Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi

AYDIN, Fatih; Aslan, zafer

Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi

Fatih AYDIN, (Kırklareli Üniversitesi, Teknik Bilimler Meslek Yüksekokulu, Bilgisayar Programcılığı Programı, 39020, Kırklareli, Türkiye)

Zafer ASLAN (İstanbul Aydın Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği, 34295, İstanbul, Türkiye)

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

0 0

Yıl: 2017 Cilt: 32 Sayı: 3 Sayfa Aralığı: 749 - 766 Metin Dili: Türkçe İndeks Tarihi: 29-07-2022

Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi

Öz:

Bu çalışma da yere uygulanan kuvvet sinyalleri kullanılarak Amyotrofik lateral skleroz (ALS), Huntington hastalığı (HD) ve Parkinson hastalığı (PD) gibi nöro dejeneratif hastalıkların (NDD) sınıflandırılmasında kullanılabileceği önerilmektedir. Deneyler 16 kontrol bireyi (CO), 13 ALS, 20 HD ve 15 PD'ye ait veriler kullanılarak gerçekleştirildi. İlk olarak kuvvet sinyalleri, Discrete Meyer (dmey) dalgacığı kullanılarak yedinci seviyeye kadar ayrıştırıldı. Yeni oluşan sinyallerden yedinci seviyedeki yaklaşım sinyali seçildi. Bu sinyal üzerinde tepe (peak) analizi gerçekleştirilerek sinyalin lokal maksimumları, tepe'nin x ekseni değerleri, tepe genişliği ve tepe çıkıntıları elde edildi. Daha sonra bu dört tepe özelliğinin her birinden 15 adet temel istatistiksel öznitelik elde edildi. Böylelikle sol ayak için 60 ve sağ ayak için 60 olmak üzere toplamda 120 öznitelik elde edildi. Daha sonra OneRules sınıflandırıcı kullanılarak bu öznitelikler içerisinden en çok enformasyon veren öznitelikler seçildi. Bir sonraki aşamada ise Radyal Tabanlı Fonksiyon Ağı (RBFNetwork), Adaptif Yükseltme (Adaboost) ve Eklemeli Lojistik Regresyon (LogitBoost) algoritmaları kullanılarak ALS-CO için %93,1 doğruluk, HD-CO için %97,22 doğruluk, PD-CO için %83,87 doğruluk ve NDD-CO için %92,18 doğruluk elde edildi

Anahtar Kelime:

Diagnosis of neuro degenerative diseases using machine learning methods and wavelet transform

Öz:

This study suggests that the force signals applied to the ground may be used to classify neuro‑degenerative diseases (NDD) such as Amyotrophic lateral sclerosis (ALS), Huntington's disease (HD) and Parkinson's disease (PD). The experiments were performed using data with 16 control subjects (CO), 13 ALS, 20 HD and 15 PD. Firstly, the force signals were separated up to level‑7 using Discrete Meyer (dmey) wavelet. Among the new signals, the approach signal at the seventh level was selected. The local maximums of the peaks, peak locations, peak widths and peak prominences were obtained by performing peak analysis on this signal. Then, 15 basic statistical features from each of these four peak features were obtained. Thus, 60 for each of left and right foot, 120 features were obtained. Among these 120 features, the ones giving the highest information were selected using OneRules classifier. Respectively, 93.1%, 97.22%, 83.87% and 92.18% accuracy was obtained on ALS‑CO, HD‑CO, PD‑CO and NDD‑CO datasets using Radial Basis Function Network (RBFNetwork), Adaptive Boosting (Adaboost) and Additive Logistic Regression (LogitBoost) algorithms

Anahtar Kelime:

