检索结果-内蒙古大学图书馆

Semantic knowledge transfer for semi-supervised medical image segmentation

Engineering Applications of Artificial Intelligence 2025年 158卷

作者： Shiwei Zhou Haifeng Zhao Leilei Ma Dengdi Sun Key Laboratory of Intelligent Computing & Signal Processing (ICSP) Ministry of Education Anhui University Hefei 230601 China Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University Hefei 230601 China School of Computer Science and Technology Anhui University Hefei 230601 China School of Artificial Intelligence Anhui University Hefei 230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei 230026 China

In semi-supervised medical image segmentation, due to possible differences in information content and distribution between labeled and unlabeled data, dealing with the two separately usually prevents knowledge transfer from labeled to unlabeled data. This prevents the model from effectively sharing learned information between the two types of data. To alleviate this problem, we train labeled and unlabeled data as a whole. Semantic mixing of labeled and unlabeled data is achieved by selecting and exchanging some of the region images of both through a mask to generate complementary input views. In addition, due to the limited labeled data, the unlabeled data has a weak ability to distinguish categories in the feature space. Traditional methods rely on pixel positions to generate positive and negative samples for contrastive learning to solve this problem, but relying on pixel position sampling can easily lead to semantic inconsistency, which affects the effect of feature learning; therefore, to address this problem, we propose an innovative labeled data-guided inter-class contrastive learning strategy, which extracts the category features from labeled and unlabeled data and exploits the accurate category information in the labeled data to guide contrastive learning, while introducing a similarity-based ranking weighting mechanism. Combining the two designs, we propose a new semantic knowledge transfer framework for semi-supervised medical image segmentation. Experiments demonstrate a significant improvement in our model compared to State of the Art (SOTA) on the Automatic Cardiac Diagnosis Challenge (ACDC) dataset and the Left Atrium (LA) dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Vision-Aided Beam Prediction Scheme for mmWave Wireless Communications

A New Vision-Aided Beam Prediction Scheme for mmWave Wireles...

引用

International Conference on Computer and Communications (ICCC)

作者： Ziqiang Ying Haojun Yang Jia Gao Kan Zheng Ministry of Education Intelligent Computing and Communications (IC2) Lab Wireless Signal Processing and Networks (WSPN) Lab Key Laboratory of Universal Wireless Communications Beijing University of Posts and Telecommunications (BUPT) Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

Beamforming is one of the most critical technologies for millimeter wave (mmWave) wireless communications. However, the classical beam selection methods generally require the large system overhead, such as frequent channel estimation. To this end, this paper proposes a new vision-aided beam prediction scheme based on object detection for mmWave wireless communications. In this scheme, the optimal beams are directly predicted based on the RGB images captured by cameras. Specifically, we first adopt the object detection model to locate the positions of all targeted users in the RGB images. Then, based on multilayer perceptron, an angle prediction model is used to estimate the angles between the users and the cameras. In addition, we select the optimal beam indexes from a pre-defined beam codebook according to the information of angle and codebook. Finally, the experimental results reveal that our proposed scheme has the lower overhead, higher accuracy and better scalability.

关键词： Wireless communication Scalability Object detection Predictive models Cameras Indexes Task analysis

来源：评论

学校读者我要写书评

暂无评论

Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems

arXiv

引用

arXiv 2025年

作者： Chen, Zheyi Huang, Sijin Min, Geyong Ning, Zhaolong Li, Jie Zhang, Yan College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian Key Laboratory of Network Fuzhou350002 China Computing and Intelligent Information Processing [Fuzhou University Fuzhou350116 China Department of Computer Science Faculty of Environment Science and Economy University of Exeter ExeterEX4 4QF United Kingdom School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Informatics University of Oslo Oslo0316 Norway

Mobile Edge computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we propose SR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear Programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposed SR-CL. Compared to benchmark methods, the SR-CL achieves superior convergence and delay performance under various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators

arXiv

引用

arXiv 2023年

作者： Cong, Runmin Yang, Wenyu Zhang, Wei Li, Chongyi Guo, Chun-Le Huang, Qingming Kwong, Sam Institute of Information Science Beijing Jiaotong University Beijing100044 China School of Control Science and Engineering Shandong University Jinan250061 China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan250061 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China College of Computer Science Nankai University Tianjin300350 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518055 China Department of Computer Science City University of Hong Kong Hong Kong City University of Hong Kong Shenzhen Research Institute Shenzhen51800 China

