检索结果-内蒙古大学图书馆

CvT-UNet: A weld pool segmentation method integrating a CNN and a transformer

HELIYON 2024年第15期10卷 e34738页

作者： Yang, Longcheng Wang, Huajun Meng, Wenjie Pan, Hongyu Chengdu Normal Univ Sichuan Key Lab Indoor Space Layout Optimizat & Se Chengdu 611130 Peoples R China Chengdu Univ Technol Minist Educ Key Lab Earth Explorat & Informat Technol Chengdu 610059 Peoples R China

In the acquisition of weld seam images, the presence of light and impurity interference often leads to weak edge problems in weld seam images, making the identification of weld seam defects challenging. In such scenarios, segmentation processing must be performed specifically at the fusion pool of the weld seam. In recent years, Transformers, which leverage self-attention mechanisms, have demonstrated superior sequence modeling capabilities compared to convolutional neural networks (CNNs). The Transformer excels at weighting different positions within a sequence, enabling effective handling of long-range dependencies. However, Transformers lack the ability of CNNs to extract local information. To address this limitation, this paper introduces a novel CvT-UNet semantic segmentation model that combines the strengths of both the convolutional neural network and the transformer. The model combines the global context information capabilities of the Transformer with the spatial information advantages provided by the convolutional neural network. The proposed model employs an encoder-decoder architecture by building a U-shaped network with designed CvT blocks. Depthwise separable convolutions are utilized to balance parameter quantities, and the skip-connection module is redesigned to enable the model to achieve more precise segmentation of weld seam fusion pools with fewer parameters. Experimental evaluations on diverse weld seam datasets under different environmental conditions demonstrate promising results. The model achieves average intersection over union (IoU) values of 93.75 %, 88.31 %, and 90.86 %, respectively. Specifically, on an automotive weld seam dataset, CvT-UNet outperforms the purely convolutional neural network structure UNet3+, with a 1.63 % increase in the mean IoU (MIOU) and a 1.39 % increase in the mean pixel accuracy (MPA). Compared to the TransUNet fusion model, CvT-UNet results in a 0.33 % increase in the MIOU and a 0.6 % increase in the MPA. Furth

关键词： encoder-decoder Transformer Deep separable convolution Skip connection

来源：评论

学校读者我要写书评

暂无评论

Fast MRI reconstruction using StrainNet with dual-domain loss on spatial and frequency spaces

引用

INTELLIGENT SYSTEMS WITH APPLICATIONS 2023年 18卷

作者： Kusakunniran, Worapan Karnjanapreechakorn, Sarattha Siriapisith, Thanongchai Saiviroonporn, Pairash Mahidol Univ Fac Informat & Commun Technol 999 Phuttamonthon 4 Rd Nakhon Pathom 73170 Thailand Mahidol Univ Siriraj Hosp Dept Radiol Fac Med 2 Wanglang Rd Bangkok 10700 Thailand

One of the main challenges to obtain a high throughput in the MRI process is a slow signal acquisition. This process could be improved using a parallel imaging technique, where fewer raw data with multiple radio frequency (RF) coils are acquired simultaneously to reconstruct a final MR image. Nowadays, all multi-coil MRI machines have a parallel imaging technique for the image reconstruction. However, the parallel imaging still cannot accelerate sufficiently to reduce the overall acquisition time. In another way, this paper proposes a solution relying on a deep convolution neural network (CNN) to generate high-quality reconstruction MR images with higher acceleration factors. The proposed method, called StrainNet, performs the reconstructions by encoding the under-sampled data (i.e., for the speeding up process) into high-level features. Then the important part of the network, called Strainer, is applied to discard irrelevance information, and decodes remaining features back to reconstruct MR images. The proposed network could be trained end-to-end with a newly presented loss function, Dual-Domain Loss (DDL), combining both spatial and frequency losses. The experimental results are based on the fastMRI dataset and show that StrainNet outperforms the competing methods for both 4- and 8-fold accelerations.

