检索结果-内蒙古大学图书馆

International Conference on Automation and computing (ICAC)

作者： Zihan Huang Jin Jin Chaolong Zhang Zhijie Xu Yuanping Xu Chao Kong Qin Wen Dan Tang School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing & Engineering University of Hudderseld Queensgate Hudderseld UK College of artificial intelligence Neijiang Normal University

Deep learning models find extensive applications across various domains. However, their large number of parameters, high storage requirements, and computational overhead pose challenges for deploying these models on resource-constrained embedded devices. This study focuses on addressing this issue by exploring techniques to optimize and deploy lightweight models on embedded devices. The approach involves optimization and adjustment of the model, followed by model conversion, quantization, and quantization calibration, aimed at reducing model size and improving inference speed. Notably, improvements are made to the quantization calibration algorithm to mitigate accuracy loss caused by model quantization. The experimental results demonstrate that light quantization significantly reduces model size, facilitating storage on embedded devices. Although there is a slight reduction in accuracy, the inference speed is substantially improved, enabling real-time human face recognition in video scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Speckle Noise Suppression Method Based on Quality Map

A Speckle Noise Suppression Method Based on Quality Map

引用

International Conference on Automation and computing (ICAC)

作者： Chengxin Zhong Chao Kong Chaolong Zhang Yuanping Xu Zhijie Xu Tukun Li Jin Jin Qin Wen School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing & Engineering University of Hudderseld Queensgate Hudderseld UK College of artificial intelligence Neijiang Normal University

Digital holography is a technique for measuring the shape of an object in 3D. It uses interference patterns generated by a laser or other light source, which record both the phase and intensity information of the light reflected from the surface of the object. This information is then encoded into digital holograms and reconstructed using computational methods to produce a 3D shape of the object. In the process of digital holography measurement, due to the high coherence of the laser, a large amount of speckle noise is generated when measuring rough surfaces due to diffuse reflection, leading to errors in the reconstruction results. Although traditional phase filtering has a good effect on noise filtering, it may cause distortion of normal phase. In order to suppress speckle noise, this study compared the common quality maps, proposed a local threshold adaptive speckle noise extraction method based on quality maps, and finally obtained the correct phase map by restoring the speckle noise points.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Redundant Data Detection and Deletion to Meet Privacy Protection Requirements in Blockchain-Based Edge computing Environment

引用

China Communications 2024年第3期21卷 149-159页

作者： Zhang Lejun Peng Minghui Su Shen Wang Weizheng Jin Zilong Su Yansen Chen Huiling Guo Ran Sergey Gataullin Cyberspace Institute Advanced Technology Guangzhou UniversityGuangzhou 510006China College of Information Engineering Yangzhou UniversityYangzhou 225127China School Math&Computer Science Quanzhou Normal UniversityQuanzhou 362000China Computer Science Department City University of Hong KongHong Kong 999077China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 21004China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Department of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou 325035China Guangzhou University Library Guangzhou UniversityGuangzhou 510006China Central Economic and Mathematics Institute Russian Academy of Sciences MIREA-Russian Technological University Moscow RegionRussia

With the rapid development of information technology,IoT devices play a huge role in physiological health data *** exponential growth of medical data requires us to reasonably allocate storage space for cloud servers and edge *** storage capacity of edge nodes close to users is *** should store hotspot data in edge nodes as much as possible,so as to ensure response timeliness and access hit rate;However,the current scheme cannot guarantee that every sub-message in a complete data stored by the edge node meets the requirements of hot data;How to complete the detection and deletion of redundant data in edge nodes under the premise of protecting user privacy and data dynamic integrity has become a challenging *** paper proposes a redundant data detection method that meets the privacy protection *** scanning the cipher text,it is determined whether each sub-message of the data in the edge node meets the requirements of the hot *** has the same effect as zero-knowledge proof,and it will not reveal the privacy of *** addition,for redundant sub-data that does not meet the requirements of hot data,our paper proposes a redundant data deletion scheme that meets the dynamic integrity of the *** use Content Extraction Signature(CES)to generate the remaining hot data signature after the redundant data is *** feasibility of the scheme is proved through safety analysis and efficiency analysis.

