检索结果-内蒙古大学图书馆

LMD2F-Net: Layered Multi-Scale Dual-Branch Dual-Temporal Fusion Network for Medical Image Segmentation

IEEE Access 2024年

作者： Ye, Siyuan Wei, Yan Chongqing Normal University College of Computer and Information Science Chongqing401331 China Chongqing Engineering Research Center of Educational Big Data Intelligent Perception and Application Chongqing401331 China

Image segmentation techniques play a crucial role in medical image analysis, which is directly related to the diagnosis of diseases, the development of treatment plans, and the evaluation of efficacy. Although Convolutional neural networks (CNNs) and transformer-based approaches have made significant progress in this area, the inherent complexity of medical images, including features such as low contrast, fuzzy boundaries, and noise, makes automated segmentation tasks still challenging. To address these issues, we propose LMD2F-Net, an innovative encoder-decoder architecture that cleverly fuses the multi-axis attention mechanism of MaxViT and the global context modelling capability of Swin Transformer through a two-branch structure. This combination not only enhances the model's ability to capture local features, but also improves the understanding of the global context. In the decoding stage, we propose the Multi-scale Bitemporal Fusion Module (MBFM), which further optimises the feature fusion through a multi-scale feature extraction and attention mechanism, and significantly improves the model's ability to identify and capture key features of medical images. In addition, we introduce the dual-level fusion (DLF) module, which acts as a bridge between the encoder and decoder to effectively integrate features at different levels through the cross-attention mechanism. Experimental results on several challenging medical image segmentation datasets show that LMD2F-Net outperforms existing methods in several evaluation metrics, especially in key metrics such as Dice similarity coefficient and Hausdorff distance, which demonstrate its superior performance. These findings confirm the potential of LMD2F-Net in improving the accuracy and robustness of medical image segmentation, providing a valuable reference for future research and clinical practice. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

In-situ synthesized SiC/TiC/SiTiOC hybrid nanofiber mats for broad-range temperature microwave absorption

引用

science China Technological sciences 2025年第6期68卷 183-196页

作者： Yashan HUO Yuetong QIAN Minshan ZHAO Lei ZHANG Yujia TAN Zhihui HE Peng MIAO Fuchun ZHANG Wei CUI Renchao CHE School of Physics and Electronic Information Yan'an University Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Laboratory of Advanced Materials Shanghai Key Lab of Molecular Catalysis and Innovative Materials Academy for Engineering &Technology Advanced Coatings Research Center of Ministry of Education of China Fudan University School of Materials and Chemical Engineering Xi'an Technological University School of Materials Science & Engineering Tongji University College of Physics Donghua University

Efficient, temperature-insensitive electromagnetic attenuation materials are critical for high microwave absorption at high temperatures. This study presents SiC/TiC/SiTiOC hybrid nanofiber mats constructed using an in-situ synthesis method;these mats incorporate SiC/TiC as the microwave loss unit and SiTiOC as the antioxidant unit, offering an innovative approach to high-temperature microwave absorption. The introduction of high-conductivity TiC not only optimizes the dielectric constant and impedance matching of the material but also enhances its thermal cycling stability. This design ensures steady electromagnetic attenuation, enabling the hybrid nanofiber mats to maintain robust absorption performance in the X-band, even at high temperatures. At 873 K, the material demonstrates an effective absorption bandwidth of 3.6 GHz and a minimum reflection loss of-45.55 dB. Compared to single-system absorbers, such as SiC/C nanofiber materials, with a single system, the multicomponent SiC/TiC/SiTiOC hybrid nanofiber mats deliver reliable absorption performance in the temperature range of 293–873 K. This study confirms that highly conductive titanium-based ceramic materials used for dielectric property regulation effectively address the challenges of poor temperature stability and limited reusability in high-temperature carbon-ceramic absorbing materials, providing valuable insights and guidance for designing efficient microwave absorbers that can operate across a wide temperature range.

