Title: Effect of Different Batch Size Parameters on Predicting of COVID19 Cases

Abstract: The new coronavirus 2019, also known as COVID19, is a very serious epidemic that has killed thousands or even millions of people since December 2019. It was defined as a pandemic by the world health organization in March 2020. It is stated that this virus is usually transmitted by droplets caused by sneezing or coughing, or by touching infected surfaces. The presence of the virus is detected by real-time reverse transcript ase polymerase chain reaction (rRT-PCR) tests with the help of a swab taken from the nose or throat. In addition, X-ray and CT imaging methods are also used to support this method. Since it is known that the accuracy sensitivity in rRT-PCR test is low, auxiliary diagnostic methods have a very important place. Computer-aided diagnosis and detection systems are developed especially with the help of X-ray and CT images. Studies on the detection of COVID19 in the literature are increasing day by day. In this study, the effect of different batch size (BH=3, 10, 20, 30, 40, and 50) parameter values on their performance in detecting COVID19 and other classes was investigated using data belonging to 4 different (Viral Pneumonia, COVID19, Normal, Bacterial Pneumonia) classes. The study was carried out using a pre-trained ResNet50 convolutional neural network. According to the obtained results, they performed closely on the training and test data. However, it was observed that the steady state in the test data was delayed as the batch size value increased. The highest COVID19 detection was 95.17% for BH = 3, while the overall accuracy value was 97.97% with BH = 20. According to the findings, it can be said that the batch size value does not affect the overall performance significantly, but the increase in the batch size value delays obtaining stable results.

Keywords: COVID19; ResNet50; batch size; pre-trained CNN model

Başlık: Farklı Parti Boyutu Parametrelerinin COVID19 Vakalarının Tahmini Üzerindeki Etkisi

Özet: COVID19 olarak da bilinen yeni tip koronavirüs, Aralık 2019'dan bu yana binlerce hatta milyonlarca kişiyi öldüren çok ciddi bir salgındır. Dünya Sağlık Örgütü tarafından Mart 2020'de pandemi olarak tanımlanmıştır. Genellikle hapşırma veya öksürme sonucu oluşan damlacıklar veya enfekte olmuş yüzeylere dokunma yoluyla bulaşır. Virüsün varlığı, burun veya boğazdan alınan bir sürüntü ile gerçek zamanlı ters transkriptaz polimeraz zincir reaksiyonu (rRT-PCR) testleri ile tespit edilir. Ayrıca bu yöntemi desteklemek için X-ışını ve bilgisayarlı tomografi (BT) görüntüleme yöntemleri de kullanılmaktadır. rRT-PCR testinde duyarlılık oranının düşük olduğu bilindiğinden yardımcı tanı yöntemleri çok önemli bir yere sahiptir. Bilgisayar destekli teşhis ve tespit sistemleri özellikle X-ışını ve BT görüntüleri yardımıyla geliştirilmektedir. Literatürde COVID19 tespitine yönelik çalışmalar her geçen gün artmaktadır. Bu çalışmada, farklı parti boyutu (PB=3, 10, 20, 30, 40 ve 50) parametre değerlerinin COVID19 ve diğer sınıfları tespit etme performansları araştırıldı. 4 farklı (Viral Zatüre, COVID19, Normal, Bakteriyel Zatüre) sınıf verileri kullanıldı. Çalışma, önceden eğitilmiş ResNet50 evrişimli sinir ağı modeli kullanılarak gerçekleştirildi. Elde edilen sonuçlara göre, PB’nin değişiminde, eğitim ve test verileri için yakın performans sergiledikleri görüldü. Bununla birlikte, test verilerindeki kararlı durumun parti boyutu değeri arttıkça geciktiği gözlendi. En yüksek COVID19 tespiti PB = 3 için %95,17 iken genel doğruluk değeri PB = 20 değerinde %97,97 elde edildi. Elde edilen bulgulara göre parti boyutu değerinin genel performansı önemli ölçüde etkilemediği ancak parti boyutundaki artışın kararlı sonuca ulaşmayı geciktirdiği söylenebilir.

