Göz Özelliklerinin LSTM-PSO Modeli kullanılarak Otizm Sınıflandırılması

Yıl 2023, , 563 - 570, 31.12.2023

Dilber Çetintaş , Taner Tuncer

https://doi.org/10.24012/dumf.1327654

Öz

Otizm birçok biyobelirteci olan karmaşık bir rahatsızlıktır. Bu karmaşık rahatsızlığı tanımlamak ve ayırtedebilmek birden fazla biyolojik özelliği kullanarak mümkün olabilmektedir. Bu özelliklerden biri de göz hareketleridir. Çalışma kullanıcılara özgü gözbebeği boyutu, göz pozisyonları(X-Y koordinatları), ilgi alanının noktaları, iris yarıçapı parametrelerinden oluşan dizileri kullanarak otizm spektrum bozukluğu olan (OSB) ve otizm spektrum bozukluğu olmayan (TS) bireyleri LSTM ağı ile otomatik olarak sınıflandırmayı amaçlamaktadır. Bu doğrultuda ilk adım olarak herbir hareketin tüm parametreleri ayrı bir dizi olarak alınır. Alınan diziler ikinci basamakta LSTM ağında işlenir. İşleme aşamasında pencere boyutunun doğru şeçilmesi sonucu etkileyen en önemli faktörlerden biridir. Bu doğrultuda modelde pencere boyutunun optimum seçilebilmesi için PSO (Parçacık Sürü Optimizasyonu) algoritması kullanılır. LSTM-PSO hibrit modeli kullanılarak iki senaryo gerçekleştirilir. Bu senaryolardan biri tüm özellikleri içerirken senaryo 2’de sadece gözbebeği boyutu ve ilgi alanı özellikleri mevcuttur ve DVM (Destek Vektör Makinesi) sınıflandırıcısı ile başarı oranı senaryo 2’de %98,64 maximum olarak ölçülür. Sonuç göz izleme verileri kullanılarak otizmin LSTM ile sınıflandırılmasının mümkün olduğunu ve bu yöntemin otizm tanısı ve tedavisi için potansiyel olarak faydalı olabileceğini göstermektedir.

