Multimedia Tools and Applications

, Volume 77, Issue 3, pp 3775–3793 | Cite as

Sensorineural hearing loss detection via discrete wavelet transform and principal component analysis combined with generalized eigenvalue proximal support vector machine and Tikhonov regularization

  • Yi Chen
  • Ming Yang
  • Xianqing Chen
  • Bin Liu
  • Hainan Wang
  • Shuihua Wang
Article

Abstract

In the past, scholars used various computer vision and artificial intelligence methods to detect brain diseases via magnetic resonance imaging (MRI). In this paper, we proposed a novel system to detect sensorineural hearing loss (SNHL). First, we used three-level bior4.4 wavelet to decompose original brain image. Second, principal component analysis (PCA) was utilized for dimensionality reduction. Third, the generalized eigenvalue proximal support vector machine (GEPSVM) with Tikhonov regularization was employed as the classifier. The 10 repetitions of five-fold cross validation showed our method achieved an overall accuracy of 95.71 %. Our sensitivities over healthy control, left-sided SNHL, and right-sided SNHL are 96.00 %, 95.33 %, and 95.71 %, respectively. The proposed system is promising and effective in SNHL detection. It gives better performance than four state-of-the-art methods.

Keywords

Discrete wavelet transform Tikhonov regularization Sensorineural hearing loss Magnetic resonance imaging Dimensionality reduction 

Notes

Acknowledgment

This paper was supported by NSFC (61602250, 61503188, 61562041), Natural Science Foundation of Jiangsu Province (BK20150983, BK20150982), Program of Natural Science Research of Jiangsu Higher Education Institutions (14KJB520021), Open Research Fund of Hunan Provincial Key Laboratory of Network Investigational Technology (2016WLZC013), Open Fund of Fujian Provincial Key Laboratory of Data Intensive Computing (BD201607), Jiangsu Key Laboratory of Image and Video Understanding for Social Safety, Nanjing University of Science and Technology (30916014107).

