检索结果-内蒙古大学图书馆

Compressing Neural Networks on Limited Computing Resources

IEEE Access 2025年 13卷 80063-80075页

作者： Seunghyun Lee Dongjun Lee Minju Hyun Heeje Kim Byung Cheol Song Department of Electrical and Computer Engineering Inha University Incheon Republic of Korea

Network compression is a crucial technique for applying deep learning models to edge or mobile devices. However, the cost of achieving higher benchmark performance through compression is continuously increasing, making network compression a significant burden—especially for small industries focused on developing compact models. Specifically, existing network compression techniques often require extensive computational resources, rendering them impractical for edge devices and small-scale applications. To democratize network compression, we propose a general-purpose framework that combines novel filter pruning and knowledge distillation techniques. First, unlike conventional filter pruning methods based on static heuristics and costly neural architecture search (NAS)-based approaches, our method leverages meta-learning for rapid and fine examination of the importance of each gate. This enables rapid and stable sub-network discovery, significantly improving the pruning process. Second, to minimize the computational cost of knowledge distillation, we introduce a synthetic teacher assistant that leverages precomputed fixed knowledge—referring to the stored feature maps/logits of the teacher network. By leveraging fixed knowledge, we mitigate the cost incurred by the teacher network and facilitate the transmission of fixed knowledge to the student via synthetic teacher assistants, thereby preventing distribution collapse. Our proposed framework dramatically reduces the compression overhead while maintaining high accuracy, achieving a 55.2% reduction in FLOPs of ResNet-50 trained on ImageNet while preserving 76.2% top-1 accuracy with only 199 GPU hours—significantly lower than previous state-of-the-art methods. Overall, our framework democratizes deep learning compression by offering a cost-effective and computationally feasible solution, enabling broader adoption in low-resource environments.

关键词： Costs Knowledge engineering Logic gates filtering algorithms Graphics processing units Computational modeling Accuracy Image coding Deep learning Workstations

来源：评论

学校读者我要写书评

暂无评论

Wireless Networked Adaptive Active Noise Control With Online Secondary Path Modeling

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1078-1087页

作者： Chuang Shi Hao Yu Feiyu Du Mingzhe Li Le Zhang Institute of Sound and Vibration Research University of Southampton Southampton U.K. School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science City University of Hong Kong Hong Kong SAR China

Active noise control (ANC) has been developed over the years to mitigate unwanted noise. However, the fixed placement of electroacoustic components often limits ANC performance. To address this constraint, wireless networked ANC (WNANC) has been proposed, incorporating wireless communication among the electroacoustic components, allowing for freedom of movement during ANC operation. WNANC operates with a digital twin architecture, where adaptation of the control filter is managed by a cloud server, resolving the disadvantages of adaptive ANC in algorithm complexity and hardware cost. Nevertheless, the secondary path model remains crucial for WNANC. This paper introduces digital twin online secondary path modeling (DT-OSPM) algorithms for continuous secondary path estimation in WNANC. A key advantage of the DT-OSPM algorithms is their data-reuse capability, which decouples nested adaptive filters into sequential ones. Control filter adaptation occurs after the secondary path model is updated, resulting in improved convergence. Simulation and experiment results demonstrate the effectiveness and efficiency of the DT-OSPM algorithms in a feedforward WNANC system.

关键词： Noise Adaptive filters Digital twins filtering algorithms Adaptation models Wireless communication Wireless sensor networks Feedforward systems Convergence Vectors

来源：评论

学校读者我要写书评

暂无评论

TS-RePSO: A Three-Stage Feature Selection Method Combing ReliefF and PSO in Bioinformatics

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 640-652页

作者： Bin Pu Haining Wang Zhaozhao Xu Fangyuan Yang Xiangqiong Wu Jianguo Chen College of Computer Science and Electronic Engineering Hunan University Changsha China School of Software South China University of Technology GuangZhou China School of Computer Science and Technology Henan Polytechnic University Jiaozuo China Department of Gynecologic Oncology The First Affiliated Hospital of Henan Polytechnic University Jiaozuo China School of Software Engineering Sun Yat-Sen University Guangzhou China

