检索结果-南通市图书馆

FSCIL-EACA: Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education department Information Network Engineering research Center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Training Adaptation models Visualization Image recognition Prototypes Self-supervised learning Power capacitors

The Caching and Pricing Strategy for Information-Centric Networking with Advertisers’Participation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China Communications 2024年第3期21卷 283-295页

作者： Zheng Quan Yan Wenliang Wu Rong Tan Xiaobin Yang Jian Yuan Liu Xu Zhenghuan Laboratory for Future networks Department of AutomationUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China Suzhou Nuclear Power research Institute Suzhou 215004China National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data(NEL-PSRPC) China Academy of Electronics and Information Technology of CETCBeijing 100041China

As users’access to the network has evolved into the acquisition of mass contents instead of IP addresses,the IP network architecture based on end-to-end communication cannot meet users’***,the Information-Centric Networking(ICN)came into *** a technical point of view,ICN is a promising future network *** and customizing a reasonable pricing mechanism plays a positive role in promoting the deployment of *** current research on ICN pricing mechanism is focused on paid ***,we study an ICN pricing model for free content,which uses game theory based on Nash equilibrium to *** this work,advertisers are considered,and an advertiser model is established to describe the economic interaction between advertisers and ICN *** solution can formulate the best pricing strategy for all ICN entities and maximize the benefits of each *** extensive analysis and numerical results show that the proposed pricing framework is significantly better than existing solutions when it comes to free content.

关键词： advertisers cache free content Information-Centric Networking pricing strategy

Stackelberg Game for wireless Powered and Backscattering Enabled Sensor networks

在线全文

学校读者我要写书评

暂无评论

China Communications 2024年第3期21卷 189-204页

作者： Lyu Bin Cao Yi Wang Shuai Guo Haiyan Hao Chengyao Key Laboratory of Ministry of Education in Broadband wireless Communication and Sensor Network Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China Jiangsu Engineering research Center of Novel Optical Fiber Technology and Communication Network Suzhou 215006China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

This paper investigates a wireless powered and backscattering enabled sensor network based on the non-linear energy harvesting model, where the power beacon(PB) delivers energy signals to wireless sensors to enable their passive backscattering and active transmission to the access point(AP). We propose an efficient time scheduling scheme for network performance enhancement, based on which each sensor can always harvest energy from the PB over the entire block except its time slots allocated for passive and active information delivery. Considering the PB and wireless sensors are from two selfish service providers, we use the Stackelberg game to model the energy interaction among them. To address the non-convexity of the leader-level problem, we propose to decompose the original problem into two subproblems and solve them iteratively in an alternating manner. Specifically, the successive convex approximation, semi-definite relaxation(SDR) and variable substitution techniques are applied to find a nearoptimal solution. To evaluate the performance loss caused by the interaction between two providers, we further investigate the social welfare maximization problem. Numerical results demonstrate that compared to the benchmark schemes, the proposed scheme can achieve up to 35.4% and 38.7% utility gain for the leader and the follower, respectively.

关键词： backscatter communication energy interaction stackelberg game wireless powered sensor network

A Lightweight Intrusion Detection System Using Convolutional Neural Network and Long Short-Term Memory in Fog Computing

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第9期80卷 4703-4728页

作者： Hawazen Alzahrani Tarek Sheltami Abdulaziz Barnawi Muhammad Imam Ansar Yaser Computer Engineering department Interdisciplinary Research Center of Smart Mobility and LogisticsKing Fahd University of Petroleum and MineralsDhahran31261Saudi Arabia Computer Engineering department Interdisciplinary Research Center for Intelligent Secure SystemsKing Fahd University of Petroleum and MineralsDhahran31261Saudi Arabia Transportation research Institute(IMOB) Hasselt UniversityHasselt3500Belgium

