检索结果-南通市图书馆

Group-wise co.salient object detection via multi-view self-labeling novel class disco.ery

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of co.puter Science 2024年第2期18卷 259-261页

作者： Yang WU Gang DONG Lingyan LIANG Yaqian ZHAO Kaihua ZHANG Inspur Electronic information Industry co. Ltd.Beijing 100080China Jiangsu Key Laboratory of Big Data Analysis technology and Jiangsu co.laborative Innovation Center of Atmospheric Environment and Equipment technology Nanjing University of Information Science and TechnologyNanjing 210044China

1 Introduction co.salient object detection(co.OD)aims to extract the salient object(s)that are co.mon across a group of relevant images[1].Group-wise clue plays a crucial role in accurately predicting the co.salient ***,numerous groupwise deep models have been proposed by exploring co.sistency across images in unsupervised clustering manners[2-4]or the semantic co.nections guidance information[5].

关键词： co.sistency Group semantic

Optimizing theπ-Bridge of Non-fullerene Acceptors to Suppress Dark Current in NIR Organic Photodetectors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chemical Research in Chinese Universities 2024年第4期40卷 712-721页

作者： SHAO Lin HUANG Yijun HONG Ling XU Zishuo YANG Xiye LIU Chunchen HUANG Fei CAO Yong State Key Laboratory of Luminescent Materials and Devices Institute of Polymer Optoelectronic Materials and DevicesSchool of Materials Science and EngineeringSouth China University of TechnologyGuangzhou510640P.R.China Lumidar technology co. Ltd.Guangzhou510530P.R.China

Recently,the rapid development of non-fullerene acceptors(NFAs)has laid the foundation for performance improvements in near-infrared(NIR)organic photodetectors(OPDs).However,reducing the bandgap of NFAs to achieve strong absorption in the shorter-wave region usually leads to increased dark current density(J_(d))and decreased responsivity(R),severely limiting the detectivity(D*)of *** date,it remains challenging to manipulate the J_(d) of NIR-OPDs through rational structure engineering of ***,three NIR-NFAs,namely bis(2-decyltetradecyl)4,4′-(2′,7′-di-tert-butylspiro[cyclopenta[2,1-b:3,4-b′]dithiophene-4,9′-fluorene]-2,6-diyl)bis(6-(((Z)-1-(dicyanomethylene)-5,6-difluoro-3-oxo-1,3-dihydro-2H-inden-2-ylidene)methyl)thieno[3,4-b]thiophene-2-carboxylate)(TSIC-4F),bis(2-decyltetradecyl)6,6′-(2′,7′-di-tert-butylspiro[cyclopenta[2,1-b:3,4-b′]dithiophene-4,9′-fluorene]-2,6-diyl)bis(4-(((Z)-1-(dicyanomethylene)-5,6-difluoro-3-oxo-1,3-dihydro-2H-inden-2-ylidene)methyl)thieno[3,4-b]thiophene-2-carboxylate)(STIC-4F),and 2,2′-((2Z,2′Z)-(((2′,7′-di-tert-butylspiro[cyclopenta[2,1-b:3,4-b′]dithiophene-4,9′-fluorene]-2,6-diyl)bis(2,3-bis(5-(2-butyloctyl)thiophen-2-yl)thieno[3,4-b]pyrazine-7,5-diyl))bis(metha-neylylidene))bis(5,6-difluoro-3-oxo-2,3-dihydro-1H-indene-2,1-diylidene))dimalononitrile(TPIC-4F),were designed using the thieno[3,4-b]thiophene(TT)and thieno[3,4-b]pyrazine(TPy)derivatives as theπ-*** to the intramolecular S-S and S-N interactions,STIC-4F and TPIC-4F exhibited smaller backbone distortions than TSIC-4F.A significantly red-shifted absorption with a peak at 1015 nm was observed in TPIC-4F film,larger than that(ca.960 nm)for TSIC-4F and STIC-4F ***,OPDs operating in a photovoltaic mode were successfully fabricated,and TPIC-4F-based OPDs achieved the lowest J_(d) of 3.18×10^(-8) A/cm^(2) at-0.1 ***,although TPIC-4F-based OPDs exhibited the lowest R,higher shot-noise-limited specific detectivity(D_(sh)*)in 1000-1200 nm co

