检索结果-南通市图书馆

维普期刊数据库

Long Short-Term Memory Spiking Neural Networks for Classification of Snoring and Non-snoring Sound Events

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of electronics 2024年第3期33卷 793-802页

作者： Rulin ZHANG Ruixue LI Jiakai LIANG Keqiang YUE Wenjun LI Yilin LI electronics and information college Hangzhou Dianzi University

Snoring is a widespread occurrence that impacts human sleep quality.It is also one of the earliest symptoms of many sleep disorders.Snoring is accurately detected,making further screening and diagnosis of sleep problems easier.Snoring is frequently ignored because of its underrated and costly detection costs.As a result,this research offered an alternative method for snoring detection based on a long short-term memory based spiking neural network(LSTM-SNN) that is appropriate for large-scale home detection for snoring.We designed acquisition equipment to collect the sleep recordings of 54 subjects and constructed the sleep sound database in the home environment.And Mel frequency cepstral coefficients(MFCCs) were extracted from these sound signals and encoded into spike trains by a threshold encoding approach.They were classified automatically as non-snoring or snoring sounds by our LSTM-SNN model.We used the backpropagation algorithm based on an alternative gradient in the LSTM-SNN to complete the parameter update.The categorization percentage reached an impressive 93.4%,accompanied by a remarkable 36.9% reduction in computer power compared to the regular LSTM model.

关键词： Costs Databases Computational modeling Backpropagation algorithms Sleep apnea Encoding Recording

A survey of decision making in adversarial games

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第4期67卷 85-112页

作者： Xiuxian LI Min MENG Yiguang HONG Jie CHEN college of electronics and information Engineering Tongji University Shanghai Research Institute for Intelligent Autonomous Systems

In many practical applications, such as poker, chess, drug interdiction, cybersecurity, and national defense, players often have adversarial stances, i.e., the selfish actions of each player inevitably or intentionally inflict loss or wreak havoc on other players. Therefore, adversarial games are important in realworld applications. However, only special adversarial games, such as Bayesian games, are reviewed in the literature. In this respect, this study aims to provide a systematic survey of three main game models widely employed in adversarial games, i.e., zero-sum normal-form and extensive-form games, Stackelberg(security) games, and zero-sum differential games, from an array of perspectives, including basic knowledge of game models,(approximate) equilibrium concepts, problem classifications, research frontiers,(approximate) optimal strategy-seeking techniques, prevailing algorithms, and practical applications. Finally, promising future research directions are also discussed for relevant adversarial games.

关键词： adversarial games zero-sum games Stackelberg games differential games Nash equilibrium correlated equilibrium regret

Multi-junction cascaded vertical-cavity surface-emitting laser with a high power conversion efficiency of 74%

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Light(Science & Applications) 2024年第3期13卷 555-565页

作者： Yao Xiao Jun Wang Heng Liu Pei Miao Yudan Gou Zhicheng Zhang Guoliang Deng Shouhuan Zhou college of electronics and information Engineering Sichuan UniversityChengdu 610064China Suzhou Everbright Photonics Co. LtdSuzhou 215163China

High electro-optical conversion efficiency is one of the most distinctive features of semiconductor lasers as compared to other types of lasers.Its further increase remains a significant objective.Further enhancing the efficiency of edgeemitting lasers(EEL),which represent the highest efficiency among semiconductor lasers at present,is challenging.The efficiency of vertical cavity surface emitting lasers(VCSELs)has always been relatively low compared to EEL.This paper,combining modeling with experiments,demonstrates the potential of multi-junction cascaded VCSELs to achieve high efficiency beyond that of EELs,our simulations show,that a 20-junction VCSEL can achieve an efficiency of more than 88%at room temperature.We fabricated VCSEL devices with different numbers of junctions and compared their energy efficiency.15-junction VCSELs achieved a maximum efficiency of 74%at room temperature under nanosecond driving current,the corresponding differential quantum efficiency exceeds 1100%,being the largest electro-optical conversion efficiency and differential quantum efficiency reported until now for VCSELs.

关键词： cascaded power cavity

On the size generalizibility of graph neural networks for learning resource allocation

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

Science China(information Sciences) 2024年第4期67卷 239-254页

作者： Jiajun WU Chengjian SUN Chenyang YANG Beihang University School of electronics and information Engineering

Size generalization is important for learning resource allocation policies in wireless systems with time-varying scales. If a neural network for learning a wireless policy is not generalizable to the size of its input, it has to be re-trained whenever the system scale changes, which hinders its practical use due to the unaffordable training costs. Graph neural networks(GNNs) have been shown with size generalization ability empirically when optimizing resource allocation. Yet, are GNNs naturally size generalizable? In this paper,we argue that GNNs are not always size generalizable for resource allocation. We find that the aggregation and activation functions of the GNNs for learning a class of wireless policies play a key role in their size generalization ability. We take the GNN with the mean aggregator, called mean-GNN, as an example to reveal a size generalization condition. To demonstrate how to satisfy the condition, we learn power and bandwidth allocation policies for ultra-reliable low-latency communications and show that selecting or pretraining the activation function in the output layer of mean-GNN can make the GNN size generalizable.Simulation results validate our analysis and evaluate the performance of the learned policies.

