Comparision xxx

Comparision xxx

• By Sasongko, Agung;
• Jurnal Khatulistiwa Informatika
• 365

Abstract—This research discusses the development of a mobile application to automatically determine the location of wounds using an artificial neural network. The first step of application development begins with creating a model with both the YOLOv5 and EfficientDetLite4 architectures, which is then converted into a model that can be run on Android mobile devices. Automatic location determination in 2D images will be very helpful for solving classification problems because it can eliminate unnecessary images during processing. In developing mobile applications made using the Flutter SDK 3.3 framework, the interpreter is built on native Android code in Java through a plugin with the Channel method. As a result, EfficientDetLite4 has a smaller file size of only 19.4MB, compared to the resulting YOLOv5 model of 40MB. Measurements show that the EfficientDetLite4 architectural model has a better accuracy of 95% and an average inference time speed of 1149ms, which is better than the YOLOv5 model which has a lower accuracy of 92.5% and a slower inference time of 5518ms.

• Katakunci
• URL http://
• Penerbit ,

REFERENSI

 

Referensi

[1]         V. N. Shenoy, E. Foster, L. Aalami, B. Majeed, and O. Aalami, “Deepwound: Automated Postoperative Wound Assessment and Surgical Site Surveillance through Convolutional Neural Networks.”

[2]         Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553. Nature Publishing Group, pp. 436–444, May 27, 2015. doi: 10.1038/nature14539.

[3]         A. Tripathi, T. V. A. Kumar, T. K. Dhansetty, J. Selva Kumar, F. Year, and B. Tech, “Real Time Object Detection using CNN,” 2018. [Online]. Available: www.sciencepubco.com/index.php/IJET

[4]         I. Martinez-Alpiste, G. Golcarenarenji, Q. Wang, and J. M. Alcaraz-Calero, “Smartphone-based real-time object recognition architecture for portable and constrained systems,” J Real Time Image Process, vol. 19, no. 1, pp. 103–115, Feb. 2022, doi: 10.1007/s11554-021-01164-1.

[5]         D. Marijanović, E. K. Nyarko, and D. Filko, “Wound Detection by Simple Feedforward Neural Network,” Electronics (Switzerland), vol. 11, no. 3, Feb. 2022, doi: 10.3390/electronics11030329.

[6]         A. Esteva et al., “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, no. 7639, pp. 115–118, Feb. 2017, doi: 10.1038/nature21056.

[7]         M. Tan, R. Pang, and Q. v. Le, “EfficientDet: Scalable and Efficient Object Detection,” Nov. 2019, [Online]. Available: http://arxiv.org/abs/1911.09070

[8]         A. Yadav, D. Thakran, and Dr. R. Gupta, “REAL-TIME IMAGE PROCESSING USING FLUTTER AND TFLITE PACKAGES,” International Journal of Innovative Research in Computer Science & Technology, vol. 9, no. 5, 2021, doi: 10.21276/ijircst.2021.9.5.6.

[9]         C. Wang et al., “A Unified Framework for Automatic Wound Segmentation and Analysis with Deep Convolutional Neural Networks.”

[10]      B. Rostami, D. M. Anisuzzaman, C. Wang, S. Gopalakrishnan, J. Niezgoda, and Z. Yu, “Multiclass wound image classification using an ensemble deep CNN-based classifier,” Comput Biol Med, vol. 134, Jul. 2021, doi: 10.1016/j.compbiomed.2021.104536.

[11]      D. M. Anisuzzaman, Y. Patel, J. Niezgoda, S. Gopalakrishnan, and Z. Yu, “A Mobile App for Wound Localization using,” IEEE Access, vol. 10, pp. 61398–61409, 2022, doi: 10.1109/ACCESS.2022.3179137.

[12]      J. Redmon and A. Farhadi, “YOLO9000: Better, faster, stronger,” in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Nov. 2017, vol. 2017-January, pp. 6517–6525. doi: 10.1109/CVPR.2017.690.

[13]      J. C. Zheng, S. D. Sun, and S. J. Zhao, “Fast ship detection based on lightweight YOLOv5 network,” IET Image Process, vol. 16, no. 6, pp. 1585–1593, May 2022, doi: 10.1049/ipr2.12432.

[14]      J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” Apr. 2018, [Online]. Available: http://arxiv.org/abs/1804.02767

[15]      J. Chen, E. Bao, and J. Pan, “Classification and Positioning of Circuit Board Components Based on Improved YOLOv5,” in 7th International Conference on Intelligent, Interactive Systems and Applications, 2022, pp. 613–626.

[16]      M. Abadi et al., “TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems,” Mar. 2016, [Online]. Available: http://arxiv.org/abs/1603.04467

[17]      O. Alsing, “Mobile Object Detection using TensorFlow Lite and Transfer Learning,” 2018.