Giyilebilir Yürüyüş Analiz Sensörü ile Kişi Sınıflandırmasının Öznitelik Seçme Algoritmaları ile İyileştirilmesi

Öz

Yürüme, canlıların bilinen en eski aktivitelerinden biridir. Konum değiştirmek amacı ile insanların kas ve kemik sistemlerinin koordineli bir şekilde hareket etmesine yürüme denir. Yürüme biyometrik bir ölçüt olarak kabul edilmektedir. Bu yüzden yürüyüş analizi ile kişi tanıma, yaş belirleme, cinsiyet belirleme, nörolojik ve ortopedik hastalık tespiti gibi çalışmalar yapılabilmektedir. Bu çalışmada da giyilebilir yürüyüş analizi sensörü ile kişilerin sınıflandırılmasında sarmal modelli öznitelik seçme yöntemleri kullanılarak daha başarılı sınıflandırma başarı parametrelerinin elde edilmesi amaçlanmıştır. 7’si bayan 9’u bay olmak üzere toplam 16 farklı gönüllü kişinin yürüyüş parametreleri hesaplanarak yürüyüş veri seti oluşturulmuştur. Her gönüllüden 3 kez yürümeleri istenmiş olup toplam 48 yürüyüş ele alınmıştır. Kişi sınıflandırma başarı parametreleri k-en yakın komşuluk yöntemi kullanılarak hesaplanmış olup birini dışarıda bırak çapraz doğrulama yöntemi ile doğrulanmıştır. Sınıflandırma sonuçları ele alındığında 0,979 doğruluk oranı elde edilmiştir. Sonuçlar sınıflandırma başarı parametreleri ve sınıflandırma işlem süresi bakımından incelenmiş olup elde edilen sonuçlar çalışmanın sınıflandırma başarı parametreleri ve sınıflandırma işlem süresi bakımından ciddi oranda iyileştirmeler sağladığı gözlemlenmiştir.

Anahtar Kelimeler

• Yürüyüş analizi,sarmal modelli öznitelik seçme,sınıflandırma,kişi tanıma

Improvement of Wearable Gait Analysis Sensor based Human Classification using Feature Selection Algorithms

Öz

Gait is one of the oldest known activity. It is called gait in the coordinated manner of muscle and bone systems of people with the purpose of changing position. Gait is considered a biometric criterion. Therefore, studies such as human identification, age determination, gender identification, detection of neurological and orthopedic diseases can be done by gait analysis. In this study, it is aimed to obtain more successful classification success parameters by using wrapper model feature selection methods in the human classification with wearable gait analysis sensor. Gait data set was created by calculating the gait parameters of a total of 16 different volunteers including 7 female and 9 male. For each volunteer, 3 different gait parameters were calculated and a total of 48 gait were discussed. Human classification success parameters were calculated by using k-nearest neighborhood method and the results was verified by leave one out cross-validation method. The results were examined in terms of the classification success parameters and the processing time, the results obtained showed significant improvements in the classification success parameters and the classification process time.

Anahtar Kelimeler

• Gait analysis,wrapper feature selection methods,classification,human recognition

Kaynakça

1. N. Yager and A. Amin, "Fingerprint classification: a review," Pattern Analysis and Applications, vol. 7, no. 1, pp. 77-93, Apr 2004, doi: 10.1007/s10044-004-0204-7.
2. L. Hong, Y. F. Wan, and A. Jain, "Fingerprint image enhancement: Algorithm and performance evaluation," Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, pp. 777-789, Aug 1998, doi: 10.1109/34.709565.
3. L. Ma, T. N. Tan, Y. H. Wang, and D. X. Zhang, "Efficient iris recognition by characterizing key local variations," Ieee Transactions on Image Processing, vol. 13, no. 6, pp. 739-750, Jun 2004, doi: 10.1109/tip.2004.827237.
4. R. P. Wildes, "Iris recognition: An emerging biometric technology," Proceedings of the Ieee, vol. 85, no. 9, pp. 1348-1363, Sep 1997, doi: 10.1109/5.628669.
5. J. C. Lee, "A novel biometric system based on palm vein image," Pattern Recognition Letters, vol. 33, no. 12, pp. 1520-1528, Sep 2012, doi: 10.1016/j.patrec.2012.04.007.
6. H. G. Wang, W. Y. Yau, A. Suwandy, and E. Sung, "Person recognition by fusing palmprint and palm vein images based on "Laplacianpalm" representation," Pattern Recognition, vol. 41, no. 5, pp. 1514-1527, May 2008, doi: 10.1016/j.patcog.2007.10.021.
7. Y. B. Zhou and A. Kumar, "Human Identification Using Palm-Vein Images," Ieee Transactions on Information Forensics and Security, vol. 6, no. 4, pp. 1259-1274, Dec 2011, doi: 10.1109/tifs.2011.2158423.
8. C. Oatis, Kinesiology: The mechanics and pathomechanics of human movement: Second edition. 2013.

