检索结果-内蒙古大学图书馆

Dual temporal attention mechanism-based convolutional LSTM model for industrial dynamic soft sensor

MEASUREMENT SCIENCE AND TECHNOLOGY 2024年第11期35卷 115103-115103页

作者： Cui, Jiarui Shi, Yuyu Huang, Jian Yang, Xu Gao, Jingjing Li, Qing Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing Peoples R China Univ Sci & Technol Beijing Shunde Innovat Sch Foshan Peoples R China

Deep learning is an appropriate methodology for modeling complex industrial data in the field of soft sensors, owing to its powerful feature representation capability. Given the nonlinear and dynamic nature of the process industry, the key challenge for soft sensor technology is to effectively mine dynamic information from long sequences and accurately extract features of relevance to quality. A dual temporal attention mechanism-based convolutional long short-term memory network (DTA-ConvLSTM) under an encoder-decoder framework is proposed as a soft sensor model to acquire quality-relevant dynamic features from serial data. Considering different influences of process variables for prediction at multiple time steps and various locations, ConvLSTM and temporal self-attention mechanism are utilized as the encoder to adaptively fuse spatiotemporal features and capture long-term dynamic properties of process in order to capture the trends of industrial variables. Furthermore, a quality-driven temporal attention mechanism is employed throughout the decoding process to dynamically select relevant features to more accurately track quality changes. The encoder-decoder model meticulously analyses the interactions between process and quality variables by incorporating dual-sequence dynamic information to improve the prediction performance. The validity and superiority of the DTA-ConvLSTM model was validated on two industrial case studies of the debutanizer column and sulfur recovery unit. Compared to the traditional LSTM model, the proposed model demonstrated a substantial improvement with the accuracy R2 up to 97.3% and 94.9% and the root mean square error reducing to 0.122 and 0.022.

关键词： dual temporal attention mechanism LSTM encoder-decoder convolutional layer soft sensor

来源：评论

学校读者我要写书评

暂无评论

Leaf vein segmentation with self-supervision

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2022年 203卷

作者： Li, Lei Hu, Wenzheng Lu, Jiang Zhang, Changshui Tsinghua Univ Inst Artificial Intelligence Beijing Natl Res Ctr Informat Sci & Technol BNRist State Key Lab Intelligent Technol & SystTsinghua Beijing Peoples R China Tsinghua Univ State Key Lab Automot Safety & Energy Beijing Peoples R China China Marine Dev & Res Ctr CMDRC Beijing Peoples R China Kuaishou Technol Co Ltd Beijing Peoples R China

The leaf vein, often viewed as the fingerprint of the leaf, is an important characteristic used to identify plant species. Leaf vein segmentation aims to extract the vein features and obtain the vein architectures from leaf images. Unlike the general semantic or instance segmentation focusing on the block and object level, the leaf vein segmentation is fine and it focuses on the internal details inside the mesophyll, whose color is indistinguishable, making this task difficult. To tackle this problem, we utilize the particularities of leaf veins, namely continuity and branching, and propose a Confidence Refining Vein Network (CoRE-Net) to segment leaf veins by handling the intersections, breakpoints, and blurred boundaries of veins to enhance segment prediction. Moreover, the proposed network only needs a few labeled samples to warm start, and then the whole network can converge without any annotated labels. Meanwhile, we collect and release the first leaf vein dataset, Leaf Vein Dataset 2021 (LVD2021). The proposed framework achieves mean Intersection over Union at 71.02% and mean Dice at 79.76% on LVD2021, which outperforms its counterparts in different settings, demonstrating the effectiveness of our framework.

关键词： Leaf vein segmentation Computer vision Self-supervision encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Sketch2Photo: Synthesizing photo-realistic images from sketches via global contexts

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartA期117卷

作者： Liu, Heng Xu, Yao Chen, Feng Anhui Univ Technol Maanshan 243032 Peoples R China Anhui Engn Res Ctr Intelligent Applicat & Secur In Maanshan 243032 Peoples R China

