Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery

Activity recognition in wearable computing faces two key challenges: i) activity characteristics may be context-dependent and change under different contexts or situations; ii) unknown contexts and activities may occur from time to time, requiring flexibility and adaptability of the algorithm. We develop a context-aware mixture of deep models termed the {\alpha}-\b{eta} network coupled with uncertainty quantification (UQ) based upon maximum entropy to enhance human activity recognition performance. We improve accuracy and F score by 10% by identifying high-level contexts in a data-driven way to guide model development. In order to ensure training stability, we have used a clustering-based pre-training in both public and in-house datasets, demonstrating improved accuracy through unknown context discovery.

[1]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[2]  Gregory J. Pottie,et al.  Context-driven, Prescription-Based Personal Activity Classification: Methodology, Architecture, and End-to-End Implementation , 2014, IEEE Journal of Biomedical and Health Informatics.

[3]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[4]  Michael I. Jordan,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1994, Neural Computation.

[5]  Roozbeh Jafari,et al.  A human-centered wearable sensing platform with intelligent automated data annotation capabilities , 2019, IoTDI.

[6]  Bobak Mortazavi,et al.  Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models , 2019, AISTATS.

[7]  Tinne Tuytelaars,et al.  Expert Gate: Lifelong Learning with a Network of Experts , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Dong Seog Han,et al.  Feature Representation and Data Augmentation for Human Activity Classification Based on Wearable IMU Sensor Data Using a Deep LSTM Neural Network , 2018, Sensors.

[9]  Olivier Gibaru,et al.  CNN features are also great at unsupervised classification , 2017, ArXiv.

[10]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[11]  Murat Sensoy,et al.  Evidential Deep Learning to Quantify Classification Uncertainty , 2018, NeurIPS.

[12]  Guang-Zhong Yang,et al.  From Wearable Sensors to Smart Implants-–Toward Pervasive and Personalized Healthcare , 2015, IEEE Transactions on Biomedical Engineering.

[13]  Jennifer Talley,et al.  Validation of an Acoustic Gastrointestinal Surveillance Biosensor for Postoperative Ileus , 2014, Journal of Gastrointestinal Surgery.

[14]  Erdogan Dogdu,et al.  Context-Aware Computing, Learning, and Big Data in Internet of Things: A Survey , 2018, IEEE Internet of Things Journal.

[15]  Shiliang Sun,et al.  Multi-view learning for visual violence recognition with maximum entropy discrimination and deep features , 2019, Inf. Fusion.

[16]  Claudio Bettini,et al.  COSAR: hybrid reasoning for context-aware activity recognition , 2011, Personal and Ubiquitous Computing.

[17]  Robert A. Jacobs,et al.  A Bayesian Approach to Model Selection in Hierarchical Mixtures-of-Experts Architectures , 1997, Neural Networks.

[18]  Guido De Roeck,et al.  Uncertainty quantification in operational modal analysis with stochastic subspace identification: Validation and applications , 2016 .

[19]  Mark J. F. Gales,et al.  Predictive Uncertainty Estimation via Prior Networks , 2018, NeurIPS.

[20]  Zhe Wang,et al.  Semi-supervised soft margin consistency based multi-view maximum entropy discrimination , 2019 .

[21]  Piyush Rai,et al.  A flexible probabilistic framework for large-margin mixture of experts , 2019, Machine Learning.

[22]  Chao Yuan,et al.  Variational Mixture of Gaussian Process Experts , 2008, NIPS.

[23]  Kibok Lee,et al.  A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks , 2018, NeurIPS.

[24]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[25]  Shuai Huang,et al.  UQ-CHI: An Uncertainty Quantification-Based Contemporaneous Health Index for Degenerative Disease Monitoring , 2019, ArXiv.

[26]  Geoffrey E. Hinton,et al.  Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer , 2017, ICLR.

[27]  Gregory J. Pottie,et al.  Personalized Active Learning for Activity Classification Using Wireless Wearable Sensors , 2016, IEEE Journal of Selected Topics in Signal Processing.

[28]  Joseph N. Wilson,et al.  Twenty Years of Mixture of Experts , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Kevin Gimpel,et al.  A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks , 2016, ICLR.

[30]  R. Srikant,et al.  Principled Detection of Out-of-Distribution Examples in Neural Networks , 2017, ArXiv.

[31]  Lutz Eckstein,et al.  Deep, spatially coherent Inverse Sensor Models with Uncertainty Incorporation using the evidential Framework , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[32]  Christophe Ambroise,et al.  A mixture model with logistic weights for disease subtyping with integrated genome association study , 2019 .

[33]  Stefan Carlsson,et al.  CNN Features Off-the-Shelf: An Astounding Baseline for Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[34]  R. Srikant,et al.  Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks , 2017, ICLR.

[35]  Lijuan Cao,et al.  Support vector machines experts for time series forecasting , 2003, Neurocomputing.

[36]  Michael I. Jordan,et al.  Convergence results for the EM approach to mixtures of experts architectures , 1995, Neural Networks.

[37]  Christopher M. Bishop,et al.  Bayesian Hierarchical Mixtures of Experts , 2002, UAI.

[38]  Paul Lukowicz,et al.  Collecting complex activity datasets in highly rich networked sensor environments , 2010, 2010 Seventh International Conference on Networked Sensing Systems (INSS).

[39]  Xiaohui Peng,et al.  Deep Learning for Sensor-based Activity Recognition: A Survey , 2017, Pattern Recognit. Lett..

[40]  Ivan Laptev,et al.  Learnable pooling with Context Gating for video classification , 2017, ArXiv.

[41]  Hanieh Niroomand-Oscuii,et al.  Brain tumor growth simulation: model validation through uncertainty quantification , 2017, Int. J. Syst. Assur. Eng. Manag..

[42]  Fernando José Von Zuben,et al.  Hybridizing mixtures of experts with support vector machines: Investigation into nonlinear dynamic systems identification , 2007, Inf. Sci..

[43]  Anind K. Dey,et al.  Understanding and Using Context , 2001, Personal and Ubiquitous Computing.

[44]  Sankaran Mahadevan,et al.  Uncertainty quantification in performance evaluation of manufacturing processes , 2014, 2014 IEEE International Conference on Big Data (Big Data).