检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Cui, Hui Jin, Qiangguo Wu, Xixi Wang, Linlin Zhang, Tiangang Nakaguchi, Toshiya Xuan, Ping Feng, David Dagan Department of Computer Science and Information Technology La Trobe University Melbourne Australia School of Software Northwestern Polytechnical University Shaanxi China School of Computer Science and Technology Heilongjiang University Harbin China Department of Radiation Oncology Shandong Cancer Hospital and Institute Shandong First Medical University Shandong Academy of Medical Sciences Jinan China School of Mathematical Science Heilongjiang University Harbin China Center for Frontier Medical Engineering Chiba University Chiba Japan Department of Computer Science School of Engineering Shantou University Shantou China School of Computer Science The University of Sydney Sydney Australia

Accurate and robust organ and tumour segmentation from CT scans are critical for precision diagnosis and prognosis of cancer, and the development of personalized treatment planning. However, automatic segmentation of tumours and organs they have invaded is challenging due to significant variations, abnormalities, and unclear boundaries. While graph convolutional networks can propagate knowledge and correlations in a flexible feature space, they suffer from information saturation during deep learning which can limit their effectiveness. To overcome this issue, we proposed a hybrid graph convolution transformer (HCGT) model. The HCGT has a channel transformer (CTrans) component, which helps to learn contextual relationships across different feature channels. Furthermore, we developed a convolutional graph transformer (convG-Trans) that can simultaneously and interactively learn enhanced relationships between different parts of the image by aggregating knowledge propagation from graph convolution and cross-node similarities from the transformer. Finally, we incorporated category-level attention to understand the significance of the two representations from the CTrans and convG-Trans, which helped adjust the fusion process before generating the segmentation output. We evaluated the HCGT on kidney and tumour and lung and non-small cell lung cancer datasets. Our evaluations included comparisons with other three-dimensional (3D) medical image segmentation benchmarks, as well as graph-based and transformer-based segmentation models. The results demonstrated improved performance in abdominal and thorax organ and tumour segmentation tasks. Additionally, ablation studies showed that the major technical innovations were effective and consistent when using different 3D medical image segmentation backbones. © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Vehicle Re-Identication Model Based on Optimized DenseNet121 with Joint Loss

引用

computers, Materials & Continua 2021年第6期67卷 3933-3948页

作者： Xiaorui Zhang Xuan Chen Wei Sun Xiaozheng He Jiangsu Engineering Center of Network Monitoring Engineering Research Center of Digital ForensicsMinistry of EducationSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&TechnologyNanjing210044China Department of Civil and Environmental Engineering Rensselaer Polytechnic InstituteTroyNY12180USA

With the increasing application of surveillance cameras,vehicle re-identication(Re-ID)has attracted more attention in the eld of public *** Re-ID meets challenge attributable to the large intra-class differences caused by different views of vehicles in the traveling process and obvious inter-class similarities caused by similar *** existing methods focus on local attributes by marking local ***,these methods require additional annotations,resulting in complex algorithms and insufferable computation *** cope with these challenges,this paper proposes a vehicle Re-ID model based on optimized DenseNet121 with joint *** model applies the SE block to automatically obtain the importance of each channel feature and assign the corresponding weight to it,then features are transferred to the deep layer by adjusting the corresponding weights,which reduces the transmission of redundant information in the process of feature reuse in *** the same time,the proposed model leverages the complementary expression advantages of middle features of the CNN to enhance the feature expression ***,a joint loss with focal loss and triplet loss is proposed in vehicle Re-ID to enhance the model’s ability to discriminate difcult-to-separate samples by enlarging the weight of the difcult-to-separate samples during the training *** results on the VeRi-776 dataset show that mAP and Rank-1 reach 75.5%and 94.8%,***,Rank-1 on small,medium and large sub-datasets of Vehicle ID dataset reach 81.3%,78.9%,and 76.5%,respectively,which surpasses most existing vehicle Re-ID methods.

