Hessenberg Elm Autoencoder Kernel For Deep Learning

Abstract

Deep Learning (DL) is an effective way that reveals on computation capability and advantage of the hidden layer in the network models. It has pre-training phases which define the output parameters in unsupervised ways and supervised training for optimization of the pre-defined classification parameters. This study aims to perform high generalized fast training for DL algorithms with the simplicity advantage of Extreme Learning machines (ELM). The applications of the proposed classifier model were experimented on RespiratoryDatabase@TR. Hilbert-Huang Transform was applied to the 12-channel lung sounds for analyzing amplitude-time-frequency domain. The statistical features were extracted from the intrinsic mode function modulations of lung sounds. The feature set was fed into the proposed Deep ELM with the HessELM-AE. The proposed model was structured with 2 hidden layers (340,580 neurons) to classify the lung sounds for separating Chronic Obstructive Pulmonary Disease and healthy subjects. The classification performance was tested using 6-fold cross-validation with proposed Deep. HessELM-AE has achieved an influential accuracy rate of 92.22% whereas the conventional ELM-AE has reached an accuracy rate of 80.82%.

Keywords

• Deep Learning,RespiratoryDatabase@TR,COPD,Lung sounds,Deep ELM,Hessenberg decomposition

References

1. [1] Duda, R. , Hart, P. and Stork, D. Pattern Classification. New York: John Wiley, Section, 2000. doi:10.1038/npp.2011.9.
2. [2] Altan, G., Kutlu, Yakup, P., Adnan Özhan and Nural, Serkan. “Deep Learning with 3D-Second Order Difference Plot on Respiratory Sounds.” Biomedical Signal Processing and Control, 2018. doi:10.1016/j.bspc.2018.05.014.
3. [3] Yan, Y, X Qin, Y Wu, N Zhang, J Fan, and L Wang, “A Restricted Boltzmann Machine Based Two-Lead Electrocardiography Classification.” 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN). https://doi.org/10.1109/BSN.2015.7299399.
4. [4] Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E Hinton, “ImageNet Classification with Deep Convolutional Neural Networks.” Advances In Neural Information Processing Systems, 2012. doi:http://dx.doi.org/10.1016/j.protcy.2014.09.007.
5. [5] Melbye, Hasse, “Auscultation of the Lungs Still a Useful Examination?” Tidsskrift for Den Norske Lægeforening : Tidsskrift for Praktisk Medicin, Ny Række 121(4) (2001): 451–54. http://www.ncbi.nlm.nih.gov/pubmed/11255861.
6. [6] Reichert, Sandra, Raymond Gass, Amir Hajjam, Christian Brandt, Emmanuel Nguyen, Karine Baldassari, and Emmanuel Andrès, “The ASAP Project: A First Step to an Auscultation’s School Creation.” Respiratory Medicine CME 2(1) (2009): 7–14. doi:10.1016/j.rmedc.2009.01.001.
7. [7] Loudon, Robert, and Raymond Murphy, “Lung Sounds.” The American Review of Respiratory Disease 130(4) (1984): 663–73. doi:10.1016/S0196-0644(97)70237-3.
8. [8] Altan, Gokhan, Allahverdi, Novruz and Kutlu, Yakup, “Diagnosis of Coronary Artery Disease Using Deep Belief Networks.” European Journal of Engineering and Natural Sciences 2(1) (2007): 29–36. http://dergipark.gov.tr/ejens/issue/27741/293042.