关键词： Fast MRI Image reconstruction encoder-decoder CNN Frequency domain

来源：评论

学校读者我要写书评

暂无评论

Urban street scene analysis using lightweight multi-level multi-path feature aggregation network

引用

MULTIAGENT AND GRID SYSTEMS 2021年第3期17卷 249-271页

作者： Singha, Tanmay Pham, Duc-Son Krishna, Aneesh Curtin Univ Sch Elect Engn Comp & Math Sci Perth WA Australia

Urban street scene analysis is an important problem in computer vision with many off-line models achieving outstanding semantic segmentation results. However, it is an ongoing challenge for the research community to develop and optimize the deep neural architecture with real-time low computing requirements whilst maintaining good performance. Balancing between model complexity and performance has been a major hurdle with many models dropping too much accuracy for a slight reduction in model size and unable to handle high-resolution input images. The study aims to address this issue with a novel model, named M2FANet, that provides a much better balance between model's efficiency and accuracy for scene segmentation than other alternatives. The proposed optimised backbone helps to increase model's efficiency whereas, suggested Multi-level Multi-path (M2) feature aggregation approach enhances model's performance in the real-time environment. By exploiting multi-feature scaling technique, M2FANet produces state-of-the-art results in resource-constrained situations by handling full input resolution. On the Cityscapes benchmark data set, the proposed model produces 68.5% and 68.3% class accuracy on validation and test sets respectively, whilst having only 1.3 million parameters. Compared with all real-time models of less than 5 million parameters, the proposed model is the most competitive in both performance and real-time capability.

关键词： DCNN semantic segmentation encoder-decoder feature map dilated convolution

来源：评论

学校读者我要写书评

暂无评论

Text Summarization Method Based on Gated Attention Graph Neural Network

引用

SENSORS 2023年第3期23卷 1654-1654页

作者： Huang, Jingui Wu, Wenya Li, Jingyi Wang, Shengchun Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China

Text summarization is an information compression technology to extract important information from long text, which has become a challenging research direction in the field of natural language processing. At present, the text summary model based on deep learning has shown good results, but how to more effectively model the relationship between words, more accurately extract feature information and eliminate redundant information is still a problem of concern. This paper proposes a graph neural network model GA-GNN based on gated attention, which effectively improves the accuracy and readability of text summarization. First, the words are encoded using a concatenated sentence encoder to generate a deeper vector containing local and global semantic information. Secondly, the ability to extract key information features is improved by using gated attention units to eliminate local irrelevant information. Finally, the loss function is optimized from the three aspects of contrastive learning, confidence calculation of important sentences, and graph feature extraction to improve the robustness of the model. Experimental validation was conducted on a CNN/Daily Mail dataset and MR dataset, and the results showed that the model in this paper outperformed existing methods.

关键词： encoder-decoder GNN contrastive learning confidence calculation of important sentences attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Single Image Dehazing via Fusion of Multilevel Attention Network for Vision-Based Measurement Applications

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷 1页

作者： Sahu, Geet Seal, Ayan Jaworek-Korjakowska, Joanna Krejcar, Ondrej Pandit Dwarka Prasad Mishra Indian Inst Informat T Jabalpur 482005 India Amity Univ Amity Ctr Artificial Intelligence Noida 201301 India Univ Hradec Kralove Fac Informat & Management Ctr Basic & Appl Sci Hradec Kralove 50003 Czech Republic AGH Univ Sci & Technol Dept Automat Control & Robot PL-30059 Krakow Poland Univ Teknol Malaysia Malaysia Japan Int Inst Technol Kuala Lumpur 54100 Malaysia

Nowadays, researchers use vision-based measurement tools to record, detect, and monitor an atmospheric phenomenon called haze. It impedes the proper functioning of many outdoor industrial systems, such as autonomous driving, surveillance, satellite imagery, and so on. Conventional visibility restoration methods cannot accurately recover image quality due to inaccurate estimations of haze thickness and the presence of color-cast effects. Deep neural networks are evolving due to their ability to directly dehaze images from hazy scenes. Therefore, a unique attention-based end-to-end dehazing network named oval-net has been proposed in this study to restore clear images from its counterpart without employing the atmospheric scattering model. The oval-net is an encoder-decoder architecture that uses spatial and channel attention at each stage to focus on dominant and significant information while avoiding the transmission of irrelevant information from the encoder to the decoder, allowing quicker convergence. The proposed approach outperforms seven state-of-the-art algorithms in quantitative and qualitative assessments of a variety of synthetic and real-world hazy images, proving its effectiveness for vision-based industrial systems.