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

1. JPND Research. What is Neurodegenerative Disease?. http://www.neurodegenerationresearch.eu/about/what/. Yayın tarihi Şubat 7, 2012. Erişim tarihi Haziran 18, 2017.
2. Özaras N., Yalçın S., Normal Yürüme ve Yürüme Analizi, Turkish Journal of Physical Medicine and Rehabilitation, 48 (3), 2002.
3. Barr A.E., Biomechanics and Gait, Orthopaedic Knowledge Update 7: Home Study Syllabus, Editör: Koval K. J., American Academy of Orthopaedic Surgeons, Rosemont, Illinois, A.B.D., 31-38, 2002.
4. Kanatlı U., Yetkin H., Songür M., Öztürk A., Bölükbaşı S., Yürüme Analizinin Ortopedik Uygulamaları, Türk Ortopedi ve Travmatoloji Birliği Derneği Dergisi, 5 (1- 2), 53-59, 2006.
5. Zengin S., İhmal Edilmiş Aşil Tendon Rüptürlerinde Lindholm Yöntemi ve Sonuçlarının Yürüme Analizi ile Değerlendirilmesi, Doktora Tezi, T.C. Sağlık Bakanlığı Okmeydanı Eğitim ve Araştırma Hastanesi Ortopedi ve Travmatoloji Kliniği, 2007.
6. Özaras N., Yalçın S., Yürüme Analizi, (2. Baskı), Avrupa Tıp Kitapçılık, İstanbul, 2002.
7. NCC-CC (Collaborating Centre for Chronic Conditions), Parkinson's Disease: National Clinical Guideline for Diagnosis and Management in Primary and Secondary Care, Royal College of Physicians of London, London, 2006.
8. Bronstein J.M., Tagliati M., Alterman R. L. and et al., Deep brain stimulation for Parkinson disease: an expert consensus and review of key issues, Archives of neurology (Arch. Neurol), 68 (2), 2011.
9. Frank S., Jankovic J., Advances in the Pharmacological Management of Huntington's Disease, Drugs, 70 (5), 561–71, 2010.
10. Russell P., Harrison R., What is amyotrophic lateral sclerosis, Clinical Pharmacist, 6 (7), 2014.
11. Han J., Jeon H.S., Yi W.J., Jeon B.S., Park K.S., Adaptive windowing for gait phase discrimination in Parkinsonian gait using 3-axis acceleration signals, Medical & biological engineering & computing (MBEC), 47, 1155-1164, 2009.
12. Dutta S., Chatterjee A., Munshi S., An automated hierarchical gait pattern identification tool employing cross-correlation-based feature extraction and recurrent neural network based classification, Expert Systems, 26 (2), 202-217, 2009.
13. Wu Y., Krishnan S., Computer-aided analysis of gait rhythm fluctuations in amyotrophic lateral sclerosis, Medical & biological engineering & computing (MBEC), 47, 1165-1171, 2009.
14. Wu Y., Krishnan S., Statistical Analysis of Gait Rhythm in Patients With Parkinson’s Disease, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 18 (2), 150-158, 2010.
15. Banaie M., Pooyan M., Mikaili M., Introduction and application of an automatic gait recognition method to diagnose movement disorders that arose of similar causes, Expert Systems with Applications, 38, 7359-7363, 2011.
16. Manap H.H., Tahir N.M., Yassin A.I.M., Statistical Analysis of Parkinson Disease Gait Classification using Artificial Neural Network, IEEE Signal Processing and Information Technology (ISSPIT), 60-65, 2011.
17. Daliri M.R., Automatic diagnosis of neuro-degenerative diseases using gait dynamics, Measurement, 45, 1729-1734, 2012.
18. Lee S., Lim J.S., Parkinson’s disease classification using gait characteristics and wavelet-based feature extraction, Expert Systems with Applications, 39, 7338-7344, 2012.
19. Xia Y., Gao Q., Ye Q., Classification of gait rhythm signals between patients withneuro-degenerative diseases and normal subjects: Experiments with statistical features and different classification models, Biomedical Signal Processing and Control, 18, 254-262, 2015.
20. Nair S.R., Tan L.K., Ramli N.M., Lim S.Y., Rahmat K., Nor H.M. A decision tree for differentiating multiple system atrophy from Parkinson’s disease using 3-T MR imaging, European Society of Radiology, 23 (6), 1459- 1466, 2013.
21. Ota M., Nakata Y., Ito K., Kamiya K., Ogawa M., Murata M., Obu S., Kunugi H., Sato N. Differential Diagnosis Tool for Parkinsonian Syndrome Using Multiple Structural Brain Measures, Computational and Mathematical Methods in Medicine, 2013 (6), 1-10, 2013.
22. Drotár P., Mekyskaa J., Rektorováb I., Masarováb L., Smékala Z., Faundez-Zanuyc M., Analysis of in-air movement in handwriting:A novel marker for Parkinson’s disease, Computer Methods and Programs in Biomedicine, 117 (3), 405-411, 2014.
23. Akdemir Ü.Ö., Tokçaer B., Karakuş A., Kapucu L.Ö., Brain 18F-FDG PET Imaging in the Differential Diagnosis of Parkinsonism, Clinical Nuclear Medicine, 93 (3), 220-226, 2014.
24. Lee S., Kim M., Lee H.M., Kwona K., Kim H., Koh S., Differential diagnosis of parkinsonism with visual inspection of posture and gait in the early stage, Gait & Posture, 39 (4), 1138-1141, 2014.
25. Pilleri M., Levedianos G., Weis L., Gasparoli E., Facchini S., Biundo R., Formento-Dojot P., Antonini A., Heart rate circadian profile in the differential diagnosis between Parkinson disease and multiple system atrophy, Parkinsonism and Related Disorders, 20 (2), 217-221, 2014.