Sketch-to-image synthesis aims to generate realistic images that match the input sketches or edge maps exactly. Most known sketch-to-image synthesis methods use various generative adversarial networks (GANs) that are trained with numerous pairs of sketches and real images. Because of the convolution locality, the low-level layers of the generators in these GANs lack global perception ability, causing feature maps derived from them easily to overlook global cues. Since the global receptive field is crucial for acquiring the non-local structures and features of sketches, the absence of global contexts will impact the generation of high-quality images. Some recent models turn to self-attention to construct global dependencies. However, they are not viable for large feature maps for the quadratic computational complexity concerning the size of feature maps. To address these problems, in this work, we propose Sketch2Photo - a new image synthesis approach that can capture global contexts as well as local features to generate photo-realistic images from weak or partial sketches or edge maps. We employ fast Fourier convolution (FFC) residual blocks to create global receptive fields in the bottom layers of the network and incorporate Swin Transformer block (STB) units to obtain long-range global contexts for large-size feature maps efficiently. We also present an improved spatial attention pooling (ISAP) module to relax the strict alignment requirements between incomplete sketches and generated images. Quantitative and qualitative experiments on multiple public datasets demonstrate the superiority of the proposed approach over many other sketch-to-image synthesis methods. The project code is available at https://***/hengliusky/Skecth2Photo.

关键词： Sketch-based image synthesis Fast Fourier convolution Swin transformer encoder-decoder Global contexts

来源：评论

学校读者我要写书评

暂无评论

Exploration of dual-attention mechanism-based deep learning for multi-step-ahead flood probabilistic forecasting

引用

JOURNAL OF HYDROLOGY 2023年第PartB期622卷

作者： Cui, Zhen Guo, Shenglian Zhou, Yanlai Wang, Jun Wuhan Univ State Key Lab Water Resources & Hydropower Engn Sc Wuhan 430072 Peoples R China

In order to improve the flood forecasting accuracy and reflect the forecast uncertainty information in the Three Gorges Reservoir (TGR) interval-basin in China, this study integrates the feature and temporal dual-attention (DA) mechanism and recursive encoder-decoder (RED) structure into the long short-term memory (LSTM) neural network to develop a DA-LSTM-RED model. The feature attention acts on the input variables of the encoder, and the temporal attention mechanism acts on the hidden layer states extracted by the LSTM neural network during encoding process, prompting the proposed model to extract critical input information among different types and moments of input variables to improve the multi-step-ahead flood forecasting accuracy. Second, the copula-based Hydrological Uncertainty Processor (copula-HUP) is used to quantify the forecast uncertainty of the proposed model meanwhile creating multi-step-ahead flood probabilistic forecasts. Combining the long-term 6 h hydrologic data series of the Xiangjiaba-TGR interval-basin and the forecasted precipitation from the European Centre for Medium-Range Weather Forecasts (ECMWF), the effectiveness of the proposed model, the effect of forecast precipitation on multi-step-ahead flood forecasting, and the effect of different copula functions on the probabilistic forecast of copula-HUP are investigated, respectively. The results show that the DALSTM-RED model can effectively improve the forecasting accuracy for long forecast horizons (3-7d) compared to the LSTM-RED model, and the average absolute error metrics are reduced by 10%-17%. Meanwhile, the proposed model can identify input variables with a high correlation with the target output variables, which improves the interpretability of deep learning to a certain extent. The Student copula-HUP has the lowest RB and CRPS metrics than the Frank and Gaussian copula-HUP, which can better quantify the DA-LSTM-RED model's forecast uncertainty. Therefore, combining the proposed mo

关键词： Dual-attention mechanism encoder-decoder Deep learning Hydrological uncertainty processor Copula function Probabilistic forecasting

来源：评论

学校读者我要写书评

暂无评论

Graph neural network-based visual relationship and multilevel attention for image captioning

引用

JOURNAL OF ELECTRONIC IMAGING 2022年第5期31卷 053022-053022页

作者： Sharma, Himanshu Srivastava, Swati GLA Univ Dept Comp Engn & Applicat Mathura Uttar Pradesh India

With the remarkable success of the image captioning tasks, visual attention methods have become a vital part of captioning models. However, most attention-based image captioning methods do not consider any relationship among regions, which play a significant role in better image understanding. We proposed an image captioning method based on local relation network using a multilevel attention approach with graph neural network. It not only fully explores the relationship between the object and the image regions but also generates significant and context-based features corresponding to every region in the image. The attention employed in our work enhances the image representation capability of our method by focusing on a given image region and its related image regions. Thus addressing the relevant contextual information, spatial locations, and deep visual features leads to improve caption generation. We verified the effectiveness of the proposed model by conducting extensive experiments on three benchmark datasets: Flickr30k, MSCOCO, and nocaps. The results show the superiority of the proposed method over the existing methods both in quantitative and qualitative manners. Detailed ablation studies are conducted to communicate how each part would contribute to the final performance. (c) 2022 SPIE and IS&T