Anahtar kelimeler: COVID-19; ResNet50; parti boyutu; önceden eğitilmiş CNN modeli

• Zou Q, Zheng S, Wang X, Liu S, Bao J, Yu F, Wu W, Wang X, Shen B, Zhou T, Zhao Z, Wang Y, Chen R, Wang W, Ma J, Li Y, Wu X, Shen W, Xie F, Vijaykrishna D, Chen Y. Influenza associated severe pneumonia in hospitalized patients: Risk factors and NAI treatments. International Journal of Infectious Diseases 2020; 92: 208-213.
• Sirazitdinov I, Kholiavchenko M, Mustafaev T, Yixuan Y, Kuleev R. Deep neural network ensemble for pneumonia localization from a largescale chest x-ray database. Computers and Electrical Engineering 2019; 78: 388–399.
• Saul CJ, Urey DY, Taktakoglu CD. Early diagnosis of pneumonia with deep learning. arXiv, 2019.
• Verma G, Prakash S. Pneumonia classification using deep learning in healthcare. International Journal of Innovative Technology and Exploring Engineering (IJITEE) 2020; 9(4): 1715-1723.
• Worldometer. COVID-19 coronavirus pandemic, Retrieved from https://www.worldometers.info/coronavirus
• World Health Organization. REtrieved from https://www.who.int/
• Jaiswal AK, Tiwari P, Kumar S, Gupta D, Khanna A, Rodrigues JJPC. Identifying pneumonia in chest x-rays: A deep learning approach. Measurement 2019; 145: 511–518.
• Ghoshal B, Tucker A. Estimating uncertainty and interpretability in deep learning for coronavirus (Covid-19) detection. arXiv, 2020.
• Zhang J, Xie Y, Li Y, Shen C, Xia Y. Covid-19 screening on chest
• x-ray images using deep learning based anomaly detection. arXiv, 2020.
• Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLOS Medicine 2018; 15(11): e1002683.
• Hemdan EE, Shouman MA, Karar ME. COVIDX-Net: A framework of deep learning classifiers to diagnose covid-19 in x-ray images. arXiv, 2020.
• Liang G, Zheng L. A transfer learning method with deep residual network for pediatric pneumonia diagnosis. Computer Methods and Programs in Biomedicine 2020; 187: 104964.
• Gaal G, Maga B, Lukacs A. Attention u-net based adversarial architectures for chest x-ray lung segmentation. arXiv, 2020.
• Quinn WO, Haddad RJ, Moore DL. Pneumonia radiograph diagnosis utilizing deep learning network. In IEEE 2nd International Conference on Electronic Information and Communication Technology, January 20-22, 2019, Harbin, China, pp. 763-767.
• Stephan O, Sain M, Maduh UJ, Jeong DU. An efficient deep learning approach to pneumonia classification in healthcare. Hindawi Journal of Healthcare Engineering 2019; 4180949.
• Sreeja S, Bhavya L, Swamynath S, Dhanuja R. Chest x-ray pneumonia prediction using machine learning algorithms. International Journal for Research in Applied Science Engineering Technology (IJRASET) 2019; 7(4): 3227-3230.
• Longjiang E, Zhao B, Guo Y, Zheng C, Zhang M, Lin J, Luo Y, Cai Y, Song X, Liang H. Using deep-learning techniques for pulmonary-thoracic segmentations and improvement of pneumonia diagnosis in pediatric chest radiographs. Pediatric Pulmonology 2019; 54: 1617-1626.
• Togacar M, Ergen B, Comert Z, Ozyurt F. A deep feature learning model for pneumonia detection applying a combination of mRMR feature selection and machine learning models. IRBM 2020; 41(4): 212-222.
• Apostopolus ID, Aznaouridis SI, Tzani MA. Extracting possibly representative COVID-19 biomarkers from x-ray images with deep learning approach and image data related to pulmonary diseases. Journal of Medical and Biological Engineering 2020; 40: 462–469.
• Apostolopoulos ID, Mpesiana TA. Covid-19: Automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine 2020; 43: 635-640.
• Sethy PK, Behera SK. Detection of coronavirus disease (COVID-19) based on deep features. Preprints 2020; 2020030300.
• Narin A, Kaya C, Pamuk Z. Automatic detection of coronavirus disease (COVID-19) using x-ray images and deep convolutional neural networks. Pattern Analysis and Applications 2021; 24: 1207-1220.
• Chowdhury MEH, Rahman T, Khandakar A, Mazhar R, Kadir MA, Mahbub ZB, Islam KR, Khan MS, Iqbal A, Al-Emadi N, Reaz MBI. Can AI help in screening viral and COVID-19 pneumonia? IEEE Access 2020; 8: 132665-132676.
• Chest X-Ray Images (Pneumonia). Retrieved from https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
• Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology And Medicine 2018; 100: 270-278.
• Narin A. Detection of focal and non-focal epileptic seizure using continuous wavelet transform-based scalogram images and pre-trained deep neural networks. IRBM 2020; In Press, Corrected Proof.
• Han D, Liu Q, Fan W. A new image classification method using CNN transfer learning and web data augmentation. Expert Systems with Applications 2018; 95: 43-56.
• He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 27-30, 2016, Las Vegas, NV, USA, pp. 770–778.