关键词： electrospinning SiC/TiC/SiTiOC hybrid nanofiber mats high-temperature microwave absorption dielectric properties thermal stability

来源：评论

学校读者我要写书评

暂无评论

Fast Sampling of Diffusion Models for Accelerated MRI using Dual Manifold Constraints

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Qiao, Lihong Wang, Rongxuan Shu, Yucheng Li, Baobin Li, Weisheng Gao, Xinbo Cai, Zhanchuan Chongqing University of Posts and Telecom munications Chongqing Big Data Collaborative Innovation Center Chongqing400065 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing101408 China Macau University of Science and Technology School of Computer Science and Engineering Macau China

Diffusion models show great potential in solving inverse problems, including MRI reconstruction. With its unique characteristics, medical imaging demands both efficiency and accuracy in the reconstruction process. However, existing MRI reconstruction methods based on diffusion models often fall short of fully leveraging the available measurements during sampling. Consequently, these methods suffer from compromised reconstruction quality and elevated bias, especially when dealing with large acceleration factors. In response to these challenges, we propose Dual Manifold Constraints (DMC), a fast MRI reconstruction method based on diffusion models. We treat the sampling process as a combination of denoising and adding noise processes, and we constrain these two processes using both pristine measurements and their noisy counterparts to adapt to the geometry of diffusion. It's worth noting that we propose a method to estimate the noisy measurement that satisfies the sub-sampling process to maintain the current data manifold when performing data consistency constraints. Experimental results show that our method outperforms the latest diffusion-based methods regarding both reconstruction speed and accuracy, and exhibits strong out-of-distribution generalization performance. © 1991-2012 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Demand Response Scheme: Achieving Sustainability in Distributed data Processing 9

Demand Response Scheme: Achieving Sustainability in Distribu...

引用

9th IEEE International Conference on data science in Cyberspace, DSC 2024

作者： Zhai, Xueying Peng, Yunfeng Guo, Xiuping Zhang, Liang Zhang, Wei University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China Beijing University of Posts and Telecommunications School of Economics and Management Beijing China Guizhou Institute of Technology Guizhou Key Laboratory of Electric Power Big Data Guizhou China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China

ISBN: (纸本)9798350391367

The rapid development of Internet of Things (IoT) technology has driven the intelligent transformation of various industries, including manufacturing, agriculture, and healthcare, etc., significantly enhancing their management capabilities and decision-making efficiency. data analysis is crucial, serving as both the core technology of this transformation and a major driving force for advancing industry intelligence. However, the increasing volume of data has led to high energy consumption during data analysis, posing significant challenges to environmental and economic sustainability. Integrating renewable energy sources (RESs) is an effective way to reduce greenhouse gas emissions due to their low-carbon and renewable nature. Additionally, the spatiotemporal variability and complementarity of RES generation and grid electricity prices provide favorable conditions for distributed data processing. Therefore, a two-stage demand response scheme is proposed to reduce carbon emissions and electricity costs by prioritizing data processing in data centers (DCs) where RES is abundant or electricity prices are low, based on RES generation and electricity price signals. Simulation results show that the proposed scheme reduces 36.37% carbon emissions and 20.49% electricity costs compared to the benchmark algorithm, indicating its potential for both environmental and economic optimization. © 2024 IEEE.

关键词： Low emission

来源：评论

学校读者我要写书评

暂无评论

Curriculum Learning for Ethereum Phishing Scam Detection

Curriculum Learning for Ethereum Phishing Scam Detection

引用

International Conference on computer Supported Cooperative Work in Design

作者： Wenhan Hou Bo Cui Yongxin Chen Ru Li Wanshui Song Engineering Research Center of Ecological Big Data Ministry of Education China College of Computer Science Inner Mongolia University Hohhot China College of Computer Science and Technology Harbin Engineering University Harbin China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The rise of Ethereum in various economic and social domains has made it a prime target for illegal activities, particularly phishing scams, which has caused substantial financial losses. Existing methods mainly model transaction records as networks and classify nodes. However, a particular challenge is that not all transactions involved in phishing nodes are illegal, which makes phishing detection very difficult. In order to address the problem, in this paper, we propose a Curriculum Learning-based method for Ethereum phishing detection. We incorporate the Local Outlier Factor to measure the difficulty of nodes, considering the significant feature differences among nodes of the same class. By assigning lower difficulty values to easily identifiable nodes and higher difficulty values to nodes involved in mixed-class transactions, we ensure an effective difficulty measure. Then we gradually increase the number of training nodes input into Graph Convolutional Network in each epoch based on a certain ratio determined by the sorted difficulty scores. Finally, we employ LightGBM as the classifier for identifying phishing nodes. Experimental evaluations on a real-world Ethereum phishing scam dataset demonstrate the superiority of our method over baseline approaches, as evidenced by several evaluation metrics.

