]Wang Rui, Harari G, Hao Peilin, et al. SmartGPA: How smartphones can assess and predict academic performance of college students[C] //Proc of the 2015 ACM Int Joint Conf on Pervasive and Ubiquitous Computing. New York: ACM, 2015: 295- 306
[21]Shiffman S, Stone A, Hufford R. Ecological momentary assessment[J]. Annual Review of Clinical Psychology, 2008, 4: 1- 32
[22]Lu Hong, Yang Jun, Liu Zhigang, et al. The Jigsaw continuous sensing engine for mobile phone applications[C] //Proc of the 8th ACM Conf on Embedded Networked Sensor Systems. New York: ACM, 2010: 71- 84
[23]Zheng Yu, Liu Furui, Hsieh P. U-air: When urban air quality inference meets big data[C] //Proc of the 19th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining. New York: ACM, 2013: 1436- 1444
[24]Blum A, Mitchell T. Combining labeled and unlabeled data with co-training[C] //Proc of the 11th Annual Conf on Computational Learning Theory. New York: ACM, 1998: 92- 100