Effective enhancement of classification of respiratory states using feed forward back propagation neural networks

In biomedical signal analysis, Artificial Neural Networks are frequently used for classification, owing to their capability to resolve nonlinearly separable problems and the flexibility to implement them on-chip processor, competently. Artificial Neural Network for a classification task attempts to hand design a network topology and to find a set of network parameters using a back propagation training algorithm. This work presents an intelligent diagnosis system using artificial neural network. Features were extracted from respiratory effort signal based on the threshold-based scheme and the respiratory states were classified into normal, sleep apnea and motion artifacts. The introduced neural classifier was then trained with different back propagation training algorithms and the classified output was compared with the hand designed results. Five different back propagation training algorithms were used for training, such as Levenberg–Marquardt, scaled conjugate gradient, BFGS algorithm, one step secant and Powell–Beale restarts. Our results revealed that the system could correctly classify at an average of 98.7%, when the LM training method was used. Receiver Operating Characteristic (ROC) analysis and confusion matrix showed that the LM method conferred a more balanced and an apt classification of sleep apnea and normal states.

[1]  M. P. Bonomini,et al.  Probability of ventricular fibrillation: allometric model based on the ST deviation , 2011, Biomedical engineering online.

[2]  H. Arabalibeik,et al.  Classification of normal and abnormal respiration patterns using flow volume curve and neural network , 2010, 2010 5th International Symposium on Health Informatics and Bioinformatics.

[3]  Saad Alshaban,et al.  Using Neural and Fuzzy Software for the Classification of ECG Signals , 2010 .

[4]  Mohammad Bagher Tavakoli,et al.  Modified Levenberg-Marquardt Method for Neural Networks Training , 2007 .

[5]  Eduardo Gil,et al.  Selection of Nonstationary Dynamic Features for Obstructive Sleep Apnoea Detection in Children , 2011, EURASIP J. Adv. Signal Process..

[6]  Veera Boonjing,et al.  Heart Disease Classification Using Neural Network and Feature Selection , 2011, 2011 21st International Conference on Systems Engineering.

[7]  Riccardo Barbieri,et al.  Database for ECG, arterial blood pressure, and respiration signal analysis: feature extraction, spectral estimation, and parameter quantification , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[8]  Myoungho Lee,et al.  An arrhythmia classification algorithm using a dedicated wavelet adapted to different subjects , 2011, Biomedical engineering online.

[9]  V.A. Maiorescu,et al.  Classification of EEG signals represented by AR models for cognitive tasks - a neural network based method , 2003, Signals, Circuits and Systems, 2003. SCS 2003. International Symposium on.

[10]  A.A. Morsy,et al.  Sleep Apnea Detection and Classification Using Fuzzy Logic: Clinical Evaluation , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[11]  Donald P. Knode.  THE IRON CURTAIN REFUGEE IN A NEW WORLD , 1952 .

[12]  Russell C. Eberhart,et al.  Neural network performance metrics for biomedical applications , 1990, [1990] Proceedings. Third Annual IEEE Symposium on Computer-Based Medical Systems.

[13]  Tony Szturm,et al.  Application of feedforward backpropagation neural network to center of mass estimation for use in a clinical environment , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[14]  Nuria Oliver,et al.  HealthGear: Automatic Sleep Apnea Detection and Monitoring with a Mobile Phone , 2007, J. Commun..

[15]  Derong Liu,et al.  A Neural Network Method for Detection of Obstructive Sleep Apnea and Narcolepsy Based on Pupil Size and EEG , 2008, IEEE Transactions on Neural Networks.

[16]  Dario Floreano,et al.  Sleep and Wake Classification With ECG and Respiratory Effort Signals , 2009, IEEE Transactions on Biomedical Circuits and Systems.

[17]  Satish S. Udpa,et al.  Feature extraction techniques for ultrasonic signal classification , 2002 .

[18]  Noriaki Suetake,et al.  Feature Extraction and Signal Reconstruction of Air and Bone Conduction Voices by Independent Component Analysis , 2008 .

[19]  Mohammad Teshnehlab,et al.  Feature selection and classification of breast MRI lesions based on multi classifier , 2011, 2011 International Symposium on Artificial Intelligence and Signal Processing (AISP).