关键词： blockchain data integrity edge computing privacy protection redundant data

来源：评论

学校读者我要写书评

暂无评论

A Novel Multi-layered Minutiae Extractor Based on OCT Fingerprints 16th

A Novel Multi-layered Minutiae Extractor Based on OCT Finge...

引用

16th Chinese Conference on Biometric Recognition, CCBR 2022

作者： Zeng, Wenfeng Zhang, Wentian Liu, Feng Tan, Xu Li, Qin College of Computer Science and Software Engineering Shenzhen University Shenzhen China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Senzhen China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Software Engineering Shenzhen Institute of Information Technology Shenzhen China

ISBN: (纸本)9783031202322

Fingerprints of Optical Coherence Tomography (OCT) imaging provide 3D volume data which have the nature property of multi-layered tissue structure. This paper, for the first time, attempts to extract minutiae for OCT-based fingerprint by making full use of the merits multi-layered structure of OCT imaging and powerful convolution al neural network (CNN). In particular, a novel multi-layered feature fusion minutiae extraction network is proposed, involving a multi-layered feature extractor to integrate the rich information of multiple subsurface fingerprints, and a two-stage object detection framework using reweighted concatenation feature to detect minutiae points. Compared with the results achieved by typical traditional and learning-based methods, our method outperforms the best one by about 2% of F1-score in minutiae extraction, and achieves the improvement of 0.09% than the best one in matching performance, which further demonstrate the effectiveness and robustness of our proposed method. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

MADDPG-Based Power Control Strategy for Unmanned Vehicles

MADDPG-Based Power Control Strategy for Unmanned Vehicles

引用

IEEE International Conference on Smart Internet of Things (SmartIoT)

作者： Zhenyuan Han Lu Sun Liangtian Wan Ruoheng Luo Xianpeng Wang Institute of Information Science Technology Dalian Maritime University Dalian China School of Software Dalian University of Technology Dalian China Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University School of Information and Communication Engineering Hainan University Haikou China

ISBN: (数字)9798350366440

ISBN: (纸本)9798350366457

In the domain of unmanned vehicle networks, efficient spectrum utilization is crucial due to the scarcity of spectrum resources. This paper addresses the challenge of dynamic spectrum access by proposing an advanced strategy to enhance spectral efficiency in such networks. We present a novel approach that combines Multi-Agent Deep Deterministic Policy Gradient (MADDPG) with Echo State Networks (ESN) and prioritized experience replay mechanisms. Our approach focuses on optimizing the power control of unmanned vehicles to maximize overall spectral efficiency while maintaining communication quality for all vehicles. The proposed MADDPG_ESN algorithm integrates the ESN to effectively capture temporal dynamics and improve learning efficiency, and incorporates prioritized experience replay to optimize training stability and performance. This combination allows for rapid and accurate decision-making in the complex environment of unmanned vehicle communications. Our findings underscore the effectiveness of combining ESNs with prioritized experience replay in reinforcement learning for dynamic spectrum access, offering significant improvements in system performance and resource utilization.

关键词： Training Spectral efficiency Heuristic algorithms System performance Power control Dynamic spectrum access Solids Stability analysis Vehicle dynamics Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Directional Improvement Prediction for Dynamic Multiobjective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Ye, Yulong Liu, Songbai Zhou, Junwei Lin, Qiuzhen Jiang, Min Tan, Kay Chen College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China School of Informatics Xiamen University Fujian China Department of Computing The Hong Kong Polytechnic University Hong Kong China

