共查询到20条相似文献，搜索用时 15 毫秒
1.
针对深度学习在处理文本分类问题时存在的适应度小、精确度较低等问题,提出一种采用双向门控循环单元(BGRU)进行池化的改进卷积神经网络模型。在池化阶段,将BGRU产生的中间句子表示与由卷积层得到的局部表示进行对比,将相似度高的判定为重要信息,并通过增大其权重来保留此信息。该模型可以进行端到端的训练,对多种类型的文本进行训练,适应性较强。实验结果表明,相较于其他同类模型,提出的改进模型在学习能力上有较大优势,分类精度也有显著提高。 相似文献
2.
在长文本数据中存在很多与主题不相关词汇,导致这些文本数据具有信息容量大、特征表征不突出等特点。增加这些文本中关键词汇的特征影响,是提高文本分类器性能需要解决的问题。提出一种结合自注意力机制的循环卷积神经网络文本分类模型RCNN_A。注意力机制对文本词向量计算其对正确分类类别的贡献度,得到注意力矩阵,将注意力矩阵和词向量矩阵相结合作为后续结构的输入。实验结果表明,RCNN_A在10类搜狗新闻数据集上,得到了97.35%的分类正确率,比Bi-LSTM(94.75%)、Bi-GRU(94.25%)、TextCNN(93.31%)、RCNN(95.75%)具有更好的文本分类表现。通过在深度神经网络模型中引入注意力机制,能够有效提升文本分类器性能。 相似文献
3.
雨滴严重影响了图像的视觉效果和后续的图像处理应用。目前,基于深度学习的单幅图像去雨方法能够有效挖掘图像的深度特征,其去雨效果优于传统方法;然而,随着网络深度的增加,网络容易出现过拟合的现象,使得去雨效果遇到瓶颈。文中在继承深度学习优点的基础上,学习有雨/无雨图像之间的残差,然后将残差与源图像进行重构,从而获得无雨图像。该方式大幅增加了网络深度,并加快了算法的收敛速度。分别利用通过不同方式获取的雨滴图像对所提方法进行实验验证,并将该方法与当前最新的去雨滴方法作比较,结果表明所提算法的去雨效果更好。 相似文献
4.
In the field of image recognition, machine learning technologies, especially deep learning, have been rapidly advancing alongside the advances of hardware such as GPUs. In image recognition, in general, large numbers of labeled images to be identified are input to a neural network, and repeatedly learning the images enables the neural network to identify objects with high accuracy. A new profiling side-channel attack method, the deep learning side-channel attack (DL-SCA), utilizes the neural network’s high identifying ability to unveil a cryptographic module’s secret key from side-channel information. In DL-SCAs, the neural network is trained with power waveforms captured from a target cryptographic module, and the trained network extracts the leaky part that depends on the secret. However, at this stage, the main target of investigation has been software implementation, and studies regarding hardware implementation, such as ASIC, are somewhat lacking. In this paper, we first depict deep learning techniques, profiling side-channel attacks, and leak models to clarify the relation between secret and side channels. Next, we investigate the use of DL-SCA against hardware implementations of AES and discuss the problem derived from the Hamming distance model and ShiftRow operation of AES. To solve the problem, we propose a new network training method called “mixed model dataset based on round-round XORed value.” We prove that our proposal solves the problem and gives the attack capability to neural networks. We also compare the attack performance and characteristics of DL-SCA to conventional analysis methods such as correlation power analysis and conventional template attack. In our experiment, a dedicated ASIC chip for side-channel analysis is utilized and the chip is also equipped with a side-channel countermeasure AES. We show how DL-SCA can recover secret keys against the side-channel countermeasure circuit. Our results demonstrate that DL-SCA can be a more powerful option against side-channel countermeasure implementations than conventional SCAs. 相似文献
5.
6.
随着深度学习的发展,图像风格转换任务开始使用卷积神经网络实现。针对传统图像转换网络在转换后,保留纹理细节的能力不足的问题,本文基于Justin等人的风格转换模型,优化了转换网络中的残差结构,并结合生成对抗的思想,改进了风格转换模型,使模型能提取图像中更抽象的特征,并对损失函数进行调整,进一步提升生成图像的质量。实验表明,本文方法在进行图像风格转换时,有效提升了风格化效果并且通过比较在多种评价指标下得到的结果,可知图像质量得到提升。 相似文献
7.
