检索结果-南通市图书馆

A comprehensive analysis of DAC-SDC FPGA low power object detection challenge

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8期67卷 300-320页

作者： Jingwei ZHANG Guoqing LI Meng ZHANG Xinye CAO Yu ZHANG Xiang LI Ziyang CHEN Jun YANG School of electronics Science and engineering Southeast University

The lower power object detection challenge(LPODC) at the IEEE/ACM Design Automation Conference is a premier contest in low-power object detection and algorithm(software)-hardware co-design for edge artificial intelligence, which has been a success in the past five years. LPODC focused on designing and implementing novel algorithms on the edge platform for object detection in images taken from unmanned aerial vehicles(UAVs), which attracted hundreds of teams from dozens of countries to participate. Our team SEUer has been participating in this competition for three consecutive years from 2020 to 2022 and obtained sixth place respectively in 2020 and 2021. Recently, we achieved the championship in 2022. In this paper, we presented the LPODC for UAV object detection from 2018 to 2022, including the dataset, hardware platform,and evaluation method. In addition, we also introduced and discussed the details of methods proposed by each year's top three teams from 2018 to 2022 in terms of network, accuracy, quantization method, hardware performance, and total score. Additionally, we conducted an in-depth analysis of the selected entries and results, along with summarizing representative methodologies. This analysis serves as a valuable practical resource for researchers and engineers in deploying the UAV application on edge platforms and enhancing its feasibility and reliability. According to the analysis and discussion, it becomes evident that the adoption of a hardware-algorithm co-design approach is paramount in the context of tiny machine learning(TinyML).This approach surpasses the mere optimization of software and hardware as separate entities, proving to be essential for achieving optimal performance and efficiency in TinyML applications.

关键词： tiny machine learning object detection convolutional neural networks algorithm-hardware co-design low power field programmable gate array

同方期刊数据库

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

在线全文

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 *** results validate our analysis and evaluate the performance of the learned policies.

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

A nano-plasmonic HMIM waveguide based concurrent dual-band BPF using circular ring resonator

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2024年第3期20卷 152-156页

作者： Miriyala Sridhar Surendra Kumar Bitra TS N Murthy Koppireddi Padmaraju department of electronics and Communication engineering Koneru Lakshmaiah Education FoundationGunturIndia Astra Microwave Products Ltd. HyderabadIndia department of electronics and Communication engineering JNTU-GV College of EngineeringVizianagaramIndia department of electronics and Communication engineering Jawaharlal Nehru Technological University KakinadaKakinadaIndia

This article analyzes the transmission line characteristics of plasmonic hybrid metal insulator metal(HMIM) wave-guide, circular ring resonator(CRR) based dual-band band-pass filters with two transmission poles in both pass-bands in the optical regime using coupled line feed. The transmission line characteristics of an HMIM waveguide, such as characteristic impedance(Z_(PV)), effective refractive index(n_(eff)) and propagation length(L_(spp)), have been obtained by using full wave simulation.

关键词： waveguide resonator circular

维普期刊数据库

Maximizing Solar Potential Using the Differential Grey Wolf Algorithm for PV System Optimization

在线全文

学校读者我要写书评

暂无评论

Energy engineering 2024年第8期121卷 2129-2142页

作者： Ezhilmathi Nagarathinam Buvana Devaraju Karthiyayini Jayamoorthy Padmavathi Radhakrishnan Santhana Lakshmi ChandraMohan Vijayakumar Perumal Karthikeyan Balakrishnan department of Electrical and electronics engineering Pandian Saraswathiyadav Engineering CollegeSivagangaiTamil Nadu630561India department of Electrical and electronics engineering Sri Balaji Chockalingam Engineering CollegeArniTamil Nadu632317India department of Information Science and engineering New Horizon College of EngineeringBangalore560103India department of Electrical and electronics engineering Rajalakshmi Engineering CollegeChennaiTamil Nadu602105India department of Electrical and electronics engineering Sona College of TechnologySalemTamil Nadu636005India School of electronics engineering Vellore Institute of TechnologyChennaiTamil Nadu600127India department of Electrical and electronics engineering Sri Krishna College of Engineering and TechnologyCoimbatoreTamil Nadu641008India

Maximum Power Point Tracking(MPPT)is crucial for maximizing the energy output of photovoltaic(PV)systems by continuously adjusting the operating point of the panels to track the point of maximum power production under changing environmental *** work proposes the design of an MPPT system for solar PV installations using the Differential Grey Wolf Optimizer(DGWO).It dynamically adjusts the parameters of the MPPT controller,specifically the duty cycle of the SEPIC converter,to efficiently track the Maximum Power Point(MPP).The proposed system aims to enhance the energy harvesting capability of solar PV systems by optimizing their performance under varying solar irradiance,temperature and shading *** results demonstrate the effectiveness of the DGWO-based MPPT system in maximizing the power output of solar PV installations compared to conventional MPPT *** research contributes to the development of advanced MPPT techniques for improving the efficiency and reliability of solar energy systems.