关键词： size generalization graph neural networks resource allocation permutation equivariance

Acousto-optic modulator-based bi-frequency interferometer for quantum technology

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第2期22卷 186-191页

作者：李文奇邓琦琦郭学石李小英 college of Precision Instrument and Opto-electronics Engineering Key Laboratory of Opto-Electronics Information TechnologyMinistry of EducationTianjin UniversityTianjin 300072China

We demonstrate a high-performance acousto-optic modulator-based bi-frequency interferometer,which can realize either beating or beating free interference for a single-photon level quantum state.Visibility and optical efficiency of the interferometer are(99.5±0.2)%and(95±1)%,respectively.The phase of the interferometer is actively stabilized by using a dithering phase-locking scheme,where the phase dithering is realized by directly driving the acousto-optic modulators with a specially designed electronic signal.We further demonstrate applications of the interferometer in quantum technology,including bi-frequency coherent combination,frequency tuning,and optical switching.These results show the interferometer is a versatile device for multiple quantum technologies.

关键词： bi-frequency interferometer acousto-optic modulator quantum optics quantum manipulation

维普期刊数据库

Radiation build-up and dissipation in Raman random fiber laser

在线全文

学校读者我要写书评

暂无评论

Science China(information Sciences) 2024年第1期67卷 254-260页

作者： Shengtao LIN Zinan WANG Jiaojiao ZHANG Pan WANG Han WU Yifei QI Key Laboratory of Optical Fiber Sensing and Communications University of Electronic Science and Technology of China college of electronics and information Engineering Sichuan University

Raman random fiber laser(RRFL) is a complex physical system that arises from the distributed Raman amplification and the intrinsic stochasticity of fiber scattering.The analysis of the underlying lightwave kinetics at steady state has been the focus of considerable interest.However,the transient state,such as the RRFL build-up and dissipation,is particularly important for revealing the lightwave interaction process.Here,we investigate for the first time the RRFL dynamics at the transient state and track the RRFL temporal and spectral evolution theoretically and experimentally.Particularly,with the contribution of random distributed feedback,RRFL build-up exhibits continuous Verhulst logistic growth curves without cavity-related features,which is significantly different from the step-like growth curve of conventional fiber lasers.Furthermore,the radiation build-up duration is inversely related to the pump power,and the spectral evolution of the RRFL undergoes two phases,i.e.,from spectral density increase to spectral broadening.From the steady state to the pump switch-off state,the RRFL output power dissipates immediately,and the remaining Stokes lightwave from the Rayleigh scattering will gradually disappear after one round trip.This work provides new insights into the transient dynamic features of the RRFL.

关键词： random fiber laser stimulated Raman scattering transient phenomenon nonlinear optics łinebreak biological growth dynamics

Random Raman Fiber Laser as a Liquid Refractive Index Sensor

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Photonic Sensors 2024年第1期14卷 13-22页

作者： Bing HAN Yuxi MA Han WU Yong ZHAO college of information Science and Engineering Northeastern UniversityShenyang 110819China Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology Qinhuangdao 066004China college of electronics and information Engineering Sichuan UniversityChengdu 610064China

In this paper,a new concept of forward-pumped random Raman fiber laser(RRFL)-based liquid refractive index sensing is proposed for the first time.For liquid refractive index sensing,the flat fiber end immersed in the liquid can act as the point reflector for generating random fiber lasing and also as the sensing head.Due to the high sensitivity of the output power of the RRFL to the reflectivity provided by the point reflector in the ultralow reflectivity regime,the proposed RRFL is capable of achieving liquid refractive index sensing by measuring the random lasing output power.We theoretically investigate the effects of the operating pump power and fiber length on the refractive index sensitivity for the proposed RRFL.As a proof-of-concept demonstration,we experimentally realize high-sensitivity half-open short-cavity RRFL-based liquid refractive index sensing with the maximum sensitivity and the sensing resolution of-39.88W/RIU and 2.5075×10^(-5) RIU,respectively.We also experimentally verify that the refractive index sensitivity can be enhanced with the shorter fiber length of the RRFL.This work extends the application of the random fiber laser as a new platform for highly-sensitive refractive index sensing in chemical,biomedical,and environmental monitoring applications,etc.

关键词： Fiber optic sensors refractive index measurements fiber lasers Rayleigh scattering stimulated Raman scattering

Designing novel adaptive dynamic event-triggered protocols for uncertain multi-agent systems

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

Science China(information Sciences) 2024年第1期67卷 310-311页

作者： Bin CHENG Bin HE college of electronics and information Engineering Tongji University Frontiers Science Center for Intelligent Autonomous Systems

Multi-agent systems (MASs) have garnered widespread attention and have been investigated by numerous researchers in recent years, primarily due to their broad applications in industry, transportation, agriculture, and astronomy. While studying the cooperative control of MASs, numerous researchers place emphasis on reducing the frequency of communication among neighboring agents.

关键词： Directed graphs

Fractional-order heterogeneous memristive Rulkov neuronal network and its medical image watermarking application

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第5期33卷 306-314页

作者：丁大为牛炎张红伟杨宗立王金王威王谋媛 School of electronics and information Engineering Anhui UniversityHefei 230601China

This article proposes a novel fractional heterogeneous neural network by coupling a Rulkov neuron with a Hopfield neural network(FRHNN),utilizing memristors for emulating neural synapses.The study firstly demonstrates the coexistence of multiple firing patterns through phase diagrams,Lyapunov exponents(LEs),and bifurcation diagrams.Secondly,the parameter related firing behaviors are described through two-parameter bifurcation diagrams.Subsequently,local attraction basins reveal multi-stability phenomena related to initial values.Moreover,the proposed model is implemented on a microcomputer-based ARM platform,and the experimental results correspond to the numerical simulations.Finally,the article explores the application of digital watermarking for medical images,illustrating its features of excellent imperceptibility,extensive key space,and robustness against attacks including noise and cropping.

关键词： fractional order memristors Rulkov neuron medical image watermarking

维普期刊数据库