融合MacBERT和Talking⁃Heads Attention实体关系联合抽取模型

针对现有的医学文本关系抽取任务模型在训练过程中存在语义理解能力不足,可能导致关系抽取的效果不尽人意的问题,文中提出一种融合MacBERT和Talking⁃Heads Attention的实体关系联合抽取模型。该模型首先利用MacBERT语言模型来获取动态字向量表达,MacBERT作为改进的BERT模型,能够减少预训练和微调阶段之间的差异,从而提高模型的泛化能力;然后,将这些动态字向量表达输入到双向门控循环单元(BiGRU)中,以便提取文本的上下文特征。BiGRU是一种改进的循环神经网络(RNN),具有更好的长期依赖捕获能力。在获取文本上下文特征之后,使用Talking⁃Heads Attention来获取全局特征。Talking⁃Heads Attention是一种自注意力机制,可以捕获文本中不同位置之间的关系,从而提高关系抽取的准确性。实验结果表明,与实体关系联合抽取模型GRTE相比,该模型F1值提升1%,precision值提升0.4%,recall值提升1.5%。

Long non-coding RNA H19 regulates neurogenesis of induced neural stem cells in a mouse model of closed head injury

Stem cell-based therapies have been proposed as a potential treatment for neural regeneration following closed head injury.We previously reported that induced neural stem cells exert beneficial effects on neural regeneration via cell replacement.However,the neural regeneration efficiency of induced neural stem cells remains limited.In this study,we explored differentially expressed genes and long non-coding RNAs to clarify the mechanism underlying the neurogenesis of induced neural stem cells.We found that H19 was the most downregulated neurogenesis-associated lnc RNA in induced neural stem cells compared with induced pluripotent stem cells.Additionally,we demonstrated that H19 levels in induced neural stem cells were markedly lower than those in induced pluripotent stem cells and were substantially higher than those in induced neural stem cell-derived neurons.We predicted the target genes of H19 and discovered that H19 directly interacts with mi R-325-3p,which directly interacts with Ctbp2 in induced pluripotent stem cells and induced neural stem cells.Silencing H19 or Ctbp2 impaired induced neural stem cell proliferation,and mi R-325-3p suppression restored the effect of H19 inhibition but not the effect of Ctbp2 inhibition.Furthermore,H19 silencing substantially promoted the neural differentiation of induced neural stem cells and did not induce apoptosis of induced neural stem cells.Notably,silencing H19 in induced neural stem cell grafts markedly accelerated the neurological recovery of closed head injury mice.Our results reveal that H19 regulates the neurogenesis of induced neural stem cells.H19 inhibition may promote the neural differentiation of induced neural stem cells,which is closely associated with neurological recovery following closed head injury.

Influences of divalent ion substitution on the magnetic and dielectric properties of W-type barium ferrite

Saturation magnetization,magneto-crystalline anisotropy field,and dielectric properties are closely related to microwave devices applied at different frequencies.For regulating the magnetic and dielectric properties of W-type barium ferrites,single-phase BaMe_(2)Fe_(16)O_(27)(Me=Fe,Mn,Zn,Ni,Co) with different Me ions were synthesized by the high-temperature solid-state method.The saturation magnetization(Ms) range from 47.77 emu/g to 95.34 emu/g and the magnetic anisotropy field(H_a) range from 10700.60 Oe(1 Oe=79.5775 A·m^(-1)) to 13739.57 Oe,depending on the type of cation substitution in the hexagonal lattice.The dielectric permittivity and dielectric loss decrease with increasing frequency of the AC electric field in the low-frequency region,while they almost remain constant in the high-frequency region.The charac teristics of easy regulation and preparation make it a potential candidate for use in microwave device applications.

