共查询到20条相似文献，搜索用时 0 毫秒
1.
2.
目的针对红外与可见光图像在融合过程中,融合图像失真以及可见光图像信息融合不足的问题,提出一种联合多网络结构的红外与可见光图像融合算法。方法首先采用基于密集残差连接的编码器对输入的红外与可见光图像进行特征提取,然后利用融合策略对得到的特征图进行融合,最后将融合后的特征图送入基于GAN网络的解码器中。结果通过与可见光图像对抗优化训练,使得融合后的图像保留了更多可见光图像的细节、背景信息,增强了图像的视觉效果。结论实验表明,与现有的融合算法相比,该算法达到了更好的实验效果,在主观感知和客观评价上都具有更好的表现力。 相似文献
3.
Si-Geng Li Qiu-Ren Chen Li Huang Min Chen Chen-Di Wei Zhong-Jie Yue Ru-Xue Liu Chao Tong Qing Liu 《先进制造进展(英文版)》2024,12(3):447-464
The stress-life curve (S-N) and low-cycle strain-life curve (E-N) are the two primary representations used to characterize the fatigue behavior of a material. These material fatigue curves are essential for structural fatigue analysis. However, conducting material fatigue tests is expensive and time-intensive. To address the challenge of data limitations on ferrous metal materials, we propose a novel method that utilizes the Random Forest Algorithm and transfer learning to predict the S-N and E-N curves of ferrous materials. In addition, a data-augmentation framework is introduced using a conditional generative adversarial network (cGAN) to overcome data deficiencies. By incorporating the cGAN-generated data, the accuracy (R2) of the Random Forest Algorithm-trained model is improved by 0.3-0.6. It is proven that the cGAN can significantly enhance the prediction accuracy of the machine-learning model and balance the cost of obtaining fatigue data from the experiment.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-024-00491-3 相似文献
4.
In recent years, extreme weather events accompanying the global warming have occurred frequently, which brought significant impact on national economic and social development. The ocean is an important member of the climate system and plays an important role in the occurrence of climate anomalies. With continuous improvement of sensor technology, we use sensors to acquire the ocean data for the study on resource detection and disaster prevention, etc. However, the data acquired by the sensor is not enough to be used directly by researchers, so we use the Generative Adversarial Network (GAN) to enhance the ocean data. We use GAN to process WOA13 dataset and use ResNet to determine if there is a thermocline layer in a sea area. We compare the classification results of the enhanced datasets of different orders of magnitude with the classification results of the original datasets. The experimental result shows that the dataset processed by GAN has a higher accuracy. GAN has a certain enhancement effect to marine data. Gan increased the accuracy of the WOA dataset from 0.91 to 0.93. At the same time, the experimental results also show that too much data cannot continue to enhance the accuracy of WOA in ResNet. 相似文献
5.
Deep learning (DL) techniques, which do not need complex pre-processing and feature analysis, are used in many areas of medicine and achieve promising results. On the other hand, in medical studies, a limited dataset decreases the abstraction ability of the DL model. In this context, we aimed to produce synthetic brain images including three tumor types (glioma, meningioma, and pituitary), unlike traditional data augmentation methods, and classify them with DL. This study proposes a tumor classification model consisting of a Dense Convolutional Network (DenseNet121)-based DL model to prevent forgetting problems in deep networks and delay information flow between layers. By comparing models trained on two different datasets, we demonstrated the effect of synthetic images generated by Cycle Generative Adversarial Network (CycleGAN) on the generalization of DL. One model is trained only on the original dataset, while the other is trained on the combined dataset of synthetic and original images. Synthetic data generated by CycleGAN improved the best accuracy values for glioma, meningioma, and pituitary tumor classes from 0.9633, 0.9569, and 0.9904 to 0.9968, 0.9920, and 0.9952, respectively. The developed model using synthetic data obtained a higher accuracy value than the related studies in the literature. Additionally, except for pixel-level and affine transform data augmentation, synthetic data has been generated in the figshare brain dataset for the first time. 相似文献
6.
Qiaochu Ma;Edward C. De Meter;Saurabh Basu; 《International journal for numerical methods in engineering》2024,125(7):e7428
Deep learning methods have become attractive recently to accelerate topology optimization (TO) because of their capability to save huge computational costs with negligible sacrifice in the quality of final topologies. However, most current approaches rely on numerical mechanics platforms for training which incur significant computation costs. Further, current approaches are not suited for dynamically changing boundary conditions. This is because these deep learning frameworks once trained using results generated with a specific set of boundary conditions do not readily adapt to others. In this article, we present a novel approach to leverage the abilities of deep learning models for TO. We demonstrate that optimization can be achieved using a neural ordinary differential equation. The evolution of the design variable in each iteration of TO is then achieved by numerical integration of this neural differential equation with respect to the starting design. To improve the quality of the results, two levels of generative adversarial networks are also introduced, at the sequence, and image levels, respectively. The proposed machine learning framework is capable of generating full optimization paths relevant to TO in high resolution within seconds and can address novel unseen boundary conditions. 相似文献
7.
