首页 > 最新文献

农学最新文献

英文 中文
IF:
Advances in functional mechanisms of genomic G-quadruplex structures in transcriptional regulation. 基因组g -四重体结构转录调控功能机制研究进展。
Q3 Medicine Pub Date : 2025-12-01 DOI: 10.16288/j.yczz.25-055
Zhen-Zhen He, Xiao-Feng Chen, Yue Hou, Tie-Lin Yang, Bo Yang, Yan Guo

As a canonical non-B DNA secondary structure, the G-quadruplex (G4) dynamically regulates core biological processes, including telomere homeostasis, DNA replication and gene transcription/translation-through its unique four-stranded conformation. The significant enrichment of G4 structures in regulatory regions, particularly promoter regions within mammalian genomes reveals their critical role in transcriptional regulation. In this review, we focus on the dynamic formation mechanisms and transcriptional regulatory functions of endogenous G4 structures, systematically elucidating their three molecular pathways in modulating gene expression: (1) orchestrating spatial assembly of transcription activation complexes; (2) dynamically regulating epigenetic modifications, includinghistone alterations and DNA methylation; (3) remodeling three-dimensional chromatin architecture to establish transcriptionally active microenvironments. By integrating advancements in G4 topological characterization techniques and dynamic equilibrium networks, this work highlights the role of the G4 as a critical cis-regulatory element and provides a theoretical framework for developing G4-targeted therapeutic strategies.

作为一种典型的非b DNA二级结构,g -四重体(G4)通过其独特的四链构象动态调节核心生物过程,包括端粒稳态、DNA复制和基因转录/翻译。在哺乳动物基因组的调控区域,特别是启动子区域,G4结构的显著富集揭示了它们在转录调控中的关键作用。本文对内源性G4结构的动态形成机制和转录调控功能进行了综述,系统阐述了其调控基因表达的三种分子途径:(1)调控转录激活复合物的空间组装;(2)动态调节表观遗传修饰,包括组蛋白改变和DNA甲基化;(3)重塑三维染色质结构,建立转录活性微环境。通过整合G4拓扑表征技术和动态平衡网络的进展,本研究突出了G4作为关键顺式调控元件的作用,并为开发针对G4的治疗策略提供了理论框架。
{"title":"Advances in functional mechanisms of genomic G-quadruplex structures in transcriptional regulation.","authors":"Zhen-Zhen He, Xiao-Feng Chen, Yue Hou, Tie-Lin Yang, Bo Yang, Yan Guo","doi":"10.16288/j.yczz.25-055","DOIUrl":"https://doi.org/10.16288/j.yczz.25-055","url":null,"abstract":"<p><p>As a canonical non-B DNA secondary structure, the G-quadruplex (G4) dynamically regulates core biological processes, including telomere homeostasis, DNA replication and gene transcription/translation-through its unique four-stranded conformation. The significant enrichment of G4 structures in regulatory regions, particularly promoter regions within mammalian genomes reveals their critical role in transcriptional regulation. In this review, we focus on the dynamic formation mechanisms and transcriptional regulatory functions of endogenous G4 structures, systematically elucidating their three molecular pathways in modulating gene expression: (1) orchestrating spatial assembly of transcription activation complexes; (2) dynamically regulating epigenetic modifications, includinghistone alterations and DNA methylation; (3) remodeling three-dimensional chromatin architecture to establish transcriptionally active microenvironments. By integrating advancements in G4 topological characterization techniques and dynamic equilibrium networks, this work highlights the role of the G4 as a critical <i>cis</i>-regulatory element and provides a theoretical framework for developing G4-targeted therapeutic strategies.</p>","PeriodicalId":35536,"journal":{"name":"遗传","volume":"47 12","pages":"1287-1299"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145775874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Current understanding of mitochondrial DNA genetic diseases and gene therapy. 线粒体DNA遗传疾病和基因治疗的最新认识。
Q3 Medicine Pub Date : 2025-12-01 DOI: 10.16288/j.yczz.25-032
Cheng Tang, Shun-Qing Xu, Han-Zeng Li

Mitochondria, as crucial organelles within eukaryotic cells, have their proteins and RNAs encoded by both the nuclear genome and the mitochondrial genome. They play vital roles in energy regulation, cellular metabolism, signal transduction, and various other physiological activities. Additionally, mitochondria interact with multiple organelles to collectively maintain cellular homeostasis. Mitochondria can also be transferred between cells and tissues through mechanisms such as migrasomes. Mitochondrial DNA (mtDNA) mutations often cause severe inherited rare diseases, characterized by tissue specificity, heterogeneity, multiple mutation sites, and challenges in achieving a complete cure. Gene editing of mtDNA holds promise for fundamentally curing such diseases. Traditional gene-editing nucleases, such as zinc-finger nucleases (ZFNs) and transcription activator-like effector nuclease (TALENs), as well as novel gene editors like DddA-derived cytosine base editors (DdCBEs), have been demonstrated to correct certain mtDNA mutations. However, CRISPR-based technologies-despite their superior programmability and efficiency-are currently limited due to the technical bottleneck of inefficient sgRNA delivery into mitochondria. This article systematically reviews the structure and function of mitochondria, related diseases, and the current state of mtDNA gene-editing therapies. Furthermore, it explores future directions for optimizing therapeutic tools to overcome the challenge of sgRNA delivery, thereby addressing the treatment barriers posed by pathogenic mtDNA mutations in inherited rare diseases.

