检索结果-内蒙古大学图书馆

9th International Conference on Intelligent Computing and Signal processing, ICSP 2024

作者： Wang, Xuewei Yuan, Shuang Yang, Lidong Niu, Dawei Inner Mongolia University of Science and Technology School of Digtial and Intelligence Industry Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing Inner Mongolia China

ISBN: (纸本)9798350376548

Cervical cytologic screening is clinically important for the prevention and diagnosis of cervical cancer. Aiming at the many challenges in the detection of abnormal cervical cells, including the difficult detection of small targets of abnormal cervical cells, complex backgrounds, and uneven cell morphology, a detection algorithm for abnormal cervical cells based on improved YOLOv7 was proposed. The algorithm utilizes Deformable Convolutional Networks v2 (DCNv2) that adaptively de-tunes the scale and receptive field size to more effectively cope with the complexity and diversity of cervical cell images. The experimental results show that the improved YOLOv7 algorithm mAP achieves 57.26%, up to 73.88% accuracy, and 46.90% recall on the cervical abnormal cell dataset. Compared with the benchmark model, they increased by 4.07%, 3.39%, and 5.69%, respectively. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

MATL: A deep neural network using multi-scale convolutions and transformer for transcription factor binding site prediction

MATL: A deep neural network using multi-scale convolutions a...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Fan, Jinli Shen, Ruyi Huang, Xiaodi Zhang, Yanju Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China College of Computer Science and Technology Huaqiao University Xiamen China

ISBN: (纸本)9798350386226

Transcription factors bind to specific sequences of DNA known as transcription factor binding sites (TFBSs) in order to regulate gene expression. Identifying TFBSs is crucial for deciphering gene expression mechanisms, understanding in vitro life characteristics, and drug design. In recent years, many deep learning methods that utilize only the sequence features or a combination of sequence and shape features have been developed to predict TFBSs. However, these methods have not fully considered the characteristics of TFBSs, and their encoding strategies are relatively simplistic, thereby failing to capture the complex dependencies hidden within TFBSs. To address these issues, we propose a novel deep neural network model called MATL, which integrates sequence and shape features for TFBSs prediction. The model employs techniques such as multi-scale convolution and Transformer, and combines different modules for feature extraction based on the distribution patterns of different feature matrices. Additionally, we introduce transfer learning to address the issue of unsatisfactory prediction results due to insufficient training data in some datasets. As the results indicate, MATL exhibits excellent predictive performance on 165 validated ChIP-seq datasets, surpassing state-of-the-art methods. We also conducted ablation experiments on sequence encoding, feature extraction, and shape modules used in this study, and demonstrated that these modules play a positive role in predicting TFBSs. Moreover, the results also indicated that transfer learning can improve prediction accuracy for some TFBSs datasets with small amounts of data. The source code of MATL is available at https://***/LittleWhiteKing/MATL. © 2024 IEEE.

关键词： Transcription

来源：评论

学校读者我要写书评

暂无评论

Guided-YNet: Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network

引用

Computers, Materials & Continua 2024年第9期80卷 4813-4832页

作者： Tao Zhou Yunfeng Pan Huiling Lu Pei Dang Yujie Guo Yaxing Wang School of Computer Science and Engineering North Minzu UniversityYinchuan750021China School of Medical Information&Engineering Ningxia Medical UniversityYinchuan750004China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission NorthMinzuUniversityYinchuan750021China

Multimodal lung tumor medical images can provide anatomical and functional information for the same *** as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and *** to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key *** solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this ***,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate ***,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after ***,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic ***,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local *** proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,*** is of great significance for computer-aided diagnosis.

关键词： Medical image segmentation U-Net saliency feature guidance cross-modal feature enhancement cross-dimension feature enhancement

来源：评论

学校读者我要写书评

暂无评论

Fusion-CAM: Fine-Grained and High-Faithfulness Explanations for Deep Convolutional Network via Hierarchical Fusion 7

Fusion-CAM: Fine-Grained and High-Faithfulness Explanations ...

