İnsan Yürüyüşünün Yapay Zekâyla Sınıflandırılması: Sistematik Bir Gözden Geçirme

Abstract

Yürüyüş, duruş ve salınım fazı olarak incelenen döngüsel sürece sahip bir kazanımdır. Yürüyüş döngüler içerisinde zaman ve mesafe farklılıkları, eklem ve kaslardaki değişimleri içeren özelliklere sahiptir. Bu özellikler yürüyüşü kişiye özel hale getirir. Yürüyüşü çıplak gözle sınıflandırmak ve tanımlamak oldukça zor sübjektif bir yaklaşımdır. Görüntüleme ve sensör teknolojisinin gelişmesiyle yürüme hakkında birçok veri elde edilmektedir. Bu verilerin çokluğu ve karmaşıklığı, yorumlanmasında hatalara yol açabilmektedir. Nesnelerinde insanlar gibi düşünmesini sağlama fikri çok uzunca zamandır insanoğlunun aklında yer etmiştir. Verilerin sağlıklı bir şekilde tanımlanıp işlenmesi süresinde yapay zeka uygulamaları kullanılmaktadır. Yapay zekâ insan beyninin mental fonksiyonlarını taklit ederek sağlık alanındaki verileri yorumlama yeteneğine sahiptir. İnsanlar gibi çözümler üretmeyi ve insanların düşünme biçimlerini taklit etmeyi sağlayan bir teknoloji olduğu söylenebilir. Veriler arası uygunluğu tespit etmesi ve yeni verileri kolayca dâhil edilebilmesi literatürdeki çalışmaları yapay zekânın yürüyüş sınıflandırmasında kullanımına yönlendirmiştir. Veri kümesi, yapay zekanın eğitilmesi ve daha sonra yeni verilen verilerin yorumlaması için daha çok olmalıdır. Yapay Zeka Algoritmaları, veri kümesinin çeşidi ile ilişkili yöntemdir. Veri kümesinin çeşitliliğine göre kullanılacak algoritma farklılık gösterebilir. Bu da yapay zekanın öğrenmesi ve yorumlamasındaki başarısını etkileyebilir. Yapay zekâ uygulamasını geliştirmeden önce ilk uygulanacak işlem, veri kümesinden istenilen sonuca göre maksimum performans sağlayacak algoritmanın seçimidir. Algoritma yapay bir sinir ağı olarak verileri işleyip yorumlamaktadır. Bu çalışmada, yapay zekâ algoritmaları kullanarak yürüyüşün tespitini ve yürüyüş sınıflandırmasını yapan literatür çalışmaları incelenmiştir. Literatürdeki çalışmaların seçimi yapılırken, algoritma ve bilgisayar teknolojisindeki yenilikler göz önüne alınarak son yıllardaki çalışmalara odaklanılmıştır. Yapay zekâ algoritmalarının yürüyüş sınıflandırmadaki başarısı, en uygun yürüyüş parametresi, ideal ortamın ve algoritmanın belirlenmesi amaçlanmaktadır.

Keywords

• Makine öğrenme
• Sağlıkta yapay zeka
• Yapay zeka
• Yürüme analizi
• Yürüyüş

Classification of Human Gait with Artificial Intelligence: A Systematic Review

Abstract

Gait is a gain together the cyclic process studied as phase of posture and oscillation. Gait has features that include time and distance differences in cycles, changes in joints, and muscles. These features personify gait. Gait is subjective approach that is quite difficult to classify and define with naked eye. A lot of data about gait is obtained with development of imaging and sensor technology. The multiplicity and complexity of data can lead to errors in its interpretation. The idea of making things think like humans have been in mind of mankind for a long-time. Artificial Intelligence (AI) applications are used to identify and process data in healthy way. AI is able to interpret data in field of health by mimicking mental functions of human brain. It can be said that there is a technology that allows you to create solutions like humans and mimic way people think. The detection of suitability in data and easy added of new data has led studies in literature to use of AI in gait classification. The dataset should be more for AI training and then interpretation of newly data. The AI algorithm is method associated with dataset and result. The algorithm to be used may vary depending on variety of dataset. It can affect AI learning and accuracy. The first process before developing the application of AI is selection of algorithm that will provide maximum accuracy based on the desired result from dataset. The algorithms process and interprets data so an artificial neural network. In this study, literature studies that detect and classify gait using AI were examined. The selection of studies focused on recent studies, taking into account innovations in algorithms and computer technology. The accuracy of AI in classification is influenced by selection of gait parameter, dataset, and algorithm.