In recent years, dynamic multiobjective evolutionary algorithms (DMOEAs) using the prediction strategy have shown promising performance for solving dynamic multiobjective optimization problems (DMOPs), as they can predict environmental changing trends in advance. However, most of them follow a regular change pattern and thus their performance is compromised when solving DMOPs with irregular change patterns (e.g., nonlinear correlations). To alleviate this challenge, this article proposes a DMOEA with a learnable prediction for tackling DMOPs. Specifically, a neural network is designed to effectively capture diverse change patterns of the environment. Based on the change patterns learned, a directional improvement prediction (DIP) is developed to guide the evolutionary search toward promising directions in the decision space. In this way, a superior initial population with good convergence and diversity is predicted by DIP, which can be more effective for solving various DMOPs. Comprehensive empirical studies show that the proposed DIP is effective and the proposed algorithm has some advantages over five competitive DMOEAs when solving three commonly used benchmarks and one real-world problem. IEEE

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

User Allocation in NOMA-Based Edge computing Environment

User Allocation in NOMA-Based Edge Computing Environment

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Congcong Dai Shaohua Cao Zijun Zhan Di Liu Danyang Zheng Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China

Due to an increasing amount of users, service providers are paying more attentions on how to properly tackle the User Allocation (UA) problem. In the literature, few solutions to the UA problem took into account the heterogeneity of devices and the complexity of the network. Therefore, the paper takes these two factors into account and studies the UA problem in Non-Orthogonal Multiple Access (NOMA)-Based heterogeneous edge computing scenarios. To solve the above problem, we propose the Heuristic Ant colony Systems (HAS) algorithm, which aims to enhance the number of allocated users while reducing the overall deadline violation time. Extensive evaluations that employ a public dataset demonstrate the benefits of our proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Specific Emitter Identification via Complex-valued Channel Attention Residual Prototypical Network

Few-Shot Specific Emitter Identification via Complex-valued ...

引用

IEEE International Conference on Smart Internet of Things (SmartIoT)

作者： Qichao Yu Liangtian Wan Yuan Tian Lu Sun Yunan Gao Xianpeng Wang School of Software Dalian University of Technology Dalian China Institute of Information Science Technology Dalian Maritime University Dalian China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China Guangdong Engineering Center for Social Computing and Mental Health School of Information and Communication Engineering Hainan University Haikou China

ISBN: (数字)9798350366440

ISBN: (纸本)9798350366457

Specific Emitter Identification (SEI) is a technique used to identify particular emitters by analyzing and comparing the unique characteristics of their radio signals. With the powerful data analysis capabilities of deep learning, it has been widely applied to many SEI tasks. However, the success of deep learning- based SEI methods depends on having a sufficient amount of labeled samples. In certain scenarios, it can be challenging to obtain a large quantity of labeled data. To address the limitation of requiring large labeled datasets, we propose a few- shot SEI method based on a Complex-valued Channel Attention Residual Prototypical Network (CCAR-ProtoNet). Specifically, in the feature embedding stage, CCAR-ProtoNet employs a complex-valued residual network, which effectively preserves both amplitude and phase information of the signal by utilizing complex-valued representations. Additionally, a channel attention mechanism is introduced to adaptively adjust the weights of different feature channels, emphasizing the most relevant features for the identification task. The residual structure also enables the model to train deeper networks, thereby obtaining richer feature representations and maintaining robust performance even in few-shot scenarios. Finally, the proposed method was validated on an ADS-B signal dataset, and simulation results demonstrate that under the 10-way-5-shot setting, this method exhibits superior feature embedding capabilities and improves identification accuracy and model robustness.

关键词： Resistance Attention mechanisms Simulation Neural networks Feature extraction Data models Stability analysis Robustness Signal to noise ratio Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Conflict-Free Genetic Algorithm with Nash Equilibrium Seeking for Game-Based Battery Swapping Station Recommendation

Conflict-Free Genetic Algorithm with Nash Equilibrium Seekin...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Chang-Long Sun Xin-Xin Xu Chun-Hua Chen Jun Hong Zhenan He Dengxiu Yu Sam Kwong Zhi-Hui Zhan School of Computer Science and Engineering South China University of Technology Guangzhou China School of Computer Science and Technology Ocean University of China Qingdao China School of Software Engineering South China University of Technology Guangzhou China College of Computer Science Sichuan University Chengdu China School of Artificial Intelligence Northwestern Polytechnical University Xi'an China Department of Computing and Decision Science Lingnan University Hong Kong SAR College of Artificial Intelligence Nankai University Tianjin China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

