A new framework using deep auto-encoder and energy spectral density for medical waveform data classification and processing

• Autorzy: Karim Ahmad M. , Güzel Mehmet S. , Tolun Mehmet R. , Kaya Hilal , Çelebi Fatih V.

Identyfikatory

DOI

10.1016/j.bbe.2018.11.004

• Języki publikacji: EN

Abstrakty

EN

This paper proposes a new framework for medical data processing which is essentially designed based on deep autoencoder and energy spectral density (ESD) concepts. The main novelty of this framework is to incorporate ESD function as feature extractor into a unique deep sparse auto-encoders (DSAEs) architecture. This allows the proposed architecture to extract more qualified features in a shorter computational time compared with the conventional frameworks. In order to validate the performance of the proposed framework, it has been tested with a number of comprehensive medical waveform datasets with varying dimensionality, namely, Epilepsy Serious Detection, SPECTF Classification and Diagnosis of Cardiac Arrhythmias. Overall, the ESD function speeds up the deep auto-encoder processing time and increases the overall accuracy of the results which are compared to several studies in the literature and a promising agreement is achieved.

Słowa kluczowe

EN

energy spectral density; deep autoencoder; deep learning; medical waveform data process

PL

gęstość widmowa; autoenkoder; uczenie głębokie

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 1
• Strony: 148--159
• Opis fizyczny: Bibliogr. 48 poz., rys., tab., wykr.

Twórcy

autor

Karim Ahmad M.

• Electrical and Electronics Engineering, Aksaray University, Aksaray, Turkey

autor

Güzel Mehmet S.

• Computer Engineering Department, Ankara University, Ankara 06830, Turkey

autor

Tolun Mehmet R.

• Computer Engineering Department, Baskent University, Ankara, Turkey

autor

Kaya Hilal

• Computer Engineering Department, AYBU, Ankara, Turkey

autor

Çelebi Fatih V.