引用

7th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Zheng, Chen Li, Wei Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan China Image Processing and Intelligent Control Key Laboratory of the Education Ministry of China Wuhan China

ISBN: (纸本)9798350339161

The interpretability of the convolutional neural networks(CNNs) has become a research hotspot. A popular explanation method is based on Class Activation Mapping (CAM), which visualizes the salient regions most relevant to neural network decisions. However, many CAM methods use the feature maps produced by the final convolution layer to generate the class activation maps, which usually have a low spatial resolution and can only generate coarse-grained visual explanations that provide a rough spatial location of the target object. In this paper, we propose a novel CAM method named Fusion-CAM. It improves traditional CAM methods by combining final class activation map containing semantic information with intermediate layer class activation maps containing fine-grained details, to generate fine-grained visual explanations with high faithfulness. In order to obtain high-quality intermediate layer class activation maps, we utilize Layer-wise Relevance Propagation (LRP) to obtain the weighting components of each channel of the intermediate layer feature maps, and the intermediate layer class activation maps generated by weighted summation are less noisy and have clear fine-grained details, which help to improve the quality of the final class activation map. Qualitative and quantitative experiments show that Fusion-CAM can be easily attached to different CAM methods to improve their performance. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Airport UAV and birds detection based on deformable DETR 2

Airport UAV and birds detection based on deformable DETR

引用

2022 2nd International Conference on Electrical, Electronics and Computing Technology, EECT 2022

作者： Shanliang, Liu Yunlong, Li Jingyi, Qu Renbiao, Wu Tianjin Key Laboratory Of Intelligent Signal And Image Processing Civil Aviation University China

The aviation industry is growing rapidly, but due to inadequate airport surveillance technology, there have been incidents of UAV intruding into airports and birds striking aircraft in the clearance area. Existing airports use radar-based detection technology to monitor UAV and birds in the clearance area, and they cannot correctly identify the type and number of UAV and the size and number of birds. Based on this problem, this paper proposes a deformable DETR (DEtection TRansformer) based detection method for UAV and birds to assist airports to better supervise the clearance area and reduce safety hazards. In response to the small size of airport UAV and birds, we adopt a deformable DETR object detection method using multi-feature fusion to detect UAV and birds in the airport environment. The model has good detection performance with mAP of 75.2 and recall of 95.0%, which meets the airport's requirements for UAV and bird detection, as verified by the actual data collection. This method can help to improve surveillance methods within the clearance area of airports and can also provide technical support for the detection of small objects in other areas. © Published under licence by IOP Publishing Ltd.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

A Dual-branch Model for Early Detection of Alzheimer's Disease Using Resting-State fMRI 7

A Dual-branch Model for Early Detection of Alzheimer's Disea...

引用

7th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Wang, Yixuan Li, Wei Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan China Image Processing and Intelligent Control Key Laboratory of the Education Ministry of China Wuhan China

ISBN: (纸本)9798350339161

Alzheimer's disease (AD) is the most prevalent form of dementia, and early diagnosis is crucial for delaying and treating AD. Resting-state functional magnetic resonance imaging (rs-fMRI), a widely used medical imaging technique, offers rich temporal and spatial data, which has led researchers to explore various feature extraction methods based on rs-fMRI images for AD identification. However, the related work still suffers from insufficient utilization of temporal and spatial information which leads to unsatisfactory early diagnosis. In this study, we propose a dual-branch fusion model to extract spatial-temporal features from rs-fMRI images. Our proposed model can extract temporal features at different levels. We developed a Class Activation Sequence (CAS) branch, which is a structure that emphasizes the function of each temporal node throughout the whole time series. Additionally, we created a time-domain local branch for local feature extraction. Further, we designed a fusion module for the model to describe temporal contextual relationships and fuse features at various levels. We tested the performance of the model on the ADNI dataset, and the experimental results show that compared with other algorithms, the dual-branch fusion model achieves higher classification accuracy on several classification tasks including early diagnosis, which proves the advantage of the dual-branch fusion model in temporal and spatial feature extraction for rs-fMRI images, and our work also provides a foundation for the temporal domain characterization of rs-fMRI images. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

image Sample Generation of Stator Surface Defects Based on Layer Mask Blending Generative Adversarial Network 23

Image Sample Generation of Stator Surface Defects Based on L...

引用

9th International Conference on Computing and Artificial Intelligence, ICCAI 2023

作者： Li, Wenzheng Tian, Lihua Sun, Zhigang Xiao, Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450399029

In industrial production processes, defect inspection plays an important role in reducing the occurrence of failures and improving production efficiency. Data-driven algorithms represented by deep learning have made great progress in recent years, but need to face the problems of small quantity and poor quality of datasets when applied to industrial defect inspection. This paper proposes a layer mask blending-based generative adversarial network (LMBGAN) and optimizes the training process to generate high-quality surface defect samples. LMBGAN generates defect images and layer masks using the defect image decoder and layer mask decoder with the Pixel Shuffle operation. Inspired by the layer mask in computer painting, LMBGAN adopts the input image as the base layer and blends the defect foreground through the layer mask, giving it the ability to focus more on generating upper-layer defect images and reducing unnecessary background changes. LMBGAN additionally introduces adaptive discriminator augmentation and non-saturating logistic loss to promote model convergence under small datasets, effectively alleviating the problem of GAN training difficulties with limited data. The experiment results show that the proposed method can generate high-quality and diverse defect image samples through easily accessible normal samples, thus reducing the difficulty of obtaining rare defect image samples. © 2023 Copyright held by the owner/author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Investigation of electroencephalogram-based emotion recognition and channel importance analysis for dual-induction patterns

Investigation of electroencephalogram-based emotion recognit...

