Abstract
Recent studies have shown the potential of exploiting GPS data for passively inferring people's mental health conditions. However, feature extraction for characterizing human mobility remains a heuristic process that relies on the domain knowledge of the condition under consideration. Moreover, we do not have guarantees that these "hand-crafted" metrics are able to effectively capture mobility behavior of users. Indeed, informative emerging patterns in the data might not be characterized by them. This is also a complex and often time-consuming task, since it usually consists of a lengthy trial-and-error process.
In this paper, we investigate the potential of using autoencoders for automatically extracting features from the raw input data. Through a series of experiments we show the effectiveness of autoencoder-based features for predicting depressive states of individuals compared to "hand-crafted" ones. Our results show that automatically extracted features lead to an improvement of the performance of the prediction models, while, at the same time, reducing the complexity of the feature design task. Moreover, through an extensive experimental performance analysis, we demonstrate the optimal configuration of the key parameters at the basis of the proposed approach.
- 2017. WHO Depression Report. http://www.who.int/mediacentre/factsheets/fs369/en/.Google Scholar
- Milton Abramowitz and Irene A Stegun. 1964. Handbook of mathematical functions: with formulas, graphs, and mathematical tables. Courier Corporation.Google Scholar
- Jorge Alvarez-Lozano, Venet Osmani, Oscar Mayora, Mads Frost, Jakob Bardram, Maria Faurholt-Jepsen, and Lars Vedel Kessing. 2014. Tell me your apps and I will tell you your mood: correlation of apps usage with bipolar disorder state. In PETRA'14. Google ScholarDigital Library
- Jakob E Bardram, Mads Frost, Károly Szántó, and Gabriela Marcu. 2012. The MONARCA self-assessment system: a persuasive personal monitoring system for bipolar patients. In IHI'12. Google ScholarDigital Library
- Gianni Barlacchi, Christos Perentis, Abhinav Mehrotra, Mirco Musolesi, and Bruno Lepri. 2017. Are you getting sick? Predicting influenza-like symptoms using human mobility behaviors. EPJ Data Science 6, 1 (2017), 27.Google ScholarCross Ref
- James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. JMLR 13, Feb (2012), 281--305. Google ScholarDigital Library
- H. Bourlard and Y. Kamp. 1988. Auto-association by Multilayer Perceptrons and Singular Value Decomposition. Biological Cybernetics 59, 4 (1988), 291--294. Google ScholarDigital Library
- Leo Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5--32. Google ScholarDigital Library
- Luca Canzian and Mirco Musolesi. 2015. Trajectories of depression: unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis. In UbiComp'15. Google ScholarDigital Library
- Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In KDD'16. Google ScholarDigital Library
- Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Machine Learning 20, 3 (1995), 273--297. Google ScholarDigital Library
- Finale Doshi-Velez and Been Kim. 2017. Towards a rigorous science of interpretable machine learning. arXiv:1702.08608v2 (2017).Google Scholar
- Afina S Glas, Jeroen G Lijmer, Martin H Prins, Gouke J Bonsel, and Patrick MM Bossuyt. 2003. The diagnostic odds ratio: a single indicator of test performance. Journal of Clinical Epidemiology 56, 11 (2003), 1129--1135.Google ScholarCross Ref
- Douglas M Hawkins. 2004. The problem of overfitting. Journal of Chemical Information and Computer Sciences 44, 1 (2004), 1--12.Google ScholarCross Ref
- Geoffrey Hinton, Li Deng, Dong Yu, George E Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara N Sainath, and others. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine 29, 6 (2012), 82--97.Google ScholarCross Ref
