Biosignals learning and synthesis using deep neural networks

BackgroundModeling physiological signals is a complex task both for understanding and synthesize biomedical signals. We propose a deep neural network model that learns and synthesizes biosignals, validated by the morphological equivalence of the original ones. This research could lead the creation of novel algorithms for signal reconstruction in heavily noisy data and source detection in biomedical engineering field.MethodThe present work explores the gated recurrent units (GRU) employed in the training of respiration (RESP), electromyograms (EMG) and electrocardiograms (ECG). Each signal is pre-processed, segmented and quantized in a specific number of classes, corresponding to the amplitude of each sample and fed to the model, which is composed by an embedded matrix, three GRU blocks and a softmax function. This network is trained by adjusting its internal parameters, acquiring the representation of the abstract notion of the next value based on the previous ones. The simulated signal was generated by forecasting a random value and re-feeding itself.Results and conclusionsThe resulting generated signals are similar with the morphological expression of the originals. During the learning process, after a set of iterations, the model starts to grasp the basic morphological characteristics of the signal and later their cyclic characteristics. After training, these models’ prediction are closer to the signals that trained them, specially the RESP and ECG. This synthesis mechanism has shown relevant results that inspire the use to characterize signals from other physiological sources.

[1]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[2]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[3]  A. Ruha,et al.  A real-time microprocessor QRS detector system with a 1-ms timing accuracy for the measurement of ambulatory HRV , 1997, IEEE Transactions on Biomedical Engineering.

[4]  Marc'Aurelio Ranzato,et al.  DeViSE: A Deep Visual-Semantic Embedding Model , 2013, NIPS.

[5]  Kaushik Sengupta,et al.  Dynamic Waveform Shaping With Picosecond Time Widths , 2017, IEEE Journal of Solid-State Circuits.

[6]  Jing Peng,et al.  An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories , 1990, Neural Computation.

[7]  Patrick E. McSharry,et al.  A dynamical model for generating synthetic electrocardiogram signals , 2003, IEEE Transactions on Biomedical Engineering.

[8]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[9]  Jean-Claude Nunes,et al.  Hilbert Transform-Based ECG Modeling , 2005 .

[10]  Yoshua Bengio,et al.  Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription , 2012, ICML.

[11]  Robert D. Nowak,et al.  Wavelet-based statistical signal processing using hidden Markov models , 1998, IEEE Trans. Signal Process..

[12]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[13]  A. Koski.  Modelling ECG signals with hidden Markov models , 1996, Artif. Intell. Medicine.

[14]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Andrew Mehnert,et al.  Analysis of phasic and tonic electromyographic signal characteristics: electromyographic synthesis and comparison of novel morphological and linear-envelope approaches. , 2009, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[16]  Simon King,et al.  Investigating gated recurrent neural networks for speech synthesis , 2016 .

[17]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[18]  Richard S. Zemel,et al.  Image Question Answering: A Visual Semantic Embedding Model and a New Dataset , 2015, ArXiv.

[19]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Hugo Gamboa,et al.  ELECTROMYOGRAPHY ONSET DETECTION: NEW METHODOLOGY , 2012 .

[21]  Liam Kilmartin,et al.  Adaptive Dictionary Reconstruction for Compressed Sensing of ECG Signals , 2017, IEEE Journal of Biomedical and Health Informatics.

[22]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[23]  P. Rubel,et al.  A neural network approach for patient-specific 12-lead ECG synthesis in patient monitoring environments , 2004, Computers in Cardiology, 2004.

[24]  Heiga Zen,et al.  Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[25]  C. Peng,et al.  Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics. , 1996, The American journal of physiology.

[26]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[27]  A. D. Moore,et al.  Synthesized EMG waves and their implications. , 1967, American journal of physical medicine.

[28]  Geoffrey E. Hinton,et al.  Generating Text with Recurrent Neural Networks , 2011, ICML.

[29]  Zhizheng Wu,et al.  Investigating gated recurrent neural networks for speech synthesis , 2016, ArXiv.

[30]  Fei-Fei Li,et al.  Visualizing and Understanding Recurrent Networks , 2015, ArXiv.

[31]  M. Libkind,et al.  Simulation of electromyograms showing interference patterns. , 1970, Electroencephalography and clinical neurophysiology.

[32]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[33]  Erik Marchi,et al.  Multi-resolution linear prediction based features for audio onset detection with bidirectional LSTM neural networks , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[34]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[35]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[36]  E. Turajlic,et al.  A novel algorithm for ECG parametrization and synthesis , 2012, 2012 IEEE-EMBS Conference on Biomedical Engineering and Sciences.

[37]  Christopher Kermorvant,et al.  Dropout Improves Recurrent Neural Networks for Handwriting Recognition , 2013, 2014 14th International Conference on Frontiers in Handwriting Recognition.

[38]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[39]  Adriana Mexicano,et al.  Hilbert-Huang transform and neural networks for electrocardiogram modeling and prediction , 2014, 2014 10th International Conference on Natural Computation (ICNC).

[40]  Maryam Mohebbi,et al.  ECG Denoising Using Marginalized Particle Extended Kalman Filter With an Automatic Particle Weighting Strategy , 2017, IEEE Journal of Biomedical and Health Informatics.

[41]  B. J. Copeland,et al.  Alan Turing’s Forgotten Ideas in Computer Science , 1999 .

[42]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[43]  Wojciech Zaremba,et al.  An Empirical Exploration of Recurrent Network Architectures , 2015, ICML.

[44]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[45]  I. S. N. Murthy,et al.  ECG synthesis via discrete cosine transform , 1989, Images of the Twenty-First Century. Proceedings of the Annual International Engineering in Medicine and Biology Society,.

[46]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[47]  J. Schmidhuber,et al.  A First Look at Music Composition using LSTM Recurrent Neural Networks , 2002 .

[48]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.