关键词： Atmospheric modeling Image restoration Image color analysis Atmospheric measurements Feature extraction Information filters Discrete wavelet transforms Channel attention (CA) encoder-decoder image dehazing spatial attention (SA) UNet

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Prediction of Ionospheric Total Electron Content Based on ED-ConvLSTM

引用

REMOTE SENSING 2023年第12期15卷 3064-3064页

作者： Li, Liangchao Liu, Haijun Le, Huijun Yuan, Jing Shan, Weifeng Han, Ying Yuan, Guoming Cui, Chunjie Wang, Junling Inst Intelligent Emergency Informat Proc Inst Disaster Prevent Langfang 065201 Peoples R China Chinese Acad Sci Inst Geol & Geophys Key Lab Earth & Planetary Phys Beijing 100029 Peoples R China Inst Disaster Prevent Sch Informat Engn Langfang 065201 Peoples R China Beijing Jingwei Text Machinery New Technol Co Ltd Beijing 100176 Peoples R China Nanjing Forestry Univ Coll Informat Sci & Technol Nanjing 210037 Peoples R China

Total electron content (TEC) is a vital parameter for describing the state of the ionosphere, and precise prediction of TEC is of great significance for improving the accuracy of the Global Navigation Satellite System (GNSS). At present, most deep learning prediction models just consider TEC temporal variation, while ignoring the impact of spatial location. In this paper, we propose a TEC prediction model, ED-ConvLSTM, which combines convolutional neural networks with recurrent neural networks to simultaneously consider spatiotemporal features. Our ED-ConvLSTM model is built based on the encoder-decoder architecture, which includes two modules: encoder module and decoder module. Each module is composed of ConvLSTM cells. The encoder module is used to extract the spatiotemporal features from TEC maps, while the decoder module converts spatiotemporal features into predicted TEC maps. We compared the predictive performance of our model with two traditional time series models: LSTM, GRU, a spatiotemporal mode1 ConvGRU, and the TEC daily forecast product C1PG provided by CODE on a total of 135 grid points in East Asia (10 & DEG;-45 & DEG;N, 90 & DEG;-130 & DEG;E). The experimental results show that the prediction error indicators MAE, RMSE, MAPE, and prediction similarity index SSIM of our model are superior to those of the comparison models in high, normal, and low solar activity years. The paper also analyzed the predictive performance of each model monthly. The experimental results indicate that the predictive performance of each model is influenced by the monthly mean of TEC. The ED-ConvLSTM model proposed in this paper is the least affected and the most stable by the monthly mean of TEC. Additionally, the paper compared the predictive performance of each model during two magnetic storm periods when TEC changes sharply. The results indicate that our ED-ConvLSTM model is least affected during magnetic storms and its predictive performance is superior to those of the c

关键词： ionospheric TEC ConvLSTM encoder-decoder spatiotemporal geomagnetic storm

来源：评论

学校读者我要写书评

暂无评论

DCENet: A dynamic correlation evolve network for short-term traffic prediction

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2023年 614卷

作者： Liu, Shuai Feng, Xiaoyuan Ren, Yilong Jiang, Han Yu, Haiyang Beihang Univ Sch Transportat Sci & Engn Beijing 100191 Peoples R China Beihang Univ Res Inst Frontier Sci Beijing 100191 Peoples R China Beihang Hangzhou Innovat Inst Yuhang Hangzhou 310023 Peoples R China Natl Engn Lab Comprehens Transportat Big Data Appl Beijing Peoples R China Beihang Univ Res Inst Frontier Sci Beijing 100191 Peoples R China

Graph neural networks (GNNs) have been extensively employed in traffic prediction tasks due to their excellent capturing capabilities of spatial dependence. However, the majority of GNN-based approaches tend to employ static graphs, whereas they evolve over time and vary dynamics in real-world traffic situations. It is challenging to capture the dynamic spatial-temporal evolution characteristics of traffic data. To address this problem, we propose a dynamic correlation evolve network (DCENet) for short-term traffic prediction. To be specific, we develop a dynamic correlation self-attention (DCSA) module, which captures dynamic node associations adaptively. In this way, the model acquires new node embedding features without explicitly constructing a new graph structure. Then, an evolution encoder-decoder (EED) module is built to learn the interactions of dynamic features and output future traffic states. The experiments are conducted on two real-world datasets, and the results show that the DCENet outperformers baseline models for most of the cases.(c) 2023 Elsevier B.V. All rights reserved.