关键词： Vehicle re-identication densenet joint loss focal loss SE block

来源：评论

学校读者我要写书评

暂无评论

Construction of Multi-Scale Fusion Attention Unified Perceptual Parsing Networks for Semantic Segmentation of Mangrove Remote Sensing Images

SSRN

引用

SSRN 2024年

作者： Wang, Xin Xu, Wenquan Zhang, Yu Wang, Yixuan Wang, Hanxi Cai, Jingye Qin, Qin Wang, Qin Zeng, Jing School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610000 China School of Marine Engineering Guilin University of Electronic Technology Beihai536000 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541010 China School of Civil Engineering and Transportation Hohai University Nanjing210000 China School of Geographical Sciences Harbin Normal University Harbin150025 China Guilin University of Technology China

In recent years, significant progress has been made in monitoring the distribution of mangrove forests using remotely sensed images. Challenges persist due to the high resolution of the images, large-scale variations, and sporadic distribution of mangrove forest boundaries, which resulted in problems such as omission, misdiagnosis, and blurring of boundary segmentation that require resolution. This study constructed the Mangrove Semantic Segmentation Dataset in Beihai of Guangxi (MSSDBG) using a combination of China's new generation of high spatial resolution earth observation satellites, which included Beijing-2(BJ-2), Beijing-3(BJ-3), Gaofen-7(GF-7), Gaojing-1(SV-1), and Jilin-1(JL-1), as the data sources for multi-source remote sensing. The study proposed a multi-scale fusion attention unified perceptual parsing network (MFA-UperNet) for semantic segmentation of mangrove remote sensing images. The network included a CPF module based on a feature pyramid network, and this module can facilitate the integration of features at different levels through multi-path connections. The Multi-scale Large Selection Kernel Attention module incorporated a multi-scale channel attention mechanism and a large selection kernel structure, which effectively addressed mangrove forests' scale variation and shape differences in remote sensing images. AES branch optimization training was conducted using a fully convolutional network and a hybrid loss function to optimize the training results considering the characteristics of the sporadic distribution of mangrove boundaries. The study demonstrated that the MFA-UperNet achieved an optimal mPA of 97.14% and a mIoU of 94.54% on the MSSDBG dataset. High evaluation index scores were obtained on the Potsdam and Vaihingen datasets. This study contributes to the advancement of mangrove monitoring and provides a valuable reference for the restoration and protection of mangrove resources. © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Curvilinear object segmentation in medical images based on ODoS filter and deep learning network

arXiv

引用

arXiv 2023年

作者： Peng, Yuanyuan Pan, Lin Luan, Pengpeng Tu, Hongbin Li, Xiong School of Electrical and Automation Engineering East China Jiaotong University Nanchang330000 China School of Computer Science Northwestern Polytechnical University Xi’an710000 China School of Software East China Jiaotong University Nanchang330000 China

Automatic segmentation of curvilinear objects in medical images plays an important role in the diagnosis and evaluation of human diseases, yet it is a challenging uncertainty in the complex segmentation tasks due to different issues such as various image appearances, low contrast between curvilinear objects and their surrounding backgrounds, thin and uneven curvilinear structures, and improper background illumination conditions. To overcome these challenges, we present a unique curvilinear structure segmentation framework based on an oriented derivative of stick (ODoS) filter and a deep learning network for curvilinear object segmentation in medical images. Currently, a large number of deep learning models emphasize developing deep architectures and ignore capturing the structural features of curvilinear objects, which may lead to unsatisfactory results. Consequently, a new approach that incorporates an ODoS filter as part of a deep learning network is presented to improve the spatial attention of curvilinear objects. Specifically, the input image is transfered into four-channel image constructed by the ODoS filter. In which, the original image is considered the principal part to describe various image appearance and complex background illumination conditions, a multi-step strategy is used to enhance the contrast between curvilinear objects and their surrounding backgrounds, and a vector field is applied to discriminate thin and uneven curvilinear structures. Subsequently, a deep learning framework is employed to extract various structural features for curvilinear object segmentation in medical images. Which can effectively capture the spatial attention of curvature objects. The performance of the computational model is validated in experiments conducted on the publicly available DRIVE, STARE and CHASEDB1 datasets. Compared with ground truths, the presented model acquired high F1 values of 0.826, 0.819 and 0.808, and high accuracy of 0.969, 0.973, and 0.973 on three