The inherent characteristics of high-dimensional feature redundancy of biomedical data lead to the “curse of dimensionality” in bioinformatics, which brings new challenges to feature selection problems. Recently, the two-stage approach combining the filter and wrapper methods has become popular for feature selection tasks. However, these two-stage or previous one-stage algorithms suffer from blindness in the setting of thresholds, and the search methods tend to fall into local optimum solutions. To this end, we propose a three-stage feature selection method that combines ReliefF and Particle swarm optimization as a specific case, called TS-RePSO, including the filter stage, grouping stage, and wrapper stage. Specifically, in the filter stage, ReliefF is utilized to compute the weights of the features and sort them in descending order. In the grouping stage, the ranked features are grouped based on the density equalization strategy so that the weight of groups in all groups is equal. In the wrapper stage, the proposed grouping PSO is employed to search for the grouped features and select them according to the in-group and out-group evaluation strategies. Extensive experiments are conducted on 5 benchmark datasets and 6 real-world datasets, and experiment results show that the proposed method achieves the best performance.

关键词： filtering algorithms Classification algorithms Bioinformatics Particle swarm optimization Feature extraction Diseases Prediction algorithms Information filters Genetic algorithms Diversity reception

来源：评论

学校读者我要写书评

暂无评论

Partition-Based Cache Replacement to Manage Shared L2 Caches

引用

Chinese Journal of Electronics 2025年第3期23卷 464-467页

作者： Juan Fang Jing Wang Chengyan Li Zhicheng Yao Weimao Ke College of Computer Science Beijing University of Technology Beijing China College of Information Engineering Capital Normal University Beijing China College of Computing and Informatics Drexel University Chapel Hill NC USA

The Least recently used (LRU) replacement has been widely employed by on-chip shared caches. With the increase of cache associativity, the performance gap between LRU and theoretical optimal re-placement algorithm is significant, motivating us to design alternative replacement algorithms to improve cache performance. We propose a Partition-based cache replacement (PCR) algorithm to manage multi-core shared L2 caches. PCR takes into consideration recency and frequency information of cache access, and cache resource interference among multiple competing applications. PCR is effective to filter out the less frequently reused blocks through a dynamic insertion/promotion policy based on the target partitions, and ensures that some fraction of the working set is retained in the cache to contribute to more hits. Our evaluation shows that PCR improves performance of an 8-core system by an average of 11.3% over LRU-based cache.

关键词： Power demand Multicore processing Heuristic algorithms Education Interference filtering algorithms Information filters Partitioning algorithms System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Outlier-Aware Recursive Instantaneous Minimum Error Entropy Algorithm

引用

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2025年第6期55卷 4076-4090页

作者： Zhong, Shan Peng, Bei Wang, Ziyi He, Jiacheng Zhang, Kun Wang, Gang Univ Elect Sci & Technol China Sch Mech & Elect Engn Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

The minimum error entropy (MEE) criterion closely relies on the quadratic information potential (QIP) estimates of Renyi's entropy. Nevertheless, the conventional obtained QIP estimates are numerically unstable, especially when the error samples contain outliers, resulting in the optimal solution of the MEE criterion deviating from the target vector to a certain extent. To address this problem, we introduce the M-estimate method from robust statistics into the QIP estimation process;thus, a robust estimation method called instantaneous M-estimate QIP (IM-QIP) is proposed, and several important properties of IM-QIP are presented. The proposed IM-QIP estimates could be implemented simply while ensuring great robustness. Naturally, we further propose the corresponding instantaneous M-estimate MEE (IM-MEE) criterion and apply it to adaptive filtering. A robust recursive adaptive filtering algorithm, called the recursive IM-MEE (RIM-MEE) algorithm, is proposed and analyzed in this article, along with its stability and theoretical steady-state performance. Additionally, we demonstrate that the RIM-MEE algorithm achieves a smaller theoretical bound compared to the traditional MEE algorithm under heavy-tailed and skewed noise conditions. The simulation results revealed the robustness of the IM-QIP estimates and verified the theoretical expectations and superior performance of the RIM-MEE algorithm.