9. [9] Roisin, Roberto Rodriguez, “Chronic Obstructive Pulmonary Disease Updated 2010 Global Initiative for Chronic Obstructive Lung Disease.” Global Initiative for Chronic Obstructive Lung Disease. Inc, 2016: 1–94. doi:10.1097/00008483-200207000-00004.
10. [10] Celli, B. R., W. MacNee, A. Agusti, A. Anzueto, B. Berg, A. S. Buist, P. M.A. Calverley, et al. “Standards for the Diagnosis and Treatment of Patients with COPD: A Summary of the ATS/ERS Position Paper.” European Respiratory Journal, 2004. doi:10.1183/09031936.04.00014304.
11. [11] Wiśniewski, Marcin, and Zieliński, Tomasz, “Digital Analysis Methods of Wheezes in Asthma.” ICSES 2010 International Conference on Signals and Electronic Circuits.
12. [12] Amaral, Jorge L M, Alvaro C D Faria, Agnaldo J Lopes, Jose M Jansen, and Pedro L Melo, “Automatic Identification of Chronic Obstructive Pulmonary Disease Based on Forced Oscillation Measurements and Artificial Neural Networks.” In 32nd Annual International Conference of the IEEE EMBS, 2010: 1394–97. doi:10.1109/IEMBS.2010.5626727.
13. [13] Ying, Jun, Joyita Dutta, Ning Guo, Lei Xia, Arkadiusz Sitek, and Quanzheng Li, “Gold Classification of COPDGene Cohort Based on Deep Learning.” In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2016–May:2474–78. https://doi.org/10.1109/ICASSP.2016.7472122.
14. [14] Kasun, L L C, H M Zhou, G B Huang, and C M Vong. “Representational Learning with ELMs for Big Data.” IEEE Intelligent Systems 28(6) (2013): 31–34.
15. [15] Altan, Gokhan, Kutlu, Yakup, Garbi, Yusuf, Pekmezci, Adnan Ozhan and Nural, Serkan, “Multimedia Respiratory Database (RespiratoryDatabase@TR): Auscultation Sounds and Chest X-Rays.” Natural and Engineering Sciences 2(3) (2017): 59–72. doi:10.28978/nesciences.349282.
16. [16] Huang, Norden E, and Zhaohua Wu, “A Review on Hilbert-Huang Transform : Method and Its Applications.” October 46 (2007): 1–23. doi:10.1029/2007RG000228.1.
17. [17] Huang, NE, Z Shen, SR Long, MC Wu, HH SHIH, Q ZHENG, NC Yen, CC Tung, and HH Liu, “The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-Stationary Time Series Analysis.” Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 454 (1971): 995, 903. doi:10.1098/rspa.1998.0193.
18. [18] Altan, Gokhan, Kutlu, Yakup, and Allahverdi, Novruz, “A New Approach to Early Diagnosis of Congestive Heart Failure Disease by Using Hilbert–Huang Transform.” Computer Methods and Programs in Biomedicine, Elsevier, 137 (December)(2016a): 23–34. doi:10.1016/J.CMPB.2016.09.003.
19. [19] Altan, Gokhan, Yayik, Apdullah, Kutlu, Yakup, Yildirim, Serdar, and Yildirim, Esen, “Analyse of Congestive Heart Failure Using Hilbert- Huang Transform.” Dokuz Eylul University Engineering Sciences 16 (2014): 94–103. http://web.deu.edu.tr/fmd/s48/S48-m10.pdf.
20. [20] Huang, Guang-bin, Qin-yu Zhu, and Chee-kheong Siew, “Extreme Learning Machine : A New Learning Scheme of Feedforward Neural Networks.” IEEE International Joint Conference on Neural Networks 2 (2004): 985–90. doi:10.1109/IJCNN.2004.1380068.
21. [21] Tang, Jiexiong, Chenwei Deng, and Guang-Bin Huang, “Extreme Learning Machine for Multilayer Perceptron.” IEEE Transactions on Neural Networks and Learning Systems 27(4) (2016): 809–21. doi:10.1109/TNNLS.2015.2424995.
22. [22] Altan, Gokhan, Kutlu, Yakup, Pekmezci, Adnan Özhan and Yayık, Apdullah. 2018. “Diagnosis of Chronic Obstructive Pulmonary Disease Using Deep Extreme Learning Machines with LU Autoencoder Kernel.” In 7th International Conference on Advanced Technologies (ICAT’18), 618–22. Antalya.
23. [23] Golub, Gene H., and Charles F. Van Loan, "The Hessenberg and Real Schur Forms", 7.4 in Matrix Computations. 3rd ed. Baltimore: Johns Hopkins University, (1996): pp:361-372
24. [24] Altan, Gokhan, Kutlu, Yakup and Allahverdi, Novruz, “A Multistage Deep Belief Networks Application on Arrhythmia Classification.” International Journal of Intelligent Systems and Applications in Engineering 4 (Special Issue-1) (2016c): 222–28.
25. [25] Kutlu, Yakup, Altan, Gokhan, and Allahverdi, Novruz, “Arrhythmia Classification Using Waveform Ecg Signals.” In 3rd International Conference on Advanced Technology & Sciences, (2016): 233–39. Konya.
26. [26] Altan, Gokhan, Kutlu, Yakup, and Allahverdi, Novruz. “Deep Belief Networks Based Brain Activity Classification Using EEG from Slow Cortical Potentials in Stroke.” International Journal of Applied Mathematics, Electronics and Computers 4 (Special Issue-1) (2016): 205–10. doi:10.18100/ijamec.270307.