引用

2024 International Conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2024

作者： Li, Zhengxiu Liao, Yijie Li, Zebin Chen, Hao Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang330063 China School of Information Engineering Nanchang Hangkong University Nanchang330063 China

ISBN: (纸本)9781510689275

Both external stimulus and self-induction can evoke human emotions. However, most current research on emotion recognition by Electroencephalogram (EEG) signals focuses only on external stimuli. It was found that ignoring the differences between induced patterns results in lower emotion recognition accuracy. To overcome this problem, we construct a hierarchical emotion recognition model, which first determines whether emotions originate from external stimulus induction or self-induction and then classifies specific emotion categories. Meanwhile, we systematically evaluate the performance of multiple feature types, feature selection, and channel reduction schemes in identifying induction methods and emotional categories. Notably, we make channel importance analysis operators to investigate the distribution of electrodes associated with different induction patterns. Our model works on a dataset that simulates real induced-emotion scenarios. The experimental results show for the first time that the features extracted in the time domain can most effectively discriminate between the induction modalities. And the hierarchical emotion recognition model with feature selection and channel importance analysis operators achieves the best accuracy of 88.53%, which is 14.69% higher than a baseline model. More critically, channel importance analysis indicates that both induction modalities display similar electrode distributions, with EEG signals from temporal and prefrontal electrodes considered to be highly correlated with emotions;stimulus-induced emotion showing an apparent lateralization effect with higher importance of the left side of the brain electrodes, while self-induction is equally distributed on the left and right sides. © 2025 SPIE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

FASTC: A Fast Attentional Framework for Semantic Traversability Classification Using Point Cloud 26

FASTC: A Fast Attentional Framework for Semantic Traversabil...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Chen, Yirui Wei, Pengjin Liu, Zhenhuan Wang, Bingchao Yang, Jie Liu, Wei Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing Ministry of Education China

ISBN: (纸本)9781643684369

Producing traversability maps and understanding the surroundings are crucial prerequisites for autonomous navigation. In this paper, we address the problem of traversability assessment using point clouds. We propose a novel pillar feature extraction module that utilizes PointNet to capture features from point clouds organized in vertical volume and a 2D encoder-decoder structure to conduct traversability classification instead of the widely used 3D convolutions. This results in less computational cost while even better performance is achieved at the same time. We then propose a new spatio-temporal attention module to fuse multi-frame information, which can properly handle the varying density problem of LIDAR point clouds, and this makes our module able to assess distant areas more accurately. Comprehensive experimental results on augmented Semantic KITTI and RELLIS-3D datasets show that our method is able to achieve superior performance over existing approaches both quantitatively and quantitatively. Our code is publicly available at https://***/chenyirui/FASTC. © 2023 The Authors.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Video Compression Artifacts Removal With Spatial-Temporal Attention-Guided Enhancement

引用

IEEE Transactions on Multimedia 2024年 26卷 5657-5669页

作者： Jiang, Nanfeng Chen, Weiling Lin, Jielian Zhao, Tiesong Lin, Chia-Wen Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou350108 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen University of Technology Xiamen361024 China Fujian Science and Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou350116 China Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan

Recently, many compression algorithms are applied to decrease the cost of video storage and transmission. This will introduce undesirable artifacts, which severely degrade visual quality. Therefore, Video Compression Artifacts Removal (VCAR) aims at reconstructing a high-quality video from its corrupted version of compression. Generally, this task is considered as a vision-related instead of media-related problem. In vision-related research, the visual quality has been significantly improved while the computational complexity and bitrate issues are less considered. In this work, we review the performance constraints of video coding and transfer to evaluate the VCAR outputs. Based on the analyses, we propose a Spatial-Temporal Attention-Guided Enhancement Network (STAGE-Net). First, we employ dynamic filter processing, instead of conventional optical flow method, to reduce the computational cost of VCAR. Second, we introduce self-attention mechanism to design Sequential Residual Attention Blocks (SRABs) to improve visual quality of enhanced video frames with bitrate constraints. Both quantitative and qualitative experimental results have demonstrated the superiority of our proposed method, which achieves high visual qualities and low computational costs. © 2023 IEEE.

关键词： Computational complexity

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：