关键词： π-Bridge Near-infrared Non-fullerene acceptor Dark current Organic photodetector

Generative adversarial networks based motion learning towards robotic calligraphy synthesis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence technology 2024年第2期9卷 452-466页

作者： Xiaoming Wang Yilong Yang Weiru Wang Yuanhua Zhou Yongfeng Yin Zhiguo Gong Department of co.puter and information Science University of MacaoMacaoChina School of Software Beihang UniversityBeijingChina Department of co.puter Science and technology Faculty of Information TechnologyBeijing University of TechnologyBeijingChina School of Foreign Languages Guangzhou Huashang CollegeGuangzhouChina

Robot calligraphy visually reflects the motion capability of robotic *** traditional researches mainly focus on image generation and the writing of simple calligraphic strokes or characters,this article presents a generative adversarial network(GAN)-based motion learning method for robotic calligraphy synthesis(Gan2CS)that can enhance the efficiency in writing co.plex calligraphy words and reproducing classic calligraphy *** key technologies in the proposed approach include:(1)adopting the GAN to learn the motion parameters from the robot writing operation;(2)co.verting the learnt motion data into the style font and realising the transition from static calligraphy images to dynamic writing demonstration;(3)reproducing high-precision calligraphy works by synthesising the writing motion data *** this study,the motion trajectories of sample calligraphy images are firstly extracted and co.verted into the robot *** robot performs the writing with motion planning,and the writing motion parameters of calligraphy strokes are learnt with *** the motion data of basic strokes is synthesised based on the hierarchical process of‘stroke-radicalpart-character’.And the robot re-writes the synthesised characters whose similarity with the original calligraphy characters is *** calligraphy characters have been tested in the experiments for method validation and the results validated that the robot can actualise the robotic calligraphy synthesis of writing motion data with GAN.

关键词： calligraphy synthesis generative adversarial networks Motion learning robot writing

Intelligent proportioning model of co.verter scrap based on optimization algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Progress in Natural Science:Materials International 2024年第1期34卷 37-44页

作者： Chaojie Zhang Jinjun Cheng Liqiang Zhang Yingxue Wang Wei Zhang Jianwei Yuan Haichuan Wang School of Metallurgical Engineering Anhui University of Technology National Engineering Research Center for Public Safety Risk Perception and co.trol by Big Data(RPP) China Academic of Electronics and Information Technology Wuhu Xinxing Pipes co. Ltd.

Scrap is one of the main raw materials in co.verter steelmaking. Due to the wide variety of scrap and the significant differences in its prices, the proportioning of scrap presents a challenge in co.verter steelmaking. This paper explores the optimal proportioning method of scrap for co.verters using an optimization mathematical model. Initially, the melting characteristics of scrap after being added to the co.verter's molten iron were investigated using finite element numerical simulations. The study found that when the weight of the scrap is fixed, both the shape and type of the scrap significantly influence the melting time. Subsequently, employing mathematical optimization methods and co.sidering co.prehensive process parameters of the 210t co.verter smelting, including the co.position and unit price of the scrap, as well as the requirements of the co.verter steelmaking process for scrap, an optimization model for the proportioning of scrap in co.verters was *** model was solved using co.puter programming languages. Through this optimization model, it is possible to obtain the lowest co.t per ton of molten steel in the co.verter smelting process by determining the optimal proportions of various types of scrap.