线粒体作为真核细胞的重要细胞器,其蛋白质和rna由核基因组和线粒体基因组共同编码。它们在能量调节、细胞代谢、信号转导和其他各种生理活动中起着重要作用。此外,线粒体与多个细胞器相互作用,共同维持细胞稳态。线粒体也可以通过迁移体等机制在细胞和组织之间转移。线粒体DNA (mtDNA)突变经常导致严重的遗传性罕见疾病,其特点是组织特异性、异质性、多突变位点以及实现完全治愈的挑战。对mtDNA进行基因编辑有望从根本上治愈这些疾病。传统的基因编辑核酸酶,如锌指核酸酶(ZFNs)和转录激活物样效应核酸酶(TALENs),以及新型基因编辑器,如ddda衍生胞嘧啶碱基编辑器(DdCBEs),已被证明可以纠正某些mtDNA突变。然而,尽管基于crispr的技术具有优越的可编程性和效率,但由于sgRNA递送到线粒体效率低下的技术瓶颈,目前受到限制。本文系统地综述了线粒体的结构和功能、相关疾病以及mtDNA基因编辑治疗的现状。此外,它还探讨了优化治疗工具以克服sgRNA递送挑战的未来方向,从而解决遗传性罕见病中致病性mtDNA突变带来的治疗障碍。
{"title":"Current understanding of mitochondrial DNA genetic diseases and gene therapy.","authors":"Cheng Tang, Shun-Qing Xu, Han-Zeng Li","doi":"10.16288/j.yczz.25-032","DOIUrl":"https://doi.org/10.16288/j.yczz.25-032","url":null,"abstract":"<p><p>Mitochondria, as crucial organelles within eukaryotic cells, have their proteins and RNAs encoded by both the nuclear genome and the mitochondrial genome. They play vital roles in energy regulation, cellular metabolism, signal transduction, and various other physiological activities. Additionally, mitochondria interact with multiple organelles to collectively maintain cellular homeostasis. Mitochondria can also be transferred between cells and tissues through mechanisms such as migrasomes. Mitochondrial DNA (mtDNA) mutations often cause severe inherited rare diseases, characterized by tissue specificity, heterogeneity, multiple mutation sites, and challenges in achieving a complete cure. Gene editing of mtDNA holds promise for fundamentally curing such diseases. Traditional gene-editing nucleases, such as zinc-finger nucleases (ZFNs) and transcription activator-like effector nuclease (TALENs), as well as novel gene editors like DddA-derived cytosine base editors (DdCBEs), have been demonstrated to correct certain mtDNA mutations. However, CRISPR-based technologies-despite their superior programmability and efficiency-are currently limited due to the technical bottleneck of inefficient sgRNA delivery into mitochondria. This article systematically reviews the structure and function of mitochondria, related diseases, and the current state of mtDNA gene-editing therapies. Furthermore, it explores future directions for optimizing therapeutic tools to overcome the challenge of sgRNA delivery, thereby addressing the treatment barriers posed by pathogenic mtDNA mutations in inherited rare diseases.</p>","PeriodicalId":35536,"journal":{"name":"遗传","volume":"47 12","pages":"1300-1325"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145775916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A journey into biological complexity: continuing the legacy of Doug and Bill. 生物复杂性之旅:继续道格和比尔的遗产。
Q3 Medicine Pub Date : 2025-12-01 DOI: 10.16288/j.yczz.25-182
Miao-Ling Yang, Zhuo Du

Given the inherent complexity, hierarchical organization, and dynamic nature of living systems, there is no single best strategy for investigation, and priorities shift with the evolution of the life sciences. In the 1990s, two classic stories, The Salvation of Doug and The Demise of Bill, used automobiles as analogies and satire to contrast two research strategies: dismantling components to uncover underlying mechanisms, or applying functional perturbations to identify critical elements. These heuristic parables stimulated broad discussion on the respective strengths and limitations of different research approaches and continue to be widely used in teaching today. The life sciences have since entered an era integrating high-throughput, high-resolution, and multidimensional approaches, where single-path strategies can no longer provide deep, systematic insights into complex biological processes. We view the intrinsic features of living systems, such as modular organization, regulatory networks, nonlinear responses, and adaptive compensation, as factors that make any single approach likely to capture only local, static aspects, thereby hindering the reconstruction of systems-level, dynamic properties. Against this backdrop, we present a modern continuation of the two parables, reimagined in a contemporary setting and featuring two protagonists with symbolic Chinese names, "Zhiwei" (meaning "decoding hidden mechanisms") and "Sixu" ("reasoning through order"), who personify biochemical and genetic mindsets. In our narrative, the two protagonists transition from working independently to collaborating, integrating high-throughput experimentation, systems-level analysis, and computational modeling to uncover structural and operational principles underlying complex systems. We believe this retelling reflects the growing emphasis on systems-level and dynamic perspectives in biology, highlighting the value of methodological integration and innovation. We hope it will serve as a valuable resource for teaching in genetics and related disciplines, while fostering reflection on the enduring relevance of genetic reasoning in contemporary research.

