首页 | 官方网站   微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 22 毫秒
1.
    
With the increase in research on AI (Artificial Intelligence), the importance of DL (Deep Learning) in various fields, such as materials, biotechnology, genomes, and new drugs, is increasing significantly, thereby increasing the number of deep-learning framework users. However, to design a deep neural network, a considerable understanding of the framework is required. To solve this problem, a GUI (Graphical User Interface)-based DNN (Deep Neural Network) design tool is being actively researched and developed. The GUI-based DNN design tool can design DNNs quickly and easily. However, the existing GUI-based DNN design tool has certain limitations such as poor usability, framework dependency, and difficulty encountered in changing GUI components. In this study, a deep learning algorithm that solves the problem of poor usability was developed using a template to increase the accessibility for users. Moreover, the proposed tool was developed to save and share only the necessary parts for quick operation. To solve the framework dependency, we applied ONNX (Open Neural Network Exchange), which is an exchange standard for neural networks, and configured it such that DNNs designed with the existing deep-learning framework can be imported. Finally, to address the difficulty encountered in changing GUI components, we defined and developed the JSON format to quickly respond to version updates. The developed DL neural network designer was validated by running it with KISTI’s supercomputer-based AI Studio.  相似文献   

2.
为了解决复杂场景下激光跟踪仪对合作目标靶球的精确识别难题,提出了基于深度学习的合作目标靶球高效检测方法。首先分析了合作目标靶球的图像特征,然后采用改进的YOLOv2模型,针对合作目标靶球多尺度与小目标占比多的特点,提出了一种基于注意力机制的改进方法,同时为提高网络模型对复杂背景的抗干扰能力,提出了一种数据增强方法。测试结果表明,所提出的基于注意力机制与数据增强的改进YOLOv2模型对复杂背景的抗干扰能力较强,且对合作目标靶球的检测精度有显著提高,在合作目标靶球测试集上的检测准确率达到92.25%,能够有效满足激光跟踪仪在大型装置精密装配过程中的目标检测精度需求。  相似文献   

3.
介绍了采用测控分开形式对近百台五六十年代制造的高温持久/蠕变试验机进行测控温系统改造的工作.改造后的控温系统创造了不同热电偶数量(测控温共偶,1~3支)都可实现对试样温度和梯度的稳定控制,系统具有较强抗外界干扰能力,而且控温过程中对电网无干扰.测量系统测量误差≤±0.1%FS.测控温系统采取单炉闭环控制、30台集中巡回...  相似文献   

4.
提出一种融合了改进的混合高斯和YOLOv2的烟雾检测算法。首先,针对烟雾的早期特征对混合高斯算法进行改进,有效框定动态目标感兴趣区域,提取出烟雾前景;在此基础上将烟雾检测转换为回归问题,利用端对端目标检测算法YOLOv2训练烟雾数据集,进行二次检测和筛选,最终框定出烟雾发生区域的具体位置和范围,满足对不同场景火灾烟雾的有效检测。实验结果表明,融合算法改善了烟雾区域的检测效果,提高准确性并有效降低烟雾误检率。  相似文献   

5.
牛晓富  黄河  张红民  胥铁峰 《光电工程》2024,51(11):240171-1-240171-14
针对现有路基边坡裂缝检测算法中检测精度低、泛化能力弱等问题,提出了一种改进YOLOv8的路基边坡裂缝检测算法.首先,在主干网络中嵌入重参数化模块和轻量化模型的同时捕获裂缝细节与全局信息,提高模型的检测精度.其次,设计C2f-GD模块实现模型特征高效融合,增强模型的泛化能力.最后,设计轻量级检测头L-GNHead,提高对不同尺度的裂缝检测精度,同时采用SIoU损失函数加速模型收敛.在自建的路基边坡裂缝数据集上的实验结果表明,改进算法与原算法相比,mAP50和mAP50-95分别提升了 3.3%和 2.5%,参数量和计算量分别降低了46.6%和44.4%,速度提高了18 f/s.在数据集RDD2022的泛化性验证结果表明,改进算法不仅达到更高的检测精度,且检测速度更快.  相似文献   

6.
    
