首页 | 本学科首页   官方微博 | 高级检索  
文章检索
  按 检索   检索词:      
出版年份:   被引次数:   他引次数: 提示:输入*表示无穷大
  收费全文   25332篇
  免费   3238篇
  国内免费   2025篇
电工技术   1487篇
技术理论   1篇
综合类   2253篇
化学工业   1374篇
金属工艺   336篇
机械仪表   814篇
建筑科学   586篇
矿业工程   197篇
能源动力   435篇
轻工业   192篇
水利工程   222篇
石油天然气   155篇
武器工业   111篇
无线电   5540篇
一般工业技术   1521篇
冶金工业   388篇
原子能技术   43篇
自动化技术   14940篇
  2024年   37篇
  2023年   565篇
  2022年   745篇
  2021年   793篇
  2020年   921篇
  2019年   903篇
  2018年   579篇
  2017年   758篇
  2016年   811篇
  2015年   1023篇
  2014年   1445篇
  2013年   1692篇
  2012年   1632篇
  2011年   1898篇
  2010年   1462篇
  2009年   1777篇
  2008年   1885篇
  2007年   1827篇
  2006年   1459篇
  2005年   1259篇
  2004年   1075篇
  2003年   947篇
  2002年   847篇
  2001年   728篇
  2000年   637篇
  1999年   521篇
  1998年   462篇
  1997年   402篇
  1996年   335篇
  1995年   267篇
  1994年   207篇
  1993年   170篇
  1992年   122篇
  1991年   70篇
  1990年   52篇
  1989年   39篇
  1988年   30篇
  1987年   21篇
  1986年   20篇
  1985年   43篇
  1984年   37篇
  1983年   35篇
  1982年   40篇
  1981年   2篇
  1980年   2篇
  1979年   6篇
  1978年   3篇
  1977年   1篇
  1976年   2篇
  1951年   1篇
排序方式: 共有10000条查询结果,搜索用时 40 毫秒
1.
无监督跨域迁移学习是行人再识别中一个非常重要的任务. 给定一个有标注的源域和一个没有标注的目标域, 无监督跨域迁移的关键点在于尽可能地把源域的知识迁移到目标域. 然而, 目前的跨域迁移方法忽略了域内各视角分布的差异性, 导致迁移效果不好. 针对这个缺陷, 本文提出了一个基于多视角的非对称跨域迁移学习的新问题. 为了实现这种非对称跨域迁移, 提出了一种基于多对多生成对抗网络(Many-to-many generative adversarial network, M2M-GAN)的迁移方法. 该方法嵌入了指定的源域视角标记和目标域视角标记作为引导信息, 并增加了视角分类器用于鉴别不同的视角分布, 从而使模型能自动针对不同的源域视角和目标域视角组合采取不同的迁移方式. 在行人再识别基准数据集Market1501、DukeMTMC-reID和MSMT17上, 实验验证了本文的方法能有效提升迁移效果, 达到更高的无监督跨域行人再识别准确率.  相似文献   
2.
子空间聚类(Subspace clustering)是一种当前较为流行的基于谱聚类的高维数据聚类框架.近年来,由于深度神经网络能够有效地挖掘出数据深层特征,其研究倍受各国学者的关注.深度子空间聚类旨在通过深度网络学习原始数据的低维特征表示,计算出数据集的相似度矩阵,然后利用谱聚类获得数据的最终聚类结果.然而,现实数据存在维度过高、数据结构复杂等问题,如何获得更鲁棒的数据表示,改善聚类性能,仍是一个挑战.因此,本文提出基于自注意力对抗的深度子空间聚类算法(SAADSC).利用自注意力对抗网络在自动编码器的特征学习中施加一个先验分布约束,引导所学习的特征表示更具有鲁棒性,从而提高聚类精度.通过在多个数据集上的实验,结果表明本文算法在精确率(ACC)、标准互信息(NMI)等指标上都优于目前最好的方法.  相似文献   
3.