- Geoffrey E Hinton and Ruslan R Salakhutdinov. 2006. Reducing the dimensionality of data with neural networks. Science 313, 5786 (2006), 504--507.Google Scholar
- Geoffrey E Hinton and Richard S Zemel. 1994. Autoencoders, Minimum Description Length and Helmholtz Free Energy. In NIPS'94. Google ScholarDigital Library
- Anil K Jain. 2010. Data clustering: 50 years beyond K-means. Pattern Recognition Letters 31, 8 (2010), 651--666. Google ScholarDigital Library
- Ian T Jolliffe. 1986. Principal component analysis and factor analysis. In Principal Component Analysis. Springer, 115--128.Google Scholar
- Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In ICML '15.Google Scholar
- Diederik P Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. Stat 1050 (2014), 1.Google Scholar
- Alex Krizhevsky and Geoffrey E Hinton. 2011. Using very deep autoencoders for content-based image retrieval. In ESANN'11.Google Scholar
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In NIPS' 12. Google ScholarDigital Library
- Kurt Kroenke, Robert L Spitzer, and Janet BW Williams. 2001. The PHQ-9. Journal of General Internal Medicine 16, 9 (2001), 606--613.Google ScholarCross Ref
- Kurt Kroenke, Robert L Spitzer, Janet BW Williams, and Bernd Löwe. 2010. The patient health questionnaire somatic, anxiety, and depressive symptom scales: a systematic review. General Hospital Psychiatry 32, 4 (2010), 345--359.Google ScholarCross Ref
- Kurt Kroenke, Tara W. Strine, Robert L Spitzer, Janet B. W. Williams, Joyce T. Berry, and Ali H. Mokdad. 2009. The PHQ-8 as a measure of current depression in the general population. Journal of Affective Disorders 114, 1 (2009), 163--173.Google ScholarCross Ref
- Quoc Le and Tomas Mikolov. 2014. Distributed representations of sentences and documents. In ICML'14. Google ScholarDigital Library
- Robert LiKamWa, Yunxin Liu, Nicholas D Lane, and Lin Zhong. 2013. Moodscope: Building a mood sensor from smartphone usage patterns. In MobiSys'13. Google ScholarDigital Library
- Xugang Lu, Yu Tsao, Shigeki Matsuda, and Chiori Hori. 2013. Speech enhancement based on deep denoising autoencoder. In INTER-SPEECH'13.Google Scholar
- Abhinav Mehrotra, Robert Hendley, and Mirco Musolesi. 2016. Towards Multimodal Anticipatory Monitoring of Depressive States through the Analysis of Human-Smartphone. In Adjunct UbiComp'16. Heidelberg, Germany. Google ScholarDigital Library
- Abhinav Mehrotra, Jo Vermeulen, Veljko Pejovic, and Mirco Musolesi. 2015. Ask, But Don't Interrupt: The Case for Interruptibility-Aware Mobile Experience Sampling. In UbiComp'15 Adjunct. Google ScholarDigital Library
- Tomáš Mikolov, Martin Karafiát, Lukáš Burget, JanČ ernockỳ, and Sanjeev Khudanpur. 2010. Recurrent neural network based language model. In INTERSPEECH'10.Google Scholar
- Vinod Nair and Geoffrey E Hinton. 2010. Rectified linear units improve restricted Boltzmann machines. In ICML'10. Google ScholarDigital Library
- Steven J Nowlan and Geoffrey E Hinton. 1992. Simplifying neural networks by soft weight-sharing. Neural Computation 4, 4 (1992), 473--493. Google ScholarDigital Library
- J Olesen, A Gustavsson, Mikael Svensson, H-U Wittchen, and B Jönsson. 2012. The economic cost of brain disorders in Europe. European Journal of Neurology 19, 1 (2012), 155--162.Google ScholarCross Ref
- Veljko Pejovic and Mirco Musolesi. 2015. Anticipatory mobile computing: A survey of the state of the art and research challenges. Comput. Surveys 47, 3 (2015), 1--47. Google ScholarDigital Library
- Thomas Plötz, Nils Y Hammerla, and Patrick Olivier. 2011. Feature learning for activity recognition in ubiquitous computing. In IJCAI'11.Google Scholar