考虑到生命系统固有的复杂性、分层组织和动态性,没有单一的最佳调查策略,优先事项随着生命科学的发展而变化。20世纪90年代,《道格的救赎》和《比尔的消亡》这两部经典小说用汽车作为类比和讽刺,对比了两种研究策略:拆解零部件以揭示潜在机制,或应用功能扰动来识别关键要素。这些启发式比喻激发了对不同研究方法各自优势和局限性的广泛讨论,并在今天的教学中继续广泛使用。生命科学已经进入了一个整合高通量、高分辨率和多维方法的时代,在这个时代,单路径策略不再能够为复杂的生物过程提供深入、系统的见解。我们认为生命系统的内在特征,如模块化组织、调节网络、非线性响应和自适应补偿,是使任何单一方法都可能只捕获局部静态方面的因素,从而阻碍了系统级动态特性的重建。在此背景下,我们呈现了这两个寓言的现代延续,在当代背景下重新构想,并以两个具有象征意义的中文名字为主角,“智为”(意为“解码隐藏机制”)和“思素”(“通过秩序推理”),他们是生化和基因思维的化身。在我们的叙述中,两位主角从独立工作转变为合作,集成高通量实验,系统级分析和计算建模,以揭示复杂系统的结构和操作原理。我们认为,这种复述反映了生物学中对系统级和动态视角的日益重视,突出了方法整合和创新的价值。我们希望它将成为遗传学和相关学科教学的宝贵资源,同时促进对遗传推理在当代研究中的持久相关性的反思。
{"title":"A journey into biological complexity: continuing the legacy of Doug and Bill.","authors":"Miao-Ling Yang, Zhuo Du","doi":"10.16288/j.yczz.25-182","DOIUrl":"https://doi.org/10.16288/j.yczz.25-182","url":null,"abstract":"<p><p>Given the inherent complexity, hierarchical organization, and dynamic nature of living systems, there is no single best strategy for investigation, and priorities shift with the evolution of the life sciences. In the 1990s, two classic stories, <i>The Salvation of Doug</i> and <i>The Demise of Bill</i>, used automobiles as analogies and satire to contrast two research strategies: dismantling components to uncover underlying mechanisms, or applying functional perturbations to identify critical elements. These heuristic parables stimulated broad discussion on the respective strengths and limitations of different research approaches and continue to be widely used in teaching today. The life sciences have since entered an era integrating high-throughput, high-resolution, and multidimensional approaches, where single-path strategies can no longer provide deep, systematic insights into complex biological processes. We view the intrinsic features of living systems, such as modular organization, regulatory networks, nonlinear responses, and adaptive compensation, as factors that make any single approach likely to capture only local, static aspects, thereby hindering the reconstruction of systems-level, dynamic properties. Against this backdrop, we present a modern continuation of the two parables, reimagined in a contemporary setting and featuring two protagonists with symbolic Chinese names, \"Zhiwei\" (meaning \"decoding hidden mechanisms\") and \"Sixu\" (\"reasoning through order\"), who personify biochemical and genetic mindsets. In our narrative, the two protagonists transition from working independently to collaborating, integrating high-throughput experimentation, systems-level analysis, and computational modeling to uncover structural and operational principles underlying complex systems. We believe this retelling reflects the growing emphasis on systems-level and dynamic perspectives in biology, highlighting the value of methodological integration and innovation. We hope it will serve as a valuable resource for teaching in genetics and related disciplines, while fostering reflection on the enduring relevance of genetic reasoning in contemporary research.</p>","PeriodicalId":35536,"journal":{"name":"遗传","volume":"47 12","pages":"1377-1386"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145775936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Economics and barriers of precision viticulture technologies: A comprehensive systematic literature review 精准葡萄栽培技术的经济与障碍:全面系统的文献综述
IF 7.4 Q1 AGRICULTURE, MULTIDISCIPLINARY Pub Date : 2025-12-01 DOI: 10.1016/j.inpa.2025.04.001
Antonino GALATI, Serena SOFIA, Maria CRESCIMANNO
Precision farming technologies are revolutionising the wine-growing sector thanks to their ability to manage crop variability, increase economic benefits, reduce the environmental impact, and improve grape yields and quality. Most earlier studies focused on the effects of precision technology adoption on plant health and canopy development—and therefore grape quality—neglecting the profitability impact. This study aims to fill this gap by presenting a systematic literature analysis discussing advancements in the economics of precision viticulture technologies. The results show how technologies such as unmanned aerial vehicles, precision irrigation, and robotics can increase efficiency in resource management, helping to reduce costs and improve vineyard profitability. However, the findings also emphasise the need for tailored approaches to integrate these advances. Furthermore, the analysis highlights the main barriers related to the cost of adopting precision technologies and the skills required to read and interpret the data. The results of this study hold interest to academics, vine growers, and farmers, providing a basis for future research into the cost-effectiveness of adopting precision technologies.
精准农业技术正在彻底改变葡萄酒种植行业,因为它们能够管理作物的变化,增加经济效益,减少对环境的影响,提高葡萄产量和质量。大多数早期的研究都集中在采用精密技术对植物健康和冠层发育的影响上,从而忽略了对盈利能力的影响。本研究旨在填补这一空白,提出了一个系统的文献分析,讨论经济的进步,精密葡萄栽培技术。研究结果表明,无人机、精准灌溉和机器人技术等技术可以提高资源管理效率,帮助降低成本,提高葡萄园的盈利能力。然而,研究结果也强调需要有针对性的方法来整合这些进步。此外,分析强调了与采用精密技术的成本和阅读和解释数据所需的技能有关的主要障碍。这项研究的结果引起了学术界、葡萄种植者和农民的兴趣,为未来研究采用精密技术的成本效益提供了基础。
{"title":"Economics and barriers of precision viticulture technologies: A comprehensive systematic literature review","authors":"Antonino GALATI,&nbsp;Serena SOFIA,&nbsp;Maria CRESCIMANNO","doi":"10.1016/j.inpa.2025.04.001","DOIUrl":"10.1016/j.inpa.2025.04.001","url":null,"abstract":"<div><div>Precision farming technologies are revolutionising the wine-growing sector thanks to their ability to manage crop variability, increase economic benefits, reduce the environmental impact, and improve grape yields and quality. Most earlier studies focused on the effects of precision technology adoption on plant health and canopy development—and therefore grape quality—neglecting the profitability impact. This study aims to fill this gap by presenting a systematic literature analysis discussing advancements in the economics of precision viticulture technologies. The results show how technologies such as unmanned aerial vehicles, precision irrigation, and robotics can increase efficiency in resource management, helping to reduce costs and improve vineyard profitability. However, the findings also emphasise the need for tailored approaches to integrate these advances. Furthermore, the analysis highlights the main barriers related to the cost of adopting precision technologies and the skills required to read and interpret the data. The results of this study hold interest to academics, vine growers, and farmers, providing a basis for future research into the cost-effectiveness of adopting precision technologies.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"12 4","pages":"Pages 487-500"},"PeriodicalIF":7.4,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145697899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Efficient instance segmentation for strawberry in greenhouses using YOLOv8n-MCP on edge devices 在边缘设备上使用YOLOv8n-MCP对温室中的草莓进行有效的实例分割
IF 7.4 Q1 AGRICULTURE, MULTIDISCIPLINARY Pub Date : 2025-12-01 DOI: 10.1016/j.inpa.2025.07.001
Xinhao Zhang , Guangpeng Zhang , Jiayi Wang , Jinqi Yang , Quanqu Ge , Ran Zhao , Yang Wang
The labor cost in agriculture is gradually increasing, making it necessary to develop robots for strawberry picking. These robots require accurate strawberry localization, which remains challenging using machine vision. While instance segmentation can improve positioning accuracy, current algorithms are inefficient on edge computing devices during robot navigation and ineffective for recognizing strawberries in elevated cultivation. This paper proposes an improved YOLOv8n model (YOLOv8n-MCP) optimized for edge computing during robot navigation. The network implements three key improvements: 1) MobileNetV3 as the backbone, enhancing strawberry feature extraction under varied lighting while reducing parameters and GFLOPs; 2) a new Cross-scale Feature Fusion Module (CCFM) as the Neck, improving detection of strawberries at varying distances; and 3) Partial Convolution (PConv) to enhance C2f and Head components, further reducing network parameters and GFLOPs while improving FPS. Experimental results show that compared to YOLOv8n, YOLOv8n-MCP reduces parameters by 69 %, GFLOPs by 56 %, and increases FPS by 42 %. Tests on Nvidia Jetson Xavier NX demonstrate that YOLOv8n-MCP achieves 49.5 FPS, significantly outperforming the original YOLOv8n’s 37.6 FPS, effectively meeting the requirements for strawberry instance segmentation during robot navigation with edge devices.