关键词： DGWO SEPIC converter MPPT PV module

Bioinspired 3D flexible devices and functional systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

National Science Review 2024年第3期11卷 271-295页

作者： Xu Cheng Zhangming Shen Yihui Zhang Applied Mechanics Laboratory Department of Engineering Mechanics Tsinghua University Laboratory of Flexible electronics Technology Tsinghua University

Flexible devices and functional systems with elaborated three-dimensional(3D) architectures can endow better mechanical/electrical performances, more design freedom, and unique functionalities, when compared to their two-dimensional(2D) counterparts. Such 3D flexible devices/systems are rapidly evolving in three primary directions, including the miniaturization, the increasingly merged physical/artificial intelligence and the enhanced adaptability and capabilities of heterogeneous *** challenges exist in this emerging research area, such as relatively poor controllability in the locomotion of soft robotic systems, mismatch of bioelectronic interfaces, and signal coupling in multi-parameter sensing. By virtue of long-time–optimized materials, structures and processes, natural organisms provide rich sources of inspiration to address these challenges, enabling the design and manufacture of many bioinspired 3D flexible devices/systems. In this Review, we focus on bioinspired 3D flexible devices and functional systems, and summarize their representative design concepts, manufacturing methods, principles of structure-function relationship and broad-ranging applications. Discussions on existing challenges, potential solutions and future opportunities are also provided to usher in further research efforts toward realizing bioinspired 3D flexible devices/systems with precisely programmed shapes,enhanced mechanical/electrical performances, and high-level physical/artificial intelligence.

关键词： bioinspired designs biomimetic 3D structures 3D flexible electronics 3D functional systems direct 3D manufacture 2D-to-3D assembly

Heating-Cooling Monitoring and Power Consumption Forecasting Using LSTM for Energy-Efficient Smart Management of Buildings: A Computational Intelligence Solution for Smart Homes

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 143-157页

作者： Omid Akbarzadeh Sahand Hamzehei Hani Attar Ayman Amer Nazanin Fasihihour Mohammad R.Khosravi Ahmed A.Solyman department of electronics and Telecommunications Politecnico di TorinoTurin 10129Italy department of Energy engineering Zarqa UniversityZarqa 13110Jordan Shandong Provincial University Laboratory for Protected Horticulture Weifang University of Science and TechnologyWeifang 262799China department of Electrical and electronics engineering Faculty of Engineering and ArchitectureNisantası UniversityIstanbul 25370The Republic of Turkiye

Energy management in smart homes is one of the most critical problems for the Quality of Life(QoL)and preserving energy *** of the relevant issues in this subject is environmental contamination,which threatens the world's *** computing-enabled Artificial Intelligence(Al)algorithms can provide impactful solutions to this *** research proposes using one of the Recurrent Neural Network(RNN)algorithms known as Long Short-Term Memory(LSTM)to comprehend how it is feasible to perform the cloud/fog/edge-enabled prediction of the building's *** parameters of power electricity,power heating,power cooling,and total power in an office/home in cold-climate cities are considered as our features in the *** on the collected data,we evaluate the LSTM approach for forecasting parameters for the next year to predict energy consumption and online monitoring of the model's performance under various *** implementing the Al predictive algorithm,several existing tools are *** results have been generated through simulations,and we find them promisingforfutureapplications.

关键词： design-builder Besos smart cities smart building neural network Long Short-Term Memory(LSTM)

An Improved Modulation Strategy for Single-phase Three-level Neutral-point-clamped Converter in Critical Conduction Mode

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Modern Power Systems and Clean Energy 2024年第3期12卷 981-990页

作者： Ning Li Yujie Cao Xiaokang Liu Yan Zhang Ruotong Wang Lin Jiang Xiao-Ping Zhang School of Electrical engineering Xi’an University of TechnologyXi’anChina the department of electronics Information and BioengineeringPolitecnico di MilanoMilanItaly Xi’an Jiaotong University Xi’anChina the department of Electrical engineering and electronics University of LiverpoolLiverpoolU.K. the department of Electronic Electrical and Systems EngineeringUniversity of BirminghamBirminghamU.K.