关键词： Estimation Signal processing algorithms Entropy Noise filtering Robustness Stability criteria filtering algorithms Probability density function Numerical stability M-estimate minimum error entropy (MEE) quadratic information potential (QIP) recursive adaptive filtering Renyi's entropy

来源：评论

学校读者我要写书评

暂无评论

Real Time Modeling and Control Algorithm of a Grid-Connected Battery Energy Storage System

Real Time Modeling and Control Algorithm of a Grid-Connected...

引用

IEEE Texas Power and Energy Conference (TPEC)

作者： Sepehr Karimi Solmaz Nazaralizadeh Anurag Srivastava Aboubakr Salem Parviz Famouri Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown USA Electrical and Computer Engineering Dept. WVU-IT Beckley USA PCS Eaton Pittsburgh PA USA

ISBN: (数字)9798331541125

ISBN: (纸本)9798331541132

This work develops real time model and associate control for a grid-tied battery energy storage system (BESS), based on the real industrial system specifications, 362kW/1499kWh lithium-ion BESS. An active and reactive power controller based on the dq reference frame is designed for the grid-tied inverter. To ensure system performance, an LCL filter with passive damping is also developed and analyzed. The system is tested using the Controller Hardware-in-the-Loop (CHIL) platform: Typhoon. The results demonstrate the controller's effective reference tracking across varying load conditions, with the filter design achieving a 3.3% output current THD, emphasizing the inverter's optimized performance.

关键词： Damping Reactive power Tropical cyclones Passive filters Battery energy storage system System performance filtering algorithms Real-time systems Inverters Load modeling

来源：评论

学校读者我要写书评

暂无评论

Innovative Median Finding Algorithm for Coherent Noise Removal in High Energy Physics Experiments

Innovative Median Finding Algorithm for Coherent Noise Remov...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Nicolas Guimarães Guilherme Aniya Bruno Sanches Irakli Mandjavidze Damien Neyret Wilhelmus Van Noije Department of Electronic Systems Engineering The School of Engineering (EPUSP) São Paulo Brazil IRFU CEA Gif-Sur-Yvette France

ISBN: (数字)9798331522124

ISBN: (纸本)9798331522131

Several high energy physics experiments suffer from coherent noise affecting their readout electronics. To solve that, the highly successful SAMPA chip is gaining a new successor, the SALSA front-end readout ASIC, which is going to be used in the EIC experiment of the Brookhaven National Laboratory, United States. This new integrated circuit is going to have a common mode noise subtraction, a non-linear filter that is based on finding median values between the many channels of the chip. To guarantee peak efficiency in the filter implementation, this work focuses on the filter's core: the median finder. This part needs to have an efficient algorithm to be implemented in hardware, therefore this paper shows three approaches, two of which are original techniques for digital median finding. These three designs were implemented and verified in TSMC 65nm technology and lastly they were compared in terms of speed, area, power consumption and a preliminary evaluation of error tolerance.

关键词： Integrated circuits High energy physics Power demand Circuits and systems Noise Layout filtering algorithms Hardware Digital filters Readout electronics

来源：评论

学校读者我要写书评

暂无评论

Novel Algorithm to Solve the Constrained Path-Based Testing Problem

Novel Algorithm to Solve the Constrained Path-Based Testing ...

引用

IEEE International Conference on Software Testing Verification and Validation Workshop, ICSTW

作者： Matej Klima Miroslav Bures Marek Miltner Chad Zanocco Gordon Fraser Sebastian Schweikl Patric Feldmeier Czech Technical University in Prague Czech Republic Stanford University California University of Passau Germany