农业的人工成本正在逐渐增加,因此有必要开发草莓采摘机器人。这些机器人需要精确的草莓定位,这仍然是使用机器视觉的挑战。虽然实例分割可以提高定位精度,但目前的算法在机器人导航过程中的边缘计算设备上效率低下,对于识别高架栽培的草莓无效。本文提出了一种改进的YOLOv8n模型(YOLOv8n- mcp),对机器人导航过程中的边缘计算进行了优化。该网络实现了三个关键改进:1)以MobileNetV3为骨干,增强了不同光照下草莓特征的提取,同时降低了参数和GFLOPs;2)采用新的跨尺度特征融合模块(Cross-scale Feature Fusion Module, CCFM)作为颈部,提高草莓在不同距离上的检测能力;3)局部卷积(Partial Convolution, PConv)增强C2f和Head分量,进一步降低网络参数和GFLOPs,同时提高FPS。实验结果表明,与YOLOv8n相比,YOLOv8n- mcp可降低69%的参数,降低56%的GFLOPs,提高42%的FPS。在Nvidia Jetson Xavier NX上的测试表明,YOLOv8n- mcp达到49.5 FPS,显著优于原版YOLOv8n的37.6 FPS,有效满足机器人边缘设备导航时草莓实例分割的要求。
{"title":"Efficient instance segmentation for strawberry in greenhouses using YOLOv8n-MCP on edge devices","authors":"Xinhao Zhang ,&nbsp;Guangpeng Zhang ,&nbsp;Jiayi Wang ,&nbsp;Jinqi Yang ,&nbsp;Quanqu Ge ,&nbsp;Ran Zhao ,&nbsp;Yang Wang","doi":"10.1016/j.inpa.2025.07.001","DOIUrl":"10.1016/j.inpa.2025.07.001","url":null,"abstract":"<div><div>The labor cost in agriculture is gradually increasing, making it necessary to develop robots for strawberry picking. These robots require accurate strawberry localization, which remains challenging using machine vision. While instance segmentation can improve positioning accuracy, current algorithms are inefficient on edge computing devices during robot navigation and ineffective for recognizing strawberries in elevated cultivation. This paper proposes an improved YOLOv8n model (YOLOv8n-MCP) optimized for edge computing during robot navigation. The network implements three key improvements: 1) MobileNetV3 as the backbone, enhancing strawberry feature extraction under varied lighting while reducing parameters and GFLOPs; 2) a new Cross-scale Feature Fusion Module (CCFM) as the Neck, improving detection of strawberries at varying distances; and 3) Partial Convolution (PConv) to enhance C2f and Head components, further reducing network parameters and GFLOPs while improving FPS. Experimental results show that compared to YOLOv8n, YOLOv8n-MCP reduces parameters by 69 %, GFLOPs by 56 %, and increases FPS by 42 %. Tests on Nvidia Jetson Xavier NX demonstrate that YOLOv8n-MCP achieves 49.5 FPS, significantly outperforming the original YOLOv8n’s 37.6 FPS, effectively meeting the requirements for strawberry instance segmentation during robot navigation with edge devices.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"12 4","pages":"Pages 539-549"},"PeriodicalIF":7.4,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145697903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Detection of fungal disease in citrus fruit based on hyperspectral imaging 基于高光谱成像的柑橘果实真菌病害检测
IF 7.4 Q1 AGRICULTURE, MULTIDISCIPLINARY Pub Date : 2025-12-01 DOI: 10.1016/j.inpa.2025.02.006
Xincai Yu , Shuangyin Liu , Chenjiaozi Wang , Binbin Jiao , Cong Huang , Bo Liu , Conghui Liu , Liping Yin , Fanghao Wan , Wanqiang Qian , Xi Qiao
Citrus fruit fungal disease is a major reason for the serious decline in citrus production and quality. Due to its highly contagious nature, timely and effective detection is an important means of prevention and control. Given the high similarity between citrus quarantine diseases and local similar diseases after invading citrus fruits, this study utilizes hyperspectral imaging technology to acquire hyperspectral images of citrus diseases caused by three types of fungi (Phytophthora citrophthora, Phytophthora citricola, Phytophthora syringae). By studying the spectral features of different regions affected by citrus diseases, the competitive adaptive resampling algorithm (CARS) was used to extract 44 feature bands for reconstructing the spectral image, aiming to reduce information redundancy without losing critical information. A simple deep learning model architecture was proposed, which achieved an accuracy of 92.50% in the test dataset. This study provides a new perspective and method for citrus disease detection, offering theoretical and scientific support for the detection of citrus diseases using deep learning and hyperspectral imaging technology.