Due to the light absorption and scattering induced by the water medium, underwater images usually suffer from some degradation problems, such as low contrast, color distortion, and blurring details, which aggravate the difficulty of downstream underwater understanding tasks. Therefore, how to obtain clear and visually pleasant images has become a common concern of people, and the task of underwater image enhancement (UIE) has also emerged as the times require. Among existing UIE methods, Generative Adversarial Networks (GANs) based methods perform well in visual aesthetics, while the physical model-based methods have better scene adaptability. Inheriting the advantages of the above two types of models, we propose a physical model-guided GAN model for UIE in this paper, referred to as PUGAN. The entire network is under the GAN architecture. On the one hand, we design a Parameters Estimation subnetwork (Par-subnet) to learn the parameters for physical model inversion, and use the generated color enhancement image as auxiliary information for the Two-Stream Interaction Enhancement subnetwork (TSIE-subnet). Meanwhile, we design a Degradation Quantization (DQ) module in TSIE-subnet to quantize scene degradation, thereby achieving reinforcing enhancement of key regions. On the other hand, we design the Dual-Discriminators for the style-content adversarial constraint, promoting the authenticity and visual aesthetics of the results. Extensive experiments on three benchmark datasets demonstrate that our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics. The code and results can be found from the link of https://***/proj_***. © 2023, CC BY-NC-SA.

关键词： Discriminators

来源：评论

学校读者我要写书评

暂无评论

A Novel Technique for Solving Characteristic Modes of Large-Scale Finite Periodic Arrays

A Novel Technique for Solving Characteristic Modes of Large-...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： G. S. Cheng Huihui Li Z. X. Huang Ministry of Education Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

ISBN: (数字)9780996007894

ISBN: (纸本)9781728146331

An efficient characteristic mode solver is proposed for the solution of characteristic modes (CMs) of large-scale finite periodic arrays. Firstly, the CMs of an isolated reference element are obtained using the standard characteristic mode solver. Then, by choosing the first several CMs of the isolated reference element with larger mode significance (MS) to construct the entire domain basis functions, the proposed method can dramatically reduce the matrix dimension of the resultant generalized eigenvalue problem governed by the entire array structure, thereby significantly reduce the computational time and memory requirement.

关键词： Finite element analysis Eigenvalues and eigenfunctions Memory management Microwave antenna arrays Phased arrays

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-user Detection Scheme Based on CVA-SSAOMP Algorithm in Uplink Grant-Free NOMA

Dynamic Multi-user Detection Scheme Based on CVA-SSAOMP Algo...

引用

International Conference on Communication Technology (ICCT)

作者： Jian Zhang Shichao Bai Lei Xu Hongwei Zhang Hongyu Fang Xiaohui Li Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei China

In the uplink grant-free non-orthogonal multiple access (NOMA) scenario, since the active user at the sender has a structured sparsity transmission characteristic, the compressive sensing recovery algorithm is initially applied to the joint detection of the active user and the transmitted data. However, the existing compressive sensing recovery algorithms with unknown sparsity often require noise power or signal-to-noise ratio (SNR) as the priori conditions, which greatly reduces the algorithm adaptability in multi-user detection. Therefore, an algorithm based on cross validation aided structured sparsity adaptive orthogonal matching pursuit (CVA-SSAOMP) is proposed to realize multi-user detection in dynamic change communication scenario of channel state information (CSI). The proposed algorithm transforms the structured sparsity model into a block sparse model, and without the priori conditions above, the cross validation method in the field of statistics and machine learning is used to adaptively estimate the sparsity of active user through the residual update of cross validation. The simulation results show that, compared with the traditional orthogonal matching pursuit (OMP) algorithm, subspace pursuit (SP) algorithm and cross validation aided block sparsity adaptive subspace pursuit (CVA-BSASP) algorithm, the proposed algorithm can effectively improve the accurate estimation of the sparsity of active user and the performance of system bit error ratio (BER), and has the advantage of low-complexity.

关键词： Matching pursuit algorithms Heuristic algorithms signal processing algorithms Multiuser detection Machine learning algorithms Adaptation models Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Analysis of Asymptotically Tight Approximation SER for Cooperative NOMA Systems

Analysis of Asymptotically Tight Approximation SER for Coope...

引用

International Conference on Communication Technology (ICCT)

作者： Dingcheng Zhu Yijing Yao Lei Xu Hongwei Zhang Hongyu Fang Xiaohui Li Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei china

The closed-form formula derivation of the power domain cooperative Non-Orthogonal Multiple Access (NOMA) system is of great significance for further improving the performance of the system. However, the system performance formulas of the channel capacity and the paired bit error rate Pairwise Error Probability (PEP) are too complicated, which have increased the difficulty in system performance optimization. Therefore, based on the Amplify Forward (AF) relay cooperative NOMA model, the signal Interference Noise Ratio (SINR) formulas of the two weak-user nodes are constructed. Through the assumption of that, the Symbol Error Rate (SER) of each user is fair, the simplification condition of Moment Generating Function (MGF) with the harmonic mean form is satisfied. Combined with the SER calculation formula of MGF, the system SER asymptotically tight approximation formula with simple structure is derived at high signal-to-noise ratio (SNR). The Monte Carlo simulation results show that, the formula can accurately describe the SER performance of the power domain cooperative NOMA system with the non-ideal Successive Interference Cancellation (SIC) system when SNR is high. Under the condition of certain total power, the optimal power distribution factor is solved in order to minimize the total system SER.