26. Navarro-Otano J., Gaig C., Muxi A., Lomeña F., Compta Y., Buongiorno M.T., Martí M.J., Tolosa E., Valldeoriola F., 123I-MIBG cardiac uptake, smell identification and 123I-FP-CIT SPECT in the differential diagnosis between vascular parkinsonism and Parkinson’s disease, Parkinsonism and Related Disorders, 20 (2), 192-197, 2014.
27. Salvatorea C., Cerasab A., Castiglioni I., Gallivanonec F., Augimerib A., Lopezd M., Arabiae G., Morellie M., Gilardi M.C., Quattrone A., Machine learning on brain MRI data for differential diagnosis of Parkinson’s disease and Progressive Supranuclear Palsy, Journal of Neuroscience Methods, 222, 230-237, 2014.
28. Feng J., Huang B., Yang W., Zhang Y., Wang L., Wang L., Zhong X., The putaminal abnormalities on 3.0T magnetic resonance imaging: can they separate parkinsonism-predominant multiple system atrophy from Parkinson’s disease?, Acta radiologica, 56 (3), 322-328, 2014.
29. Baudrexel S., Seifried C., Penndorf B., Klein J.C., Middendorp M., Steinmetz H., Grünwald F., Hilker R., The Value of Putaminal Diffusion Imaging Versus 18- Fluorodeoxyglucose Positron Emission Tomography for the Differential Diagnosis of the Parkinson Variant of Multiple System Atrophy, Movement Disorders, 29 (3), 380-387, 2014.
30. Huertas-Fernández I., García-Gómez F.J., García-Solís D., Benítez-Rivero S., Marín-Oyaga V.A., Jesús S.,
Cáceres-Redondo M.T., Lojo J.A., Martín-Rodríguez J.F., Carrillo F., Mir P., Machine learning models for the differential diagnosis of vascular parkinsonism and Parkinson’s disease using [123I]FP-CIT SPECT, European journal of nuclear medicine and molecular imaging, 42 (1), 112-119, 2015.
31. Zanigni S., Testa C., Calandra-Buonaura G., Sambati L., Guarino M., Gabellini A., Evangelisti S., Cortelli P., Lodi R., Tonon C., The contribution of cerebellar proton magnetic resonance spectroscopy in the differential diagnosis among parkinsonian syndromes, Parkinsonism and Related Disorders, 21 (8), 929-937, 2015.
32. Bradvica I.S., Mihaljevic´ I., Butkovic´-Soldo S., Kadojic´ D., Titlic´ M., Bradvica M., Kralik K., Transcranial sonography and the pocket smell test in the differential diagnosis between parkinson’s disease and essential tremor, Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology, 36 (8), 1403- 1410, 2015.
33. Vranová H.P, Hényková E., Mareš J., Kaiserová M., Menšíková K., Vaštík M., Hluštík P., Zapletalová J., Strnadb M., Stejskal D., Kaňovský P., Clusterin CSF levels in differential diagnosis of neurodegenerative disorders, Journal of the Neurological Sciences, 361, 117-121, 2016.
34. Drotár P., Mekyska J., Rektorová I., Masarová L., Smékal Z., Faundez-Zanuy M., Evaluation of handwriting kinematics and pressure for differentialdiagnosis of Parkinson’s disease, Artificial Intelligence in Medicine, 67, 39-46, 2016.
35. Aydın F., Aslan Z. Classification of Neurodegenerative Diseases using Machine Learning Methods, International Journal of Intelligent Systems and Applications in Engineering, 5 (1), 1-9, 2017.
36. PhysioNET. Gait Dynamics in Neuro-Degenerative Disease Data Base. http://www.physionet.org/physiobank/database/gaitndd /. Güncelleme tarihi Ekim 28, 2016. Erişim tarihi Haziran 18, 2017.
37. Hausdorff J. M., Ladin Z., Wei J. Y., Footswitch system for measurement of the temporal parameters of gait, Journal of Biomechanics (J. Biomech.), 28, 347–351, 1995.
38. Haşiloğlu A., Dalgacık dönüşümü ve yapay sinir ağları ile döndürmeye duyarsız doku analizi ve sınıflandırma, Turkish Journal of Engineering and Environmental Sciences (Turk J Engin Environ Sci.), 25, 405-413, 2001.
39. Shaker M.M., EEG waves classifier using Wavelet transform and Fourier transform, International Journal of Biological and Life Sciences (Int. J. Biol. Sci.), 1 (2), 85-88, 2005.
40. Proch´azka A., Jech J., Smith J., Wavelet transform use in signal processing, 31st International Conference in Acoustics., Prague, Czech Technical University, 209-213, 1994.
41. Morlet J., Arens G., Fourgeau E., Giard D., Wave propagation and sampling theory, Part1: Complex signal land scattering in multilayer media, Journal of Geophysics, 47, 203-221, 1982.
42. Mallat S. G., Multiresolution approximations and Wavelet orthonormal bases of L2(R), Transactions of the American Mathematical Society (Journal of the AMS), 315 (1), 69-87, 1989.
43. Miner N.E., An introduction to Wavelet theory and analysis, Sandia Raporu, Sandia National Laboratories, Albuquerque, New Mexico, California, A.B.D., 1998.
44. Huang N.E., Introduction to the Hilbert-Huang Transform and Its Related Mathematical Problems, Hilbert Huang transform and its applications, Vol. 5, Editör: Huang N. E., Shen S. S. P., World Scientific Publishing, Hackensack, A.B.D., 1-24, 2005.