Keywords

• Artificial intelligence
• Artificial intelligence in health
• Gait
• Gait analysis
• Machine learning

References

1. Alsancak S, Yürüyüş terminolojisi. Ankara Sağlık Hizmetleri Dergisi. 2015; 14(2): 6-1.
2. Erbahçeci F, Bayramlar K. Yürüyüş. Ankara: Hipokrat Kitabevi; 2018.
3. Süzen AA, Şimşek M. A Novel Approach to Machine Learning Application to Protection Privacy Data in Healthcare: Federated Learning. Namık Kemal Tıp Dergisi. 2020; 8 (1), 22-30.
4. Mitchell RS, Michalski JG, Carbonell TM. An artificial intelligence approach. Springer, Berlin. 2013.
5. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S ve ark. Artificial intelligence in healthcare: past, present and future. Stroke and vascular neurology. 2017; 2(4), 230-243.
6. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. New England Journal of Medicine. 2019; 380(14), 1347-1358.
7. Holzinger A. Interactive machine learning for health informatics: when do we need the human-in-the-loop?. Brain Informatics. 2016; 3(2), 119-131.
8. Finlayson SG, Bowers JD, Ito J, Zittrain JL, Beam AL, Kohane IS. Adversarial attacks on medical machine learning. Science. 2019; 363(6433), 1287-1289.