Two-level totem-pole power factor correction(PFC)converters in critical conduction mode(CRM)suffer from the wide regulation range of switching ***,in highfrequency applications,the number of switching times increases,resulting in significant switching *** solve these issues,this paper proposes an improved modulation strategy for the single-phase three-level neutral-point-clamped(NPC)converter in CRM with *** optimizing the discharging strategy and switching state sequence,the switching frequency and its variation range have been efficiently *** detailed performance analysis is also presented regarding the switching frequency,the average switching times,and the effect of voltage gain.A 2 k W prototype is built to verify the effectiveness of the proposed modulation strategy and analysis *** with the totem-pole PFC converter,the switching frequency regulation range of the three-level PFC converter is reduced by 36.48%and the average switching times is reduced by 45.10%.The experimental result also shows a 1.2%higher efficiency for the three-level PFC converter in the full load range.

关键词： Critical conduction mode(CRM) on-board charger switching frequency range switching times power factor correction(PFC) three-level converter

维普期刊数据库

Application of Response Surface Methodology for Analysing and Optimizing the Finned Solar Air Heater

在线全文

学校读者我要写书评

暂无评论

Journal of Thermal Science 2024年第3期33卷 985-1009页

作者： Vineet SINGH Vinod Singh YADAV Vaibhav TRIVEDI Manoj KUMAR Niraj KUMAR department of Mechanical engineering School of Engineering&TechnologyIFTM UniversityMoradabadUttar PradeshIndia department of Mechanical engineering NITUttarakhandPauriUttarakhandIndia department of electronics and Communication engineering Jaypee Institute of Information TechnologyNoidaUttar Pradesh201309India

In this research paper,a solar air heater with triangular fins has been experimentally analysed and ***,an experimental set-up of a solar air heater having triangular fins has been developed at the location of 28.10°N,78.23°*** heat transfer rate through fins and fins efficiency has been determined by the Finite Difference Method model *** experimental data and modeled data of response parameters have been optimized in MINITAB-17 software by the Response Surface Methodology *** creating the response surface design,three input parameters have been selected namely solar intensity,Reynolds number,and fin base-to-height *** range of solar intensity,Reynolds number,and fin base-to-height ratio is 600 to 1000W/m^(2),4000 to 6000,and 0.4 to 0.8 *** response surface design has been analyzed by calculating the outlet temperature,friction factor,Nusselt number,fin efficiency,thermal performance factor,and exergy *** optimum settings of input parameters:solar intensity is 1000 W/m^(2);Reynolds number is 4969.7,and the fin base to height ratio is 0.6060,on which these response:namely outlet temperature of 92.531℃,friction factor of 0.2350,Nusselt number of 127.761,thermal efficiency of 50.836%,thermal performance factor of 1.4947,and exergy efficiency of 8.762%.

关键词： solar air heater optimization fins exergy response surface methodology air

维普期刊数据库

Air-stable,all-dry transferred ReS_(2)/GaSe heterostructure-based NO_(2)gas sensor

在线全文

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2024年第1期168卷 79-87页

作者： A.Venkatesan Hyeyoon Ryu Anupom Devnath Hyungyu Yoo Seunghyun Lee department of Electronic engineering Kyung Hee UniversityYongin-Si 17104South Korea department of electronics and Information Convergence engineering Kyung Hee UniversityYongin-Si 17104South Korea

Two-dimensional(2D)materials have gained considerable attention in chemical sensing owing to their naturally high surface-to-volume ***,the poor response time and incomplete recovery re-strict their application in practical,high performance gas *** this work,we fabricated air-stable ReS_(2)/GaSe heterostructure-based NO_(2)gas sensors with excellent gas sensing response,recovery,selectiv-ity and a low limit of detection(LOD)toward nitrogen dioxide(NO_(2)).The ReS_(2)/GaSe heterostructure was prepared via mechanical exfoliation and an all-dry transfer *** the sensing measurements,temperature-dependant transport measurements were carried *** Schottky Barrier Height(SBH)of the ReS_(2)/GaSe heterostructure was calculated and the corresponding transport mechanisms were *** fabricated gas sensors showed a significant response enhancement with full reversibility to-ward ppm-level NO_(2)(response of∼17%at 3 ppm,a LOD of∼556 ppb)at an operating temperature of(33°C).In particular,the total response and recovery time of the ReS_(2)/GaSe was revealed to be less than 4 min(∼38 s and∼174 s,respectively)for the 250 ppm concentration,which is one of the best response and recovery time toward ppm-level NO_(2).The excellent sensing performances and recovery characteris-tics of the ReS_(2)/GaSe structure are attributed to its efficient charge separation,unique interlayer coupling and desirable band *** atomically thin,ultrasensitive gas sensor that operates at room tem-perature is a strong technological contender to conventional metal oxide gas sensors,which often require elevated temperatures.

关键词： 2D materials All-dry transfer Gas sensor Van der Waals heterostructure ReS_(2)/GaSe Gas sensing response Transition metal dichalcogenide