关键词： Conferences Communications technology

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Compatibitility Analysis with Ultra-Wideband Simultaneous Switching Noise Suppression for Antenna-in-Package

Electromagnetic Compatibitility Analysis with Ultra-Wideband...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Hao-Ran Zhu Yu-Fa Sun Xian-Liang Wu Ministry of Education Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei China

ISBN: (数字)9780996007894

ISBN: (纸本)9781728146331

In this paper, a compact power distribution network (PDN) structure with ultra-wideband simultaneous switching noise (SSN) mitigation for antenna in package is presented. Only one spiral slot is etched on the square patch of the EBG pattern, which is constituted the presented PDN structure. The equivalent circuit model is developed to analyze the mechanism of the electromagnetic compatibility behavior that a high-impedance is provided for reducing the SSN coupling. An ultra-wideband SSN mitigation performance is obtained from 0.35 GHz to 20 GHz under the suppression level of -40 dB. Good agreements are observed between the simulated and measured results.

关键词： Periodic structures Metamaterials Spirals Switches Equivalent circuits Integrated circuit modeling Power systems

来源：评论

学校读者我要写书评

暂无评论

A Compact Circularly Polarized Mono-pulse Antenna with Frequency Agility

A Compact Circularly Polarized Mono-pulse Antenna with Frequ...

引用

Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL)

作者： Yan Xue Jie Wu Lihua Wang Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9781728153049

ISBN: (纸本)9781728153056

This paper presents a 1 × 4 circularly polarized patch antenna array with frequency agility. A compact 4-cell array patch antenna with low-profile (i.e., about 0.013λ 0 ) has been designed for circular polarization mono-pulse applications. By properly switching between the different states of these p-i-n diodes, four discrete operating frequency bands can be achieved. Circularly polarization can be achieved by the perturbation segment. A Rat-Race coupler based feed network is developed showing the high isolation between input terminals as well as efficient placement of sum and difference ports, including to generate sum and difference patterns for mono-pulse applications operating. Because of a suitable replacement of the sum and difference ports, the antenna radiation patterns were symmetrical. The simulated peak gains of the four discrete operating frequencies for 4.4 GHz, 4.7 GHz, 5.3 GHz and 5.6 GHz are 11.7 dBi, 12.0 dBi, 12.1 dBi, and 12.3 dBi, respectively. Both the null-depth at four different frequencies are less than -15 dBi. The simulation results show that the 3 dB axial ratio at four different center frequencies are 0.89 dB, 1.87 dB, 0.91 dB and 2.15 dB, respectively.

关键词： Antenna arrays Switches Patch antennas Pins Polarization Antenna radiation patterns

来源：评论

学校读者我要写书评

暂无评论

A Compact Bandpass Filter Using Novel Microstrip Dual-mode Resonator with Hexagonal Structure

A Compact Bandpass Filter Using Novel Microstrip Dual-mode R...

引用

Progress in Electromagnetics Research Symposium - Fall (PIERS - FALL)

作者： Xin-Yu Ning Han-Ran Zhu Zhi-Xiang Huang Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9781728153049

ISBN: (纸本)9781728153056

A dual-mode bandpass filter with miniaturized size is presented in this paper. A hexagonal microstrip dual-mode resonator is employed to reduce the size of the filter. A pair of tortuous parallel coupled input and output structures are used to introduce the transmission zeros, which can improve the selectivity and the stopband of the filter. Compared to other dual-mode resonator filters, a compact advantage is also achieved with the presented design. A sample circuit is fabricated with the thin film technology to validate the design. The size of the filter is 4.98 × 4.57mm 2 , which is equivalent to $0.147 \times 0.134\lambda _g^2$ at 8.75GHz. The prototype filter has a fractional bandwidth of 5.7%, a low passband insertion loss of 0.6dB. Moreover, excellent out-of-band rejection characteristics are achieved in the hexagonal dual mode filter. Four transmission zeros are generated in the stopband to improve out-of-band rejection, and out of-band rejection greater than 20dB can be achieved in the stopband below 15GHz. In addition, a size reduction of approximately 30% is observed when compared with miniaturized rectangular ring patch resonators, for the same center frequency.

关键词： Microstrip resonators Resonant frequency Optical ring resonators Filtering theory Passband Perturbation methods

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：