Knowledge, Attitude, and Practice of Using Helmets in Children amongst Parents to Prevent Head Injuries: A Cross-Sectional Study in Riyadh, Saudi Arabia

Objectives: The primary objective was to characterize the range of Knowledge, Attitude, and Practice (KAP) of Helmet use in children amongst parents to prevent head injuries and death. Methods: This is a cross-sectional study, done by online survey using a snowball sampling technique, the number of included responses were 386 parents (Male and female) living in Riyadh Aged 21 - 60 years old or above. Results: The study showed that there is a difference in Parents’ belief in the importance of helmet use while riding a Bicycle vs Motorcycle/Quad bike and that was affected by parents’ education level, almost all the people who answered the survey (76.7%) agree that it is important for their children to wear a helmet when riding both a Bicycle and a Motorcycle or Quadbike with a cumulative percentage of (93.8%). And almost all agreed on multiple approaches to help increase helmet use be it by forcing rental shops to give out helmets, forcing sellers to recommend the use of helmets, increasing awareness campaigns, and imposing fines for not wearing helmets. Conclusions: This study is the first to explore Family helmet use while riding Bicycles and Motorcycles/Quad bikes. Although Parent’s belief in the importance of helmet use for their children was high, it is clear that the level of practice is low. With that the risk of head injuries might be high, our findings suggest that safety interventions for increasing pediatric helmet use are needed to increase helmet use and reduce the risk of head injury and hospitalization.

Numerical simulation of the influence factors of NO_(x) emission on a W-type radiant tube

The radiant tube burner was modeled and analyzed by the numerical simulation method to investigate the influence factors and rules of NO_(x) emissions in a W-type radiant tube.These factors,which include air preheating temperature,excess air coefficient,and fuel gas composition,were modified to study their effects on NO_(x) emissions under varying working conditions.Simulation results were compared with the theoretical calculation value based on chemical reaction equilibrium theory and the onsite experimental value to verify the simulation accuracy.The results show that NO_(x) emissions rise with increasing air preheating temperatures.NO_(x) production increases to an extreme value and then decreases during the oxygen-poor to oxygen-enriched process with the rise of the excess air coefficient.Enhancing the proportion of coke oven gas in the fuel gas raises the combustion temperature as well as the NO_(x) discharge.Both the thermal efficiency and NO_(x) emissions should be balanced.Therefore,the recommended values based on the simulation results are as follows:the air preheating temperature should not exceed 400℃,the excess air coefficient should be between 1.1 and 1.2,and the volume fraction of the coke oven gas should not exceed 30%.

Experimental and numerical simulation study on forced ventilation and dust removal of coal mine heading surface

In order to study the problems of unreasonable airflow distribution and serious dust pollution in a heading surface,an experimental platform for forced ventilation and dust removal was built based on the similar principles.Through the similar experiment and numerical simulation,the distribution of airflow field in the roadway and the spatial and temporal evolution of dust pollution under the conditions of forced ventilation were determined.The airflow field in the roadway can be divided into three zones:jet zone,vortex zone and reflux zone.The dust concentration gradually decreases from the head to the rear of the roadway.Under the forced ventilation conditions,there is a unilateral accumulation of dust,with higher dust concentrations away from the ducts.The position of the equipment has an interception effect on the dust.The maximum error between the test value and the simulation result is 12.9%,which verifies the accuracy of the experimental results.The research results can provide theoretical guidance for the application of dust removal technology in coal mine.

基于改进Double-Head RCNN的无人机航拍图像小目标检测算法

为解决无人机航拍图像中小目标特征信息少且容易被噪声干扰导致现有算法漏检率和误检率高的问题,提出一种改进Double-Head Region-卷积神经网络(RCNN)的无人机航拍图像小目标检测算法。在骨干网络ResNet-50上引入Transformer和可变形卷积(DCN)模块,更有效提取小目标特征信息和语义信息;提出一种基于内容感知特征重组(CARAFE)的特征金字塔网络(FPN)结构模块,解决特征融合过程中小目标被背景噪声干扰而丢失特征信息的问题;在区域建议网络中针对小目标尺度分布特点重新设置Anchor生成尺度,进一步提升小目标检测性能。在VisDrone-DET2021数据集上的实验结果表明:所提算法能提取更具有表征能力的小目标特征信息和语义信息,对比Double-Head RCNN算法,所提算法的参数量增加了9.73×10^(6),FPS损失了0.6,但是AP、AP50和AP75分别提升了2.6%、6.2%和2.1%,APs提升了3.1%。

Tilapia Head Glycolipid Alleviates Indomethacin-Induced Gastric Ulcer via Regulating Oxidative Stress and Inflammation Through COX/PGE2 Signaling Pathway in Adult Rats

