Sistem Pendeteksi Jenis Penyakit Pernafasan Menggunakan Metode Gabungan GRU dan LSTM Melalui Suara Pasien dengan Gangguan Pernafasan
Abstract
Penelitian ini bertujuan untuk mengklasifikasikan penyakit pernapasan berdasarkan suara pasien menggunakan gabungan GRU (Gated Recurrent Unit) dan LSTM (Long Short-Term Memory). Model GRU dilatih dengan 50 epoch menggunakan dataset suara pasien yang dikumpulkan. Hasil evaluasi menunjukkan akurasi sebesar 75%, dengan precision, recall, dan f1-score yang bervariasi untuk setiap jenis penyakit pernapasan. Penelitian ini menggambarkan potensi penggunaan metode klasifikasi suara dalam diagnosis penyakit pernapasan. Meskipun demikian, perlu dilakukan penyesuaian parameter dan peningkatan jumlah data pelatihan untuk meningkatkan performa model. Dengan konvergensi yang baik pada epoch 50, hasil ini menunjukkan kemampuan model dalam mengklasifikasikan penyakit pernapasan berdasarkan suara pasien. Namun, validasi dan pengujian lebih lanjut pada dataset yang lebih besar diperlukan untuk menguji keandalan dan generalisasi model secara menyeluruh. Penelitian ini dapat memberikan kontribusi dalam pengembangan alat bantu diagnostik non-invasif untuk penyakit pernapasan berdasarkan analisis suara pasien. Penelitian ini memberikan bukti awal tentang potensi metode klasifikasi suara dalam diagnosis penyakit pernapasan. Namun, penyesuaian parameter dan peningkatan jumlah data pelatihan perlu dilakukan untuk meningkatkan performa model secara keseluruhan.
Downloads
References
Ali, S. W., Asif, M., Zia, M. Y. I., Rashid, M., Syed, S. A., & ... (2023). CDSS for Early Recognition of Respiratory Diseases based on AI Techniques: A Systematic Review. Wireless Personal …. https://doi.org/10.1007/s11277-023-10432-1
Dondi, A., Carbone, C., Manieri, E., Zama, D., & ... (2023). Outdoor Air Pollution and Childhood Respiratory Disease: The Role of Oxidative Stress. International Journal of …. https://www.mdpi.com/1422-0067/24/5/4345
Greenough, A., & Milner, A. D. (2023). Early origins of respiratory disease. Journal of Perinatal Medicine. https://doi.org/10.1515/jpm-2022-0257
Jakiela, B., Soja, J., Sladek, K., Przybyszowski, M., & ... (2023). Bronchial epithelial cell transcriptome shows endotype heterogeneity of asthma in patients with NSAID-exacerbated respiratory disease. Journal of Allergy and …. https://www.sciencedirect.com/science/article/pii/S0091674922015111
Krefft, S. D., & Zell-Baran, L. M. (2023). Deployment-Related Respiratory Disease: Where Are We? … in Respiratory and Critical Care …. https://doi.org/10.1055/s-0043-1764407
Pierre, A. A., Akim, S. A., Semenyo, A. K., & Babiga, B. (2023). Peak Electrical Energy Consumption Prediction by ARIMA, LSTM, GRU, ARIMA-LSTM and ARIMA-GRU Approaches. Energies. https://www.mdpi.com/1996-1073/16/12/4739
Pongdee, T., Larson, N. B., Divekar, R., Bielinski, S. J., Liu, H., & ... (2023). Automated Identification of Aspirin-Exacerbated Respiratory Disease Using Natural Language Processing and Machine Learning: Algorithm Development …. JMIR AI. https://ai.jmir.org/2023/1/e44191/
Prakash, S., Jalal, A. S., & Pathak, P. (2023). Forecasting COVID-19 Pandemic using Prophet, LSTM, hybrid GRU-LSTM, CNN-LSTM, Bi-LSTM and Stacked-LSTM for India. … on Information Systems and …. https://ieeexplore.ieee.org/abstract/document/10112065/
Ramírez-Vélez, R., Iriarte-Fernandez, M., Santafé, G., & ... (2023). Association of intrinsic capacity with respiratory disease mortality. Respiratory …. https://www.sciencedirect.com/science/article/pii/S0954611123001312
Ream, C., Sabitsky, M., Huang, R., Hammelef, E., Yeo, T. P., & ... (2023). Association of Smoking and Respiratory Disease History with Pancreatic Pathologies Requiring Surgical Resection. Cancers. https://www.mdpi.com/2072-6694/15/11/2935
Shejul, A. A., Chaudhari, A., Dixit, B. A., & ... (2023). Stock Price Prediction Using GRU, SimpleRNN and LSTM. Intelligent Systems and …. https://doi.org/10.1007/978-981-19-6581-4_42
Shi, Y., Chen, L., Zhang, H., Nie, G., Zhang, Z., & Zhu, M. (2023). The potential of nano-enabled oral ecosystem surveillance for respiratory disease management. Nano Today. https://www.sciencedirect.com/science/article/pii/S1748013222003218
Song, H., & Choi, H. (2023). Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models. Applied Sciences. https://www.mdpi.com/2076-3417/13/7/4644
Wang, K., Shen, D., Dai, P., & Li, C. (2023). Particulate matter in poultry house on poultry respiratory disease: A systematic review. Poultry Science. https://www.sciencedirect.com/science/article/pii/S0032579123000809
Wang, Y., Duong, M. L., Brauer, M., & ... (2023). Household Air Pollution and Adult Lung Function Change, Respiratory Disease, and Mortality across Eleven Low-and Middle-Income Countries from the PURE Study. Environmental …. https://doi.org/10.1289/EHP11179
Zhang, M., Li, M., Guo, L., & Liu, J. (2023). A Low-Cost AI-Empowered Stethoscope and a Lightweight Model for Detecting Cardiac and Respiratory Diseases from Lung and Heart Auscultation Sounds. Sensors. https://www.mdpi.com/1424-8220/23/5/2591
Copyright (c) 2023 andriyan jatmiko, Nofrian Deny Hendrawan, Arif Saivul Affandi, Divira Salsabiil Susanto
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright for articles published in this journal is retained by the authors, with first publication rights granted to the journal. By virtue of their appearance in this open access journal, articles are free to use after initial publication under the International Creative Commons Attribution-NonCommercial 4.0 Creative Commons CC_BY_NC.