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

MetaSlicing: A Novel Resource Allocation Framework for Metaverse

arXiv

引用

arXiv 2022年

作者： Chu, Nam H. Hoang, Dinh Thai Nguyen, Diep N. Phan, Khoa T. Dutkiewicz, Eryk Niyato, Dusit Shu, Tao The School of Electrical and Data Engineering University of Technology Sydney Australia School of Engineering and Mathematical Sciences Department of Computer Science and Information Technology La Trobe University Melbourne Australia The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The Department of Computer Science and Software Engineering Auburn University AuburnAL36849 United States

Creating and maintaining the Metaverse requires enormous resources that have never been seen before, especially computing resources for intensive data processing to support the Extended Reality, enormous storage resources, and massive networking resources for maintaining ultra high-speed and low-latency connections. Therefore, this work aims to propose a novel framework, namely MetaSlicing, that can provide a highly effective and comprehensive solution in managing and allocating different types of resources for Metaverse applications. In particular, by observing that Metaverse applications may have common functions, we first propose grouping applications into clusters, called MetaInstances. In a MetaInstance, common functions can be shared among applications. As such, the same resources can be used by multiple applications simultaneously, thereby enhancing resource utilization dramatically. To address the real-time characteristic and resource demand's dynamic and uncertainty in the Metaverse, we develop an effective framework based on the semi-Markov decision process and propose an intelligent admission control algorithm that can maximize resource utilization and enhance the Quality-of-Service for end-users. Extensive simulation results show that our proposed solution outperforms the Greedy-based policies by up to 80% and 47% in terms of long-term revenue for Metaverse providers and request acceptance probability, respectively. Copyright © 2022, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

A Swin transformer encoder-based StyleGAN for unbalanced endoscopic image enhancement

引用

computers in Biology and Medicine 2024年 175卷 108472-108472页

作者： Deng, Bo Zheng, Xiangwei Chen, Xuanchi Zhang, Mingzhe School of Information Science and Engineering Shandong Normal University Jinan250352 China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan250352 China State Key Laboratory of High–end Server & Storage Technology Jinan250101 China

With the rapid development of artificial intelligence, automated endoscopy-assisted diagnostic systems have become an effective tool for reducing the diagnostic costs and shortening the treatment cycle of patients. Typically, the performance of these systems depends on deep learning models which are pre-trained with large-scale labeled data, for example, early gastric cancer based on endoscopic images. However, the expensive annotation and the subjectivity of the annotators lead to an insufficient and class-imbalanced endoscopic image dataset, and these datasets are detrimental to the training of deep learning models. Therefore, we proposed a Swin Transformer encoder-based StyleGAN (STE-StyleGAN) for unbalanced endoscopic image enhancement, which is composed of an adversarial learning encoder and generator. Firstly, a pre-trained Swin Transformer is introduced into the encoder to extract multi-scale features layer by layer from endoscopic images. The features are subsequently fed into a mapping block for aggregation and recombination. Secondly, a self-attention mechanism is applied to the generator, which adds detailed information of the image layer by layer through recoded features, enabling the generator to autonomously learn the coupling between different image regions. Finally, we conducted extensive experiments on a private intestinal metaplasia grading dataset from a Grade-A tertiary hospital. The experimental results show that the images generated by STE-StyleGAN are closer to the initial image distribution, achieving a Fréchet Inception Distance (FID) value of 100.4. Then, these generated images are used to enhance the initial dataset to improve the robustness of the classification model, and achieved a top accuracy of 86 %. © 2024 Elsevier Ltd

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Distributed quantum architecture search

arXiv

引用

arXiv 2024年

作者： Situ, Haozhen He, Zhimin Zheng, Shenggen Li, Lvzhou College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China School of Electronic and Information Engineering Foshan University Foshan528000 China Shenzhen518045 China Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China