As they have nutritional, therapeutic, so values, plants were regarded as important and they’re the main source of humankind’s energy supply. Plant pathogens will affect its leaves at a certain time during crop cultivation, leading to substantial harm to crop productivity & economic selling price. In the agriculture industry, the identification of fungal diseases plays a vital role. However, it requires immense labor, greater planning time, and extensive knowledge of plant pathogens. Computerized approaches are developed and tested by different researchers to classify plant disease identification, and that in many cases they have also had important results several times. Therefore, the proposed study presents a new framework for the recognition of fruits and vegetable diseases. This work comprises of the two phases wherein the phase-I improved localization model is presented that comprises of the two different types of the deep learning models such as You Only Look Once (YOLO)v2 and Open Exchange Neural (ONNX) model. The localization model is constructed by the combination of the deep features that are extracted from the ONNX model and features learning has been done through the convolutional-05 layer and transferred as input to the YOLOv2 model. The localized images passed as input to classify the different types of plant diseases. The classification model is constructed by ensembling the deep features learning, where features are extracted dimension of from pre-trained Efficientnetb0 model and supplied to next 07 layers of the convolutional neural network such as 01 features input, 01 ReLU, 01 Batch-normalization, 02 fully-connected. The proposed model classifies the plant input images into associated labels with approximately 95% prediction scores that are far better as compared to current published work in this domain.  相似文献   

7.
目的 针对目前智能垃圾分类设备使用的垃圾检测方法存在检测速度慢且模型权重文件较大等问题,提出一种基于YOLOv4的轻量化方法,以实现可回收垃圾的检测。方法 采用MobileNetV2轻量级网络为YOLOv4的主干网络,用深度可分离卷积来优化颈部和头部网络,以减少参数量和计算量,提高检测速度;在颈部网络中融入CBAM注意力模块,提高模型对目标特征信息的敏感度;使用K-means算法重新聚类,得到适合自建可回收数据集中检测目标的先验框。结果 实验结果表明,改进后模型的参数量减少为原始YOLOv4模型的17.0%,检测的平均精度达到96.78%,模型权重文件的大小为46.6 MB,约为YOLOv4模型权重文件的19.1%,检测速度为20.46帧/s,提高了约25.4%,检测精度和检测速度均满足实时检测要求。结论 改进的YOLOv4模型能够在检测可回收垃圾时保证较高的检测精度,同时具有较好的实时性。  相似文献   

8.
陈宏彩  程煜  任亚恒 《包装工程》2024,45(9):135-140
目的 为了克服药包玻璃瓶缺陷样本不足带来的缺陷检测模型精度不准的问题,提出改进StyleGAN2-ADA的缺陷样本生成方法,提升模型鲁棒性。方法 首先,基于StyleGAN2-ADA算法,在无缺陷图像集上训练网络模型并作为骨干。其次,在骨干网络上添加缺陷感知残差块,生成缺陷掩码,在少量的缺陷图像数据集上训练网络模型操纵掩码区域的特征,模拟缺陷图像生成过程,合成缺陷图像。最后,采用YOLOv7检测网络验证该样本生成方法的效果。结果 实验结果表明,该方法在大量正常图像和少量缺陷图像基础上生成逼真且多样性的缺陷图像,应用该缺陷样本合成方法丰富数据集后,西林瓶缺陷检测平均准确率(mAP)达到97.3%,较原始数据集合和StyleGAN2-ADA算法分别提高了33.1%和4.1%。结论 该图像生成方法可以在少量缺陷样本下生成高质量的缺陷图像,优化不均衡数据集,增强模型训练的稳定性,提高药用玻璃包装产品的质量和合格率。  相似文献   

9.
梁礼明  陈康泉  陈林俊  龙鹏威 《光电工程》2025,52(2):240280-1-240280-12

针对现有钢材表面缺陷检测算法在资源消耗、检测精度和效率等方面存在的不足,提出一种基于YOLOv8n的轻量级钢材缺陷检测算法(FCM-YOLOv8n)。该方法一是采用频率感知特征融合网络,高效提取并融合高频信息,以降低计算成本并提升检测速度;二是重构轻量化特征交互模块(Cc-C2f),有效保留空间和通道依赖关系,减少特征冗余,以降低模型参数量和计算复杂度;三是利用多谱注意力机制,从频域维度减少特征信息缺失,以提升复杂缺陷的识别准确度。在Severstal和NEU-DET钢材缺陷数据集上的实验结果表明,相较于YOLOv8n算法,FCM-YOLOv8n算法的mAP@0.5分别提高2.2%和1.5%;参数量和复杂度分别降低0.5 M和1.5 G;FPS分别达到143 f/s和154 f/s,展示优异的实时性。该算法在检测精度、计算成本和效率之间实现良好的平衡,为边缘终端设备应用提供有力的支持。在GC10-DET数据集上的进一步验证表明,FCM-YOLOv8n相较于基线模型mAP@0.5提升2.9%,充分佐证其卓越的泛化能力。