Anahtar Kelimeler

Göz hareketleri, LSTM, PSO, Pencere Boyutu

Kaynakça

• [1] Wing, L., & Gould, J. (1979). Severe impairments of social interaction and associated abnormalities in children: Epidemiology and classification. Journal of autism and developmental disorders, 9(1), 11-29.
• [2] Loth, E., Spooren, W., Ham, L. M., Isaac, M. B., Auriche-Benichou, C., Banaschewski, T., ... & Murphy, D. G. (2016). Identification and validation of biomarkers for autism spectrum disorders. Nature reviews Drug discovery, 15(1), 70-70.
• [3] Volkmar, F. R., Cicchetti, D. V., Dykens, E., Sparrow, S. S., Leckman, J. F., & Cohen, D. J. (1988). An evaluation of the autism behavior checklist. Journal of autism and developmental disorders, 18(1), 81-97.
• [4] Schopler, E., Reichler, R. J., DeVellis, R. F., & Daly, K. (1980). Toward objective classification of childhood autism: Childhood Autism Rating Scale (CARS). Journal of autism and developmental disorders.
• [5] Ghosh, S., & Guha, T. (2021, November). Towards Autism Screening through Emotion-guided Eye Gaze Response. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 820-823). IEEE.
• [6] Minissi ME, Chicchi Giglioli IA, Mantovani F, Alcañiz Raya M. Assessment of the Autism Spectrum Disorder Based on Machine Learning and Social Visual Attention: A Systematic Review. J Autism Dev Disord. 2022 May;52(5):2187-2202. doi: 10.1007/s10803-021-05106-5. Epub 2021 Jun 8. PMID: 34101081; PMCID: PMC9021060.
• [7] M. Okano and M. Asakawa, "Eye tracking analysis of consumer's attention to the product message of web advertisements and TV commercials," 2017 5th International Conference on Cyber and IT Service Management (CITSM), 2017, pp. 1-5, doi: 10.1109/CITSM.2017.8089270.
• [8] Kang, J., Han, X., Song, J., Niu, Z., & Li, X. (2020). The identification of children with autism spectrum disorder by SVM approach on EEG and eye-tracking data. Computers in biology and medicine, 120, 103722.
• [9] Wang, J., Barstein, J., Ethridge, L. E., Mosconi, M. W., Takarae, Y., & Sweeney, J. A. (2013). Resting state EEG abnormalities in autism spectrum disorders. Journal of neurodevelopmental disorders, 5(1), 1-14.
• [10] Kang, J., Han, X., Song, J., Niu, Z., & Li, X. (2020). The identification of children with autism spectrum disorder by SVM approach on EEG and eye-tracking data. Computers in biology and medicine, 120, 103722.
• [11] Sheikhani, A., Behnam, H., Mohammadi, M. R., Noroozian, M., & Mohammadi, M. (2012). Detection of abnormalities for diagnosing of children with autism disorders using of quantitative electroencephalography analysis. Journal of medical systems, 36(2), 957-963.
• [12] Mou, L., Zhou, C., Zhao, P., Nakisa, B., Rastgoo, M. N., Jain, R., & Gao, W. (2021). Driver stress detection via multimodal fusion using attention-based CNN-LSTM. Expert Systems with Applications, 173, 114693.
• [13] Kang, J., Zhou, T., Han, J., & Li, X. (2018). EEG-based multi-feature fusion assessment for autism. Journal of Clinical Neuroscience, 56, 101-107.
• [14] Kang, J., Zhou, T., Han, J., & Li, X. (2018). EEG-based multi-feature fusion assessment for autism. Journal of Clinical Neuroscience, 56, 101-107.
• [15] Stein, N., Bremer, G., & Lappe, M. (2022, March). Eye tracking-based lstm for locomotion prediction in vr. In 2022 IEEE Conference on Virtual Reality and 3D User Interfaces (VR) (pp. 493-503). IEEE.
• [16] A S DiCriscio and V Troiani, “Pupil adaptation corresponds to quantitative measures of autism traits in children,” Scientific reports, vol. 7, no. 1, pp. 1–9, 2017.
• [17] A Klin, W Jones, R Schultz, F Volkmar, and D Cohen, “Visual fixation patterns during viewing of naturalistic social situations as predictors of social competence in individuals with autism,” Archives of General Psychiatry, vol. 59(9), pp. 809–816, 2002.
• [18] Z Akhtar and T Guha, “Computational analysis of gaze behavior in autism during interaction with virtual agents,” in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019, pp. 1075–1079.
• [19] Ghosh, S., & Guha, T. (2021, November). Towards Autism Screening through Emotion-guided Eye Gaze Response. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 820-823). IEEE.
• [20] Ahmed, I. A., Senan, E. M., Rassem, T. H., Ali, M. A., Shatnawi, H. S. A., Alwazer, S. M., & Alshahrani, M. (2022). Eye tracking-based diagnosis and early detection of autism spectrum disorder using machine learning and deep learning techniques. Electronics, 11(4), 530.
• [21] Lakhan, A., Mohammed, M. A., Abdulkareem, K. H., Hamouda, H., & Alyahya, S. (2023). Autism Spectrum Disorder detection framework for children based on federated learning integrated CNN-LSTM. Computers in Biology and Medicine, 166, 107539.
• [22] Cilia, F., Carette, R., Elbattah, M., Guérin, J. L., & Dequen, G. (2022). Eye-tracking dataset to support the research on autism spectrum disorder.
• [23] Cetintas, Dilber & Tuncer, Taner. (2021). Eye-Tracking Analysis with Deep Learning Method. 512-515. 10.1109/3ICT53449.2021.9581943.
• [24] Cetintas, Dilber & Tuncer, Taner. (2022). Determining the Type of Document Read Using Eye Movement Properties by Hybrid CNN Method. Traitement du Signal. 39. 10.18280/ts.390402.
• [25] R. Carette, F. Cilia, G. Dequen, J. Bosche, J.L. Guerin, L. Vandromme, Automatic Autism Spectrum Disorder Detection Thanks to Eye-Tracking and Neural Network-Based Approach. In: Bastel JB, Ahmed MU, Begum S, ''editors'.: Springer Verlag, 2018. p. 75-81.
• [26] C. Xia, K. Chen, K. Li, H. Li (Eds.), Identification of autism spectrum disorder via an eye-tracking based representation learning model2020 2020-01-01: Association for Computing Machinery.
• [27] V. Yaneva, H. Le An, S. Eraslan, Y. Yesilada, R. Mitkov Detecting High-Functioning Autism in Adults Using Eye Tracking and Machine Learning Ieee T Neur Sys Reh., 28 (6) (2020), pp. 1254-1261.
• [28] K.J. Tsuchiya, S. Hakoshima, T. Hara, et al. Diagnosing Autism Spectrum Disorder Without Expertise: A Pilot Study of 5- to 17-Year-Old Individuals Using Gazefinder Front. Neurol., 11 (2021).
• [29] F. Cilia, R. Carette, M. Elbattah, et al. Computer-Aided Screening of Autism Spectrum Disorder: Eye-Tracking Study Using Data Visualization and Deep Learning JMIR Hum. Factors, 8 (4) (2021), p. e27706.
• [30] R. Carette, F. Cilia, G. Dequen, J. Bosche, J.L. Guerin, L. Vandromme, Automatic Autism Spectrum Disorder Detection Thanks to Eye-Tracking and Neural Network-Based Approach. In: Bastel JB, Ahmed MU, Begum S, ''editors'.: Springer Verlag, 2018. p. 75-81.
• [31] Elbattah M, Loughnane C, Guérin J-L, Carette R, Cilia F, Dequen G. Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data. Journal of Imaging. 2021; 7(5):83. https://doi.org/10.3390/jimaging7050083.