ISBN: (数字)9798331534677

ISBN: (纸本)9798331534684

Constrained Path-based Testing (CPT) is a technique that extends traditional path-based testing by adding constraints on the order or presence of specific sequences of actions in the tests of System Under Test (SUT) processes. Through such an extension, CPT enhances the ability of the model to capture more real-life situations. In CPT, we define four types of constraints that either enforce or prohibit the use of a pair of actions in the resulting test set. We propose a novel Constrained Path-based Testing Composition (CPC) algorithm to solve the Constrained Path-based Testing Problem. We compare the results returned by the CPC algorithm with two alternatives, (1) the Filter algorithm, which solves the CPT problem in a greedy manner, and (2) the Edge algorithm, which generates a set of test cases that satisfy edge coverage. We evaluated the algorithms on 200 problem instances, with the CPC algorithm returning test sets (T) that have, on average, 350 edges, which is 2.4% and 11.1% shorter than the average number of edges in T returned by the Filter algorithm and the Edge algorithm, respectively. Regarding the compliance of the generated T with the constraints, the CPC algorithm produced T that satisfied the constraints in 95% of the cases, the Filter algorithm in 45% cases, and the Edge algorithm returned T that satisfied the constraints only for 6% SUT instances. Regarding the coverage of edges, the CPC algorithm returned test sets that contained, on average, 91.5% of edges in the graphs, while for T returned by the Filter algorithm, it was 90.8% edges. When comparing the average results of the edge coverage criterion and the fulfillment of the constraint criterion by individual algorithms, we consider the incomplete edge coverage achieved by the CPC algorithm and, at the same time, 95% fulfillment of the graph constraints to be a reasonable compromise.

关键词： Software testing Scalability Conferences Software algorithms Semantics Metaheuristics Employment Directed graphs filtering algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

Environment Perception and Spatial Localization algorithms in Virtual Reality

Environment Perception and Spatial Localization Algorithms i...

引用

Digital Analysis and Processing, Intelligent Computation (DAPIC), International Conference on

作者： Yetong Wang Bing Zheng Kongduo Xing Hainan Vocational University of Science and Technology Haikou Hainan China

ISBN: (数字)9798331536169

ISBN: (纸本)9798331536176

With the rapid development of virtual reality technology, environment perception and spatial localization algorithms have become an important technical foundation for improving the accuracy and inter activity of virtual experience. Environment perception mainly involves the perception and understanding of various objects and situations in the virtual environment, while spatial localization is the key technology to realize the precise positioning and action tracking of users in the virtual space. This paper reviews the research progress of environment perception and spatial localization in virtual reality, focusing on the current mainstream localization methods, including sensor-based localization technology, computer vision algorithms and their fusion technology. By analyzing the characteristics and application scenarios of various types of algorithms, the advantages and limitations of them in virtual reality are discussed. Especially in terms of multi-sensor fusion and real-time localization accuracy improvement, the paper proposes possible innovative directions. The article also discusses the role of emerging technologies, such as artificial intelligence and 5G communication, in promoting environment sensing and spatial localization algorithms, and looks forward to the future wide application in the fields of gaming, health care, and education. Significant progress has been made in current technologies, and high-precision, low-latency, and low-cost solutions remain the focus of future research.

关键词： Location awareness Accuracy Heuristic algorithms Virtual reality filtering algorithms Prediction algorithms Real-time systems User experience Sensors Kalman filters

来源：评论

学校读者我要写书评

暂无评论

EeNCache : Neighborhood Cooperative Content Caching and Delivery in Named Data Networks

EeNCache : Neighborhood Cooperative Content Caching and Deli...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Pankaj Chaudhary Neminath Hubballi Indian Institute of Technology Indore India

ISBN: (数字)9798331520960

ISBN: (纸本)9798331520977

Named Data Networking (NDN) offers in-network caching which helps to improve content delivery efficiency and minimizes bandwidth usage. However, cache being a prized commodity needs to be used judiciously. Hence, many studies propose different caching techniques aimed at improving content delivery. However, achieving a balance between good performance and overhead in real-world scenarios remains a challenge. In this paper, we outline a lightweight neighborhood cooperative searching and caching technique for NDN, named EeNCache. It cooperates with routers in the neighborhood to base its caching and searching decisions. This cooperation is achieved through routers periodically sharing their cache catalogue with their neighbors. This catalogue is maintained in the form of a Bloom filter data structure. In addition, EeNCache also uses a simple mechanism to cache popular content. The performance of EeNCache is evaluated on a large-scale network topology, comparing it with traditional and recent caching techniques using the Python-based Icarus simulator. Our findings demonstrate that cooperative caching yields better results in terms of cache hit ratio and content access time.

关键词： Cooperative caching Network topology Simulation Bandwidth filtering algorithms Data structures Topology Next generation networking

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：