9. S. Arivazhagan and P. Induja, "Gait Recognition-Based Human Identification and Gender Classification," Proceedings of International Conference on Computer Vision and Image Processing, Cvip 2016, Vol 1, vol. 459, pp. 533-544, 2017, doi: 10.1007/978-981-10-2104-6_48.
10. A. Gümüşçü, "Wearable Sensor based Gait Recognition for Human Identification," in International Conference on Multidisciplinary, Science, Engineering and Technology, Dubai, United Arab Emirates, October 25 -27, 2018 2018, vol. 1, no. 1, pp. 31-33.
11. M. H. Ahmed and A. T. Sabir, "Human Gender Classification based on Gait Features using Kinect Sensor," (in English), 2017 3rd Ieee International Conference on Cybernetics (Cybconf), pp. 243-247, 2017.
12. R. Borras, A. Lapedriza, and L. Igual, "Depth Information in Human Gait Analysis: An Experimental Study on Gender Recognition," in Image Analysis and Recognition, Pt Ii, vol. 7325, A. Campilho and M. Kamel Eds., (Lecture Notes in Computer Science, 2012, pp. 98-105.
13. J. W. Lu, G. Wang, and P. Moulin, "Human Identity and Gender Recognition From Gait Sequences With Arbitrary Walking Directions," Ieee Transactions on Information Forensics and Security, vol. 9, no. 1, pp. 51-61, Jan 2014, doi: 10.1109/tifs.2013.2291969.
14. J. W. Lu and Y. P. Tan, "Gait-Based Human Age Estimation," Ieee Transactions on Information Forensics and Security, vol. 5, no. 4, pp. 761-770, Dec 2010, doi: 10.1109/tifs.2010.2069560.
15. T. Cover and P. Hart, "Nearest neighbor pattern classification," IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21 - 27, 1967, doi: 10.1109/TIT.1967.1053964.
16. M. Schena, D. Shalon, R. Davis, and P. Brown, Quantitative Monitoring of Gene Expression Patterns With a Complementary DNA Microarray. 1995, pp. 467-70.
17. I. I. Yvan Saeys, Pedro Larrañaga, "A review of feature selection techniques in bioinformatics," Bioinformatics, vol. 23, no. 19, pp. 2507-2517, 2007.
18. C. ÇELİK. and H. Ş. BİLGE., "AĞIRLIKLANDIRILMIŞ KOŞULLU KARŞILIKLI BİLGİ İLE ÖZNİTELİK SEÇİMİ," Journal of the Faculty of Engineering and Architecture of Gazi University, vol. 30, no. 4, pp. 0-0, 2015, doi: http://dx.doi.org/10.17341/gummfd.81654.
19. A. Gumuscu, K. Karadag, M. E. Tenekeci, I. B. Aydilek, and Ieee, "Genetic Algorithm Based Feature Selection on Diagnosis of Parkinson Disease via Vocal Analysis," in 25th Signal Processing and Communications Applications Conference (SIU), Antalya, TURKEY, May 15-18 2017, in Signal Processing and Communications Applications Conference, 2017. [Online]. Available: ://WOS:000413813100247
20. J. R. Quinlan, C4.5: programs for machine learning. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc, 1993.
21. E. Abdulhay, N. Arunkumar, K. Narasimhan, E. Vellaiappan, and V. Venkatraman, "Gait and tremor investigation using machine learning techniques for the diagnosis of Parkinson disease," Future Generation Computer Systems-the International Journal of Escience, vol. 83, pp. 366-373, Jun 2018, doi: 10.1016/j.future.2018.02.009.
22. S. Aich, K. W. Choi, P. M. Pradhan, J. Park, and H. C. Kim, "A Performance Comparison Based on Machine Learning Approaches to Distinguish Parkinson's Disease from Alzheimer Disease Using Spatiotemporal Gait signals," Advanced Science Letters, vol. 24, no. 3, pp. 2058-2062, Mar 2018, doi: 10.1166/asl.2018.11847.
23. M. Amboni, A. Cozzolino, K. Longo, M. Picillo, and P. Barone, "Freezing of gait and executive functions in patients with Parkinson's disease," Movement Disorders, vol. 23, no. 3, pp. 395-400, Feb 2008, doi: 10.1002/mds.21850.
24. M. Boutaayamou, M. Demonceau, O. Bruls, J. G. Verly, and G. Garraux, "Analysis of temporal gait features extracted from accelerometer-based signals during ambulatory walking in Parkinson's disease," Movement Disorders, vol. 31, pp. S188-S188, Jun 2016.
25. L. Wang, T. Tan, H. Z. Ning, and W. M. Hu, "Silhouette analysis-based gait recognition for human identification," Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 12, pp. 1505-1518, Dec 2003, doi: 10.1109/tpami.2003.1251144.
26. D. Zhang and Y. H. Wang, "Gender Recognition Based on Fusion of Face and Multi-view Gait," in Advances in Biometrics, vol. 5558, M. Tistarelli and M. S. Nixon Eds., (Lecture Notes in Computer Science, 2009, pp. 1010-1018.