The Internet of Things(IoT)links various devices to digital services and significantly improves the quality of our ***,as IoT connectivity is growing rapidly,so do the risks of network vulnerabilities and *** interesting Intrusion Detection Systems(IDSs)are presented based on machine learning(ML)techniques to overcome this *** the resource limitations of fog computing environments,a lightweight IDS is *** paper introduces a hybrid deep learning(DL)method that combines convolutional neural networks(CNN)and long short-term memory(LSTM)to build an energy-aware,anomaly-based *** test this system on a recent dataset,focusing on reducing overhead while maintaining high accuracy and a low false alarm *** compare CICIoT2023,KDD-99 and NSL-KDD datasets to evaluate the performance of the proposed IDS model based on key metrics,including latency,energy consumption,false alarm rate and detection rate *** findings show an accuracy rate over 92%and a false alarm rate below 0.38%.These results demonstrate that our system provides strong security without excessive resource *** practicality of deploying IDS with limited resources is demonstrated by the successful implementation of IDS functionality on a Raspberry Pi acting as a Fog *** proposed lightweight model,with a maximum power consumption of 6.12 W,demonstrates its potential to operate effectively on energy-limited devices such as low-power fog nodes or edge *** prioritize energy efficiency whilemaintaining high accuracy,distinguishing our scheme fromexisting *** experiments demonstrate a significant reduction in false positives,ensuring accurate identification of genuine security threats while minimizing unnecessary alerts.

关键词： Intrusion detection fog computing CNN LSTM energy consumption

Advances in neuromorphic computing:Expanding horizons for AI development through novel artificial neurons and in-sensor computing

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第3期33卷 1-23页

作者：杨玉波赵吉哲刘胤洁华夏扬王天睿郑纪元郝智彪熊兵孙长征韩彦军王健李洪涛汪莱罗毅 department of Electronic Engineering Tsinghua UniversityBeijing 100084China Beijing National research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China

AI development has brought great success to upgrading the information *** the same time,the large-scale artificial neural network for building AI systems is thirsty for computing power,which is barely satisfied by the conventional computing *** the post-Moore era,the increase in computing power brought about by the size reduction of CMOS in very large-scale integrated circuits(VLSIC)is challenging to meet the growing demand for AI computing *** address the issue,technical approaches like neuromorphic computing attract great attention because of their feature of breaking Von-Neumann architecture,and dealing with AI algorithms much more parallelly and energy *** by the human neural network architecture,neuromorphic computing hardware is brought to life based on novel artificial neurons constructed by new materials or *** it is relatively difficult to deploy a training process in the neuromorphic architecture like spiking neural network(SNN),the development in this field has incubated promising technologies like in-sensor computing,which brings new opportunities for multidisciplinary research,including the field of optoelectronic materials and devices,artificial neural networks,and microelectronics integration *** vision chips based on the architectures could reduce unnecessary data transfer and realize fast and energy-efficient visual cognitive *** paper reviews firstly the architectures and algorithms of SNN,and artificial neuron devices supporting neuromorphic computing,then the recent progress of in-sensor computing vision chips,which all will promote the development of AI.

关键词： neuromorphic computing spiking neural network(SNN) in-sensor computing artificial intelligence

Design of Protograph LDPC-Coded MIMO-VLC Systems with Generalized Spatial Modulation

在线全文

学校读者我要写书评

暂无评论

China Communications 2024年第3期21卷 118-136页

作者： Dai Lin Fang Yi Guan Yongliang Mohsen Guizani School of Information Engineering Guangdong University of TechnologyGuangzhou 51006China The State Key Laboratory of Integrated Services networks Xidian UniversityXi’an 710126China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore department of Machine Learning Mohamed Bin Zayed University of Artificial Intelligence(MBZUAI)Abu DhabiUnited Arab Emirates

This paper investigates the bit-interleaved coded generalized spatial modulation(BICGSM) with iterative decoding(BICGSM-ID) for multiple-input multiple-output(MIMO) visible light communications(VLC). In the BICGSM-ID scheme, the information bits conveyed by the signal-domain(SiD) symbols and the spatial-domain(SpD) light emitting diode(LED)-index patterns are coded by a protograph low-density parity-check(P-LDPC) code. Specifically, we propose a signal-domain symbol expanding and re-allocating(SSER) method for constructing a type of novel generalized spatial modulation(GSM) constellations, referred to as SSERGSM constellations, so as to boost the performance of the BICGSM-ID MIMO-VLC ***, by applying a modified PEXIT(MPEXIT) algorithm, we further design a family of rate-compatible P-LDPC codes, referred to as enhanced accumulate-repeat-accumulate(EARA) codes,which possess both excellent decoding thresholds and linear-minimum-distance-growth property. Both analysis and simulation results illustrate that the proposed SSERGSM constellations and P-LDPC codes can remarkably improve the convergence and decoding performance of MIMO-VLC systems. Therefore, the proposed P-LDPC-coded SSERGSM-mapped BICGSMID configuration is envisioned as a promising transmission solution to satisfy the high-throughput requirement of MIMO-VLC applications.