The aim of this experiment was to investigate the ameliorative effect and molecular mechanism of tilapia head glycolipid(TH-GL)on indomethacin(IDM)-induced gastric ulcer in male Sprague Dawley(SD)rats.The gastric ulcer model was established by oral administration of 30mgkg^(-1) IDM after 7 days of TH-GL or omeprazole(OME)administration in rats.Then the macroscopic gastric injury symptoms,gastric mucosa protective factor cyclooxygenase 1(COX-1),cyclooxygenase 2(COX-2),prostaglandin E_(2)(PGE_(2)),the levels of oxidative stress,and inflammatory cytokine expression levels in the rats were analyzed.The experimental results showed that multiple ulcers appeared on the gastric surface of the rats in the model group.Compared to the model group,TH-GL significantly alleviated gastric ulcers and reduced the gastric damage index in rats.In addition,TH-GL significantly promoted the expression of constitutive enzyme COX-1 while inhibited the expression of inducible enzyme COX-2,and make PGE2 maintain at normal levels.TH-GL also inhibited oxidative stress and inflammatory responses,increased superoxide dismutase(SOD)activity and glutathione(GSH)content,decreased the level of malondialdehyde(MDA)and the content of pro-inflammatory factor.In conclusion,these results suggested that TH-GL could maintain the expression levels of COX-1 and PGE2 while inhibit the expression of COX-2 in the gastric of rat and then prevent IDM-induced gastric ulcer,which may be related to the regulation of oxidative stress and inflammatory response.Therefore,TH-GL might be a new option for the prevention of gastric diseases induced by IDM.

Basal defense is enhanced in a wheat cultivar resistant to Fusarium head blight

Fusarium head blight(FHB),mainly caused by the fungal pathogen Fusarium graminearum,is one of the most destructive wheat diseases.Besides directly affecting the yield,the mycotoxin residing in the kernel greatly threatens the health of humans and livestock.Xinong 979(XN979)is a widely cultivated wheat elite with high yield and FHB resistance.However,its resistance mechanism remains unclear.In this study,we studied the expression of genes involved in plant defense in XN979 by comparative transcriptomics.We found that the FHB resistance in XN979 consists of two lines of defense.The first line of defense,which is constitutive,is knitted via the enhanced basal expression of lignin and jasmonic acid(JA)biosynthesis genes.The second line of defense,which is induced upon F.graminearum infection,is contributed by the limited suppression of photosynthesis and the struggle of biotic stress-responding genes.Meanwhile,the effective defense in XN979 leads to an inhibition of fungal gene expression,especially in the early infection stage.The formation of the FHB resistance in XN979 may coincide with the breeding strategies,such as selecting high grain yield and lodging resistance traits.This study will facilitate our understanding of wheat-F.graminearum interaction and is insightful for breeding FHB-resistant wheat.

YOLO-MFD:Remote Sensing Image Object Detection with Multi-Scale Fusion Dynamic Head

Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.

Bilateral Avascular Necrosis of the Femoral Head in Renal Transplant Recipient: A Case Report

Osteoarticular complications are common after renal transplantation. The complications may result from the bone condition prior to transplantation or the iatrogenic effects of the treatments administered. These complications lead to significant morbidity and mortality, in addition to chronic pain and functional impairment. We report the clinical case of bilateral avascular necrosis (AVN) of the femoral head in a kidney transplant recipient. Clinical Case: 53-year-old male with a history of chronic hypertension. He underwent chronic hemodialysis for 12 months and was treated with Entecavir for chronic hepatitis B. The patient received a kidney transplant from a non-related living donor. Induction therapy included Thymoglobulin along with tapered corticosteroids, reaching a dose of 5 mg/day after 3 months, Mycophenolate mofetil (2 g/day), and Tacrolimus adjusted based on residual levels. There was good recovery of renal graft function. After six months, the patient reported bilateral hip pain and functional impairment of both lower limbs. Pelvic X-rays showed signs suggestive of bilateral AVN of the femoral heads. The diagnosis was confirmed by MRI. The patient underwent right hip drilling and total left hip replacement (THR). A right THR was performed a year later. Conclusion: AVN constitutes a frequent cause of morbidity and mortality after RT. The pathophysiology of osteonecrosis remains complex and multifactorial. We emphasize the importance of conducting a thorough assessment of bone health in patients both before and after RT.

