Dikkat mekanizmalı ve bayesyan optimizasyonlu topluluk öğrenme modelleri ile maske tespiti

Öz

Salgın hastalıklar, insanlık tarihinde büyük kayıplara neden olmuş ve günümüzde nüfus artışı nedeniyle daha sık görülmektedir. COVID-19 ve maymun çiçeği gibi salgınlar, insan etkileşiminden kaynaklanan bulaşma yollarıyla hızla yayılmaktadır. Maske kullanımı bulaşmayı azaltan etkili bir yöntem olmasına rağmen, yetersiz uygulanması denetim ihtiyacını doğurmaktadır. Bu çalışma, yapay zeka ve derin öğrenme algoritmalarıyla maske kullanımı tespitini sağlayarak salgınların yayılmasını önlemeyi amaçlamaktadır. Resnet101, MobileNet ve Xception algoritmaları kullanılarak maskeli, maskesiz ve yanlış takılan maske görselleri üzerinde modeller eğitilmiş; Mask Ensemble, Attention Mask Ensemble ve Bayes Mask Ensemble modelleri geliştirilmiştir. Bayes Search optimizasyonuyla hiperparametre ayarları incelenmiş, Bayes Mask Ensemble modelinin en yüksek performansı gösterdiği, bunu Attention Mask Ensemble modelinin takip ettiği ve Mask Ensemble modelinin üçüncü sırada yer aldığı bulunmuştur. Bayes Search ile optimize edilmiş model, literatürdeki diğer yöntemlere göre üstün maske tespiti sağlamıştır.

Anahtar Kelimeler

• Derin öğrenme
• Salgın hastalıklar
• Maske tespiti
• Bayes arama optimizasyonu
• Topluluk öğrenmesi

Advancing mask detection with attention-driven and bayesian-optimized ensemble models

Öz

Infectious diseases have caused significant losses throughout human history and are increasingly prevalent today due to population growth. Pandemics such as COVID-19 and monkeypox have rapidly spread through human interaction-driven transmission pathways. Although mask usage is an effective method to reduce transmission, its inadequate implementation necessitates monitoring. This study aims to prevent the spread of pandemics by detecting mask usage through artificial intelligence and deep learning algorithms. Models were trained on images of masked, unmasked, and improperly masked individuals using Resnet101, MobileNet, and Xception algorithms, and three models were developed: Mask Ensemble, Attention Mask Ensemble, and Bayes Mask Ensemble. Hyperparameter tuning was performed using Bayes Search optimization, revealing that the Bayes Mask Ensemble model achieved the highest performance, followed by the Attention Mask Ensemble model, with the Mask Ensemble model ranking third. The Bayes Search-optimized model demonstrated superior mask detection performance compared to other methods in the literature.

Anahtar Kelimeler

• Deep learning
• Infectious diseases
• Mask detection
• Bayesian search optimization
• Ensemble learning

Kaynakça

1. F. A. Muhammed Ali and M. S. Al-Tamimi, Face mask detection methods and techniques: A review. International Journal of Nonlinear Analysis and Applications, 13 (1), 3811-3823, 2022. http://dx.doi.org/10.22075/ijnaa.2022.6166.
2.     J. G. Chowdary, N. S. Punn, S. K. Sonbhadra and S. Agarwal, Face mask detection using transfer learning of InceptionV3. Big Data Analytics: 8th International Conference (BDA 2020), pp. 81-90, Sonepat, India, 15-18 December 2020. https://doi.org/10.1007/978-3-030-66665-1_6.
3.     H. Adusumalli, D. Kalyani, R. K. Sri, M. Pratapteja and P. P. Rao, Face mask detection using OpenCV. Third International Conference on Smart Communication Technologies and Virtual Mobile Networks (ICICV), pp. 1304-1309, IEEE, Tirunelveli, India, 11-12 February 2021. https://doi.org/10.1109/ICICV50876.2021.9388375.
4.     S. Sethi, M. Kathuria and T. Kaushik, Face mask detection using deep learning: An approach to reduce risk of Coronavirus spread. Journal of Biomedical Informatics, 120, 103848, 1-10, 2021. https://doi.org/10.1016/j.jbi.2021.103848.
5.     K. M. Hosny, N. A. Ibrahim, E. R. Mohamed and H. M. Hamza, Artificial intelligence-based masked face detection: A survey. Intelligent Systems with Applications, 22, 200391, 1-22, 2024. https://doi.org/10.1016/j.iswa.2024.200391.
6.     Y. Himeur, S. Al-Maadeed, I. Varlamis, N. Al-Maadeed, K. Abualsaud and A. Mohamed, Face mask detection in smart cities using deep and transfer learning: Lessons learned from the COVID-19 pandemic. Systems, 11 (2), 107, 1-28, 2023. https://doi.org/10.3390/systems11020107.
7.     G. Kaur, R. Sinha, P. K. Tiwari, S. K. Yadav, P. Pandey, R. Raj, A. Vashisth and M. Rakhra, Face mask recognition system using CNN model. Neuroscience Informatics, 2 (3), 100035, 1-9, 2022. https://doi.org/10.1016/j.neuri.2021.100035.
8.     S. Teboulbi, S. Messaoud, M. A. Hajjaji and A. Mtibaa, Real-time implementation of AI-based face mask detection and social distancing measuring system for COVID-19 prevention. Scientific Programming, 2021 (1), 8340779, 1-14, 2021. https://doi.org/10.1155/2021/8340779.