References

  1. 1.
    Aharamuthu K, Ayyasamy EP (2013) Application of discrete wavelet transform and Zhao-Atlas-Marks transforms in non stationary gear fault diagnosis. J Mech Sci Technol 27(3):641–647CrossRefGoogle Scholar
  2. 2.
    Akbarpour T, et al. (2015) Medical image fusion using discrete wavelet transform and lifting scheme. In: 22nd Iranian Conference on Biomedical Engineering (Icbme). Tehran, IEEE, pp 293-298Google Scholar
  3. 3.
    Bai YQ et al (2015) Sparse Proximal Support Vector Machine with a Specialized Interior-Point Method. J Oper Res Soc Chin 3(1):1–15MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Baklouti R et al (2016) Iterated Robust kernel Fuzzy Principal Component Analysis and application to fault detection. J Comput Sci 15:34–49MathSciNetCrossRefGoogle Scholar
  5. 5.
    Balochian S, et al. (2014) Artificial intelligence and its applications. Mathematical Problems in Engineering. Article ID: 840491Google Scholar
  6. 6.
    Chen P (2016a) Computer-aided detection of left and right sensorineural hearing loss by wavelet packet decomposition and least-square support vector machine. J Am Geriatr Soc 64(S2):S350Google Scholar
  7. 7.
    Chen C (2016b) Multiscale imaging, modeling, and principal component analysis of gas transport in shale reservoirs. Fuel 182:761–770CrossRefGoogle Scholar
  8. 8.
    Chen M (2016c) Morphological analysis of dendrites and spines by hybridization of ridge detection with twin support vector machine. PeerJ 4:e2207CrossRefGoogle Scholar
  9. 9.
    Chen S et al (2015) Magnetic resonance brain image classification based on weighted-type fractional Fourier transform and nonparallel support vector machine. Int J Imaging Syst Technol 25(4):317–327CrossRefGoogle Scholar
  10. 10.
    Dash, R. et al. (2015) Least squares SVM approach for abnormal brain detection in MRI using multiresolution analysis. In International Conference on Computing, Communication and Security (ICCCS). Pamplemousses, IEEE, pp 6-10Google Scholar
  11. 11.
    Davo F et al (2016) Post-processing techniques and principal component analysis for regional wind power and solar irradiance forecasting. Sol Energy 134:327–338CrossRefGoogle Scholar
  12. 12.
    Deokar SA, Waghmare LM (2013) Discrete wavelet transform based classifier for PQ disturbance detection. J Sci Ind Res 72(2):92–100Google Scholar
  13. 13.
    Dufrenois F, Noyer JC (2015) Generalized eigenvalue proximal support vector machines for outlier description. In: International Joint Conference on Neural Networks. Killarney, IEEE, pp 12-17Google Scholar
  14. 14.
    Gorriz JM, Ramírez J (2016) Wavelet entropy and directed acyclic graph support vector machine for detection of patients with unilateral hearing loss in MRI scanning. Front Comput Neurosci 2016(10):160Google Scholar
  15. 15.
    Gunning D, Yeh PZ (2016) Innovative Applications of Artificial Intelligence 2015. AI Mag 37(2):5–6CrossRefGoogle Scholar
  16. 16.
    Hager WW et al (2016) Projection algorithms for nonconvex minimization with application to sparse principal component analysis. J Glob Optim 65(4):657–676MathSciNetCrossRefMATHGoogle Scholar
  17. 17.
    Hakimi F, et al. (2015) Image splicing forgery detection using local binary pattern and discrete wavelet transform. In 2nd International Conference on Knowledge-Based Engineering And Innovation. Tehran, IEEE, pp 1074-1077Google Scholar
  18. 18.
    Ikawa N (2013) Automated averaging of auditory evoked response waveforms using wavelet analysis. Int J Wavelets Multiresolution Inf Process 11(4):1360009CrossRefMATHGoogle Scholar
  19. 19.
    Ikuzawa T et al (2016) Reducing memory usage by the lifting-based discrete wavelet transform with a unified buffer on a GPU. Journal of Parallel and Distributed Computing 93-94:44–55CrossRefGoogle Scholar
  20. 20.
    Jenkal W, et al. (2015) Enhanced algorithm for QRS detection using discrete wavelet transform (DWT). In: 27th International Conference on Microelectronics. Casablanca, IEEE, pp 39-42Google Scholar
  21. 21.
    Ji G (2013) An MR brain images classifier system via particle swarm optimization and kernel support vector machine. The Scientific World Journal. Article ID: 130134Google Scholar
  22. 22.
    Ji G (2014) Fruit classification using computer vision and feedforward neural network. J Food Eng 143:167–177CrossRefGoogle Scholar
  23. 23.
    Karelle S et al (2012) Sudden sensorineural hearing loss: when ophthalmology meets otolaryngology. B-Ent 8(2):135–139Google Scholar
  24. 24.
    Liu A (2015) Magnetic resonance brain image classification via stationary wavelet transform and generalized eigenvalue proximal support vector machine. J Med Imaging Health Inform 5(7):1395–1403CrossRefGoogle Scholar
  25. 25.
    Liu G et al (2016) Detection of alzheimer’s disease by three-dimensional displacement field estimation in structural magnetic resonance imaging. J Alzheimers Dis 50(1):233–248Google Scholar
  26. 26.
    Maldonado S et al (2016) A second-order cone programming formulation for twin support vector machines. Appl Intell 45(2):265–276CrossRefGoogle Scholar
  27. 27.
    Mangasarian OL, Wild EW (2006) Multisurface proximal support vector machine classification via generalized eigenvalues. IEEE Trans Pattern Anal Mach Intell 28(1):69–74CrossRefGoogle Scholar
  28. 28.
    Mao Y, et al. (2008) Phase synchronization analysis of theta-band of local field potentials in the anterior cingulated cortex of rats under fear conditioning. In: International symposium on intelligent information technology application. Los Alamitos: IEEE Computer Soc, pp 737-741Google Scholar
  29. 29.
    Masalski M, Krecicki T (2013) Self-Test web-based pure-tone audiometry: validity evaluation and measurement error analysis. J Med Internet Res 15(4):10 Article ID: UNSP e71CrossRefGoogle Scholar
  30. 30.
