Disentangled Adversarial Transfer Learning for Physiological Biosignals

Recent developments in wearable sensors demonstrate promising results for monitoring physiological status in effective and comfortable ways. One major challenge of physiological status assessment is the problem of transfer learning caused by the domain inconsistency of biosignals across users or different recording sessions from the same user. We propose an adversarial inference approach for transfer learning to extract disentangled nuisance-robust representations from physiological biosignal data in stress status level assessment. We exploit the trade-off between task-related features and person-discriminative information by using both an adversary network and a nuisance network to jointly manipulate and disentangle the learned latent representations by the encoder, which are then input to a discriminative classifier. Results on cross-subjects transfer evaluations demonstrate the benefits of the proposed adversarial framework, and thus show its capabilities to adapt to a broader range of subjects. Finally we highlight that our proposed adversarial transfer learning approach is also applicable to other deep feature learning frameworks.

[1]  Dimitrios Tzovaras,et al.  Subject-dependent biosignal features for increased accuracy in psychological stress detection , 2013, Int. J. Hum. Comput. Stud..

[2]  Mehrdad Nourani,et al.  A wrist-worn biosensor system for assessment of neurological status , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Amos J. Storkey,et al.  Censoring Representations with an Adversary , 2015, ICLR.

[4]  Mehrdad Nourani,et al.  A Non-EEG Biosignals Dataset for Assessment and Visualization of Neurological Status , 2016, 2016 IEEE International Workshop on Signal Processing Systems (SiPS).

[5]  Motoaki Kawanabe,et al.  Learning a common dictionary for subject-transfer decoding with resting calibration , 2015, NeuroImage.

[6]  Matthew S. Goodwin,et al.  Time-Series Prediction of Proximal Aggression Onset in Minimally-Verbal Youth with Autism Spectrum Disorder Using Physiological Biosignals , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[7]  Klaus-Robert Müller,et al.  Subject-independent mental state classification in single trials , 2009, Neural Networks.

[8]  Guillaume Lample,et al.  Fader Networks: Manipulating Images by Sliding Attributes , 2017, NIPS.

[9]  Ye Wang,et al.  Learning Invariant Representations From EEG via Adversarial Inference , 2020, IEEE Access.

[10]  U. Rajendra Acharya,et al.  Deep learning for healthcare applications based on physiological signals: A review , 2018, Comput. Methods Programs Biomed..

[11]  Manolis Tsiknakis,et al.  Review on Psychological Stress Detection Using Biosignals , 2019, IEEE Transactions on Affective Computing.

[12]  Ye Wang,et al.  Transfer Learning in Brain-Computer Interfaces with Adversarial Variational Autoencoders , 2019, 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER).

[13]  Kunal Mankodiya,et al.  Emotional reactivity monitoring using electrodermal activity analysis in individuals with suicidal behaviors , 2016, 2016 10th International Symposium on Medical Information and Communication Technology (ISMICT).

[14]  Leontios J. Hadjileontiadis,et al.  Emotion Recognition From EEG Using Higher Order Crossings , 2010, IEEE Transactions on Information Technology in Biomedicine.

[15]  Manfredo Atzori,et al.  Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands , 2016, Front. Neurorobot..

[16]  Yann LeCun,et al.  Disentangling factors of variation in deep representation using adversarial training , 2016, NIPS.

[17]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[18]  Shiliang Sun,et al.  A subject transfer framework for EEG classification , 2012, Neurocomputing.