Arsitektur Resnet-152 dengan Perbandingan Optimizer Adam dan RMSProp untuk Mendeteksi Penyakit Paru â€“ Paru

SITI ASY SYIFA; IRMA AMELIA DEWI

doi:10.26760/mindjournal.v7i2.139-150

Arsitektur Resnet-152 dengan Perbandingan Optimizer Adam dan RMSProp untuk Mendeteksi Penyakit Paru â€“ Paru

SITI ASY SYIFA, IRMA AMELIA DEWI

Sari

ABSTRAK

Penyakit paru-paru pada manusia sering terjadi di seluruh dunia umumnya terjadi karena polusi udara dan asap rokok. Untuk mendeteksi penyakit paru-paru manusia ini diperlukan kemampuan secara tepat dengan menggunakan Chest X-Rays (CXR). CXR umumnya sulit dibedakan oleh manusia, maka dari itu pada penelitian ini menerapkan model Deep Learning sebagai sarana untuk mendeteksi penyakit paru-paru manusia melalui citra CXR. Eksperimen dilakukan dengan menggunakan model arsitektur yaitu ResNet-152 serta 2 optimizer yaitu Adam dan RMSProp. Selain itu, pengujian model dilakukan dengan menggunakan accuracy, precision, recall, f1-score, specitifity dan grafik Receiver Operating Characteristic (ROC). Pada penelitian ini menunjukkan bahwa model ResNet-152-R10 yang memiliki tingkat accuracy, precision, recall, f1-score dan specitifity terbaik yaitu masing-masing 92%, 94%, 92%, 93% dan 96,75%.

Kata kunci: adam optimizer, rmsprop optimizer, resnet-152, penyakit paru-paru, pneumonia, lung opacity

ABSTRACT

Lung disease in humans often occurs throughout the world generally occurs due to air pollution and cigarette smoke. To detect human lung disease, it requires the ability to be precise using Chest X-Rays (CXR). CXR is generally difficult to distinguish by humans, therefore this study applies the Deep Learning model as a means of detecting human lung disease through CXR imagery. Experiments were carried out using the architectural model, namely ResNet-152 and 2 optimizers, namely Adam and RMSProp. In addition, model testing is carried out using accuracy, precision, recall, f1-score, specificity and Receiver Operating Characteristic (ROC) graphs. This study shows that the ResNet-152-R10 model has the best levels of accuracy, precision, recall, f1-score and specificity, namely 92%, 94%, 92%, 93% and 96.75% respectively.

Keywords: adam optimizer, rmsprop optimizer, resnet-152, lung disease, pneumonia, lung opacity

Teks Lengkap:

PDF

Referensi

Albawi, S., Mohammed, T. A. M., & Alzawi, S. (2017). Layers of a Convolutional Neural Network. Ieee, 16.

Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., SantamarÃa, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. In Journal of Big Data (Vol. 8, Issue 1). Springer International Publishing. https://doi.org/10.1186/s40537-021-00444-8

Bera, S., & Shrivastava, V. K. (2020). Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification. International Journal of Remote Sensing, 41(7), 2664â€“2683. https://doi.org/10.1080/01431161.2019.1694725

Bharati, S., Podder, P., & Mondal, M. R. H. (2020). Hybrid deep learning for detecting lung diseases from X-ray images. Informatics in Medicine Unlocked, 20, 100391. https://doi.org/10.1016/j.imu.2020.100391

Chowdhury, M. E. H., Rahman, T., Khandakar, A., Mazhar, R., Kadir, M. A., Mahbub, Z. Bin, Islam, K. R., Khan, M. S., Iqbal, A., Emadi, N. Al, Reaz, M. B. I., & Islam, M. T. (2020). Can AI Help in Screening Viral and COVID-19 Pneumonia? IEEE Access, 8, 132665â€“132676. https://doi.org/10.1109/ACCESS.2020.3010287

Chowdhury, N. K., Kabir, M. A., Rahman, M. M., & Rezoana, N. (2020). ECOVNet: An Ensemble of Deep Convolutional Neural Networks Based on EfficientNet to Detect COVID-19 From Chest X-rays. https://doi.org/10.7717/peerj-cs.551