关键词： bit-interleaved coded modulation generalized spatial modulation multiple-input multipleoutput protograph LDPC codes visible light communication

Mixed H_(∞)/Passive Exponential Synchronization for Delayed Memristive Neural networks with Switching Event-Triggered Control

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第1期37卷 294-317页

作者： WU Wenhuang GUO Lulu CHEN Hong Shanghai research Institute for Intelligent Autonomous Systems Tongji UniversityShanghai 200092China department of Control Science and Engineering Tongji UniversityShanghai 201804China

This paper is devoted to event-triggered synchronization of delayed memristive neural networks with H∞and passivity *** aim is to guarantee the exponential synchronization and mixed H∞and passivity control for memristive neural networks by using event-triggered ***,a switching system is constructed under the event-triggered control ***,by adopting a piece-wise Lyapunov functional,a sufficient condition is established for the exponential synchronization and mixed H_(∞)and passivity ***,an event-triggered controller design scheme is proposed using matrix decoupling ***,the effectiveness of the designed controller is exemplified by a numerical example.

关键词： Event-triggered control exponential synchronization memristive neural networks time delays.

Super-resolution diffractive neural network for alloptical direction of arrival estimation beyond diffraction limits

在线全文

学校读者我要写书评

暂无评论

Light(Science & Applications) 2024年第8期13卷 1602-1614页

作者： Sheng Gao Hang Chen Yichen Wang Zhengyang Duan Haiou Zhang Zhi Sun Yuan Shen Xing Lin department of Electronic Engineering Tsinghua UniversityBeijing 100084China Beijing National research Center for Information Science and Technology Tsinghua UniversityBeijing 100084China

wireless sensing of the wave propagation direction from radio sources lays the foundation for communication,radar,navigation,***,the existing signal processing paradigm for the direction of arrival estimation requires the radio frequency electronic circuit to demodulate and sample the multichannel baseband signals followed by a complicated computing process,which places the fundamental limit on its sensing speed and energy ***,we propose the super-resolution diffractive neural networks(S-DNN)to process electromagnetic(EM)waves directly for the DOA estimation at the speed of *** multilayer meta-structures of S-DNN generate super-oscillatory angular responses in local angular regions that can perform the all-optical DOA estimation with angular resolutions beyond the diffraction *** spatial-temporal multiplexing of passive and reconfigurable S-DNNs is utilized to achieve high-resolution DOA estimation over a wide field of *** S-DNN is validated for the DOA estimation of multiple radio sources over 5 GHz frequency bandwidth with estimation latency over two to four orders of magnitude lower than the state-of-the-art commercial devices in *** results achieve the angular resolution over an order of magnitude,experimentally demonstrated with four times,higher than diffraction-limited *** also apply S-DNN’s edge computing capability,assisted by reconfigurable intelligent surfaces,for extremely low-latency integrated sensing and communication with low power *** work is a significant step towards utilizing photonic computing processors to facilitate various wireless sensing and communication tasks with advantages in both computing paradigms and performance over electronic computing.

关键词： beyond optical network

Special Topic on Near-Field Communication and Sensing Towards 6G

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

ZTE Communications 2024年第1期22卷 1-2页

作者： WEI Guo ZHAO Yajun CHEN Li 不详 the wireless and Computing Product R&D Institute ZTE Corporation department of Electronic Engineering and Information Science USTC

6G wireless technologies involve dense device deployment,utilize large-scale antenna arrays,and operate in the millimeter-wave and terahertz *** will shift the challenges of communication and sensing from the far field to the radiative near field,where traditional models and algorithms may incur errors or even become obsolete due to ***,there is an urgent need to discuss localization and communication issues in the near-field *** near-field assumption allows us to capture more information in electromagnetic signals,unlocking new possibilities for improving communication quality and localization *** can be anticipated that research on the near-field will play an increasingly important role in 6G and future wireless networks.

关键词： communication millimeter antenna