• Computer Engineering Department, AYBU, Ankara, Turkey

Bibliografia

• [1] Xu G, Fang W. Shape retrieval using deep auto-encoder learning representation. 2016 13th Int Comput Conf Wavelet Act Media Technol Inf Process ICCWAMTIP 2017. 2017. pp. 227–30.
• [2] Sze V, Chen Y-H, Yang T-J, Emer J. Efficient processing of deep neural networks: a tutorial and survey, vol. 105, no. 12; 2017;2295–329.
• [3] Memisevic R. Deep learning: architectures, algorithms, applications; 2015.
• [4] Luckow A, Cook M, Ashcraft N, Weill E, Djerekarov E, Vorster B. Deep learning in the automotive industry: applications and tools. Big Data Int Conf Big Data 2016;3759–68.
• [5] Ibrahim S, Djemal R, Alsuwailem A. Electroencephalography (EEG) signal processing for epilepsy and autism spectrum disorder diagnosis. Biocybern Biomed Eng 2018;38(1):16–26.
• [6] Yavuz E, Kasapbaşı MC, Eyüpoğlu C, Yazıcı R. An epileptic seizure detection system based on cepstral analysis and generalized regression neural network. Biocybern Biomed Eng 2018;38(2):201–16.
• [7] Djemili R, Bourouba H, Amara Korba MC. Application of empirical mode decomposition and artificial neural network for the classification of normal and epileptic EEG signals. Biocybern Biomed Eng 2016;36(1):285–91.
• [8] Rincon JM, Santofimia MJ, Toro X, Barba J, Romero F, Navas P, et al. Non-linear classifiers applied to EEG analysis for epilepsy seizure detection. Expert Syst Appl 2017;86:99–112.
• [9] Ahmed K, Nia K, Khan SA, Shaukat A. Identifying best feature subset for cardiac arrhythmia classification; 2015;494–9.
• [10] Mustaqeem A, Anwar SM, Majid M, Khan AR. Wrapper method for feature selection to classify cardiac arrhythmia. Proc Annu Int Conf IEEE Eng Med Biol Soc EMBS. 2017. pp. 3656–9.
• [11] Zuo WM, Lu WG, Wang KQ, Zhang H. Diagnosis of cardiac arrhythmia using kernel difference weighted KNN classifier. Comput Cardiol 2008;35:253–6.
• [12] Jadhav SM, Nalbalwar SL, Ghatol A. Artificial neural network based cardiac arrhythmia classification using ECG signal data. 2010 Int Conf Electron Inf Eng (ICEIE), vol. 1. 2010. pp. 228–31.
• [13] Sahebi G, Majd A, Ebrahimi M, Plosila J, Tenhunen H. A reliable weighted feature selection for auto medical diagnosis. Proc. – 2017 IEEE 15th Int Conf Ind Informatics, INDIN 2017. 2017. pp. 985–91.
• [14] Persada AG, Setiawan NA, Nugroho HA. Comparative study of attribute reduction on arrhythmia classification dataset. Proc – 2013 Int Conf Inf Technol Electr Eng Intelligent Green Technol Sustain Dev ICITEE 2013. 2013. pp. 68–72.
• [15] Jadhav SM, Nalbalwar SL, Ghatol AA, Advisor T. ECG arrhythmia classification using modular neural network model. 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences (IECBES); 2010.
• [16] Saraçoglu R. Hidden Markov model-based classification of heart valve disease with PCA for dimension reduction. Eng Appl Artif Intell 2012;25(7):1523–8.
• [17] Srinivas M, Bharath R, Rajalakshmi P, Mohan CK. Multi-level classification: a generic classification method for medical datasets. 2015 17th Int Conf E-Health Networking, Appl Serv Health 2015. 2016. pp. 262–7.
• [18] Wei J, Yu HY, Lu Q, Wang J. The research of Bayesian method from small sample of high-dimensional dataset in poison identification; 2013;705–9.
• [19] Cha M, Kim JS, Baek JG. Density weighted support vector data description. Expert Syst Appl 2014;41(7):3343–50.
• [20] Liu B, Xiao Y, Cao L, Hao Z, Deng F. SVDD-based outlier detection on uncertain data. Knowl Inf Syst 2013;34(3):597–618.
• [21] Kumar R, Chen T, Hardt M, Beymer D, Brannon K, Syeda- Mahmood T. Multiple kernel completion and its application to cardiac disease discrimination. Proc Int Symp Biomed Imaging 2013;764–7.
• [22] Li-lin C, Hai-chao Z, Lin-ke Z, Rui-peng L. Improved k nearest neighbors transductive confidence machine for pattern recognition, vol. 3. ICCDA; 2010. p. 172–6.
• [23] Tian D, Zeng XJ, Keane J. Core-generating approximate minimum entropy discretization for rough set feature selection in pattern classification. Int J Approx Reason 2011;52(6):863–80.
• [24] Baldi P. Auto-encoders, unsupervised learning, and deep architectures. ICML unsupervised Transf Learn. 2012;37–50.
• [25] Ren L, Sun Y, Cui J, Zhang L. Bearing remaining useful life prediction based on deep auto-encoder and deep neural networks. J Manuf Syst 2018;2017. 0-1.
• [26] Nath A, Karthikeyan S. Enhanced prediction of recombination hotspots using input features extracted by class specific auto-encoders. J Theor Biol 2018;444:73–82.
• [27] Sethi A, Singh M, Singh R, Vatsa M. Pattern Recognit Lett 2018.
• [28] Liu Y, Zhang Y. Low-dose CT restoration via stacked sparse denoising auto-encoders. Neurocomputing 2018;284:80–9.
• [29] Chen Z, Yeo CK, Lee BS, Lau CT, Jin Y. US CR. Neurocomputing 2018.
• [30] Zeng N, Zhang H, Song B, Liu W, Li Y, Dobaie AM. Facial expression recognition via learning deep sparse auto-encoders. Neurocomputing 2018;273:643–9.
• [31] Srinivasan V, Eswaran C, Sriraam AN. Artificial neural network based epileptic detection using time-domain and frequency-domain features. Med Syst 2005;29(6):647–60.
• [32] Subasi A, Erçelebi E. Classification of EEG signals using neural network and logistic regression. Comput Methods Programs Biomed 2005;78(2):87–99.
• [33] Subasi A. EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst Appl 2007;32(4):1084–93.
• [34] Kannathal N, Choo ML, Acharya UR, Sadasivan PK. Entropies for detection of epilepsy in EEG. Comput Methods Programs Biomed 2005;80(3):187–94.
• [35] Tzallas AT, Tsipouras MG, Fotiadis DI. Automatic seizure detection based on time-frequency analysis and artificial neural networks. Comput Intell Neurosci 2007;2007.
• [36] Polat K, Güneş S. Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform. Appl Math Comput 2007;187(2):1017–26.
• [37] Rajendra Acharya U, Vinitha Sree S, Alvin APC, Suri JS. Use of principal component analysis for automatic classification of epileptic EEG activities in wavelet framework. Expert Syst Appl 2012;39(10):9072–8.
• [38] Acharya UR, Sree SV, Ang PCA, Yanti R, Suri JS. Application of non-linear and wavelet based features for the automated identification of epileptic EEG signals. Int J Neural Syst 2012;22(2):1250002.
• [39] Peker M, Sen B, Delen D. A novel method for automated diagnosis of epilepsy using complex-valued classifiers. IEEE J Biomed Health Inf 2015;2194:1–11.
• [40] Karim AM, Güzel MS, Tolun MR, Kaya H, Çelebi FV. A new generalized deep learning framework combining sparse auto-encoder and Taguchi method for novel data classification and processing; 2018;1–22.
• [41] Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE. Indications of nonlinear deterministic and finite- dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys Rev E 2001;64(6):61907.
• [42] Dua D, Taniskidou K. Machine learning repository, University of California, Irvine, School of Information and Computer Sciences; 2017. http://archive.ics.uci.edu/ml.
• [43] Panchal FS, Panchal M. Review on methods of selecting number of hidden nodes in artificial neural network, vol. 3, no. 11; 2014;455–64.
• [44] Jadhav SM, Nalbalwar SL, Ghatol AA. Artificial neural network based cardiac arrhythmia disease diagnosis. 2011 Int Conf Process Autom Control Comput. 2011. pp. 1–6.
• [45] Kohli N, Verma NK, Roy A. SVM based methods for arrhythmia classification in ECG. 2010 Int Conf Comput Commun Technol ICCCT-2010. 2010. pp. 486–90.
• [46] Özçift A. Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis. Comput Biol Med 2011;41(5):265–71.
• [47] Güzel MS. Performance evaluation for feature exctractors on street view images. Imaging Sci J 2016;64(1):26–33.
• [48] Karsoliya S. Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture, vol. 3; 2012;714–7.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).