柑桔果实真菌病是柑桔产量和品质严重下降的主要原因。由于其高传染性,及时有效的检测是预防和控制的重要手段。鉴于柑橘检疫性疾病与柑橘果实侵染后的当地类似疾病高度相似,本研究利用高光谱成像技术获取了柑橘疫霉(Phytophthora citrophthora)、citricola疫霉(Phytophthora citricola)、丁香疫霉(Phytophthora syringae)三种真菌引起的柑橘病害的高光谱图像。通过研究柑橘病害不同区域的光谱特征,采用竞争自适应重采样算法(CARS)提取44个特征波段进行光谱图像重构,在不丢失关键信息的前提下减少信息冗余。提出了一种简单的深度学习模型架构,在测试数据集中达到了92.50%的准确率。本研究为柑橘病害检测提供了新的视角和方法,为利用深度学习和高光谱成像技术检测柑橘病害提供了理论和科学支持。
{"title":"Detection of fungal disease in citrus fruit based on hyperspectral imaging","authors":"Xincai Yu ,&nbsp;Shuangyin Liu ,&nbsp;Chenjiaozi Wang ,&nbsp;Binbin Jiao ,&nbsp;Cong Huang ,&nbsp;Bo Liu ,&nbsp;Conghui Liu ,&nbsp;Liping Yin ,&nbsp;Fanghao Wan ,&nbsp;Wanqiang Qian ,&nbsp;Xi Qiao","doi":"10.1016/j.inpa.2025.02.006","DOIUrl":"10.1016/j.inpa.2025.02.006","url":null,"abstract":"<div><div>Citrus fruit fungal disease is a major reason for the serious decline in citrus production and quality. Due to its highly contagious nature, timely and effective detection is an important means of prevention and control. Given the high similarity between citrus quarantine diseases and local similar diseases after invading citrus fruits, this study utilizes hyperspectral imaging technology to acquire hyperspectral images of citrus diseases caused by three types of fungi (<em>Phytophthora citrophthora</em>, <em>Phytophthora citricola</em>, <em>Phytophthora syringae</em>). By studying the spectral features of different regions affected by citrus diseases, the competitive adaptive resampling algorithm (CARS) was used to extract 44 feature bands for reconstructing the spectral image, aiming to reduce information redundancy without losing critical information. A simple deep learning model architecture was proposed, which achieved an accuracy of 92.50% in the test dataset. This study provides a new perspective and method for citrus disease detection, offering theoretical and scientific support for the detection of citrus diseases using deep learning and hyperspectral imaging technology.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"12 4","pages":"Pages 456-465"},"PeriodicalIF":7.4,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145697843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Karyotype and genome characterization analysis of Chilobrachys jingzhao (Theraphosidae: Chilobrachys). 景照赤蝽核型及基因组特征分析(龙蝇科:赤蝽)。
Q3 Medicine Pub Date : 2025-12-01 DOI: 10.16288/j.yczz.25-026
Yu-Xuan Zhang, Meng-Ying Zhang, Han-Ting Yang, Chi Song, Zi-Zhong Yang, Shi-Lin Chen

The medicinal preparation of Chilobrachys jingzhao possesses various therapeutic properties, including anti-inflammatory, detoxifying, analgesic, and anti-edema effects. However, research on its genetic background and toxin mechanisms is held back by the lack of chromosome karyotype and genome data. In this study, we analyzed the karyotype of C. jingzhao using chromosome preparation techniques, estimated the genome size using flow cytometry and K-mer analysis, and performed genome sequencing and assembly using second- and third-generation single molecule real-time sequencing technologies. The results showed that C. jingzhao has a diploid chromosome number of 2n=68, with a karyotype formula of 2n=46m+18sm+4st and a chromosomal complement of 2n=10L+18M2+38M1+2S. Using Solanum lycopersicum and Trichonephila clavata as references, flow cytometry estimates the genome size at 7,775.49 Mb and 7,680.26 Mb, respectively. The 19-mer analysis also estimated the genome size to be 7,626.00 Mb, consistent with the flow cytometry results. Further analysis indicated that the genome of C. jingzhao has a high level of heterozygosity (8.45%) and a high proportion of repetitive sequences (67.10%), classifying it as an ultra-high heterozygous and high-repeat genome. The initial genome assembly of C. jingzhao was 8,804.93 Mb in size, with a contig N50 of 55.55 Mb and a BUSCO completeness score of 95.9%, indicating high assembly quality. This study first reveals the karyotype and genome information of C. jingzhao, offering crucial data for future research on its whole genome, toxin mechanisms, genetics, origin, evolution, and taxonomy.

本发明具有多种治疗特性,包括抗炎、解毒、镇痛和抗水肿作用。然而,由于缺乏染色体核型和基因组数据,对其遗传背景和毒素机制的研究受到阻碍。本研究利用染色体制备技术对荆芥的核型进行分析,利用流式细胞术和K-mer分析估算其基因组大小,并利用第二代和第三代单分子实时测序技术对其基因组进行测序和组装。结果表明,荆芥二倍体染色体数为2n=68,核型公式为2n=46m+18sm+4st,染色体补体为2n=10L+18M2+38M1+2S。以番茄茄(Solanum lycopersicum)和锥虫(Trichonephila clavata)为参照,流式细胞技术估计其基因组大小分别为7,775.49 Mb和7,680.26 Mb。19-mer分析还估计基因组大小为7,626.00 Mb,与流式细胞术结果一致。进一步分析表明,荆芥基因组杂合性高(8.45%),重复序列比例高(67.10%),属于超高杂合高重复基因组。荆芥基因组初始组装体大小为8804.93 Mb,序列N50为55.55 Mb, BUSCO完整性评分为95.9%,组装质量较高。本研究首次揭示了荆芥的核型和基因组信息,为今后荆芥全基因组、毒素机制、遗传学、起源、进化和分类等方面的研究提供了重要数据。
{"title":"Karyotype and genome characterization analysis of <i>Chilobrachys jingzhao</i> (Theraphosidae: <i>Chilobrachys</i>).","authors":"Yu-Xuan Zhang, Meng-Ying Zhang, Han-Ting Yang, Chi Song, Zi-Zhong Yang, Shi-Lin Chen","doi":"10.16288/j.yczz.25-026","DOIUrl":"https://doi.org/10.16288/j.yczz.25-026","url":null,"abstract":"<p><p>The medicinal preparation of <i>Chilobrachys jingzhao</i> possesses various therapeutic properties, including anti-inflammatory, detoxifying, analgesic, and anti-edema effects. However, research on its genetic background and toxin mechanisms is held back by the lack of chromosome karyotype and genome data. In this study, we analyzed the karyotype of <i>C. jingzhao</i> using chromosome preparation techniques, estimated the genome size using flow cytometry and K-mer analysis, and performed genome sequencing and assembly using second- and third-generation single molecule real-time sequencing technologies. The results showed that <i>C. jingzhao</i> has a diploid chromosome number of 2<i>n</i>=68, with a karyotype formula of 2<i>n</i>=46m+18sm+4st and a chromosomal complement of 2<i>n</i>=10L+18M2+38M1+2S. Using <i>Solanum lycopersicum</i> and <i>Trichonephila clavata</i> as references, flow cytometry estimates the genome size at 7,775.49 Mb and 7,680.26 Mb, respectively. The 19-mer analysis also estimated the genome size to be 7,626.00 Mb, consistent with the flow cytometry results. Further analysis indicated that the genome of <i>C. jingzhao</i> has a high level of heterozygosity (8.45%) and a high proportion of repetitive sequences (67.10%), classifying it as an ultra-high heterozygous and high-repeat genome. The initial genome assembly of <i>C. jingzhao</i> was 8,804.93 Mb in size, with a contig N50 of 55.55 Mb and a BUSCO completeness score of 95.9%, indicating high assembly quality. This study first reveals the karyotype and genome information of <i>C. jingzhao</i>, offering crucial data for future research on its whole genome, toxin mechanisms, genetics, origin, evolution, and taxonomy.