关键词： graph neural network relation network semantic attention encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

A novel method for cage whirl motion capture of high-precision bearing inspired by U-Net

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartA期117卷

作者： Niu, Xiaoliang Yang, Zhaohui Zhou, Ningning Li, Chonghe Northwestern Polytech Univ Sch Aeronaut Xian 710072 Peoples R China Northwestern Polytech Univ Shenzhen Res & Dev Inst Shenzhen 518057 Peoples R China Beijing Inst Control Engn Beijing Key Lab Long Life Technol Precise Rotat & Beijing 100094 Peoples R China Aviat Ind Dev Res Ctr China AVICADR Res Inst Management Engn Beijing Peoples R China

To solve the problem of cage whirl motion capture and evaluation, this paper developed an efficient non -contact measurement method based on semantic segmentation technology. An encoder-decoder network whose backbone is U-Net is constructed by introducing residual learning and attention mechanism for cage motion state segmentation. A random move augmentation strategy is used to simulate the random movement of cage mass center. The network is trained with 1368 high-speed cage rotational images using the augmentation strategy. Additionally, 150 images are validation set, and 5000 images under different operating conditions are test set. A trained network is applied to the cage whirl motion capture under different operating conditions by matching the suitable parameters during the training phase. The results show that our method effectively predicts the trend of cage whirl motion, with the predicted cage whirl orbit used for the accurate analysis of cage rotational stability.

关键词： High-precision bearing Semantic segmentation encoder-decoder Random move augmentation Cage whirl motion

来源：评论

学校读者我要写书评

暂无评论

TAN: A Transferable Adversarial Network for DNN-Based UAV SAR Automatic Target Recognition Models

引用

DRONES 2023年第3期7卷 205-205页

作者： Du, Meng Sun, Yuxin Sun, Bing Wu, Zilong Luo, Lan Bi, Daping Du, Mingyang Natl Univ Def Technol Coll Elect Engn Hefei 230037 Peoples R China Sci & Technol Electroopt Informat Secur Control La Tianjin 300308 Peoples R China China Satellite Maritime Tracking & Control Dept Jiangyin 214430 Peoples R China Lanzhou Univ Coll Commun Engn Lanzhou 730030 Peoples R China

Recently, the unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) has become a highly sought-after topic for its wide applications in target recognition, detection, and tracking. However, SAR automatic target recognition (ATR) models based on deep neural networks (DNN) are suffering from adversarial examples. Generally, non-cooperators rarely disclose any SAR-ATR model information, making adversarial attacks challenging. To tackle this issue, we propose a novel attack method called Transferable Adversarial Network (TAN). It can craft highly transferable adversarial examples in real time and attack SAR-ATR models without any prior knowledge, which is of great significance for real-world black-box attacks. The proposed method improves the transferability via a two-player game, in which we simultaneously train two encoder-decoder models: a generator that crafts malicious samples through a one-step forward mapping from original data, and an attenuator that weakens the effectiveness of malicious samples by capturing the most harmful deformations. Particularly, compared to traditional iterative methods, the encoder-decoder model can one-step map original samples to adversarial examples, thus enabling real-time attacks. Experimental results indicate that our approach achieves state-of-the-art transferability with acceptable adversarial perturbations and minimum time costs compared to existing attack methods, making real-time black-box attacks without any prior knowledge a reality.

关键词： unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) automatic target recognition (ATR) deep neural network (DNN) adversarial example transferability encoder-decoder real-time attack

来源：评论

学校读者我要写书评

暂无评论

Wall segmentation in 2D images using convolutional neural networks

引用

PEERJ COMPUTER SCIENCE 2023年 9卷 e1565页

作者： Bjekic, Mihailo Lazovic, Ana Venkatachalam, K. Bacanin, Nebojsa Zivkovic, Miodrag Kvascev, Goran Nikolic, Bosko Everseen Belgrade Serbia Daon Belgrade Serbia Univ Hradec Kralove Fac Sci Dept Appl Cybernet Hradec Kralove Czech Republic Singidunum Univ Dept Informat & Comp Belgrade Serbia Univ Belgrade Sch Elect Engn Belgrade Serbia