Class imbalance is a common characteristic of industrial data that adversely affects industrial data mining because it leads to the biased training of machine learning models. To address this issue, the augmentation of samples in minority classes based on generative adversarial networks (GANs) has been demonstrated as an effective approach. This study proposes a novel GAN-based minority class augmentation approach named classifier-aided minority augmentation generative adversarial network (CMAGAN). In the CMAGAN framework, an outlier elimination strategy is first applied to each class to minimize the negative impacts of outliers. Subsequently, a newly designed boundary-strengthening learning GAN (BSLGAN) is employed to generate additional samples for minority classes. By incorporating a supplementary classifier and innovative training mechanisms, the BSLGAN focuses on learning the distribution of samples near classification boundaries. Consequently, it can fully capture the characteristics of the target class and generate highly realistic samples with clear boundaries. Finally, the new samples are filtered based on the Mahalanobis distance to ensure that they are within the desired distribution. To evaluate the effectiveness of the proposed approach, CMAGAN was used to solve the class imbalance problem in eight real-world fault-prediction applications. The performance of CMAGAN was compared with that of seven other algorithms, including state-of-the-art GAN-based methods, and the results indicated that CMAGAN could provide higher-quality augmented results.The full text can be downloaded at https://link.springer.com/article/10.1007/s40436-024-00496-y 相似文献
8.
目的 针对包装产品上QR码在采集过程中的运动模糊、失焦模糊,长期磨损形成的自模糊和环境中的噪声等因素,导致QR码无法识别的问题,提出一种基于生成对抗网络的QR码去模糊算法。方法 采用深度学习模型生成对抗网络对模糊核和环境噪声具有的强大拟合和估计能力,提取模糊QR码图像与真实图像的深层特征和差距,并通过生成器与判别器不断迭代对抗,使生成器具有由输入的模糊QR码产生与之对应的去模糊QR码图像的能力。结果 生成器能较好地对模糊核和环境噪声进行估计,而且能够实现对数据集内多种不同模糊程度QR码的去模糊,去模糊QR码图像效果较好,处理时间快,识别率较高。结论 采用基于生成对抗网络的QR码去模糊算法能够广泛应用于包装产品外壳上QR码的预处理过程,泛化能力较好,能有效提高扫描识别率。 相似文献
9.
目的为了解决传统压缩感知图像重构方法存在的重构时间长、重构图像质量不高等问题,提出一种基于生成对抗网络的压缩感知图像重构方法。方法基于生成对抗网络思想设计一种由具有稀疏采样功能的鉴别器和具有图像重构功能的生成器组成的深度学习网络模型,利用对抗损失和重构损失2个部分组成的新的损失函数对网络参数进行优化,完成图像压缩重构过程。结果实验表明,文中方法在12.5%的低采样率下重构时间为0.009s,相较于常用的OMP算法、CoSaMP算法、SP算法和IRLS算法,其峰值信噪比(PSNR)提高了10～12 dB。结论文中设计的方法应用于图像重构时重构时间短,在低采样率下仍能获得高质量的重构效果。 相似文献
10.
给出了大数据和机器学习的子领域——深度学习的概念,阐述了深度学习对获取大数据中的有价值信息的重要作用。描述了大数据下利用图像处理单元(GPU)进行并行运算的深度学习框架,对其中的大规模卷积神经网络(CNN)、大规模深度置信网络(DBN)和大规模递归神经网络(RNN)进行了重点论述。分析了大数据的容量、多样性、速率特征,介绍了大规模数据、多样性数据、高速率数据下的深度学习方法。展望了大数据背景下深度学习的发展前景,指出在不远的将来,大数据与深度学习融合的技术将会在计算机视觉、机器智能等多个领域获得突破性进展。 相似文献
11.
12.
目的 探索数智时代下创意服务设计产业应用于智能交互产品创新的模式机制与路径.方法 阐述创意服务产业时代的内涵与特征,梳理数字时代智能交互产品的创意服务需求,并从产品的品质创新需求、创新绩效提升需求和经济价值转化路径优化需求三个视角剖析创意服务设计模式的创新策略.结果 提出\"多元设计大数据创新-智能生成式设计工具优化-利益相关者协同设计平台重构\"三段式创意服务设计模式,并结合案例进行分析.结论 通过对创意服务设计的数据资源创新、设计工具的智能优化和协同创新的价值链重构,可有效提升智能交互产品设计结果的输出品质和数量,优化设计迭代周期,实现设计驱动的产品价值创新绩效和经济价值效益的双向提升.通过对知识生产力要素进行数智化整合重构,构建全链设计要素集成的智能辅助设计工具体系,提升设计师群体的创新能力,从而为社会经济价值提升带来强劲的可持续创新设计新动力. 相似文献
13.
14.
15.
A framework combining artificial neural network (ANN) modelling technique, data mining and ant colony optimisation (ACO) algorithm is proposed for determining multiple-input multiple-output (MIMO) process parameters from the initial chemical-mechanical planarisation (CMP) processes used in semiconductor manufacturing. Owing to the invisibility of the ANN in the solution procedures, the decision tree approach of data mining is adopted to provide the necessary information for a real-valued ACO. The simulation result demonstrates that the proposed method can be an efficient tool for selecting properly defined parameter combination with the CMP process. 相似文献
16.