45. Drozdov A., Pomortsev I., Tyutyukin K., Baloshin Y., Comparison of Wavelet Transform and Fourier Transform Applied to Analysis of Non-Stationary Processes, Nanosystems: Physics, Chemistry, Mathematics (Nanosist.: fiz. him. mat.), 5 (3), 363-373, 2014.
46. Donald M., Spiegelhalter D.J., Taylor C.C., Machine Learning: Neural and Statistical Classification, Overseas Press, 2009.
47. Nilsson N.J., Introduction to Machine Learning: An Early Draft of a Proposed Textbook, Robotics Laboratory, Department of Computer Science, Stanford University.http://ai.stanford.edu/people/nilsson/MLBO OK.pdf. Yayın tarihi Kasım 3, 1998. Erişim tarihi Haziran 18, 2017.
48. Kohavi R., Provost F., Glossary of Terms, Machine Learning, 30, (2-3), 271-274, 1998.
49. Duda R.O., Hart P.E., Stork D.G., Pattern classification, 2nd ed., Wiley-Interscience, New York, 2001.
50. Alpaydın E., Introduction to Machine Learning, 3rd ed., The MIT Press, 2014.
51. Wolpert D., The Lack of A Priori Distinctions between Learning Algorithms, Neural Computation, 1341-1390, 1996.
52. Wolpert D.H., Macready W.G., No Free Lunch Theorems for Optimization. IEEE Transactions on Evolutionary Computation (TEVC), 1 (1), 67-82, 1997.
53. Witten I.H., Frank E., Data mining : practical machine learning tools and techniques, 3rd ed., Morgan Kaufmann, 2011.
54. Moody J., Fast learning in networks of locally-tuned processing units, Neural Computation, 1, 281-294, 1989.
55. Casdagli M., Nonlinear prediction of chaotic time series, Physica D Nonlinear Phenomena (Physica D), 35, 335-356, 1989.
56. Broomhead D.S., Lowe D., Multivariable functional interpolation and adaptive networks, Complex Systems, 2, 321-355, 1988.
57. Matej S., Lewitt R.M., Practical considerations for 3 D image reconstruction using spherically volume elements, IEEE Transactions on Medical Imaging (IEEE-TMI), 15, 68-78, 1996.
58. Mashor M.Y., Hybrid Training Algorithm for RBF Network, In International Journal of the Computer, The Internet and Management (IJCIM), 8 (2), 50-65, 2000.
59. Freund Y., Schapire R. E., Experiments with a new boosting algorithm, In: Thirteenth International Conference on Machine Learning, San Francisco, A.B.D., 148-156, 1996.
60. Ratsch G., Onoda T., Muller K.R., Soft margins for AdaBoost, Machine Learning, 42, 287–320, 2001.
61. Friedman J., Hastie T., Tibshirani R., Additive logistic regression: a statistical view of boosting, The Annals of Statistics, 28 (2), 337–407, 2000.
62. Cai Y., Feng K., Lu W., Chou K., Using LogitBoost classifier to predict protein structural classes, Journal of Theoretical Biology, 238 (1), 172-176, 2006.
63. Holte R.C., Very simple classification rules perform well on most commonly used datasets, Machine Learning, 11, 63-91, 1993.
64. Rendell L., Seshu R. Learning Hard Concepts Through Constructive Induction, Computational Intelligence, 6, 247−270, 1990.
65. Shavlik J., Mooney R.J., Towell G., Symbolic and Neural Learning Algorithms: An Experimental Comparison, Machine Learning, 6, 111−143, 1991.
66. Buntine W., Niblett T., A Further Comparison of Splitting Rules for Decision−Tree Induction, Machine Learning, 8, 75−86, 1992.
67. Clark P., Niblett T., The CN2 Induction Algorithm, Machine Learning, 3, 261−283, 1989.
68. Mingers J., An Empirical Comparison of Pruning Methods for Decision Tree Induction, Machine Learning, 4 (2), 227−243, 1989.
69. Buddhinath G., Derry D., A Simple Enhancement to One Rule Classification, Department of Computer Science & Software Engineering, University of Melbourne, Australia, 2007.
70. Cohen J., A coefficient of agreement for nominal scales, Educational and Psychological Measurement (EPM), 20 (1), 37–46, 1960.
71. Gwet K., Handbook of Inter-Rater Reliability: The Definitive Guide to Measuring the Extent of Agreement Among Raters, (4th ed.), Advanced Analytics, 2014.
72. Landis J. R., Koch G. G., The measurement of observer agreement for categorical data, Biometrics, 33, 159– 174, 1977.
73. Haltaş A., Alkan A., Karabulut M., Performance Analysis of Heuristic Search Algorithms in Text Classification,Journal of the Faculty of Engineering and Architecture of Gazi University, 30 (3), 417-427, 2015.
74. Lehmann E.L., Casella George, Theory of Point Estimation, (2nd ed.), Springer, New York, A.B.D., 2003.
75. Domingos P., A Unifed Bias-Variance Decomposition and its Applications, In Proc. 17th International Conf. on Machine Learning, San Francisco, CA, A.B.D., 231- 238, 2000.
76. Geman S., Bienenstock E., Doursat R., Neural networks and the bias/variance dilemma, Neural Computation, 4 (1), 1-58, 1992.
77. Mitchell T. M., Machine Learning, McGraw-Hill Science/Engineering/Math, 1997.
78. Bouckaert R.R., Frank E., Hall M., Kirkby R., Reutemann P., Seewald A., Seuse D., WEKA Manual for 3-6-15. https://sourceforge.net/projects/weka/ files/documentation/3.6.x/. Yayın tarihi Aralık 19, 2016. Erişim tarihi Haziran 18, 2017.