9. Lakany H. Extracting a diagnostic gait signature. Pattern Recognit. 2008; 41:1627–37.
10. Alaqtash M, Yu H, Brower R, Abdelgawad A, Sarkodie-Gyan T. Application of wearable sensors for human gait analysis using fuzzy computational algorithm. Eng Appl Artif Intell. 2011;24:1018–25.
11. Uzun T. Yapay Zeka Ve Sağlık Uygulamaları. İzmir Katip Çelebi Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi. 2020; Erken Görünüm: 0-0.
12. Lai DT, Levinger P, Begg RK, Gilleard WL, Palaniswami M. Automatic recognition of gait patterns exhibiting patellofemoral pain syndrome using a support vector machine approach. IEEE Transactions on Information Technology in Biomedicine. 2009; 13(5): 810-817.
13. Asadi H, Dowling R, Yan B, Mitchell P. Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy. PloS one. 2014; 9(2).
14. Das D, Chakrabarty A. Human Gait Recognition using Deep Neural Networks. In Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies; 2016 Mart; 1-6.
15. Shi X, Li Y, Zhou F, Liu L. Human activity recognition based on deep learning method. In 2018 International Conference on Radar (RADAR); 2018 Ağustos; 1-5.
16. Sun L, Yuan YX, Zhang Q, Wu YC. Human Gait Classification Using Micro-Motion and Ensemble Learning. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium; 2018 Temmuz; 6971-6974.
17. Liu L, Yin Y, Qin W, Li Y. Gait recognition based on outermost contour. International Journal of Computational Intelligence Systems. 2011; 4(5): 1090-1099.
18. Benouis M, Senouci M, Tlemsani R, Mostefai L. Gait recognition based on model-based methods and deep belief networks. International Journal of Biometrics. 2016; 8(3-4), 237-253.
19. Choi A, Jung H, Lee KY, Lee S, Mun JH. Machine learning approach to predict center of pressure trajectories in a complete gait cycle: a feedforward neural network vs. LSTM network. Medical & biological engineering & computing. 2019; 57(12), 2693-2703.
20. Das D, Saharia S. Human gait analysis and recognition using support vector machines. International Journal of Computer Science & Information Technology. 2014; 6(5).
21. Das D. Human gait classification using combined HMM & SVM hybrid classifier. In 2015 International Conference on Electronic Design, Computer Networks & Automated Verification (EDCAV); 2015 Ocak; 169-174.
22. Dehzangi O, Taherisadr M, ChangalVala R. IMU-based gait recognition using convolutional neural networks and multi-sensor fusion. Sensors. 2017; 17(12), 2735.
23. Ismail H, Radwan I, Suominen H, Goecke R. Gait Estimation and Analysis from Noisy Observations. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2019 Temmuz; 2707-2712.
24. Kong W, Saad MH, Hannan MA, Hussain A. Human gait state classification using artificial neural network. In 2014 IEEE symposium on computational intelligence for multimedia, signal and vision processing (CIMSIVP); 2014 Aralık; 1-5.
25. Serrano MM, Chen YP, Howard A, Vela PA. Automated feet detection for clinical gait assessment. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2016, Ağustos; 2161-2164.
26. Sharif M, Attique M, Tahir MZ, Yasmim M, Saba T, Tanik, UJ. A Machine Learning Method with Threshold Based Parallel Feature Fusion and Feature Selection for Automated Gait Recognition. Journal of Organizational and End User Computing (JOEUC). 2020; 32(2), 67-92.
27. Tan HX, Aung NN, Tian J, Chua MCH, Yang YO. Time series classification using a modified LSTM approach from accelerometer-based data: A comparative study for gait cycle detection. Gait & posture. 2019; 74, 128-134.
28. Wang X,Yan WQ. Human Gait Recognition Based on Frame-by-Frame Gait Energy Images and Convolutional Long Short-Term Memory. International journal of neural systems. 2019;1950027-1950027.
29. Wang Q, Ye L, Luo H, Men A, Zhao F, Huang Y. Pedestrian stride-length estimation based on LSTM and denoising autoencoders. Sensors. 2019; 19(4), 840.
30. Wolf T, Babaee M, Rigoll G. Multi-view gait recognition using 3D convolutional neural networks. In 2016 IEEE International Conference on Image Processing (ICIP); 2016 Eylül; 4165-4169. IEEE.
31. Wu J, Wu B. The novel quantitative technique for assessment of gait symmetry using advanced statistical learning algorithm. BioMed research international. 2015.
32. Yoo JH, Hwang D, Moon KY, Nixon MS. Automated human recognition by gait using neural network. In 2008 First Workshops on Image Processing Theory, Tools and Applications; 2008, Kasım;1-6).
33. Yu T, Liu X, Mei Y, Dai C, Yan J. Identification by Gait Using Convolutional Restricted Boltzmann Machine and Voting Algorithm. In 2018 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData); 2018 Temmuz; 677-681.
34. Zhang H, Ye C. RGB-D camera based walking pattern recognition by support vector machines for a smart rollator. International journal of intelligent robotics and applications. 2017; 1(1), 32-42.
35. Ferrari A, Bergamini L, Guerzoni G, Calderara S, Bicocchi N, Vitetta G ve ark. Gait-Based Diplegia Classification Using LSMT Networks. Journal of healthcare engineering. 2019.
36. Wang C, Zhang J, Wang L, Pu J, Yuan X. Human identification using temporal information preserving gait template. IEEE transactions on pattern analysis and machine intelligence. 2012; 34(11), 2164-2176.
37. Begg RK, Palaniswami M, Owen B. Support vector machines for automated gait classification. IEEE transactions on Biomedical Engineering. 2005; 52(5), 828-838.
38. Begg R, Kamruzzaman J. A machine learning approach for automated recognition of movement patterns using basic, kinetic and kinematic gait data. Journal of biomechanics. 2005; 38(3), 401-408.
39. Kamruzzaman J, Begg RK. Support vector machines and other pattern recognition approaches to the diagnosis of cerebral palsy gait. IEEE Transactions on Biomedical Engineering. 2006; 53(12), 2479-2490.