  相似文献   

10.
The tumour suppressor p53 is activated to induce cell-cycle arrest or apoptosis in the DNA damage response (DDR). p53 phosphorylation at Ser46 by HIPK2 (homeodomain-interacting protein kinase 2) is a critical event in apoptosis induction. Interestingly, HIPK2 is degraded by Mdm2 (a negative regulator of p53), whereas Mdm2 is downregulated by HIPK2 through several mechanisms. Here, we develop a four-module network model for the p53 pathway to clarify the role of interplay between Mdm2 and HIPK2 in the DDR evoked by ultraviolet radiation. By numerical simulations, we reveal that Mdm2-dependent HIPK2 degradation promotes cell survival after mild DNA damage and that inhibition of HIPK2 degradation is sufficient to trigger apoptosis. In response to severe damage, p53 phosphorylation at Ser46 is promoted by the accumulation of HIPK2 due to downregulation of nuclear Mdm2 in the later phase of the response. Meanwhile, the concentration of p53 switches from moderate to high levels, contributing to apoptosis induction. We show that the presence of three mechanisms for Mdm2 downregulation, i.e. repression of mdm2 expression, inhibition of its nuclear entry and HIPK2-induced degradation, guarantees the apoptosis of irreparably damaged cells. Our results agree well with multiple experimental observations, and testable predictions are also made. This work advances our understanding of the regulation of p53 activity in the DDR and suggests that HIPK2 should be a significant target for cancer therapy.  相似文献   

11.
基于全寿命周期的项目成功标准的系统思考   总被引:11,自引:0,他引:11  
项目成功标准的研究对项目管理起着导向性的作用。本文在各种成熟的项目成功标准理论的基础上,建立了基于全寿命周期的项目成功标准系统:在时间轴上按照项目运作的顺序,将项目分为策划阶段、实施阶段和运营阶段;在指标轴上,将项目成功标准分为“项目固有标准”和“项目关系方的评价标准”,这两类标准在项目管理不同阶段有不同的表现,即对应于项目寿命周期中的策划、实施和运营阶段,这两类标准又划分为“预成功标准”、“建成成功标准”和“运营成功标准”。基于全寿命周期的项目成功标准系统,为项目管理提供了系统化、整体化的成功方向的引导,对于项目的不同运作阶段,该成功标准系统既有针对性,又充分考虑了其它阶段成功标准的影响,保证了项目的顺利运行。  相似文献   

12.
    
In engineering design, the decision to select an optimal material for a particular product is a problem requiring multi-criteria decision analysis that involves both qualitative and quantitative factors. The evaluation of alternative materials may be based on imprecise information or uncertain data. Furthermore, there can be significant dependence and feedbacks between the different criteria for material selection. However, most existing decision approaches cannot capture these complex interrelationships. In response, this paper proposes a general framework for evaluating and selecting the best material for a given application. A novel hybrid multiple criteria decision making (MCDM) model combining DEMATEL-based ANP (DANP) and modified VIKOR is used to solve the material selection problems of multiple dimensions and criteria that are interdependent. Moreover, target-based criteria as well as cost and benefit criteria can be addressed simultaneously in the proposed model. Finally, an empirical case concerning the bush material selection for a split journal bearing is presented to illustrate the potential of the new model. The results show that the proposed method for material selection is effective and provides meaningful implications for designers and engineers to refer.  相似文献   

13.
正2014 Joint Meeting on Social Management and Public Service Standardization was held by SAC on August 19,2014.The leaders and relevant staff from 23 ministries,such as NDRC,MOST,MPS,MOCA,etc.,were present.SAC ViceAdministrator Cui Gang addressed the meeting.The meeting presented the standardization work of social management and public service standardization last year.Over ten member organizations like NDRC,MPS,MOST,etc.,separately introduced the working condition,and proposed  相似文献   

14.
根据树脂传递模塑(RTM)成型的缎纹机织复合材料T型接头的结构特征和纤维布局特点, 基于ANSYS有限元数值分析平台, 建立符合其真实结构的几何模型和有限元分析模型。基于渐进失效强度预测方法的基本思想, 使用有限元计算软件ANSYS的参数化设计语言(APDL)开发相应的程序, 实现改进形式的Hashin失效准则。采用合适的最终失效评价方法, 建立二维机织结构复合材料T型接头受弯曲载荷时的渐进失效预测方法, 能够有效地模拟从初始加载到最终失效过程中机织复合材料T型接头结构的力学响应及损伤的萌生与发展, 并预测结构的静强度。   相似文献   

15.
    