27. J. C. Christensen et al., "Visual knee-kinetic biofeedback technique normalizes gait abnormalities during high-demand mobility after total knee arthroplasty," The Knee, vol. 25, no. 1, pp. 73-82, 2018, doi: 10.1016/j.knee.2017.11.010.
28. P. J. McNair, M. G. Boocock, N. D. Dominick, R. J. Kelly, B. J. Farrington, and S. W. Young, "A Comparison of Walking Gait Following Mechanical and Kinematic Alignment in Total Knee Joint Replacement," The Journal of Arthroplasty, vol. 33, no. 2, pp. 560-564, 2018/02/01/ 2018, doi: https://doi.org/10.1016/j.arth.2017.09.031.
29. V. Aharonson, I. Schlesinger, A. M. McDonald, S. Dubowsky, and A. D. Korczyn, "A Practical Measurement of Parkinson's Patients Gait Using Simple Walker-Based Motion Sensing and Data Analysis," Journal of Medical Devices-Transactions of the Asme, vol. 12, no. 1, Mar 2018, Art no. 011012, doi: 10.1115/1.4038810.
30. N. H. Ghassemi et al., "Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson's Disease," Sensors, vol. 18, no. 1, Jan 2018, Art no. 145, doi: 10.3390/s18010145.
31. Ł. Kidziński, S. Delp, and M. Schwartz, "Automatic real-time gait event detection in children using deep neural networks," PLOS ONE, vol. 14, no. 1, p. e0211466, 2019, doi: 10.1371/journal.pone.0211466.
32. I. Mileti et al., "Measuring Gait Quality in Parkinson’s Disease through Real-Time Gait Phase Recognition," Sensors, vol. 18, no. 3, 2018, doi: 10.3390/s18030919.
33. A. Samà et al., "Determining the optimal features in freezing of gait detection through a single waist accelerometer in home environments," Pattern Recognition Letters, vol. 105, pp. 135-143, 2018/04/01/ 2018, doi: https://doi.org/10.1016/j.patrec.2017.05.009.
34. J. Ziegier, H. Gattringer, and A. Mueller, "Classification of Gait Phases Based on Bilateral EMG Data Using Support Vector Machines," in 2018 7th IEEE International Conference on Biomedical Robotics and Biomechatronics (Biorob), 26-29 Aug. 2018 2018, pp. 978-983, doi: 10.1109/BIOROB.2018.8487750.
35. A. P. Rocha et al., "Parkinson's Disease Assessment Based on Gait Analysis Using an Innovative RGB-D Camera System," in 2014 36th Annual International Conference of the Ieee Engineering in Medicine and Biology Society, (IEEE Engineering in Medicine and Biology Society Conference Proceedings, 2014, pp. 3126-3129.
36. G. M. Meurisse, F. Dierick, B. Schepens, and G. J. Bastien, "Determination of the vertical ground reaction forces acting upon individual limbs during healthy and clinical gait," Gait & Posture, vol. 43, pp. 245-250, 2016/01/01/ 2016, doi: https://doi.org/10.1016/j.gaitpost.2015.10.005.
37. F. Kluge et al., "Pre-operative sensor-based gait parameters predict functional outcome after total knee arthroplasty," Gait & Posture, vol. 66, pp. 194-200, 2018/10/01/ 2018, doi: https://doi.org/10.1016/j.gaitpost.2018.08.026.
38. C. Raccagni et al., "Sensor-based gait analysis in atypical parkinsonian disorders," Brain and behavior, vol. 8, no. 6, pp. e00977-e00977, 2018, doi: 10.1002/brb3.977.
39. S. M. H. Sithi Shameem Fathima and R. S. D. Wahida Banu, Abnormal walk identification for systems using gait patterns. 2016, pp. S112-S117.
40. A. de M. e Souza and M. Stemmer, Extraction and Classification of Human Body Parameters for Gait Analysis. 2018.
41. M. Nieto-Hidalgo, F. J. Ferrández-Pastor, R. J. Valdivieso-Sarabia, J. Mora-Pascual, and J. M. García-Chamizo, "A vision based proposal for classification of normal and abnormal gait using RGB camera," Journal of Biomedical Informatics, vol. 63, pp. 82-89, 2016/10/01/ 2016, doi: https://doi.org/10.1016/j.jbi.2016.08.003.
42. B. Mariani, "Assessment of Foot Signature Using Wearable Sensors for Clinical Gait Analysis and Real-Time Activity Recognition," EPFL. [Online]. Available: http://infoscience.epfl.ch/record/180626/files/EPFL_TH5434.pdf
43. A. Brégou Bourgeois, B. Mariani, K. Aminian, P. Y. Zambelli, and C. J. Newman, "Spatio-temporal gait analysis in children with cerebral palsy using, foot-worn inertial sensors," Gait & Posture, vol. 39, no. 1, pp. 436-442, 2014/01/01/ 2014, doi: https://doi.org/10.1016/j.gaitpost.2013.08.029.
44. J. H. Holland, "Genetic Algorithms," Scientific American, vol. 267, 1992, doi: doi:10.1038/scientificamerican0792-66.
45. H. Jeon et al., "Automatic Classification of Tremor Severity in Parkinson's Disease Using a Wearable Device," Sensors, vol. 17, no. 9, Sep 2017, Art no. 2067, doi: 10.3390/s17092067.