关键词： Training Measurement Learning systems Graph convolutional networks Federated learning Phishing Smart contracts

来源：评论

学校读者我要写书评

暂无评论

Ranking on Heterogeneous Manifold for Multimodal Information Retrieval 21

Ranking on Heterogeneous Manifold for Multimodal Information...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on big data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Jin, Zhenkun Wan, Xingshi Nie, Xin Zhou, Xinlei Yi, Yuanyuan Zhou, Gefei Wuhan Business University Wuhan Research Institute of Posts and Telecommunications Wuhan China Wuhan Research Institute of Posts and Telecommunications Wuhan China Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Wuhan China Huazhong University of Science and Technology School of Journalism and Information Communication Wuhan China Huazhong University of Science and Technology School of Computer Science & Technology Wuhan China

ISBN: (纸本)9798350329223

In light of recent advancements in Internet of Multimedia Things (IoMT) and 5G technology, both the variety and quantity of data have been rapidly increasing. Consequently, handling zero-shot cross-modal retrieval (ZSCMR) of unlabeled multi-modal data has emerged as a prominent research topic. Early models utilized generative adversarial networks and class embeddings to assist in building a common feature space. However, this approach resulted in a loss of reliability in the feature distributions of individual modalities. In this paper, we propose a method called Ranking on Heterogeneous Manifold (RHM) to address the aforementioned issue. Our model comprises three feature extractors, each dedicated to extracting features from text, images and multimodal data. Subsequently, the relationship structures derived from these feature extractors are employed to construct a heterogeneous manifold. A diffusion process is then conducted on this heterogeneous manifold, ultimately yielding the final ranking scores. Comprehensive experiments demonstrate that the proposed modal has the capability to acquire more effective knowledge representation, thus enhancing the effectiveness of ZSCMR. © 2023 IEEE.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

data center Energy Consumption Prediction Model Based on Deep Neural Network BiLSTM

Data Center Energy Consumption Prediction Model Based on Dee...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Junqiang Zhou Yan Wang JieFeng Lil College of Computer Science Inner Mongolia University Hohhot 010021 China Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

With the rapid development of big data and artificial intelligence technologies, a variety of high-performance plat-forms and applications in data centers have significantly increased their energy consumption and operating costs. Energy consumption prediction plays an important role in the optimization and management of energy consumption in data centers. Due to the complexity of power system, there are many complex correlations between various energy consumption parameters and prediction results. In order to improve the accuracy of energy consumption prediction, in this paper, a new prediction model based on BiLSTM is proposed, name SLCOA-BiLSTM (Saltation learning-based coati optimization algorithm and Bi-directionallong short-term memory). Aiming at the minimum prediction error, the model adopts the improved coati optimization algorithm (SLCOA) to optimize the BiLSTM network's learning rate, lstm_layers number, number of units and dropout. In the process of optimization, in order to solve the shortcomings of coati optimization algorithm, Sobol sequence initialization and Salation learning are improved. The experiments are carried out based on the real-time energy consumption data of a data center, and the results show that the model is superior to the relative comparison model in terms of prediction error. Since SLCOA-BiLSTM predicts are stable and accurate, it can be used as an effective tool to solve energy consumption problems.

关键词： Energy consumption data centers Accuracy Computational modeling Software algorithms Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Revenue and User Traffic Maximization in Mobile Short-Video Advertising 21

Revenue and User Traffic Maximization in Mobile Short-Video ...