- Kiran K. Rachuri, Mirco Musolesi, Cecilia Mascolo, Jason Rentfrow, Chris Longworth, and Andrius Aucinas. 2010. EmotionSense: A Mobile Phones based Adaptive Platform for Experimental Social Psychology Research. In UbiComp'10. Google ScholarDigital Library
- Babak Roshanaei-Moghaddam, Wayne J Katon, and Joan Russo. 2009. The longitudinal effects of depression on physical activity. General Hospital Psychiatry 31, 4 (2009), 306--315.Google ScholarCross Ref
- Joss Roßmann. 2010. Data quality in web surveys of the German longitudinal election study 2009. In 3rd ECPR Graduate Conference.Google Scholar
- Sohrab Saeb, Mi Zhang, Christopher J Karr, Stephen M Schueller, Marya E Corden, Konrad P Kording, and David C Mohr. 2015. Mobile phone sensor correlates of depressive symptom severity in daily-life behavior: an exploratory study. Journal of Medical Internet Research 17, 7 (2015), e175.Google ScholarCross Ref
- Sandra Servia-Rodríguez, Kiran K Rachuri, Cecilia Mascolo, Peter J Rentfrow, Neal Lathia, and Gillian M Sandstrom. 2017. Mobile Sensing at the Service of Mental Wellbeing: a Large-scale Longitudinal Study. In WWW'17. Google ScholarDigital Library
- Richard Socher, Eric H Huang, Jeffrey Pennin, Christopher D Manning, and Andrew Y Ng. 2011. Dynamic pooling and unfolding recursive autoencoders for paraphrase detection. In NIPS' 11. Google ScholarDigital Library
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: A simple way to prevent neural networks from ovefitting. JMLR 15, 1 (2014), 1929--1958. Google ScholarDigital Library
- Yoshihiko Suhara, Yinzhan Xu, and Alex'Sandy' Pentland. 2017. DeepMood: Forecasting Depressed Mood Based on Self-Reported Histories via Recurrent Neural Networks. In WWW'17. Google ScholarDigital Library
- Sara Ann Taylor, Natasha Jaques, Ehimwenma Nosakhare, Akane Sano, and Rosalind Picard. 2017. Personalized Multitask Learning for Predicting Tomorrow's Mood, Stress, and Health. IEEE Transactions on Affective Computing 99, 1 (2017), 17--33.Google Scholar
- Peter D Turney. 2002. Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews. In ACL'02. Google ScholarDigital Library
- Pascal Vincent, Hugo Larochelle, Isabelle Lajoie, Yoshua Bengio, and Pierre-Antoine Manzagol. 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 11, 12 (2010), 3371--3408. Google ScholarDigital Library
- David Warde-Farley, Ian J Goodfellow, Aaron Courville, and Yoshua Bengio. 2013. An empirical analysis of dropout in piecewise linear networks. In ICLR'14.Google Scholar
Index Terms
- Using Autoencoders to Automatically Extract Mobility Features for Predicting Depressive States
Recommendations
Using linguistic features to automatically extract web page title
Successful title extraction must analyze both the DOM nodes and the title tag.Natural language processing improves the quality of the title.Visual and formatting features are less relevant for the task.Simpler classifier like k-NN perform as well as an ...
Document Content Extraction Using Automatically Discovered Features
ICDAR '09: Proceedings of the 2009 10th International Conference on Document Analysis and RecognitionWe report an automatic feature discovery method that achieves results comparable to a manually chosen, larger feature set on a document image content extraction problem: the location and segmentation of regions containing handwriting and machine-printed ...
Automatically learning semantic features for defect prediction
ICSE '16: Proceedings of the 38th International Conference on Software EngineeringSoftware defect prediction, which predicts defective code regions, can help developers find bugs and prioritize their testing efforts. To build accurate prediction models, previous studies focus on manually designing features that encode the ...
Comments