万晓丹 《计算机应用与软件》2021,38(1):192-196
在目标检测方法中,通过使用具有不同遮挡程度的数据集进行训练,能够提升目标检测算法对遮挡的不变性,但现实生活中的数据集往往存在长尾效应。因此提出一种基于对抗网络与卷积神经网络的目标检测方法。通过对抗网络在输入数据上进行计算得到不同遮挡程度的样本,使用Faster RCNN算法进行训练提升遮挡不变性,以此提高算法检测精度。实验结果表明,该方法与Faster RCNN相比,在VOC 2007数据集上平均精度提升了2.2个百分点,在VOC 2007和VOC 2012联合数据集上平均精度提升了1.3个百分点。 相似文献
8.
Convolutional Neural Network (CNN) has demonstrated its superior ability to achieve amazing accuracy in computer vision field. However, due to the limitation of network depth and computational complexity, it is still difficult to obtain the best classification results for the specific image classification tasks. In order to improve classification performance without increasing network depth, a new Deep Topology Network (DTN) framework is proposed. The key idea of DTN is based on the iteration of multiple learning rate feedback. The framework consists of multiple sub-networks and each sub-network has its own learning rate. After the determined iteration period, these learning rates can be adjusted according to the feedback of training accuracy, in the feature learning process, the optimal learning rate is updated iteratively to optimize the loss function. In practice, the proposed DTN framework is applied to several state-of-the-art deep networks, and its performance is tested by extensive experiments and comprehensive evaluations of CIFAR-10 and MNIST benchmarks. Experimental results show that most deep networks can benefit from the DTN framework with an accuracy of 99.5% on MINIST dataset, which is 5.9% higher than that on the CIFAR-10 benchmark. 相似文献
9.
10.
The outbreak of the novel coronavirus has spread worldwide, and millions of people are being infected. Image or detection classification is one of the first application areas of deep learning, which has a significant contribution to medical image analysis. In classification detection, one or more images (detection) are usually used as input, and diagnostic variables (such as whether there is a disease) are used as output. The novel coronavirus has spread across the world, infecting millions of people. Early-stage detection of critical cases of COVID-19 is essential. X-ray scans are used in clinical studies to diagnose COVID-19 and Pneumonia early. For extracting the discriminative features through these modalities, deep convolutional neural networks (CNNs) are used. A siamese convolutional neural network model (COVID-3D-SCNN) is proposed in this study for the automated detection of COVID-19 by utilizing X-ray scans. To extract the useful features, we used three consecutive models working in parallel in the proposed approach. We acquired 575 COVID-19, 1200 non-COVID, and 1400 pneumonia images, which are publicly available. In our framework, augmentation is used to enlarge the dataset. The findings suggest that the proposed method outperforms the results of comparative studies in terms of accuracy 96.70%, specificity 95.55%, and sensitivity 96.62% over (COVID-19 vs. non-COVID19 vs. Pneumonia). 相似文献
11.
12.
为了提高卷积神经网络对非线性特征以及复杂图像隐含的抽象特征提取能力,提出优化卷积神经网络结构的人体行为识别方法.通过优化卷积神经网络模型,构建嵌套Maxout多层感知器层的网络结构,增强卷积神经网络的卷积层对前景目标特征提取能力.通过嵌套Maxout多层感知器层网络结构可以线性地组合特征图并选择最有效特征信息,获取的特... 相似文献
13.
14.