引用

21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022

作者： Ran, Dezhi Zheng, Weiqiang Li, Yunqi Bian, Kaigui Zhang, Jie Deng, Xiaotie School of Computer Science Peking University China Department of Computer Science Yale University United States School of Computer Science National Engineering Laboratory for Big Data Analysis and Applications Peking University China Electronics and Computer Science University of Southampton United Kingdom Center on Frontiers of Computing Studies Peking University China

ISBN: (纸本)9781713854333

A new mobile attention economy has emerged with the explosive growth of short-video apps such as TikTok. In this internet market, three types of agents interact with each other: the platform, influencers, and advertisers. A short-video platform encourages its influencers to attract users by creating appealing content through short-form videos and allows advertisers to display their ads in short-form videos. There are two options for the advertisers: one is to bid for platform advert slots in a similar way to search engine auctions;the other is to pay an influencer to make engaging short videos and promote them through the influencer's channel. The second option will generate a higher conversion ratio if advertisers choose the right influencers whose followers match their target market. Although displaying influencer ads will generate less revenue, it is more engaging than platform ads, which is better for maintaining user traffic. Therefore, it is crucial for a platform to balance these factors by establishing a sustainable business agreement with its influencers and advertisers. In this paper, we develop a two-stage solution for a platform to maximize short-term revenue and long-term user traffic maintenance. In the first stage, we estimate the impact of user traffic generated by displaying influencer ads and characterize the user traffic the platform should allocate to influencers for overall revenue maximization. In the second stage, we devise an optimal (1 - 1/e)-competitive algorithm for ad slot allocation. To complement this analysis, we examine the ratio of the revenue generated by our online algorithm to the optimal offline revenue. Our simulation results show that this ratio is 0.94 on average, which is much higher than (1 - 1/e) and outperforms four baseline algorithms. © 2022 International Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Dual Contrastive Learning Model for Representation Learning and Background Debiasing in SAR Object Classification

Dual Contrastive Learning Model for Representation Learning ...

引用

2023 SAR in big data Era, bigSARdata 2023

作者： Wang, Jing Tian, Sirui Feng, Xiaolin Zhang, Bo Wu, Fan Wang, Chao School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China International Research Center of Big Data for Sustainable Development Goals Beijing100094 China Aerospace Information Research Institute Chinese Academy of Sciences Key Laboratory of Digital Earth Science Beijing100094 China

ISBN: (纸本)9798350326239

As a popular representation learning framework, contrastive learning has been widely used in SAR image interpretation for feature extraction. Recent studies have shown that some features obtained by the model are related to the background information due to the spurious correlation of the backgrounds during the SAR data collection. As a result, the generalization ability of the representation learning model will be greatly affected by the background information and cannot satisfy the requirements of practical applications. This paper constructed a multi-branch dual contrastive learning model that simultaneously compares the similarities between objects and backgrounds of various images. The motivation is to alleviate the impact of the spurious correlation between background information and the object category. The experimental results and interpretable Shapley value demonstrated that the proposed method significantly improved the generalization performance of the SAR object classification algorithm. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enhanced Federated Learning for Secure and Intelligent Consumer Electronics : An Overview

引用

IEEE Consumer Electronics Magazine 2025年

作者： Zhu, Chenlu Wang, Shuilong Fan, Xiaoxuan Deng, Xianjun Liu, Shenghao He, Yuanyuan Wu, Celimuge Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China The University of Electro-Communications China

With the rapid advancement of Artificial Intelligence (AI) and Internet of Things (IoT), consumer electronics have become essential in daily life. However, these devices generate and store vast amounts of personal data, posing significant security threats. Federated learning, a distributed machine learning method, protects user privacy by training models collaboratively without sharing raw data. However, it still faces numerous challenges. To further enhance data security, the integration of blockchain technology is crucial. Blockchain's decentralized and immutable characteristics enable secure data sharing and privacy protection in consumer electronics. This paper analyzes the application of federated learning in consumer electronics, examines how blockchain can enhance federated learning, and discusses future research directions. The primary contributions of this paper include a detailed application of blockchain-enhanced federated learning in consumer electronics, intended to serve as a reference for future research. © 2012 IEEE.

关键词： Federated learning

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：