Etkili Cinsiyet Tanıma için Yürüyüş Verisinin Kullanımı

Year 2021, , 27 - 31, 31.12.2021

Zehra Karapınar Şentürk

https://doi.org/10.31590/ejosat.1040002

Abstract

Biyometrik tanıma uygulamaları, çoğunlukla otomatik algılama için güvenilirlik ve kullanım kolaylığı nedeniyle günümüzde sıklıkla kullanılmaktadır. Kimlik doğrulama ve cinsiyet sınıflandırması için göz, yüz, parmak izi ve sese dayalı birçok uygulama bulunmaktadır. Bu makalede, insanların adımlarının özelliklerini kullanarak cinsiyet tespiti üzerinde durduk. Farklı bir biyometrik işaret araştırıldı. Kişilerin cinsiyet bilgilerini belirlemek için yürüyüş analizleri yapıldı. Bir yürüyüşün hızı, değişkenliği, simetrisi gibi temel parametreleri, Physilog 5 sensörü ile elde edilen çeşitli geçici, uzamsal ve yükseklik parametreleri analizde kullanılmıştır. Bu öznitelikler temel alınarak bir 321-D öznitelik vektörü oluşturulmuş ve bunlarla bir Yapay Sinir Ağları (YSA) modeli eğitilmiştir. %95.83 doğruluk elde edildi. Deneysel sonuçlar, önerilen YSA tabanlı yürüyüş analizi sisteminin cinsiyet sınıflandırması için en son teknolojiye karşı başarısını göstermektedir.

Keywords

Yapay Sinir Ağları, Yürüyüş Analizi, Cinsiyet Sınıflandırması.

Gait Data for Efficient Gender Recognition

Abstract

Biometric recognition applications have been frequently used nowadays mostly because of reliability and ease of use for automated detection. There are many applications based on eyes, face, fingerprint, and voice for authentication and gender classification. In this paper, we focused on gender detection using the features of the steps of people. A different biometric sign has been investigated. Gait analyses were examined to determine the gender information of the people. Basic parameters like speed, variability, and symmetry of a gait, its several temporary, spatial, and height parameters, which were obtained via Physilog 5 sensor, were used in the analysis. A 321-D feature vector was comprised based on these features and an Artificial Neural Networks (ANN) model was trained with them. 95.83% accuracy was obtained. The experimental results show the success of the proposed ANN-based gait analysis system against the state-of-the-art for gender classification.