目的 本文旨在系统综述膝骨关节炎(Knee Osteoarthritis)全病程数字化医疗健康领域的最新创新与前沿技术,探讨这些技术如何提升膝骨关节炎患者的康复效果、治疗体验及个性化全病程管理的科学性。方法 利用文献调研方法,分析膝骨关节炎全病程中各阶段数字化技术的应用,包括筛查、治疗及康复过程中的数字化工具、载体及其设计方法,并对比这些技术在不同医疗场景中的具体应用形式。结果 研究明确了数字化技术在膝骨关节炎病程中不同阶段的应用价值,涵盖从筛查阶段的早期风险评估到治疗中的个性化干预及康复阶段的实时监测与反馈。同时总结了当前数字化医疗健康领域的研究难点及未来发展趋势。结论 膝骨关节炎全病程管理中的数字化创新,特别是智能算法的引入、数字化社区康复场景的拓展,以及跨学科合作模式的深化,显著提高了膝骨关节炎患者的康复效率、治疗体验和管理精度。这些前沿技术的发展将持续推动膝骨关节炎治疗与管理的创新与提升。 相似文献
17.
Existing approaches for DEA cross-efficiency evaluation are mainly focused on the calculation of cross-efficiency matrix but pay little attention to the aggregation of the efficiencies in the cross-efficiency matrix. The most widely used approach is to aggregate the efficiencies in each row or column in the cross-efficiency matrix with equal weights into an average cross-efficiency score for each Decision Making Unit (DMU) and view it as the overall performance measurement of the DMU. This paper focuses on the aggregation process of the efficiencies in the cross-efficiency matrix and proposes the use of Shannon entropy for cross-efficiency aggregation. In the study, we propose an entropy model to generate a set of weights for aggregating and determining the ultimate cross-efficiency instead of the traditional average cross-efficiency. We prove that the set of weight is a unique global optimal solution which can reflect the goodness of this method. Finally, two examples of a flexible manufacturing system and 27 industrial robots are illustrated to examine the validity of the proposed method. 相似文献
18.
When the Wireless Sensor Network (WSN) is combined with the Internet of Things (IoT), it can be employed in a wide range of applications, such as agriculture, industry 4.0, health care, smart homes, among others. Accessing the big data generated by these applications in Cloud Servers (CSs), requires higher levels of authenticity and confidentiality during communication conducted through the Internet. Signcryption is one of the most promising approaches nowadays for overcoming such obstacles, due to its combined nature, i.e., signature and encryption. A number of researchers have developed schemes to address issues related to access control in the IoT literature, however, the majority of these schemes are based on homogeneous nature. This will be neither adequate nor practical for heterogeneous IoT environments. In addition, these schemes are based on bilinear pairing and elliptic curve cryptography, which further requires additional processing time and more communication overheads that is inappropriate for real-time communication. Consequently, this paper aims to solve the above-discussed issues, we proposed an access control scheme for IoT environments using heterogeneous signcryption scheme with the efficiency and security hardiness of hyperelliptic curve. Besides the security services such as replay attack prevention, confidentiality, integrity, unforgeability, non-repudiations, and forward secrecy, the proposed scheme has very low computational and communication costs, when it is compared to existing schemes. This is primarily because of hyperelliptic curve lighter nature of key and other parameters. The AVISPA tool is used to simulate the security requirements of our proposed scheme and the results were under two backbends (Constraint Logic-based Attack Searcher (CL-b-AtSER) and On-the-Fly Model Checker (ON-t-FL-MCR)) proved to be SAFE when the presented scheme is coded in HLPSL language. This scheme was proven to be capable of preventing a variety of attacks, including confidentiality, integrity, unforgeability, non-repudiation, forward secrecy, and replay attacks.
相似文献19.
Magdy M. Fadel Sally M. El-Ghamrawy Amr M. T. Ali-Eldin Mohammed K. Hassan Ali I. El-Desoky 《计算机、材料和连续体（英文）》2022,73(2):2293-2312
Distributed denial-of-service (DDoS) attacks are designed to interrupt network services such as email servers and webpages in traditional computer networks. Furthermore, the enormous number of connected devices makes it difficult to operate such a network effectively. Software defined networks (SDN) are networks that are managed through a centralized control system, according to researchers. This controller is the brain of any SDN, composing the forwarding table of all data plane network switches. Despite the advantages of SDN controllers, DDoS attacks are easier to perpetrate than on traditional networks. Because the controller is a single point of failure, if it fails, the entire network will fail. This paper offers a Hybrid Deep Learning Intrusion Detection and Prevention (HDLIDP) framework, which blends signature-based and deep learning neural networks to detect and prevent intrusions. This framework improves detection accuracy while addressing all of the aforementioned problems. To validate the framework, experiments are done on both traditional and SDN datasets; the findings demonstrate a significant improvement in classification accuracy. 相似文献
20.