A Dual-Cluster-Head Based Medium Access Control for Large-Scale UAV Ad-Hoc Networks

Unmanned Aerial Vehicle(UAV)ad hoc network has achieved significant growth for its flexibility,extensibility,and high deployability in recent years.The application of clustering scheme for UAV ad hoc network is imperative to enhance the performance of throughput and energy efficiency.In conventional clustering scheme,a single cluster head(CH)is always assigned in each cluster.However,this method has some weaknesses such as overload and premature death of CH when the number of UAVs increased.In order to solve this problem,we propose a dual-cluster-head based medium access control(DCHMAC)scheme for large-scale UAV networks.In DCHMAC,two CHs are elected to manage resource allocation and data forwarding cooperatively.Specifically,two CHs work on different channels.One of CH is used for intra-cluster communication and the other one is for inter-cluster communication.A Markov chain model is developed to analyse the throughput of the network.Simulation result shows that compared with FM-MAC(flying ad hoc networks multi-channel MAC,FM-MAC),DCHMAC improves the throughput by approximately 20%~50%and prolongs the network lifetime by approximately 40%.

Surgical Treatment of Osteonecrosis of the Femoral Head Using Minimally Invasive Surgical Drilling and Cancellous Grafting at Brazzaville University Hospital

Introduction: Osteonecrosis of the femoral head (ONTF) is a debilitating condition. Several treatments have been proposed with controversial results. The aim of our study was to evaluate treatment by surgical drilling coupled with in situ cancellous grafting. Materials and methods: Our study was a case-control study conducted at Brazzaville University Hospital from 1st January 2018 to 31 December 2023. It compared two groups of patients with ONTF: non-operated (13 patients, 20 hips) and operated (22 patients, 35 hips). We used the visual digital scale (VDS) for pain assessment, the Merle D’Aubigne-Postel (MDP) scoring system for clinical and functional assessment, and the evolution of necrosis. Results: The group of non-operated patients had a mean age of 35.69 ± 3.4 years, no improvement in pain with an EVN above seven at the last recoil and a mean global MDP score falling from 12.7 before offloading to 10.13 at one year. The group of patients operated on had a mean age of 37.86 ± 7.02 years, a significant reduction in pain (p = 0.00004) and a significantly increased MDP score (p = 0.0034). A comparison of the two groups of patients showed significant stabilization of the necrotic lesions in the operated patients (p = 0.00067), with better satisfaction in the same group. Conclusion: Surgical drilling combined with grafting in the treatment of early-stage ONTF has improved progress in our series. The technique is reproducible and less invasive. It has made it possible to delay unfavorable progression and, consequently, hip replacement surgery.

Fetal Head Compression: Its Possible Role in Neurologic Injury

It is widely assumed that fetal ischemic brain injury during labor derives almost exclusively from severe, systemic hypoxemia with marked neonatal depression and acidemia. Severe asphyxia, however, is one of several causes of perinatal neurological injury and may not be the most common;most neonates diagnosed with hypoxic-ischemic encephalopathy do not have evidence of severe asphyxia. Sepsis, direct brain trauma, and drug or toxin exposure account for some cases, while mechanical forces of labor and delivery that increase fetal intracranial pressure sufficiently to impair brain perfusion may also contribute. Because of bony compliance and mobile suture lines, the fetal skull changes shape and redistributes cerebrospinal fluid during labor according to constraints imposed by contractions, and bony and soft tissue elements of the birth canal as the head descends. These accommodations, including the increase in intracranial pressure, are adaptive and necessary for efficient descent of the head while safeguarding cerebral blood flow. Autonomic reflexes mediated through central receptors normally provide ample protection of the brain from the considerable pressure exerted on the skull. On occasion, those forces, which are transmitted intracranially, may overcome the various adaptive anatomical, cardiovascular, metabolic, and neurological mechanisms that maintain cerebral perfusion and oxygen availability, resulting in ischemic brain injury. Accepting the notion of a potentially adverse impact of fetal head compression suggests that avoidance of excessive uterine activity and of relentless pushing without steady progress in descent may offer protection for the fetal brain during parturition. Excessive head compression should be considered in the differential diagnosis of ischemic encephalopathy.