The rapid growth of electric vehicles (EVs) has led to significant challenges in providing efficient and sustainable charging solutions. This paper addresses the battery swapping station (BSS) recommendation problem by proposing a novel conflict-free genetic algorithm (CFGA) integrated with a Nash equilibrium seeking (NES) approach to identify optimal Nash equilibrium (ONE) solutions to such a non-cooperative optimization problem. The CFGA employs specialized crossover and mutation operators to generate offspring that satisfy the constraints of the problem, ensuring that each EV decides a unique battery swap strategy without conflict. Firstly, an order crossover operator is proposed to preserve the order of genes in the chromosomes. Secondly, a replacement and exchange mutation operator is proposed to enhance mutation diversity. The resulting optimal solution is then used as the initial strategy for the NES, which iteratively converges to the ONE. The proposed CFGA with NES algorithm is evaluated under both small-scale and large-scale cases, demonstrating its effectiveness in achieving a balance between costs for EVs and utilization for BSSs. The study's findings have practical implications for the smart grid and EV integration, offering a robust method for optimizing EV infrastructure and operations.

关键词： Costs Scalability Ecosystems Nash equilibrium Electric vehicles Batteries Smart grids Optimization Cybernetics Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Starfish optimization algorithm (SFOA): a bio-inspired metaheuristic algorithm for global optimization compared with 100 optimizers

引用

Neural computing and Applications 2025年第5期37卷 3641-3683页

作者： Zhong, Changting Li, Gang Meng, Zeng Li, Haijiang Yildiz, Ali Riza Mirjalili, Seyedali School of Civil Engineering and Architecture Hainan University Haikou570228 China Department of Engineering Mechanics State Key Laboratory of Structural Analysis Optimization and CAE Software for Industrial Equipment Dalian University of Technology Dalian116024 China Ningbo Institute of Dalian University of Technology No. 26 Yucai Road Jiangbei District Ningbo315016 China School of Civil Engineering Hefei University of Technology Hefei230009 China Jianghuai Advance Technology Center Hefei230000 China BIM for Smart Engineering Centre Cardiff School of Engineering Cardiff University Queen’s Buildings Whales CardiffCF24 3AA United Kingdom Department of Mechanical Engineering College of Engineering Bursa Uludağ University Görükle Bursa16059 Turkey Centre for Artificial Intelligence Research and Optimisation Torrens University Australia Brisbane Australia University Research and Innovation Center Obuda University Budapest1034 Hungary

This work presents the starfish optimization algorithm (SFOA), a novel bio-inspired metaheuristic for solving optimization problems, which simulates behaviors of starfish, including exploration, preying, and regeneration. SFOA consists of two main phases of exploration and exploitation. The exploration phase mimics the explorative behavior of starfish by the hybrid search pattern of combining with the five-dimensional and unidimensional search patterns to increase the computational efficiency and ensure the search capacity. The exploitation phase simulates the preying and regeneration behaviors of starfish, with a two-directional search strategy and special movement, to ensure convergence in exploitation. This work validates SFOA’s performance on 65 benchmark functions from classical functions, CEC 2017 and CEC 2022 test suites, and compares with 100 different metaheuristic algorithms, including state-of-the-art optimizers, such as marine predators algorithm, water flow optimizer (WFO), LSHADE, LSHADE-cnEpSin, and LSHADE-SPACMA. Statistical results from one-on-one comparisons demonstrate that the proposed SFOA outperforms 95 compared algorithms in accuracy and 97 algorithms in efficiency, which is only worse than WFO both in accuracy and efficiency. The scalability analysis also demonstrates that SFOA has the capacity to solve high-dimensional benchmark functions. Furthermore, ten real-world engineering optimization problems illustrate the effectiveness of SFOA to achieve global solutions and exhibit stable results. In conclusion, SFOA is promising for solving various optimization problems. The source code of SFOA is publicly available at: https://***/matlabcentral/fileexchange/173735-starfish-optimization-algorithm-sfoa. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Particle swarm optimization (PSO)

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：