9.     M. Loey, G. Manogaran, M. H. N. Taha and N. E. M. Khalifa, Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection. Sustainable Cities and Society, 65, 102600, 1-9, 2021. https://doi.org/10.1016/j.scs.2020.102600.
10.   A. Chavda, J. Dsouza, S. Badgujar and A. Damani, Multi-stage CNN architecture for face mask detection. 6th International Conference for Convergence in Technology (I2CT), pp. 1-8, IEEE, Maharashtra, India, 2-3 April 2021. https://doi.org/10.1109/I2CT51068.2021.9418207.
11.   B. Qin and D. Li, Identifying facemask-wearing condition using image super-resolution with classification network to prevent COVID-19. Sensors, 20 (18), 5236, 1-16, 2020. https://doi.org/10.3390/s20185236.
12.   S. Yadav, Deep learning based safe social distancing and face mask detection in public areas for COVID-19 safety guidelines adherence. International Journal for Research in Applied Science and Engineering Technology, 8 (7), 1368-1375, 2020. https://doi.org/10.22214/ijraset.2020.30560.
13.   S. Shiekh Burhan, Face Mask Dataset. Kaggle, 2020. https://www.kaggle.com/datasets/shiekhburhan/face-mask-dataset, Accessed 4 March 2025.
14.   Y. Tong, W. Lu, Q. Q. Deng, C. Chen and Y. Shen, Automated identification of retinopathy of prematurity by image-based deep learning. Eye and Vision, 7, 40, 1-12, 2020. https://doi.org/10.1186/s40662-020-00206-2.
15.   Z. Wu, C. Shen and A. Van Den Hengel, Wider or deeper: Revisiting the ResNet model for visual recognition. Pattern Recognition, 90, 119-133, 2019. https://doi.org/10.1016/j.patcog.2019.01.006.
16.   N. S. Sanjay and A. Ahmadinia, MobileNet-Tiny: A deep neural network-based real-time object detection for Raspberry Pi. 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 647-652, IEEE, Boca Raton, FL, USA, 16-19 December 2019. https://doi.org/ 10.1109/ICMLA.2019.00118.
17.   A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand and H. Adam, MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint, arXiv:1704.04861, 1-9, 2017. https://doi.org/10.48550/arXiv.1704.04861.
18.   Y. Liu, L. Zhang, Z. Hao, Z. Yang, S. Wang, X. Zhou and Q. Chang, An Xception model based on residual attention mechanism for the classification of benign and malignant gastric ulcers. Scientific Reports, 12 (1), 15365, 1-13, 2022. https://doi.org/10.1038/s41598-022-19639-x.
19.   F. Chollet, Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1251-1258, IEEE, Honolulu, HI, USA, 21-26 July 2017. https://doi.org/10.1109/CVPR.2017.195.
20.   V. Nguyen, Bayesian optimization for accelerating hyper-parameter tuning. 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), pp. 302-305, IEEE, Cagliari, Italy, 3-5 June 2019. https://doi.org/10.1109/AIKE.2019.00060.
21.   M. Feurer and F. Hutter, Hyperparameter optimization. in Automated Machine Learning: Methods, Systems, Challenges. F. Hutter, L. Kotthoff, J. Vanschoren (Eds.), Springer, pp. 3-33, Cham, 2019. https://doi.org/10.1007/978-3-030-05318-5_1.
22.   A. Doğan and D. Birant, A Weighted majority voting ensemble approach for classification. 2019 4th International Conference on Computer Science and Engineering (UBMK), pp. 1-6, IEEE, Samsun, Turkey, 11-15 September 2019. https://doi.org/10.1109/UBMK.2019.8907028.
23.   J. M. Banda, R. A. Angryk and P. C. H. Martens, Steps toward a large-scale solar image data analysis to differentiate solar phenomena. Solar Physics, 288, 435-462, 2013. https://doi.org/10.1007/s11207-013-0304-x.
24.   C. Hark, Sahte haber tespiti için derin bağlamsal kelime gömülmeleri ve sinirsel ağların performans değerlendirmesi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 34 (2), 733-742, 2022. https://doi.org/10.35234/fumbd.1126688.
25.   A. Kulkarni, D. Chong and F. A. Batarseh, Foundations of data imbalance and solutions for a data democracy. in Data Democracy. F. A. Batarseh, R. Freeman (Eds.), Academic Press, pp. 83-106, London, 2020. https://doi.org/10.1016/B978-0-12-818366-3.00005-8.
26.   D. M. Powers, Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint, arXiv:2010.16061, 1-23, 2020. https://doi.org/10.48550/arXiv.2010.16061.