Keywords

Artificial Neural Networks, Gait Analysis, Gender Classification

References

• Barkana, B. D., & Zhou, J. (2015). A new pitch-range based feature set for a speaker’s age and gender classification. Applied Acoustics, 98, 52–61. https://doi.org/10.1016/j.apacoust.2015.04.013
• Cascone, L., Medaglia, C., Nappi, M., & Narducci, F. (2020). Pupil size as a soft biometrics for age and gender classification. Pattern Recognition Letters, 140, 238–244. https://doi.org/10.1016/j.patrec.2020.10.009
• Chandra Sekhar Reddy, P., Sarma, K. S. R. K., Sharma, A., Varaprasada Rao, P., Govinda Rao, S., Sakthidharan, G. R., & Kavitha, K. (2020).
• Enhanced age prediction and gender classification (EAP-GC) framework using regression and SVM techniques. Materials Today: Proceedings. https://doi.org/10.1016/j.matpr.2020.10.857
• Chen, Z., Edwards, A., Gao, Y., & Zhang, K. (2019). Learning discriminative subregions and pattern orders for facial gender classification. Image and Vision Computing, 89, 144–157. https://doi.org/10.1016/j.imavis.2019.06.012
• Duan, M., Li, K., Yang, C., & Li, K. (2018). A hybrid deep learning CNN–ELM for age and gender classification. Neurocomputing, 275, 448–461. https://doi.org/10.1016/j.neucom.2017.08.062
• Gattal, A., Djeddi, C., Siddiqi, I., & Chibani, Y. (2018). Gender classification from offline multi-script handwriting images using oriented Basic Image Features (oBIFs). Expert Systems with Applications, 99, 155–167. https://doi.org/10.1016/j.eswa.2018.01.038
• Gümüşçü, A. (2019). Giyilebilir Yürüyüş Analiz Sensörü ile Kişi Sınıflandırmasının Öznitelik Seçme Algoritmaları ile İyileştirilmesi. In Fırat Üniversitesi Müh. Bil. Dergisi (Vol. 31, Issue 2).
• Gumuscu, A., Karadag, K., Caliskan, M., Tenekeci, M. E., & Akaslan, D. (2018). Gender classification via wearable gait analysis sensor. 26th IEEE Signal Processing and Communications Applications Conference, SIU 2018, 1–4. https://doi.org/10.1109/SIU.2018.8404181
• Horin, A. P., Myers, P. S., Pickett, K. A., Earhart, G. M., & Campbell, M. C. (2021). Resting-state functional connectivity associated with gait characteristics in people with Parkinson’s disease. Behavioural Brain Research, 113398. https://doi.org/10.1016/j.bbr.2021.113398
• Isaac, E. R. H. P., Elias, S., Rajagopalan, S., & Easwarakumar, K. S. (2019). Multiview gait-based gender classification through pose-based voting. Pattern Recognition Letters, 126, 41–50. https://doi.org/10.1016/j.patrec.2018.04.020
• Jain, A., & Kanhangad, V. (2018). Gender classification in smartphones using gait information. Expert Systems with Applications, 93, 257–266. https://doi.org/10.1016/j.eswa.2017.10.017
• Kaya, H., Salah, A. A., Karpov, A., Frolova, O., Grigorev, A., & Lyakso, E. (2017). Emotion, age, and gender classification in children’s speech by humans and machines. Computer Speech and Language, 46, 268–283. https://doi.org/10.1016/j.csl.2017.06.002
• Kitade, I., Nakajima, H., Takahashi, A., Matsumura, M., Shimada, S., Kokubo, Y., & Matsumine, A. (2020). Kinematic, kinetic, and musculoskeletal modeling analysis of gait in patients with cervical myelopathy using a severity classification. Spine Journal, 20(7), 1096–1105. https://doi.org/10.1016/j.spinee.2020.01.014
• Lv, C., Wu, Z., Zhang, D., Wang, X., & Zhou, M. (2019). 3D Nose shape net for human gender and ethnicity classification. Pattern Recognition Letters, 126, 51–57. https://doi.org/10.1016/j.patrec.2018.11.010
• Nishida, D., Mizuno, K., Yamada, E., Tsuji, T., Hanakawa, T., & Liu, M. (2021). Correlation between the brain activity with gait imagery and gait performance in adults with Parkinson’s disease: A data set. Data in Brief, 36, 106993. https://doi.org/10.1016/j.dib.2021.106993
• Nutakki, C., Mathew, R. J., Suresh, A., Vijay, A. R., Krishna, S., Babu, A. S., & Diwakar, S. (2020). Classification and Kinetic Analysis of Healthy Gait using Multiple Accelerometer Sensors. Procedia Computer Science, 171, 395–402. https://doi.org/10.1016/j.procs.2020.04.041
• Pathan, R. K., Uddin, M. A., Nahar, N., Ara, F., Hossain, M. S., & Andersson, K. (2020). Gender Classification from Inertial Sensor-Based Gait Dataset. International Conference on Intelligent Computing and Optimization, 583–596. https://doi.org/10.1007/978-3-030-68154-8_51
• Physilog® | Inertial Measurement Sensor (IMU). (n.d.). Retrieved June 3, 2021, from https://research.gaitup.com/physilog/
• Prabhu, P., Karunakar, A. K., Anitha, H., & Pradhan, N. (2020). Classification of gait signals into different neurodegenerative diseases using statistical analysis and recurrence quantification analysis. Pattern Recognition Letters, 139, 10–16. https://doi.org/10.1016/j.patrec.2018.05.006
• Qawaqneh, Z., Mallouh, A. A., & Barkana, B. D. (2017). Age and gender classification from speech and face images by jointly fine-tuned deep neural networks. Expert Systems with Applications, 85, 76–86. https://doi.org/10.1016/j.eswa.2017.05.037
• Reynaldo, N., Goenawan, Chanrico, W., Suhartono, D., & Purnomo, F. (2019). Gender demography classification on instagram based on user’s comments section. Procedia Computer Science, 157, 64–71. https://doi.org/10.1016/j.procs.2019.08.142
• Rwigema, J., Mfitumukiza, J., & Tae-Yong, K. (2021). A hybrid approach of neural networks for age and gender classification through decision fusion. In Biomedical Signal Processing and Control (Vol. 66, p. 102459). Elsevier Ltd. https://doi.org/10.1016/j.bspc.2021.102459
• Swaminathan, A., Chaba, M., Sharma, D. K., & Chaba, Y. (2020). Gender Classification using Facial Embeddings: A Novel Approach. Procedia Computer Science, 167, 2634–2642. https://doi.org/10.1016/j.procs.2020.03.342
• Zakaria, N. K., Jailani, R., & Tahir, N. M. (2015). Application of ANN in Gait Features of Children for Gender Classification. Procedia Computer Science, 76, 235–242. https://doi.org/10.1016/j.procs.2015.12.348
• Zeng, W., Liu, F., Wang, Q., Wang, Y., Ma, L., & Zhang, Y. (2016). Parkinson’s disease classification using gait analysis via deterministic learning. Neuroscience Letters, 633, 268–278. https://doi.org/10.1016/j.neulet.2016.09.043