关键词： scrap proportioning Optimization model co.verter steelmaking mathematical model numerical simulation

An Adaptive Hybrid Optimization Strategy for Resource Allocation in Network Function Virtualization

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

co.puter Modeling in Engineering & Sciences 2024年第2期138卷 1617-1636页

作者： Chumei Wen Delu Zeng School of Mathematics South China University of TechnologyGuangzhou510640China School of Electronic and information Engineering South China University of TechnologyGuangzhou510640China

With the rapid development of Network Function Virtualization(NFV),the problem of low resource utilizationin traditional data centers is gradually being ***,existing research does not optimize both localand global allocation of resources in data ***,we propose an adaptive hybrid optimization strategy thatco.bines dynamic programming and neural networks to improve resource utilization and service quality in *** approach enco.passes a service function chain simulation generator,a parallel architecture servicesystem,a dynamic programming strategy formaximizing the utilization of local server resources,a neural networkfor predicting the global utilization rate of resources and a global resource optimization strategy for bottleneck andredundant *** the implementation of our local and global resource allocation strategies,the systemperformance is significantly optimized through simulation.

关键词： NFV resource allocation decision-making optimization service function

Joint co.putation offloading and parallel scheduling to maximize delay-guarantee in co.perative MEC 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

Digital co.munications and Networks 2024年第3期10卷 693-705页

作者： Mian Guo Mithun Mukherjee Jaime Lloret Lei Li Quansheng Guan Fei Ji School of Electronics and information Guangdong Polytechnic Normal UniversityGuangzhouChina School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjingChina Universitat Politecnica de Valencia 46022ValenciaSpain South China University of technology China

The growing development of the Internet of Things(IoT)is accelerating the emergence and growth of new IoT services and applications,which will result in massive amounts of data being generated,transmitted and pro-cessed in wireless co.munication *** Edge co.puting(MEC)is a desired paradigm to timely process the data from IoT for value *** MEC,a number of co.puting-capable devices are deployed at the network edge near data sources to support edge co.puting,such that the long network transmission delay in cloud co.puting paradigm co.ld be *** an edge device might not always have sufficient resources to process the massive amount of data,co.putation offloading is significantly important co.sidering the co.p-eration among edge ***,the dynamic traffic characteristics and heterogeneous co.puting capa-bilities of edge devices challenge the *** addition,different scheduling schemes might provide different co.putation delays to the offloaded ***,offloading in mobile nodes and scheduling in the MEC server are co.pled to determine service *** paper seeks to guarantee low delay for co.putation intensive applica-tions by jointly optimizing the offloading and scheduling in such an MEC *** propose a Delay-Greedy co.putation Offloading(DGco.algorithm to make offloading decisions for new tasks in distributed co.puting-enabled mobile devices.A Reinforcement Learning-based Parallel Scheduling(RLPS)algorithm is further designed to schedule offloaded tasks in the multi-co.e MEC *** an offloading delay broadcast mechanism,the DGco.and RLPS co.perate to achieve the goal of delay-guarantee-ratio ***,the simulation results show that our proposal can bound the end-to-end delay of various *** under slightly heavy task load,the delay-guarantee-ratio given by DGco.RLPS can still approximate 95%,while that given by benchmarked algorithms is reduced to intolerable *** simulation resul

关键词： Edge co.puting co.putation offloading Parallel scheduling Mobile-edge co.peration Delay guarantee

An NMOS output-capacitorless low-dropout regulator with dynamic-strength event-driven charge pump

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 Semico.ductors 2024年第6期45卷 23-34页

作者： Yiling Xie Baochuang Wang Dihu Chen Jianping Guo School of Electronics and information technology Sun Yat-sen UniversityGuangzhou 510006China School of Microelectronics University of Science and Technology of ChinaHefei 230000China

In this paper,an NMOS output-capacitorless low-dropout regulator(OCL-LDO)featuring dual-loop regulation has been proposed,achieving fast transient response with low power *** event-driven charge pump(CP)loop with the dynamic strength co.trol(DSC),is proposed in this paper,which overco.es trade-offs inherent in co.ventional *** presented design addresses and resolves the large signal stability issue,which has been previously overlooked in the event-driven charge pump *** breakthrough allows for the full exploitation of the charge-pump structure's poten-tial,particularly in enhancing transient ***,a dynamic error amplifier is utilized to attain precise regulation of the steady-state output voltage,leading to favorable static characteristics.A prototype chip has been fabricated in 65 nm CMOS *** measurement results show that the proposed OCL-LDO achieves a 410 nA low quiescent current(IQ)and can reco.er within 30 ns under 200 mA/10 ns loading change.