APA	AYDIN F, Aslan z (2017). Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. , 749 - 766.
Chicago	AYDIN Fatih,Aslan zafer Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. (2017): 749 - 766.
MLA	AYDIN Fatih,Aslan zafer Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. , 2017, ss.749 - 766.
AMA	AYDIN F,Aslan z Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. . 2017; 749 - 766.
Vancouver	AYDIN F,Aslan z Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. . 2017; 749 - 766.
IEEE	AYDIN F,Aslan z "Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi." , ss.749 - 766, 2017.
ISNAD	AYDIN, Fatih - Aslan, zafer. "Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi". (2017), 749-766.

APA	AYDIN F, Aslan z (2017). Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 32(3), 749 - 766.
Chicago	AYDIN Fatih,Aslan zafer Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi 32, no.3 (2017): 749 - 766.
MLA	AYDIN Fatih,Aslan zafer Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, vol.32, no.3, 2017, ss.749 - 766.
AMA	AYDIN F,Aslan z Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi. 2017; 32(3): 749 - 766.
Vancouver	AYDIN F,Aslan z Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi. 2017; 32(3): 749 - 766.
IEEE	AYDIN F,Aslan z "Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi." Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 32, ss.749 - 766, 2017.
ISNAD	AYDIN, Fatih - Aslan, zafer. "Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nöro dejeneratif hastalıkların teşhisi". Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi 32/3 (2017), 749-766.