Optimasi YOLOv5 Berbasis Network Reduction Strategy untuk Deteksi Jenis Sel Darah

Main Article Content

Ni Putu Sutramiani

Abstract

Darah adalah kombinasi plasma dan sel yang beredar di seluruh tubuh. Komponen cair dan padat membentuk dua komponen darah. Air, protein, dan garam membentuk plasma, yang merupakan bagian cair dari darah. Sementara Trombosit, Sel Darah Merah (RBC), dan Sel Darah Putih (WBC) merupakan bagian padat. Identifikasi sel darah sangat penting karena merupakan populasi yang dapat diakses dengan mudah dan bentuk, biokimia, dan ekologinya dapat memberikan petunjuk untuk diagnosis penyakit atau kesehatan pasien secara keseluruhan. Karena banyaknya karakteristik sel dan kompleksitas data, deteksi sel yang andal dan akurat seringkali menjadi tantangan yang menantang. Kehadiran sel tertentu, seperti leukosit, dapat dideteksi dalam gambar mikroskopis. Penelitian ini mengusulkan network reduction strategy pada model YOLOv5 untuk mendeteksi jenis sel darah. Pendekatan yang diusulkan bertujuan untuk menghasilkan model YOLOv5 yang lebih optimal untuk meningkatkan kinerja model. Berdasarkan hasil eksperimen, strategi optimasi yang diusulkan dapat mendeteksi jenis sel darah dengan kinerja mencapai 94,8%.

Article Details

How to Cite
SUTRAMIANI, Ni Putu. Optimasi YOLOv5 Berbasis Network Reduction Strategy untuk Deteksi Jenis Sel Darah. Prosiding Seminar Nasional Sains dan Teknologi (Senastek), [S.l.], v. 8, n. 1, p. 279-284, dec. 2023. Available at: <https://ojs.unud.ac.id/index.php/senastek/article/view/108713>. Date accessed: 28 feb. 2024.
Section
Articles

References

[1] D. R. Loh, W. X. Yong, J. Yapeter, K. Subburaj, dan R. Chandramohanadas, “A deep learning approach to the screening of malaria infection: Automated and rapid cell counting, object detection and instance segmentation using Mask R-CNN,” Computerized Medical Imaging and Graphics, vol. 88, hlm. 101845, 2021, doi: 10.1016/j.compmedimag.2020.101845.
[2] L. Vogado dkk., “Diagnosis of Leukaemia in Blood Slides Based on a Fine-Tuned and Highly Generalisable Deep Learning Model,” Sensors 2021, Vol. 21, Page 2989, vol. 21, no. 9, hlm. 2989, Apr 2021, doi: 10.3390/S21092989.
[3] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “CARVING-DETC: A network scaling and NMS ensemble for Balinese carving motif detection method,” Visual Informatics, Jun 2023, doi: 10.1016/j.visinf.2023.05.004.
[4] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “GFF-CARVING: Graph Feature Fusion for the Recognition of Highly Varying and Complex Balinese Carving Motifs,” IEEE Access, 2022, doi: 10.1109/ACCESS.2022.3228382.
[5] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “Balinese Carving Recognition using Pre-Trained Convolutional Neural Network,” dalam 2020 4th International Conference on Informatics and Computational Sciences (ICICoS), 2020, hlm. 1–5. doi: 10.1109/ICICoS51170.2020.9299021.
[6] I. W. A. S. Darma, N. Suciati, dan D. Siahaan, “A Performance Comparison of Balinese Carving Motif Detection and Recognition using YOLOv5 and Mask R-CNN,” hlm. 52–57, Des 2021, doi: 10.1109/ICICOS53627.2021.9651855.
[7] X. Han dan J. Chang, “Real-time object object detection detection based based on on YOLO-v2 for for tiny tiny vehicle vehicle object object,” Procedia Comput Sci, vol. 183, hlm. 61–72, 2021, doi: 10.1016/j.procs.2021.02.031.
[8] S. Du, P. Zhang, B. Zhang, dan H. Xu, “Weak and Occluded Vehicle Detection in Complex Infrared Environment Based on Improved YOLOv4,” IEEE Access, vol. 9, hlm. 25671–25680, Okt 2021, doi: 10.1109/ACCESS.2021.3057723.
[9] A. A. Je, V. Priyangka, I. Made, dan S. Kumara, “Classification Of Rice Plant Diseases Using the Convolutional Neural Network Method,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 12, no. 2, hlm. 123–129, Agu 2021, doi: 10.24843/LKJITI.2021.V12.I02.P06.
[10] G. Zhou, W. Zhang, A. Chen, M. He, dan X. Ma, “Rapid Detection of Rice Disease Based on FCM-KM and Faster R-CNN Fusion,” IEEE Access, vol. 7, hlm. 143190–143206, 2019, doi: 10.1109/ACCESS.2019.2943454.
[11] G. H. Aly, M. Marey, S. A. El-Sayed, dan M. F. Tolba, “YOLO Based Breast Masses Detection and Classification in Full-Field Digital Mammograms,” Comput Methods Programs Biomed, vol. 200, hlm. 105823, 2021, doi: https://doi.org/10.1016/j.cmpb.2020.105823.
[12] M. Sharif dkk., “Recognition of Different Types of Leukocytes Using YOLOv2 and Optimized Bag-of-Features,” IEEE Access, vol. 8, hlm. 167448–167459, 2020, doi: 10.1109/ACCESS.2020.3021660.
[13] G. Fang, Y. suhua, dan J. shaofeng, “Detection of white blood cells using YOLOV3 network,” dalam 2019 14th IEEE International Conference on Electronic Measurement & Instruments (ICEMI), IEEE, Nov 2019, hlm. 1683–1688. doi: 10.1109/ICEMI46757.2019.9101709.
[14] S. Banerjee dan S. S. Chaudhuri, “Total contribution score and fuzzy entropy based two-stage selection of FC, ReLU and inverseReLU features of multiple convolution neural networks for erythrocytes detection,” IET Computer Vision, vol. 13, no. 7, hlm. 640–650, 2019, doi: 10.1049/iet-cvi.2018.5545.