</p>","PeriodicalId":35536,"journal":{"name":"遗传","volume":"47 12","pages":"1351-1364"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145775877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Assessment of the tomato cluster yield estimation algorithms via tracking-by-detection approaches 基于检测跟踪方法的番茄聚类产量估计算法评估
IF 7.4 Q1 AGRICULTURE, MULTIDISCIPLINARY Pub Date : 2025-12-01 DOI: 10.1016/j.inpa.2025.02.005
Zhongxian Qi , Tianxue Zhang , Ting Yuan , Wei Zhou , Wenqiang Zhang
Automated vision-based detection and counting are critical for accurate tomato yield estimation, which contribute to precise yield management strategies and an efficient food supply chains. Special conditions, including background clutter, occlusion, and varying sunlight, affect the accuracy of crop detection and counting. To determine the most suitable algorithms for this yield estimation context, we herein establish a public multi-object tracking (MOT) dataset for tomato cluster counts, while evaluating and comparing state-of-the-art target detection and MOT-based algorithms. The evaluated detectors consist of YOLOv8 and RT-DETR, which represent algorithms that achieve a balance between accuracy and speed. The tracking algorithms included state-of-the-art methodologies such as SORT, DeepSort, ByteTrack, and BotSort. Initially, the performance of the detectors was rigorously evaluated, followed by a comprehensive assessment of the four tracking algorithms within a multi-target tracking database tailored for this research and structured in the MOT context. The findings reveal that YOLOv8 and RT-DETR achieve 93.6% and 94.9% results at mAP@75, respectively, with RT-DETR exhibiting fewer false detections. When combined with the RT-DETR detector, the ByteTrack-based algorithm registers the highest counting accuracy at 95.5%, whereas BotSort achieves the highest MOTA score with 84.6%. Notably, the trackers without the ReID module (i.e., SORT and ByteTrack) demonstrate greater adaptability to frame rate variations in the test videos. At a 30-fps frame rate, the incorporation of ReID modules in DeepSort and BotSort algorithms significantly enhances the MOTA metric. Looking ahead, we plan to leverage these algorithms into an autonomous inspection platform that aims to estimate crop yield in real-time.
基于视觉的自动检测和计数对于准确估计番茄产量至关重要,这有助于精确的产量管理策略和高效的食品供应链。特殊条件,包括背景杂乱,遮挡和变化的阳光,会影响作物检测和计数的准确性。为了确定最适合这种产量估计上下文的算法,我们在此建立了一个公共多目标跟踪(MOT)数据集,用于番茄簇计数,同时评估和比较最先进的目标检测和基于MOT的算法。评估的检测器由YOLOv8和RT-DETR组成,它们代表了实现准确性和速度之间平衡的算法。跟踪算法包括最先进的方法,如SORT, DeepSort, ByteTrack和BotSort。首先,对探测器的性能进行了严格评估,然后在为本研究量身定制的多目标跟踪数据库中对四种跟踪算法进行了全面评估,并在MOT环境中构建。研究结果表明,YOLOv8和RT-DETR在mAP@75上分别达到93.6%和94.9%的结果,RT-DETR的误检率更低。当与RT-DETR检测器结合使用时,基于bytetrack的算法的计数准确率最高,为95.5%,而BotSort的MOTA得分最高,为84.6%。值得注意的是,没有ReID模块的跟踪器(即SORT和ByteTrack)在测试视频中对帧速率变化表现出更大的适应性。在30帧/秒的帧速率下,ReID模块在DeepSort和BotSort算法中的结合显著提高了MOTA指标。展望未来,我们计划利用这些算法建立一个自主检测平台,旨在实时估计作物产量。
{"title":"Assessment of the tomato cluster yield estimation algorithms via tracking-by-detection approaches","authors":"Zhongxian Qi ,&nbsp;Tianxue Zhang ,&nbsp;Ting Yuan ,&nbsp;Wei Zhou ,&nbsp;Wenqiang Zhang","doi":"10.1016/j.inpa.2025.02.005","DOIUrl":"10.1016/j.inpa.2025.02.005","url":null,"abstract":"<div><div>Automated vision-based detection and counting are critical for accurate tomato yield estimation, which contribute to precise yield management strategies and an efficient food supply chains. Special conditions, including background clutter, occlusion, and varying sunlight, affect the accuracy of crop detection and counting. To determine the most suitable algorithms for this yield estimation context, we herein establish a public multi-object tracking (MOT) dataset for tomato cluster counts, while evaluating and comparing state-of-the-art target detection and MOT-based algorithms. The evaluated detectors consist of YOLOv8 and RT-DETR, which represent algorithms that achieve a balance between accuracy and speed. The tracking algorithms included state-of-the-art methodologies such as SORT, DeepSort, ByteTrack, and BotSort. Initially, the performance of the detectors was rigorously evaluated, followed by a comprehensive assessment of the four tracking algorithms within a multi-target tracking database tailored for this research and structured in the MOT context. The findings reveal that YOLOv8 and RT-DETR achieve 93.6% and 94.9% results at mAP@75, respectively, with RT-DETR exhibiting fewer false detections. When combined with the RT-DETR detector, the ByteTrack-based algorithm registers the highest counting accuracy at 95.5%, whereas BotSort achieves the highest MOTA score with 84.6%. Notably, the trackers without the ReID module (i.e., SORT and ByteTrack) demonstrate greater adaptability to frame rate variations in the test videos. At a 30-fps frame rate, the incorporation of ReID modules in DeepSort and BotSort algorithms significantly enhances the MOTA metric. Looking ahead, we plan to leverage these algorithms into an autonomous inspection platform that aims to estimate crop yield in real-time.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"12 4","pages":"Pages 445-455"},"PeriodicalIF":7.4,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145697898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Lightweight precision model for watermelon seed group density estimation and counting 西瓜种子群密度估算与计数的轻量级精度模型