Deng, L., & Yu, D. (2014). REAL-TIME COLOR IMAGE CLASSIFICATION BASED ON DEEP LEARNING NETWORK. 54(5), 1â€“134. https://doi.org/10.1227/01.NEU.0000255452.20602.C9

E. P, I. W. S., Wijaya, A. Y., & Soelaiman, R. (2016). Klasifikasi Citra Menggunakan Convolutional Neural Network (Cnn) Pada Caltech 101. Jurnal Teknik ITS, 5(1), 76. http://repository.its.ac.id/48842/

Hastomo, W. (2021). Diagnosa COVID-19 Chest X-Ray Dengan Convolution Neural Network Arsitektur Resnet-152. KERNEL: Jurnal Riset Inovasi Bidang Informatika Dan Pendidikan Informatika, 2(1), 26â€“33. https://doi.org/10.31284/j.kernel.2021.v2i1.1884

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-Decem, 770â€“778. https://doi.org/10.1109/CVPR.2016.90

Jabra, M. Ben, Koubaa, A., Benjdira, B., Ammar, A., & Hamam, H. (2021). Covid-19 diagnosis in chest x-rays using deep learning and majority voting. Applied Sciences (Switzerland), 11(6). https://doi.org/10.3390/app11062884

Khaliluzzaman, M., Md. Abu Bakar Siddiq Sayem, & Lutful KaderMisbah. (2021). HActivityNet: A Deep Convolutional Neural Network for Human Activity Recognition. EMITTER International Journal of Engineering Technology, 9(2), 357â€“376. https://doi.org/10.24003/emitter.v9i2.642

Kumar, V., & L., M. (2018). Deep Learning as a Frontier of Machine Learning: A Review. International Journal of Computer Applications, 182(1), 22â€“30. https://doi.org/10.5120/ijca2018917433

Liang, J. (2020). Image classification based on RESNET. Journal of Physics: Conference Series, 1634(1). https://doi.org/10.1088/1742-6596/1634/1/012110

Muniasamy, A., & Alasiry, A. (2020). Deep learning: The impact on future eLearning. International Journal of Emerging Technologies in Learning, 15(1), 188â€“199. https://doi.org/10.3991/IJET.V15I01.11435

Pranav, J. V., Anand, R., Shanthi, T., Manju, K., Veni, S., & Nagarjun, S. (2020). Detection and identification of COVID -19 based on chest medical image by using convolutional neural networks. International Journal of Intelligent Networks, 1(November), 112â€“118. https://doi.org/10.1016/j.ijin.2020.12.002

Rahman, T., Khandakar, A., Qiblawey, Y., Tahir, A., Kiranyaz, S., Abul Kashem, S. Bin, Islam, M. T., Al Maadeed, S., Zughaier, S. M.,

Khan, M. S., & Chowdhury, M. E. H. (2021). Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Computers in Biology and Medicine, 132(November 2020), 104319. https://doi.org/10.1016/j.compbiomed.2021.104319

Sadre, R., Sundaram, B., Majumdar, S., & Ushizima, D. (2021). Validating deep learning inference during chest X-ray classification for COVID-19 screening. Scientific Reports, 11(1), 1â€“10. https://doi.org/10.1038/s41598-021-95561-y

Sensusiati, A. D., Pramulen, A. S., Rumala, D. J., & ... (2021). A New Approach to Detect COVID-19 in X-Ray Images of Indonesians. Journal of Hunan â€¦, 48(6). http://www.jonuns.com/index.php/journal/article/view/595

Soydaner, D. (2020). A Comparison of Optimization Algorithms for Deep Learning. International Journal of Pattern Recognition and Artificial Intelligence, 34(13), 1â€“26. https://doi.org/10.1142/S0218001420520138

Wibowo, A., Wiryawan, P. W., & Nuqoyati, N. I. (2019). Optimization of neural network for cancer microRNA biomarkers classification. Journal of Physics: Conference Series, 1217(1). https://doi.org/10.1088/1742-6596/1217/1/012124

DOI: https://doi.org/10.26760/mindjournal.v7i2.139-150