Variational quantum algorithms, inspired by neural networks, have become a novel approach in quantum computing. However, designing efficient parameterized quantum circuits remains a challenge. Quantum architecture search tackles this by adjusting circuit structures along with gate parameters to automatically discover high-performance circuit structures. In this study, we propose an end-to-end distributed quantum architecture search framework, where we aim to automatically design distributed quantum circuit structures for interconnected quantum processing units with specific qubit connectivity. We devise a circuit generation algorithm which incorporates TeleGate and TeleData methods to enable nonlocal gate implementation across quantum processing units. While taking into account qubit connectivity, we also incorporate qubit assignment from logical to physical qubits within our quantum architecture search framework. A two-stage progressive training-free strategy is employed to evaluate extensive circuit structures without circuit training costs. Through numerical experiments on three VQE tasks, the efficacy and efficiency of our scheme is demonstrated. Our research into discovering efficient structures for distributed quantum circuits is crucial for near-term quantum computing where a single quantum processing unit has a limited number of qubits. Distributed quantum circuits allow for breaking down complex computations into manageable parts that can be processed across multiple quantum processing units. Copyright © 2024, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

CommGPT: A Graph and Retrieval-Augmented Multimodal Communication Foundation Model

arXiv

引用

arXiv 2025年

作者： Jiang, Feibo Zhu, Wanyun Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua Dobre, Octavia A. Hunan Normal University China Hunan University of Technology and Business China Department of Computer Science Brunel University London United Kingdom School of Intelligent Software and Engineering Nanjing University China Southeast University China Memorial University Canada

Large Language Models (LLMs) possess human-level cognitive and decision-making capabilities, making them a key technology for 6G. However, applying LLMs to the communication domain faces three major challenges: 1) Inadequate communication data;2) Restricted input modalities;and 3) Difficulty in knowledge retrieval. To overcome these issues, we propose CommGPT, a multimodal foundation model designed specifically for communications. First, we create high-quality pretraining and fine-tuning datasets tailored in communication, enabling the LLM to engage in further pretraining and fine-tuning with communication concepts and knowledge. Then, we design a multimodal encoder to understand and process information from various input modalities. Next, we construct a Graph and Retrieval-Augmented Generation (GRG) framework, efficiently coupling Knowledge Graph (KG) with Retrieval-Augmented Generation (RAG) for multi-scale learning. Finally, we demonstrate the feasibility and effectiveness of the CommGPT through experimental validation. Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

arXiv

引用

arXiv 2022年

作者： Ji, Jiahao Wang, Jingyuan Jiang, Zhe Jiang, Jiawei Zhang, Hu State Key Laboratory of Software Development Environment School of Computer Science & Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Department of Computer & Information Science & Engineering The University of Florida United States MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science & Engineering Beihang University Beijing China

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio- Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

SDCM: An Efficient Camellia Oleifera Fruits Detection Algorithm in Dense Occlusion Scenes

SDCM: An Efficient Camellia Oleifera Fruits Detection Algori...

引用

Computing and Big Data (ICCBD), International Conference on

作者： Youyang Zhang Qiuxia Chen Wenhua Cui Jinfeng Yang School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China Institute of Applied Artificial Intelligence of the Guang-dong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic Shenzhen China

ISBN: (数字)9798350317008

ISBN: (纸本)9798350317015

To realize intelligent management in the Camellia oleifera fruit industry and foster the efficient growth of its supply chain, the accurate identification and detection of Camellia oleifera fruits are essential. However, in natural environments, these fruits exhibit challenges such as clustering, mutual occlusion, and obstruction by leaves. This paper proposes a Camellia oleifera fruits detection algorithm based on an improved YOLOv7 deep convolutional neural network, which is referred to as the SDCM network model, and add the function of counting the number of fruits. We introduce an enhancement to the backbone layer of the YOLOv7 model by incorporating a module called SDCM (Shortcut and Dilation Convolution based Module). This module enriches multiscale edge information, enabling the network to extract features more effectively, thus improving detection accuracy. The experimental results show that the detection accuracy of the SDCM network model is significantly improved compared with the original YOLOv7 model, and the detection performance of the model in this paper is superior compared with other classical detection models. By enhancing the detection accuracy of the model and adding the function of fruit counting, the model in this paper can provide more reliable and accurate detection performance and the function of predicting fruit yield for the development of the Camellia oleifera fruit industry, improve the production efficiency, and reduce the artificial resources.

关键词： Industries Accuracy Image edge detection Supply chains Production Predictive models Feature extraction

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：