IF 7.4 Q1 AGRICULTURE, MULTIDISCIPLINARY Pub Date : 2025-12-01 DOI: 10.1016/j.inpa.2025.07.003
Helong Yu , Liyun Han , Chengcheng Chen , Honghong Su , Qichao Niu , Ronghao Meng , Mingxuan Xue
The accurate counting of overlapping watermelon seeds is a key foundation for seed quality testing, breeding selection, resource allocation, and other processes. To improve the counting accuracy for flat and slightly overlapping seeds, we introduce LOYOLO-GC, a Lightweight Occlusion YOLO8n-based group counting model. It adopts HGNetV2 as its backbone, where HGBlocks extract multi-level features for improved learning. GhostConv replaces the standard convolution in HGBlocks, forming LightHGBlock to reduce the number of parameters by generating intrinsic and ghost feature maps with fewer kernels. In addition, a Large Separable Kernel Attention mechanism (LSKA) is used to decompose deep convolution kernels into horizontal and vertical 1D kernels, enabling efficient large kernel attention with lower computational and memory cost. After optimizing the model, we build a multi-occlusion watermelon seed dataset and employ it to develop a LOYOLO-based group counting method. The experimental results show that LOYOLO-GC outperforms SOTA models, achieving 96.08 % accuracy and 86.66 % mAP, an improvement of 0.48 % and 1.67 %, respectively. The model parameters decrease by 63.8 % and GMACs decrease by 38.9 %. Counting accuracy is also improved, with ACC increasing by 5.32 % and L-ACC increasing by 5.04 %, while MAE and RMSE are decreased by 3.68 and 3.28, respectively.
西瓜重叠种子的准确计数是西瓜种子质量检测、育种选择、资源配置等过程的重要基础。为了提高平坦和轻微重叠种子的计数精度,我们引入了基于轻量级遮挡yolo8n的分组计数模型LOYOLO-GC。它采用HGNetV2作为主干,其中HGBlocks提取多层次特征以提高学习。GhostConv取代HGBlocks中的标准卷积,形成LightHGBlock,通过生成内核更少的内在和幽灵特征映射来减少参数的数量。此外,采用大可分离核注意机制(Large分离式核注意机制,LSKA)将深度卷积核分解为水平和垂直的一维核,在降低计算和内存成本的同时实现高效的大核注意。在对模型进行优化后,我们构建了一个多遮挡的西瓜种子数据集,并利用该数据集开发了一种基于loyolo的分组计数方法。实验结果表明,LOYOLO-GC模型的准确率为96.08%,mAP的准确率为86.66%,分别比SOTA模型提高0.48%和1.67%。模型参数降低63.8%,gmac降低38.9%。计数精度也有所提高,ACC提高了5.32%,L-ACC提高了5.04%,MAE和RMSE分别降低了3.68和3.28。
{"title":"Lightweight precision model for watermelon seed group density estimation and counting","authors":"Helong Yu ,&nbsp;Liyun Han ,&nbsp;Chengcheng Chen ,&nbsp;Honghong Su ,&nbsp;Qichao Niu ,&nbsp;Ronghao Meng ,&nbsp;Mingxuan Xue","doi":"10.1016/j.inpa.2025.07.003","DOIUrl":"10.1016/j.inpa.2025.07.003","url":null,"abstract":"<div><div>The accurate counting of overlapping watermelon seeds is a key foundation for seed quality testing, breeding selection, resource allocation, and other processes. To improve the counting accuracy for flat and slightly overlapping seeds, we introduce LOYOLO-GC, a Lightweight Occlusion YOLO8n-based group counting model. It adopts HGNetV2 as its backbone, where HGBlocks extract multi-level features for improved learning. GhostConv replaces the standard convolution in HGBlocks, forming LightHGBlock to reduce the number of parameters by generating intrinsic and ghost feature maps with fewer kernels. In addition, a Large Separable Kernel Attention mechanism (LSKA) is used to decompose deep convolution kernels into horizontal and vertical 1D kernels, enabling efficient large kernel attention with lower computational and memory cost. After optimizing the model, we build a multi-occlusion watermelon seed dataset and employ it to develop a LOYOLO-based group counting method. The experimental results show that LOYOLO-GC outperforms SOTA models, achieving 96.08 % accuracy and 86.66 % mAP, an improvement of 0.48 % and 1.67 %, respectively. The model parameters decrease by 63.8 % and GMACs decrease by 38.9 %. Counting accuracy is also improved, with ACC increasing by 5.32 % and L-ACC increasing by 5.04 %, while MAE and RMSE are decreased by 3.68 and 3.28, respectively.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"12 4","pages":"Pages 565-580"},"PeriodicalIF":7.4,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145697905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
EConv-ViT: A strongly generalized apple leaf disease classification model based on the fusion of ConvNeXt and Transformer EConv-ViT:基于ConvNeXt和Transformer融合的强广义苹果叶病分类模型
IF 7.4 Q1 AGRICULTURE, MULTIDISCIPLINARY Pub Date : 2025-12-01 DOI: 10.1016/j.inpa.2025.03.001
Xin Huang , Demin Xu , Yongqiao Chen , Qian Zhang , Puyu Feng , Yuntao Ma , Qiaoxue Dong , Feng Yu
The accurate recognition of apple leaf diseases is crucial for ensuring crop health and agricultural productivity. However, deep learning models often suffer from poor generalization across diverse environments due to variations in lighting, background complexity, and leaf appearance. To address these challenges, we proposed EConv-ViT, a novel robust generalization model integrating ConvNeXt and Vision Transformer (ViT), enhanced with Efficient Channel Attention (ECA) for superior feature extraction and DropKey to improve generalization and applied the mode on image dataset both captured in laboratory and natural environments for healthy apple leaves, alternaria blotch, grey spot, rust, and mosaic disease. The propsed EConv-ViT model was tested on an independent dataset and achieved accuracy of 99.2% on laboratory-captured image dataset and 79.3% on images captured in natural environments. The classification accuracy for EConv-ViT model exhibited 18.6%, 36.1% and 37.8% improvements compared with ViT, ConvNeXt, and ResNet50 models on a dataset captured in natural environments. EConv-ViT can effectively capture both local and global features and demonstrate its potential for the application on related automated disease monitoring systems.