Brain-computer interfaces (BCIs) records brain activity using electroencephalogram (EEG) headsets in the form of EEG signals; these signals can be recorded, processed and classified into different hand movements, which can be used to control other IoT devices. Classification of hand movements will be one step closer to applying these algorithms in real-life situations using EEG headsets. This paper uses different feature extraction techniques and sophisticated machine learning algorithms to classify hand movements from EEG brain signals to control prosthetic hands for amputated persons. To achieve good classification accuracy, denoising and feature extraction of EEG signals is a significant step. We saw a considerable increase in all the machine learning models when the moving average filter was applied to the raw EEG data. Feature extraction techniques like a fast fourier transform (FFT) and continuous wave transform (CWT) were used in this study; three types of features were extracted, i.e., FFT Features, CWT Coefficients and CWT scalogram images. We trained and compared different machine learning (ML) models like logistic regression, random forest, k-nearest neighbors (KNN), light gradient boosting machine (GBM) and XG boost on FFT and CWT features and deep learning (DL) models like VGG-16, DenseNet201 and ResNet50 trained on CWT scalogram images. XG Boost with FFT features gave the maximum accuracy of 88%.  相似文献   
4.
Most of the internet users connect through wireless networks. Major part of internet traffic is carried by Transmission Control Protocol (TCP). It has some design constraints while operated across wireless networks. TCP is the traditional predominant protocol designed for wired networks. To control congestion in the network, TCP used acknowledgment to delivery of packets by the end host. In wired network, packet loss signals congestion in the network. But rather in wireless networks, loss is mainly because of the wireless characteristics such as fading, signal strength etc. When a packet travels across wired and wireless networks, TCP congestion control theory faces problem during handshake between them. This paper focuses on finding this misinterpretation of the losses using cross layer approach. This paper focuses on increasing bandwidth usage by improving TCP throughput in wireless environments using cross layer approach and hence named the proposed system as CRLTCP. TCP misinterprets wireless loss as congestion loss and unnecessarily reduces congestion window size. Using the signal strength and frame error rate, the type of loss is identified and accordingly the response of TCP is modified. The results show that there is a significant improvement in the throughput of proposed TCP upon which bandwidth usage is increased.  相似文献   
5.
近年来,深度学习模型已在医疗领域的预测任务上得到广泛应用,并取得了不错的效果.然而,深度学习模型常会面临带标签训练数据不足、整体数据分布偏移和类别之间数据分布偏移的问题,导致模型预测的准确度下降.为解决上述问题,提出一种基于域对抗和加性余弦间隔损失的无监督域适应方法(additive margin softmax based adversarial domain adaptation,AMS-ADA).首先,该方法使用带有注意力机制的双向长短程记忆网络来提取特征.其次,该方法引入了生成对抗网络的思想,以域对抗的形式减少了整体数据之间数据分布偏移.然后,该方法引入了度量学习的思想,以最大化角度空间内决策边界的方式进一步减少了类别之间的数据分布偏移.该方法能够提升域适应的效果与模型预测的准确度.在真实世界的医疗数据集上进行了重症监护病人死亡风险预测任务,实验结果表明:由于该方法相较于其他5种基线模型能够更好地解决数据分布偏移的问题,取得比其他基线模型更好的分类效果.  相似文献   
6.
面部视觉信息和语音信息是人机交互过程中最为直接和灵活的方式,从而基于智能方式的人脸和语音跨模态感知吸引了国内外研究学者的广泛关注.然而,由于人脸-语音样本的异质性以及语义鸿沟问题,现有方法并不能很好地解决一些难度比较高的跨人脸-语音匹配任务.提出了一种结合双流网络和双向五元组损失的跨人脸-语音特征学习框架,该框架学到的特征可直接用于4种不同的跨人脸-语音匹配任务.首先,在双流深度网络顶端引入一种新的权重共享的多模态加权残差网络,以挖掘人脸和语音模态间的语义关联;接着,设计了一种融合多种样本对构造策略的双向五元组损失,极大地提高了数据利用率和模型的泛化性能;最后,在模型训练中进行ID分类学习,以保证跨模态表示的可分性.实验结果表明,与现有方法相比,能够在4个不同跨人脸-语音匹配任务上取得效果的全面提升,某些评价指标效果提升近5%.  相似文献   
7.