Repeatability,interocular correlation and agreement of optic nerve head vessel density in healthy eyes:a sweptsource optical coherence tomographic angiography study

AIM:To assess the repeatability,interocular correlation,and agreement of quantitative swept-source optical coherence tomography angiography(OCTA)optic nerve head(ONH)parameters in healthy subjects.METHODS:Thir ty-three healthy subjects were enrolled.The ONH of both eyes were imaged four times by a swept-source-OCTA using a 3 mm×3 mm scanning protocol.Images of the radial peripapillary capillary were analyzed by a customized Matlab program,and the vessel density,fractal dimension,and vessel diameter index were measured.The repeatability of the four scans was determined by the intraclass correlation coefficient(ICC).The most well-centered optic disc from the four repeated scans was then selected for the interocular correlation and agreement analysis using the Pearson correlation coefficient,ICC and Bland-Altman plots.RESULTS:All swept-source-OCTA ONH parameters exhibited certain repeatability,with ICC>0.760 and coefficient of variation(CoV)≤7.301%.The obvious interocular correlation was observed for papillary vessel density(ICC=0.857),vessel diameter index(ICC=0.857)and fractal dimension(ICC=0.906),while circumpapillary vessel density exhibited moderate interocular correlation(ICC=0.687).Bland-Altman plots revealed an agreement range of-5.26%to 6.21%for circumpapillary vessel density.CONCLUSION:OCTA ONH parameters demonstrate good repeatability in healthy subjects.The interocular correlations of papillary vessel density,fractal dimension and vessel diameter index are high,but the correlation for circumpapillary vessel density is moderate.

Three-dimensional analysis of age and sex differences in femoral head asphericity in asymptomatic hips in the United States

BACKGROUND The sphericity of the femoral head is a metric used to evaluate hip pathologies and is associated with the development of osteoarthritis and femoral-acetabular impingement.AIM To analyze the three-dimensional asphericity of the femoral head of asymptomatic pediatric hips.We hypothesized that femoral head asphericity will vary significantly between male and female pediatric hips and increase with age in both sexes.METHODS Computed tomography scans were obtained on 158 children and adolescents from a single institution in the United States(8-18 years;50%male)without hip pain.Proximal femoral measurements including the femoral head diameter,femoral head volume,residual volume,asphericity index,and local diameter difference were used to evaluate femoral head sphericity.RESULTS In both sexes,the residual volume increased by age(P<0.05).Despite significantly smaller femoral head size in older ages(>13 years)in females,there were no sex-differences in residual volume and aspherity index.There were no age-related changes in mean diameter difference in both sexes(P=0.07)with no significant sex-differences across different age groups(P=0.06).In contrast,there were significant increases in local aspherity(maximum diameter difference)across whole surface of the femoral head and all quadrants except the inferior regions in males(P=0.03).There were no sex-differences in maximum diameter difference at any regions and age group(P>0.05).Increased alpha angle was only correlated to increased mean diameter difference across overall surface of the femoral head(P=0.024).CONCLUSION There is a substantial localized asphericity in asymptomatic hips which increases with age in.While 2D measured alpha angle can capture overall asphericity of the femoral head,it may not be sensitive enough to represent regional asphericity patterns.

Vehicle Head and Tail Recognition Algorithm for Lightweight DCDSNet

In the model of the vehicle recognition algorithm implemented by the convolutional neural network,the model needs to compute and store a lot of parameters.Too many parameters occupy a lot of computational resources making it difficult to run on computers with poor performance.Therefore,obtaining more efficient feature information of target image or video with better accuracy on computers with limited arithmetic power becomes the main goal of this research.In this paper,a lightweight densely connected,and deeply separable convolutional network(DCDSNet)algorithmis proposed to achieve this goal.Visual Geometry Group(VGG)model is improved by utilizing the convolution instead of the fully connected module,the deeply separable convolution module,and the densely connected network module,with the first two modules reducing the parameters and the third module allowing the algorithm to have more features in a limited number of parameters.The algorithm achieves better results in the mine vehicle recognition dataset.Experiments show that the recognition accuracy is improved by 4.41% compared to VGG19 and the amount of parameters is reduced by 71% compared to VGG19.