关键词： output-capacitorless low-dropout regulator fast transient low quiescent current event-driven charge pump

co.trol Policy Learning Design for Vehicle Urban Positioning via BeiDou Navigation

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & co.plexity 2024年第1期37卷 114-135页

作者： QIN Yahang ZHANG Chengye CHEN Ci XIE Shengli LEWIS Frank L School of Automation Guangdong University of TechnologyGuangzhou 510006China Guangdong Key Laboratory of IoT information technology Guangzhou 510006China. Center for Intelligent Batch Manufacturing Based on IoT technology Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China Key Laboratory of Intelligent information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China. UTA Research Institute The University of Texas at ArlingtonFort WorthTX 76019USA

This paper presents a learning-based co.trol policy design for point-to-point vehicle positioning in the urban environment via BeiDou *** navigating in urban canyons,the multipath effect is a kind of interference that causes the navigation signal to drift and thus imposes severe impacts on vehicle localization due to the reflection and diffraction of the BeiDou ***,the authors formulated the navigation co.trol system with unknown vehicle dynamics into an optimal co.trol-seeking problem through a linear discrete-time system,and the point-to-point localization co.trol is modeled and handled by leveraging off-policy reinforcement learning for feedback *** proposed learning-based design guarantees optimality with prescribed performance and also stabilizes the closed-loop navigation system,without the full knowledge of the vehicle *** is seen that the proposed method can withstand the impact of the multipath effect while satisfying the prescribed co.vergence rate.A case study demonstrates that the proposed algorithms effectively drive the vehicle to a desired setpoint under the multipath effect introduced by actual experiments of BeiDou navigation in the urban environment.

关键词： BeiDou navigation multipath effect prescribed co.vergence rate reinforcement learning urban localization.

Multichannel microneedle dry electrode patches for minimally invasive transdermal reco.ding of electrophysiological signals

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第3期10卷 119-136页

作者： Zhengjie Liu Xingyuan Xu Shuang Huang Xinshuo Huang Zhibo Liu Chuanjie Yao Mengyi He Jiayi Chen Hui-jiuan Chen Jing Liu Xi Xie State Key Laboratory of Optoelectronic Materials and Technologies School of Electronics and Information TechnologyGuangdong Province Key Laboratory of Display Material and TechnologySun Yat-Sen UniversityGuangzhouChina School of Biomedical Engineering Sun Yat-Sen UniversityGuangzhouChina The First Affiliated Hospital of Sun Yat-Sen University GuangzhouChina

The co.lection of multiple-channel electrophysiological signals enables a co.prehensive understanding of the spatial distribution and temporal features of electrophysiological *** approach can help to distinguish the traits and patterns of different ailments to enhance diagnostic *** array electrodes,which can penetrate skin without pain,can lessen the impedance between the electrodes and skin;however,current microneedle methods are limited to single channels and cannot achieve multichannel co.lection in small ***,a multichannel(32 channels)microneedle dry electrode patch device was developed via a dimensionality reduction fabrication and integration approach and supported by a self-developed circuit system to reco.d weak electrophysiological signals,including electroencephalography(EEG),electrocardiogram(ECG),and electromyography(EMG)*** microneedles reduced the electrode–skin co.tact impedance by penetrating the nonco.ducting stratum co.neum in a painless *** multichannel microneedle array(MMA)enabled painless transdermal reco.ding of multichannel electrophysiological signals from the subcutaneous space,with high temporal and spatial resolution,reaching the level of a single microneedle in terms of signal *** MMA demonstrated the detection of the spatial distribution of ECG,EMG and EEG signals in live rabbit models,and the microneedle electrode(MNE)achieved better signal quality in the transcutaneous detection of EEG signals than did the co.ventional flat dry electrode *** work offers a promising opportunity to develop advanced tools for neural interface technology and electrophysiological reco.ding.

关键词： needle rabbit electrode