Wireless Sensor Network (WSN) forms an essential part of IoT. It is embedded in the target environment to observe the physical parameters based on the type of application. Sensor nodes in WSN are constrained by different features such as memory, bandwidth, energy, and its processing capabilities. In WSN, data transmission process consumes the maximum amount of energy than sensing and processing of the sensors. So, diverse clustering and data aggregation techniques are designed to achieve excellent energy efficiency in WSN. In this view, the current research article presents a novel Type II Fuzzy Logic-based Cluster Head selection with Low Complexity Data Aggregation (T2FLCH-LCDA) technique for WSN. The presented model involves a two-stage process such as clustering and data aggregation. Initially, three input parameters such as residual energy, distance to Base Station (BS), and node centrality are used in T2FLCH technique for CH selection and cluster construction. Besides, the LCDA technique which follows Dictionary Based Encoding (DBE) process is used to perform the data aggregation at CHs. Finally, the aggregated data is transmitted to the BS where it achieves energy efficiency. The experimental validation of the T2FLCH-LCDA technique was executed under three different scenarios based on the position of BS. The experimental results revealed that the T2FLCH-LCDA technique achieved maximum energy efficiency, lifetime, Compression Ratio (CR), and power saving than the compared methods.  相似文献   
8.
In recent years, the number of Gun-related incidents has crossed over 250,000 per year and over 85% of the existing 1 billion firearms are in civilian hands, manual monitoring has not proven effective in detecting firearms. which is why an automated weapon detection system is needed. Various automated convolutional neural networks (CNN) weapon detection systems have been proposed in the past to generate good results. However, These techniques have high computation overhead and are slow to provide real-time detection which is essential for the weapon detection system. These models have a high rate of false negatives because they often fail to detect the guns due to the low quality and visibility issues of surveillance videos. This research work aims to minimize the rate of false negatives and false positives in weapon detection while keeping the speed of detection as a key parameter. The proposed framework is based on You Only Look Once (YOLO) and Area of Interest (AOI). Initially, the models take pre-processed frames where the background is removed by the use of the Gaussian blur algorithm. The proposed architecture will be assessed through various performance parameters such as False Negative, False Positive, precision, recall rate, and F1 score. The results of this research work make it clear that due to YOLO-v5s high recall rate and speed of detection are achieved. Speed reached 0.010 s per frame compared to the 0.17 s of the Faster R-CNN. It is promising to be used in the field of security and weapon detection.  相似文献   
9.
An important requirement in a military domain is a highly reliable mobility management method, especially when components of the networks are moving in tactical network environments. To increase reliability, the mobility management technology of the tactical network should be able to reflect the characteristics of the tactical network, such as a limited environment, failure, and hierarchical unit structure. In this paper, we propose a proxy-based hierarchical distributed mobility management scheme, which is highly focused on tactical networks. Considering the characteristics of tactical networks, the proposed scheme is composed of the following: 1) a proxy-based method, 2) a distributed mobility management method that synchronizes a mobility database between entities, and 3) a method of managing mobility by dividing the tactical network into upper and lower layers. Mathematical analysis and modeling and simulation results demonstrate that the method outperforms the existing state-of-the-art method in overcoming entity failure, handover cost, and delay in tactical environments.  相似文献   
10.
Diabetic retinopathy (DR) is a complication of diabetes mellitus that appears in the retina. Clinitians use retina images to detect DR pathological signs related to the occlusion of tiny blood vessels. Such occlusion brings a degenerative cycle between the breaking off and the new generation of thinner and weaker blood vessels. This research aims to develop a suitable retinal vasculature segmentation method for improving retinal screening procedures by means of computer-aided diagnosis systems. The blood vessel segmentation methodology relies on an effective feature selection based on Sequential Forward Selection, using the error rate of a decision tree classifier in the evaluation function. Subsequently, the classification process is performed by three alternative approaches: artificial neural networks, decision trees and support vector machines. The proposed methodology is validated on three publicly accessible datasets and a private one provided by Hospital Sant Joan of Reus. In all cases we obtain an average accuracy above 96% with a sensitivity of 72% in the blood vessel segmentation process. Compared with the state-of-the-art, our approach achieves the same performance as other methods that need more computational power. Our method significantly reduces the number of features used in the segmentation process from 20 to 5 dimensions. The implementation of the three classifiers confirmed that the five selected features have a good effectiveness, independently of the classification algorithm.  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