Wall segmentation is a special case of semantic segmentation, and the task is to classify each pixel into one of two classes: wall and no-wall. The segmentation model returns a mask showing where objects like windows and furniture are located, as well as walls. This article proposes the module's structure for semantic segmentation of walls in 2D images, which can effectively address the problem of wall segmentation. The proposed model achieved higher accuracy and faster execution than other solutions. An encoder-decoder architecture of the segmentation module was used. Dilated ResNet50/101 network was used as an encoder, representing ResNet50/101 network in which dilated convolutional layers replaced the last convolutional layers. The ADE20K dataset subset containing only interior images, was used for model training, while only its subset was used for model evaluation. Three different approaches to model training were analyzed in the research. On the validation dataset, the best approach based on the proposed structure with the ResNet101 network resulted in an average accuracy at the pixel level of 92.13% and an intersection over union (IoU) of 72.58%. Moreover, all proposed approaches can be applied to recognize other objects in the image to solve specific tasks.

关键词： Semantic segmentation Wall segmentation encoder-decoder ADE20K PSPNet

来源：评论

学校读者我要写书评

暂无评论

ARF-Net: An Adaptive Receptive Field Network for breast mass segmentation in whole mammograms and ultrasound images

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2022年第PartA期71卷 103178-103178页

作者： Xu, Chunbo Qi, Yunliang Wang, Yiming Lou, Meng Pi, Jiande Ma, Yide Lanzhou Univ Sch Informat Sci & Engn Lanzhou Gansu Peoples R China

UNet adopting an encoder-decoder structure has been used widely in medical image segmentation tasks for its outstanding performance. However, in our work, we find that UNet has the worse segmentation performance of small masses. The reason behind this is that the sizes of receptive fields are limited. In this work, to address this issue, we develop a novel end-to-end model, Adaptive Receptive Field Network (ARF-Net), for the precise breast mass segmentation in whole mammographic images and ultrasound images. ARF-Net composes of an encoder network and a corresponding decoder network, followed by a pixel-wise classifier. In ARF-Net, a Selective Receptive Filed Module (SRFM) is proposed to allocate the suitable sizes of receptive fields to the breast masses of different sizes. SRFM consists of a Multiple Receptive Field Module (MRFM) for generating multiple receptive fields of different sizes and a Multi-Scale Selection Module (MSSM) for selecting the suitable sizes of receptive fields based on the objects' size. The proposed ARF-Net achieves the dice index of 86.1%, 85.75%, and 88.12% on the two mammographic databases (INbreast and CBIS-DDSM) and one ultrasonic database (UDIAT), respectively. Moreover, extensive ablation experiments show that ARF-Net transcends several state-of-the-art segmentation networks, and the developed MSSM exceeds several counterparts.

关键词： Segmentation Mammogram Ultrasound image Deep learning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Image captioning using transformer-based double attention network

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期125卷

作者： Parvin, Hashem Naghsh-Nilchi, Ahmad Reza Mohammadi, Hossein Mahvash Univ Isfahan Fac Comp Engn Dept Artificial Intelligence Esfahan Iran

Image captioning generates a human-like description for a query image, which has attracted considerable attention recently. The most broadly utilized model for image description is an encoder-decoder structure, where the encoder extracts the visual information of the image, and the decoder generates textual descriptions of the image. Transformers have significantly enhanced the performance of image description models. However, a single attention structure in transformers cannot consider more complex relationships between key and query vectors. Furthermore, attention weights are assigned to entire candidate vectors based on the assumption that entire vectors are related. In this paper, a new double-attention framework is presented, which improves the encoder-decoder structure to consider image captioning problems. Hence, a local generator module and a global generator module are designed to predict textual descriptions collaboratively. The proposed approach improves Self-Attention (SA) from two aspects to enhance the performance of image description. First, a Masked Self-Attention module is presented to attend on the most relevant information. Second, to evade a single shallow attention distribution and make deeper internal relations, a Hybrid Weight Distribution (HWD) module is proposed, that develops SA to use the relations between key and query vectors efficiently. Experiments over the Flickr30k and MS-COCO datasets prove that the proposed approach achieves desirable performance on different evaluation measures compared to the state-of-the-art frameworks.

关键词： Self-attention Transformer Image captioning encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：