    Monzack EL et al (2015) Live imaging the phagocytic activity of inner ear supporting cells in response to hair cell death. Cell Death Differ 22(12):1995–2005CrossRefGoogle Scholar
  31. 31.
    Morales JA et al (2016) Ultra high speed deterministic algorithm for transmission lines disturbance identification based on principal component analysis and Euclidean norm. Int J Electr Power Energy Syst 80:312–324CrossRefGoogle Scholar
  32. 32.
    Nakagawa T et al (2016) Prognostic impact of salvage treatment on hearing recovery in patients with sudden sensorineural hearing loss refractory to systemic corticosteroids: A retrospective observational study. Auris Nasus Larynx 43(5):489–494CrossRefGoogle Scholar
  33. 33.
    Nayak DR et al (2016) Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests. Neurocomputing 177:188–197CrossRefGoogle Scholar
  34. 34.
    Nguyen VB et al (2016) Maximizing the sum of a generalized Rayleigh quotient and another Rayleigh quotient on the unit sphere via semidefinite programming. J Glob Optim 64(2):399–416MathSciNetCrossRefMATHGoogle Scholar
  35. 35.
    Pasadas DJ et al (2016) Automatic parameter selection for Tikhonov regularization in ECT Inverse problem. Sensor Actuat A Phys 246:73–80CrossRefGoogle Scholar
  36. 36.
    Rathinavelu A et al (2007) Three dimensional articulator model for speech acquisition by children with hearing loss. In: Stephanidis C (ed) Universal access in human computer interaction: coping with diversity. Springer-Verlag Berlin, Berlin, pp. 786–794CrossRefGoogle Scholar
  37. 37.
    Saliba I, Sidani K (2009) Prognostic indicators for sensorineural hearing loss in temporal bone histiocytosis. Int J Pediatr Otorhinolaryngol 73(12):1616–1620CrossRefGoogle Scholar
  38. 38.
    Singh M et al (2013) Discrete Wavelet Transform Based Measurement of Inner Race Defect Width in Taper Roller Bearing. Mapan-Journal of Metrology Society of India 28(1):17–23Google Scholar
  39. 39.
    Vasta R et al (2016) Hippocampal Subfield Atrophies in Converted and Not-Converted Mild Cognitive Impairments Patients by a Markov Random Fields Algorithm. Curr Alzheimer Res 13(5):566–574CrossRefGoogle Scholar
  40. 40.
    Vaswani R et al (2008) Rinne test modified to quantify hearing. South Med J 101(1):107–108CrossRefGoogle Scholar
  41. 41.
    Wright GD, Horn HF (2016) Three-dimensional image analysis of the mouse cochlea. Differentiation 91(4-5):104–108CrossRefGoogle Scholar
  42. 42.
    Wu L (2012a) Classification of fruits using computer vision and a multiclass support vector machine. Sensors 12(9):12489–12505Google Scholar
  43. 43.
    Wu L (2012b) An MR brain images classifier via principal component analysis and kernel support vector machine. Prog Electromagn Res 130:369–388CrossRefGoogle Scholar
  44. 44.
    Xiong H et al (2011) Simultaneously reduced NKCC1 and Na,K-ATPase expression in murine cochlear lateral wall contribute to conservation of endocochlear potential following a sensorineural hearing loss. Neurosci Lett 488(2):204–209CrossRefGoogle Scholar
  45. 45.
    Xuan SB et al (2016) Structural interpretation of the Chuan-Dian block and surrounding regions using discrete wavelet transform. Int J Earth Sci 105(5):1591–1602CrossRefGoogle Scholar
  46. 46.
    Yahia K et al (2014) Induction motors airgap-eccentricity detection through the discrete wavelet transform of the apparent power signal under non-stationary operating conditions. ISA Trans 53(2):603–611CrossRefGoogle Scholar
  47. 47.
    Yang J (2015) Preclinical diagnosis of magnetic resonance (MR) brain images via discrete wavelet packet transform with Tsallis entropy and generalized eigenvalue proximal support vector machine (GEPSVM). Entropy 17(4):1795–1813Google Scholar
  48. 48.
    Yang M (2016) Dual-tree complex wavelet transform and twin support vector machine for pathological brain detection. Appl Sci 6(6):169Google Scholar
  49. 49.
    Yang M et al (2016) Detection of left-sided and right-sided hearing loss via fractional fourier transform. Entropy 18(5):194Google Scholar
  50. 50.
    Yuan TF (2015) Detection of subjects and brain regions related to Alzheimer’s disease using 3D MRI scans based on eigenbrain and machine learning. Front Comput Neurosci 9:66Google Scholar
  51. 51.
    Zhang Y (2015) Detection of Alzheimer’s disease by displacement field and machine learning. PeerJ 3:e1251CrossRefGoogle Scholar
  52. 52.
    Zhang YD et al (2014) An improved reconstruction method for CS-MRI based on exponential wavelet transform and iterative shrinkage/thresholding algorithm. Journal of Electromagnetic Waves and Applications 28(18):2327–2338CrossRefGoogle Scholar
  53. 53.
    Zhou X-X (2016) Comparison of machine learning methods for stationary wavelet entropy-based multiple sclerosis detection: decision tree, k-nearest neighbors, and support vector machine. Simulation 92(9):861–871CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Yi Chen
    • 1
    • 2
    • 3
  • Ming Yang
    • 4
    • 5
  • Xianqing Chen
    • 6
  • Bin Liu
    • 7
  • Hainan Wang
    • 1
    • 3
    • 5
  • Shuihua Wang
    • 1
    • 8
  1. 1.School of Computer Science and TechnologyNanjing Normal UniversityNanjingChina
  2. 2.Hunan Provincial Key Laboratory of Network Investigational TechnologyHunan Policy AcademyChangshaChina
  3. 3.Key Laboratory of Image and Video Understanding for Social SafetyNanjing University of Science and TechnologyNanjingChina
  4. 4.Department of Radiology, Nanjing Children’s HospitalNanjing Medical UniversityNanjingChina
  5. 5.Key Laboratory of Intelligent Computing and Information Processing in Fujian Provincial UniversityQuanzhou Normal UniversityQuanzhouChina
  6. 6.Department of electrical engineering, College of engineeringZhejiang Normal UniversityJinhuaChina
  7. 7.Department of RadiologyZhong-Da Hospital of Southeast UniversityNanjingChina
  8. 8.Department of Electrical EngineeringThe city college of New YorkNew YorkUSA

Personalised recommendations