关键词： Traffic prediction Dynamic correlations Self-attention encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

WaveletFusion: enhancing plant leaf disease classification with multi-scale feature extraction and explainable AI

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 285卷

作者： Panchananam, Lakshmi Srinivas Chandaliya, Praveen Kumar Akhtar, Zahid Upla, Kishor Ramachandra, Raghavendra Natl Inst Technol Puducherry Pondicherry India Sardar Vallabhbhai Natl Inst Technol Surat India State Univ New York Polytech Inst Utica NY USA Norwegian Univ Sci & Technol Trondheim Norway

Plant leaf disease classification is critical for effective crop protection, yet traditional methods often fail to capture complex, multi-scale disease patterns without relying on dataset augmentation techniques or pre-trained CNN model weights. To address this limitation, we propose WaveletFusion, a novel deep learning framework that integrates channel-wise concatenation of Stationary Wavelet Transform (SWT), Discrete Wavelet Transform (DWT), and grayscale images within a ResNet18-based encoder-decoder architecture. The encoder extracts hierarchical features from RGB images, while SWT and DWT enhance multi-scale feature extraction, enabling robust representation learning. The decoder reconstructs detailed representations, which are then classified using a ResNet-based classifier. To ensure interpretability, we incorporate explainable AI techniques such as t-SNE, Grad-CAM, and LIME, providing insights into model predictions. Extensive experiments on diverse disease datasets-including PlantVillage, Embrapa, Plant Disease, New Plant Leaf, Grape Disease, Augmented Grapevine, and Tomato Leaf Disease-demonstrate that WaveletFusion outperforms state-of-the-art methods in accuracy, robustness, and generalization. Notably, these results are achieved without dataset augmentation techniques or pre-trained model weights, making WaveletFusion a promising tool for agricultural applications.

关键词： Plant leaf disease classification encoder-decoder Stationary wavelet transform Wavelet transform Dataset augmentation Explainable AI ResNet-18

来源：评论

学校读者我要写书评

暂无评论

VATEX2020: pLSTM framework for video captioning

引用

Procedia Computer Science 2023年 218卷 1229-1237页

作者： Alok Singh Salam Michael Singh Loitongbam Sanayai Meetei Ringki Das Thoudam Doren Singh Sivaji Bandyopadhyay

Captioning a video involves condensing the video's information into text, which can be useful in video sentiment analysis, video-guided machine translation (VMT), visual question-answering and humanitarian aid. This paper discusses the details of the architecture of the pLSTM framework that is employed for the VATEX-2020 video captioning challenge. In this work, a sequential method is employed wherein to encode visual features a 3D convolutional neural network (C3D) is used. C3D was pretrained using the Sports-1M dataset. In the decoding phase, the input captions and visual features are fused separately in Long Short Term Memory networks (LSTM). The element-wise dot product is performed on the output of both LSTMs to get the final output. On both publicly available and private test data sets, our model achieves BLEU-4 scores of 0.20 and 0.22, respectively.

关键词： Video captioning 3D CNN encoder-decoder VATEX LSTM C3D

来源：评论

学校读者我要写书评

暂无评论

MSLEFC: A low-frequency focused underwater acoustic signal classification and analysis system

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartB期123卷

作者： Zhang, Yunqi Zeng, Qunfeng Xi An Jiao Tong Univ Key Lab Educ Minist Modern Design & Rotor Bearing Xian 710049 Peoples R China

Many feature extraction techniques are employed to study the classification of underwater acoustic, however, most of these techniques result in the loss of detailed information in this field. A Multi-scale short-time Fourier transform (MS-STFT) method was proposed to improve the low-frequency information and maintain the detailed information by increasing the number of channels. An effective data augmentation approach was proposed and a Ladder-like Encode (LE) architecture was built to increase the generalizability of the model and the classification accuracy for the features extracted. Finally, A Frequency-CAM (FC) method is proposed to analyze the frequency band locations that the neural network is interested in when conducting classification tasks on various classes of data. The integration of the above technologies is called MSLEFC. The performance of this system has been tested on two ship radiation noise datasets and obtained 82.94% and 96.06% accuracy, respectively. On the ShipsEar dataset, the proposed method increases the accuracy by 0.7% over the previous state-of-the-art method. The proposed model architecture has significant improvements in parameter size and computation compared to ResNet50.

关键词： Underwater acoustics encoder-decoder Multi-scale short-time fourier transform Frequency-CAM

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：