The main idea of this work is an application of relative entropy in the numerical analysis of probabilistic divergence between original material tensors of the composite constituents and its effective tensor in the presence of material uncertainties. The homogenization method is based upon the deformation energy of the representative volume elements for the fiber-reinforced and particulate composites and uncertainty propagation begins with elastic moduli of the fibers, particles, and composite matrices. Relative entropy follows a mathematical model originating from Bhattacharyya probabilistic divergence and has been applied here for Gaussian distributions. The semi-analytical probabilistic method based on analytical integration of polynomial bases obtained via the least squares method fittings enables for determination of the basic probabilistic characteristics of the effective tensor and the relative entropies. The methodology invented in this work may be extended toward other probability distributions and relative entropies, for homogenization of nonlinear composites and also accounting for some structural interface defects.  相似文献   

16.
         下载免费PDF全文
In response to the problems of traditional defect detection algorithms, such as poor accuracy and feature loss in practical applications due to the inconspicuous characteristics of welding defects and complex background information, this paper proposes a welding surface defect detection algorithm based on the improved YOLOv8 (GD-YOLO). The model first introduces the fusion of feature extraction modules and convolutional modules to enhance its information extraction capabilities. Then, a slim-neck structure is embedded in the neck network, and the upsampling operator CAFARE is referenced in the feature fusion stage to assist in enhancing the model's performance. Subsequently, the attention mechanism module is improved to optimize the overall performance without significantly increasing the computational burden. Finally, the loss function is changed to Inner-SIOU to address the problem of mismatched bounding boxes. Experimental results show that the mAP0.5 detection metric of the model in this paper is 7.8% higher than that of the baseline model, and the number of parameters and the amount of computation are reduced by 0.2 M and 0.7 G, respectively.  相似文献   

17.
目的 针对复杂强噪背景下物流违规操作难以有效识别的问题,提出一种轻量化对抗增强的物流违规操作检测方法。方法 以YOLOv5为基础框架,提出轻量化的GhostC3模块,运用对抗学习的思想提出轻量对抗模块,将原有结构中的C3模块修改为轻量化的GhostC3模块,Conv模块修改为轻量对抗模块,并将定位损失修改为CIOU损失。结果 通过实验验证可知,本文方法针对复杂强噪背景下物流违规操作具有优异的检测效果,其中本文方法相较于YOLOv5方法的检测平均精度均值提高了1.69%,模型参数量降低了45.14%,检测速度提高了2.46%。结论 本文提出的方法具有参数量低、检测速度快和精度高等特点,针对复杂强噪背景下物流违规操作的检测具有一定的先进性和实用性,充分满足物流违规操作检测需求。  相似文献   

18.
基于YOLOv5s网络的垃圾分类和检测   总被引:2,自引:0,他引:2       下载免费PDF全文
目的 为了实现垃圾自动按类处理,通过研究基于视觉的垃圾检测与分类模型,实现对垃圾的自动识别和检测.方法 采用YOLOv5s网络作为垃圾检测与分类的模型,在自制垃圾分类数据集上对网络进行训练,利用训练好的YOLOv5s网络提取不同种类垃圾图像的特征和位置信息,实现垃圾的分类与检测.结果 在真实场景中进行了测试,基于YOLOv5s的垃圾分类检测模型可以有效识别6种不同形态的垃圾,检测mAP值为99.38%,测试精度为95.34%,目标检测速度达到6.67FPS.结论 实验结果表明,基于YOLOv5s网络的垃圾分类检测模型在不同光照、视角等条件下,检测准确率高,鲁棒性好、计算速度快.同时,有助于促进垃圾处理公司实现智能分拣,提高工作效率.  相似文献   

19.
传统基于灰度梯度分割的液位识别方法容易受到光照、清晰度等因素的影响,鲁棒性较低。为了解决这一问题,本文提出采用深度学习的液位图像检测算法;针对量器玻璃管液位线特点裁剪网络压缩卷积层,加快提取速度;使用K-means聚类设计先验框,增强尺度适应性。实验结果表明,基于YOLOv4的改进模型在液位线动态识别中,平均准确率mAP达到98.63%,帧处理速度达到了40fps。  相似文献   

20.
目的 针对传统的基于人工的腌制蔬菜真空缺陷包装剔除效率低、漏检率高等问题,提出一种基于改进YOLOv5s的腌制蔬菜真空包装缺陷检测方法。方法 首先,使用Ghost卷积替换CSP模块中的卷积,在提高模型特征提取能力的同时降低网络的参数量;其次,利用空间换深度(Space-to-Depth, SPD)和深度可分离卷积(Depthwise-Separable Convolution, DSConv)组合操作SPD–DSConv进行下采样,减少下采样造成的特征信息损耗;最后,在网络中引入SE注意力机制,提高算法的精确率。结果 在自制的腌制蔬菜真空包装数据集上,改进后的网络平均精度(man Average Precision, AmAP)为93.88%,模型尺寸为3.91MB,相比原网络精度提高了2.05%,模型尺寸缩减了44.38%。结论 文中方法能够实现腌制蔬菜真空缺陷包装的分类和定位,为基于机器人的缺陷包装剔除奠定了基础。  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号

京公网安备 11010802026262号