苹果叶片病害的准确识别对于保证作物健康和农业生产力至关重要。然而,由于光照、背景复杂性和树叶外观的变化,深度学习模型在不同环境下的泛化能力往往较差。为了解决这些问题,我们提出了EConv-ViT模型,这是一种新的鲁棒泛化模型,集成了ConvNeXt和Vision Transformer (ViT),增强了高效通道注意(ECA)以获得卓越的特征提取和DropKey以提高泛化,并将该模型应用于实验室和自然环境中捕获的健康苹果叶片,交替斑病,灰斑病,锈病和花叶病的图像数据集。在独立数据集上对所提出的EConv-ViT模型进行了测试,在实验室捕获的图像数据集上实现了99.2%的准确率,在自然环境中捕获的图像上实现了79.3%的准确率。在自然环境数据集上,EConv-ViT模型的分类准确率比ViT、ConvNeXt和ResNet50模型分别提高了18.6%、36.1%和37.8%。EConv-ViT可以有效地捕捉局部和全局特征,并展示其在相关自动化疾病监测系统中的应用潜力。
{"title":"EConv-ViT: A strongly generalized apple leaf disease classification model based on the fusion of ConvNeXt and Transformer","authors":"Xin Huang ,&nbsp;Demin Xu ,&nbsp;Yongqiao Chen ,&nbsp;Qian Zhang ,&nbsp;Puyu Feng ,&nbsp;Yuntao Ma ,&nbsp;Qiaoxue Dong ,&nbsp;Feng Yu","doi":"10.1016/j.inpa.2025.03.001","DOIUrl":"10.1016/j.inpa.2025.03.001","url":null,"abstract":"<div><div>The accurate recognition of apple leaf diseases is crucial for ensuring crop health and agricultural productivity. However, deep learning models often suffer from poor generalization across diverse environments due to variations in lighting, background complexity, and leaf appearance. To address these challenges, we proposed EConv-ViT, a novel robust generalization model integrating ConvNeXt and Vision Transformer (ViT), enhanced with Efficient Channel Attention (ECA) for superior feature extraction and DropKey to improve generalization and applied the mode on image dataset both captured in laboratory and natural environments for healthy apple leaves, alternaria blotch, grey spot, rust, and mosaic disease. The propsed EConv-ViT model was tested on an independent dataset and achieved accuracy of 99.2% on laboratory-captured image dataset and 79.3% on images captured in natural environments. The classification accuracy for EConv-ViT model exhibited 18.6%, 36.1% and 37.8% improvements compared with ViT, ConvNeXt, and ResNet50 models on a dataset captured in natural environments. EConv-ViT can effectively capture both local and global features and demonstrate its potential for the application on related automated disease monitoring systems.</div></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"12 4","pages":"Pages 466-477"},"PeriodicalIF":7.4,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145697844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
全部 生态学报 Acta Agronomica Sinica 畜牧与饲料科学 中国农学通报 CCV 中国畜牧杂志 生态学杂志 Chinese Journal of Eco-agriculture 中国比较医学杂志 中国畜牧兽医 中国水稻科学 中国烟草科学 农药学学报 棉花学报 Crop research 中国食用菌 福建稻麦科技 福建农业学报 广东农业科学 湖北农业科学 Journal of Agriculture 农业资源与环境学报 北京农学院学报 中国农业大学学报 水产学报 中国水产科学 果树学报 南京农业大学学报 核农学报 植物遗传资源学报 Journal of Plant Resources and Environment Journal of Plant Protection 山西农业科学 沈阳农业大学学报 南方农业学报 现代农药 Modern Agricultural Science and Technology 动物医学进展 西南农业学报 Tobacco Science & Technology Oil Crop Science 遗传 Aquaculture and Fisheries 中国农业气象 湖泊科学 中国农业科学 Journal of Agricultural Sciences aBIOTECH Journal of Resources and Ecology Information Processing in Agriculture 美国植物学期刊(英文) 土壤科学期刊(英文) 园艺研究(英文) 耕作与栽培 湖北农学院学报 昆虫学(英文) 海洋渔业 J Immune Based Ther Vaccines Antimicrob 海岸生命医学杂志(英文版) Life Res (Auckl) 兽医学(英文) Anim. Nutr. Plant Diseases and Pests(植物病虫害研究:英文版) 动物科学期刊(英文) 农业科学 Zhi Wu Sheng Li Yu Fen Zi Sheng Wu Xue Xue Bao 水产研究 湿地科学 湖南农业大学学报(自然科学版) 亚洲兽医病例研究 农业化学和环境(英文) 生态科学 土壤科学 经济动物学报 福建畜牧兽医
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1