[20]  S. Cerutti,et al.  Detection of Sleep Apnea from surface ECG based on features extracted by an Autoregressive Model , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[21]  H. Nazeran,et al.  EEG feature extraction for classification of sleep stages , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[22]  Zoi-Heleni Michalopoulou,et al.  Performance evaluation of multilayer perceptrons in signal detection and classification , 1995, IEEE Trans. Neural Networks.

[23]  Taikang Ning,et al.  Classification of Respiration Episodes using Fuzzy Logic , 2006, Proceedings of the IEEE 32nd Annual Northeast Bioengineering Conference.

[24]  J.Q. Liu,et al.  Apnea Detection Based on Time Delay Neural Network , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[25]  A.A. Ghatol,et al.  A brief performance evaluation of ECG feature extraction techniques for artificial neural network based classification , 2007, TENCON 2007 - 2007 IEEE Region 10 Conference.

[26]  S. Palanivel,et al.  HMM Based Automatic Video Classification Using Static and Dynamic Features , 2007, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007).

[27]  Taikang Ning,et al.  Automatic classification of respiratory signals , 1989, Images of the Twenty-First Century. Proceedings of the Annual International Engineering in Medicine and Biology Society,.

[28]  Oliver Faust,et al.  Analysis of cardiac signals using spatial filling index and time-frequency domain , 2004, Biomedical engineering online.

[29]  F. Ebrahimi,et al.  Automatic sleep stage classification based on EEG signals by using neural networks and wavelet packet coefficients , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[30]  Jiang Wang,et al.  Feature extraction of brain-computer interface based on improved multivariate adaptive autoregressive models , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[31]  Choo Min Lim,et al.  Classification of cardiac patient states using artificial neural networks. , 2003, Experimental and clinical cardiology.

[32]  Liviu Goras,et al.  An ECG Signals Compression Method and Its Validation Using NNs , 2008, IEEE Transactions on Biomedical Engineering.

[33]  Eric Laciar,et al.  Sleep apnea detection based on spectral analysis of three ECG - derived respiratory signals , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[34]  R. Hornero,et al.  Applying Neural Network Classifiers in the Diagnosis of the Obstructive Sleep Apnea Syndrome from Nocturnal Pulse Oximetric Recordings , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[35]  Witold Pedrycz,et al.  Fuzzy wavelet packet based feature extraction method and its application to biomedical signal classification , 2005, IEEE Transactions on Biomedical Engineering.

[36]  Mark F. Bocko,et al.  Methods to extract respiration information from ECG signals , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[37]  M. Arthanari,et al.  ECG Feature Extraction Techniques - A Survey Approach , 2010, ArXiv.

[38]  Neural network classification in non-homogeneous feature space , 2011, Optical Memory and Neural Networks.

[39]  Vladimir Friedman,et al.  A zero crossing algorithm for the estimation of the frequency of a single sinusoid in white noise , 1994, IEEE Trans. Signal Process..

[40]  E.J. Tkacz,et al.  Feature extraction for improving the support vector machine biomedical data classifier performance , 2008, 2008 International Conference on Information Technology and Applications in Biomedicine.

[41]  B. AnanyaS,et al.  Feature Extraction and Classification of Brain Tumor using MRI , 2015 .

[42]  Zoltán Benyó,et al.  A novel method for the detection of apnea and hypopnea events in respiration signals , 2002, IEEE Transactions on Biomedical Engineering.

[43]  E.J. Tkacz,et al.  An improvement of unsupervised hybrid biomedical signal classifiers by optimal feature extraction in system preliminary layer , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[44]  B. Roth,et al.  A mathematical model for electrical stimulation of a monolayer of cardiac cells. , 2004 .

[45]  Michael R. Neuman,et al.  Sleep Versus Wake Classification From Heart Rate Variability Using Computational Intelligence: Consideration of Rejection in Classification Models , 2008, IEEE Transactions on Biomedical Engineering.

[46]  S. Sumathi,et al.  Introduction to neural networks using MATLAB 6.0 , 2006 .

[47]  Keum-Shik Hong,et al.  Backpropagation neural networks training for single trial EEG classification , 2010, Proceedings of the 29th Chinese Control Conference.