arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.01807cs.CVcs.AI
收藏

用于牛痘病识别的自适应混合优化器框架

Adaptive Hybrid Optimizer based Framework for Lumpy Skin Disease Identification

Department of Computer Science, NUST Balochistan Campus, NUST, Pakistan（巴基斯坦努斯大学巴尔奇斯坦校区计算机科学系）；Australian e-Health Research Centre (AEHRC), CSIRO, Brisbane, Australia（澳大利亚电子健康研究中心（AEHRC）、CSIRO、布里斯班，澳大利亚）；Queensland University of Technology, Brisbane, Australia（昆士兰技术大学、布里斯班，澳大利亚）；CQI Lab, Department of Electronics and Information Convergence Engineering, Kyung Hee University, Global Campus, South Korea（韩国庆熙大学全球校区电子与信息融合工程系CQI实验室）

Ubaidullah, Muhammad Abid Hussain, Mohsin Raza Jafri, Rozi Khan, Moid Sandhu, Abd Ullah Khan, Hyundong Shin

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出LUMPNet框架，结合自适应混合优化器和EfficientNet，实现高精度的牛痘病早期检测。

摘要：

牛痘病（LSD）是一种传染性病毒感染，严重损害牲畜健康，从而对全球经济和粮食安全构成严重威胁。由于其传播速度快，早期和精确的识别对于防止疫情爆发和确保及时干预至关重要。本文提出了一种混合深度学习方法，称为LUMPNet，用于LSD的早期检测。LUMPNet利用图像数据检测和分类皮肤结节——LSD的主要指标。为此，LUMPNet使用YOLOv11、基于EfficientNet的CNN分类器以及具有复合缩放的新型自适应混合优化器。更具体地说，LUMPNet在牛图像上检测并定位LSD皮肤结节和病变。它利用EfficientNet将局部化的牛图像分类为受LSD影响或健康的类别。为了稳定和加速YOLOv11和EfficientNet混合模型的训练，提出并使用了新的自适应混合优化器。我们使用公开可用的数据集在LSD的不同阶段评估LUMPNet。结果表明，所提出的方法在LSD检测训练准确率上达到99%，优于现有方案。该模型还实现了98%的验证准确率。此外，为了进一步评估，我们使用优化后的EfficientNet-B0模型，使用AdamW优化器进行训练，并将其性能与LUMPNet进行比较。结果表明，LUMPNet实现了更优的性能。

英文摘要：

Lumpy Skin Disease (LSD) is a contagious viral infection that significantly deteriorates livestock health, thereby posing a serious threat to the global economy and food security. Owing to its rapid spread characteristics, early and precise identification is crucial to prevent outbreaks and ensure timely intervention. In this paper, we propose a hybrid deep learning-based approach called LUMPNet for the early detection of LSD. LUMPNet utilizes image data to detect and classify skin nodules -- the primary indicator of LSD. To this end, LUMPNet uses YOLOv11, EfficientNet-based CNN classifier with compound scaling, and a novel adaptive hybrid optimizer. More precisely, LUMPNet detects and localizes LSD skin nodules and lesions on cattle images. It exploits EfficientNet to classify the localized cattle images into LSD-affected or healthy categories. To stabilize and accelerate the training of YOLOv11 and EfficientNet hybrid model, a novel adaptive hybrid optimizer is proposed and utilized. We evaluate LUMPNet at various stages of LSD using a publicly available dataset. Results indicate that the proposed scheme achieves 99% LSD detection training accuracy, and outperforms existing schemes. The model also achieves validation accuracy of 98%. Moreover, for further evaluation, we conduct a case study using an optimized EfficientNet-B0 model trained with the AdamW optimizer, and compare its performance with LUMPNet. The results show that LUMPNet achieves superior performance.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