New perspectives on biology,disease progression,and therapy response of head and neck cancer gained from single cell RNA sequencing and spatial transcriptomics

Head and neck squamous cell carcinoma(HNSCC)is one of the most frequent cancers worldwide.The main risk factors are consumption of tobacco products and alcohol,as well as infection with human papilloma virus.Approved therapeutic options comprise surgery,radiation,chemotherapy,targeted therapy through epidermal growth factor receptor inhibition,and immunotherapy,but outcome has remained unsatisfactory due to recurrence rates of~50%and the frequent occurrence of second primaries.The availability of the human genome sequence at the beginning of the millennium heralded the omics era,in which rapid technological progress has advanced our knowledge of the molecular biology of malignant diseases,including HNSCC,at an unprecedented pace.Initially,microarray-based methods,followed by approaches based on next-generation sequencing,were applied to study the genetics,epigenetics,and gene expression patterns of bulk tumors.More recently,the advent of single-cell RNA sequencing(scRNAseq)and spatial transcriptomics methods has facilitated the investigation of the heterogeneity between and within different cell populations in the tumor microenvironment(e.g.,cancer cells,fibroblasts,immune cells,endothelial cells),led to the discovery of novel cell types,and advanced the discovery of cell-cell communication within tumors.This review provides an overview of scRNAseq,spatial transcriptomics,and the associated bioinformatics methods,and summarizes how their application has promoted our understanding of the emergence,composition,progression,and therapy responsiveness of,and intercellular signaling within,HNSCC.

Expression changes of mi RNA-regulated genes associated with the formation of the leafy head in cabbage

The vegetative development of cabbage(Brassica oleracea var.capitata)passes through seedling,rosette,folding and heading stages.Leaves that form the rosette are large and mostly flat.In the following developmental stages,the plants produce leaves that curve inward to produce the leafy head.Many microRNAs and their target genes have been described participating in leaf development and leaf curvature.The aim of this study is to investigate the role of miRNA-regulated genes in the transition from the rosette to the heading stage.We compared the mi RNA and gene abundances between emerging rosette and heading leaves.To remove transcripts(miRNAs and genes)whose regulation was most likely associated with plant age rather than the change from rosette to heading stage,we utilized a non-heading collard green(B.oleracea var.acephala)morphotype as control.This resulted in 33 DEMs and 1998 DEGs with likely roles in the transition from rosette to heading stage in cabbage.Among these 1998 DEGs,we found enriched GO terms related to DNA-binding transcription factor activity,transcription regulator activity,iron ion binding,and photosynthesis.We predicted the target genes of these 33 DEMs and focused on the subset that was differentially expressed(1998DEGs)between rosette and heading stage leaves to construct mi RNA-target gene interaction networks.Our main finding is a role for miR396b-5p targeting two Arabidopsis thaliana orthologues of GROWTH REGULATING FACTORs 3(GRF3)and 4(GRF4)in pointed cabbage head formation.

Detection of fusarium head blight using a YOLOv5s-based method improved by attention mechanism

Fusarium head blight (FHB) is one of the most destructive diseases in global wheat production. In order to count the FHB-infected wheat ears under field conditions, this study proposed an algorithm for diseased wheat ear detection based on improved YOLOv5s (Tr-YOLOv5s). The Swin Transformer was used to replace the CSPDarknet backbone network to enhance the extraction of characteristic information of the population wheat ears of FHB in the field background. The convolutional block attention module (CBAM) attention mechanism was added to improve the detection effect of target wheat ears, subsequently improving the overall accuracy of the model. The original loss function complete intersection over union (CIoU) was replaced by Scylla intersection over union (SIoU) loss to accelerate the model convergence and decrease the loss value. The results showed that the mean average precision (mAP) of the Tr-YOLOv5s model reached 90.64%, making a 4.63% improvement compared to the original YOLOv5s model. The improved model could quickly detect and count wheat FHB ear in the field environment, which laid a foundation for the subsequent automatic disease identification and grading of wheat FHB under field conditions.