Maintenance planning of groundwater delivery infrastructure, such as canals, requires labor-intensive field inspection for properly allocating maintenance resources to sections of water infrastructure based on their deterioration conditions. Defective canal sections have cracks where the water delivery performance degrades. In practice, canals can be tens or even hundreds of miles long. Manual canal inspections could take weeks, while could hardly achieve comprehensive water leakage assessment. Another difficulty is that most cracks are developing under the water. Without drying up the canals, inspectors could not observe underwater conditions. They would have to assess visible parts of water facilities and environments (e.g., humidity changes and vegetation growths nearby) for prioritizing canal sections in terms of leaking risks. Even experienced inspectors need much time to complete a reliable canal condition assessment.This paper presents a deep-learning approach augmented by canal inspection knowledge to achieve automated and reliable water leak detection of canal sections from Landsat 8 satellite images. Such integration utilizes the domain knowledge of experienced inspectors in augmenting the deep-learning methods for more reliable image pattern classification that supports rapid canal condition assessment. Compared with machine learning algorithms trained by raw satellite images manually labeled as leaking, domain-knowledge-augmented deep learning algorithms use satellite image augmented by pixel-level land surface temperature (LST), fractional vegetation coverage (FVC) and Temperature Vegetation Dryness Index (TVDI) as training samples. Specifically, LST, FVC, and TVDI for each pixel are physical parameters derived from Landsat 8 satellite images by remote sensing methods. The “leaking” or “no-leaking” labels of the training samples are from the concrete surface inspection records collected during annual dry-ups of the canal from 2016 to 2019. Testing results on data sets collected for canals flowing through both urban and rural areas show that the proposed approach can achieve recall at 86%, precision at 86%, and accuracy at 85%. The precision, recall, and accuracy of the proposed approach are similar to a conventional deep learning algorithm that uses raw images for training while being more computationally efficient. The reason is that the new approach only processes three channels rather than the 11 channels in raw images. The authors also tested how different combinations of environmental features influence the performance of the algorithm. The results showed that two feature combinations: (LST, FVC) and (LST, FVC, TVDI) achieve the most robust performance in diverse geospatial environments. 相似文献
15.
针对在将卡口非结构化视频图像数据转化为智能结构化信息的过程中存在环境的复杂性、需求的多样性、任务的关联性和识别的实时性等问题,提出了一种级联多任务深度学习网络的卡口识别引擎方法,其通过充分利用分割、检测、识别等任务之间的相互联系实现了高精度的、高效的、同步实时的卡口车辆多种基本信息的识别(车型、品牌、车系、车身颜色以及车牌等识别任务)。首先,利用深度卷积神经网络自动完成车型的深度特征学习,在特征图上进行逻辑回归,从卡口道路复杂背景中提取出感兴趣区域(包括多车辆对象);然后,利用多任务深度学习网络对提取出来的车辆对象实现多层次的多任务识别。实验结果表明,提出的方法在识别精度和效率上都明显优于传统计算机视觉方法和现有的基于深度学习的识别引擎技术,该方法对车型、品牌、车系及车牌的识别与检测精度均达到98%以上,检测效率提升了1.6倍。 相似文献
16.
Examining past near-miss reports can provide us with information that can be used to learn about how we can mitigate and control hazards that materialise on construction sites. Yet, the process of analysing near-miss reports can be a time-consuming and labour-intensive process. However, automatic text classification using machine learning and ontology-based approaches can be used to mine reports of this nature. Such approaches tend to suffer from the problem of weak generalisation, which can adversely affect the classification performance. To address this limitation and improve classification accuracy, we develop an improved deep learning-based approach to automatically classify near-miss information contained within safety reports using Bidirectional Transformers for Language Understanding (BERT). Our proposed approach is designed to pre-train deep bi-directional representations by jointly extracting context features in all layers. We validate the effectiveness and feasibility of our approach using a database of near-miss reports derived from actual construction projects that were used to train and test our model. The results demonstrate that our approach can accurately classify ‘near misses’, and outperform prevailing state-of-the-art automatic text classification approaches. Understanding the nature of near-misses can provide site managers with the ability to identify work-areas and instances where the likelihood of an accident may occur. 相似文献
17.
对文本的特征提取方法以及深度神经网络的分类器的搭建进行研究。首先,在全局和局部的特征提取方法的基础上,通过对文本特征内耦合关系和文本特征间耦合关系进行分析,确定用于分类的文本特征,建立文本特征的耦合关系模型;其次, 将文本特征 作为深度神经网络输入层进行分类;最后,通过逐层无监督的方式对网络进行训练,在顶层增加区分性结点来实现文本分类功能。 相似文献
18.
19.
20.
It is essential to precisely model the spindle thermal error due to its dramatic influence on the machining accuracy. In this paper, the deep learning convolutional neural network (CNN) is used to model the axial and radial thermal errors of horizontal and vertical spindles. Unlike the traditional CNN model that relies entirely on thermal images, this model combines the thermal image with the thermocouple data to fully reflect the temperature field of the spindle. After pre-processing and data enhancement of the thermal images, a multi-classification model based on CNN is built and verified for accuracy and robustness. The experimental results show that the model prediction accuracy is approximately 90 %–93 %, which is higher than the BP model. When the spindle rotation speed changes, the model also shows good robustness. Real cutting tests show that the deep learning model has good applicability to the spindle thermal error prediction and compensation. 相似文献