检索结果-南通市图书馆

Semantic segmentation via pixel-to-center similarity calculation

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 87-100页

作者： Dongyue Wu Zilin Guo Aoyan Li Changqian Yu Nong Sang Changxin Gao National Key Laboratory of Science and Technology on Multispectral information processing School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Meituan Inc. BeijingChina

Since the fully convolutional network has achieved great success in semantic segmentation,lots of works have been proposed to extract discriminative pixel ***,the authors observe that existing methods still suffer from two typical challenges:(i)The intra-class feature variation between different scenes may be large,leading to the difficulty in maintaining the consistency between same-class pixels from different scenes;(ii)The inter-class feature distinction in the same scene could be small,resulting in the limited performance to distinguish different classes in each *** authors first rethink se-mantic segmentation from a perspective of similarity between pixels and class *** weight vector of the segmentation head represents its corresponding semantic class in the whole dataset,which can be regarded as the embedding of the class ***,the pixel-wise classification amounts to computing similarity in the final feature space between pixels and the class *** this novel view,the authors propose a Class Center Similarity(CCS)layer to address the above-mentioned challenges by generating adaptive class centers conditioned on each scenes and supervising the similarities between class *** CCS layer utilises the Adaptive Class Center Module to generate class centers conditioned on each scene,which adapt the large intra-class variation between different *** designed Class Distance Loss(CD Loss)is introduced to control both inter-class and intra-class distances based on the predicted center-to-center and pixel-to-center ***,the CCS layer outputs the processed pixel-to-center similarity as the segmentation *** experiments demonstrate that our model performs favourably against the state-of-the-art methods.

关键词： computer vision deep neural networks image segmentation scene understanding

FP-Zernike:An Open-source Structural Database Construction Toolkit for Fast Structure Retrieval

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2024年第1期22卷 111-119页

作者： Junhai Qi Chenjie Feng Yulin Shi Jianyi Yang Fa Zhang Guojun Li Renmin Han Research Center for Mathematics and Interdisciplinary Sciences Shandong UniversityQingdao 266237China BioMap Research Menlo ParkCA 94025USA College of medical information and Engineering Ningxia Medical UniversityYinchuan 750004China institute of Engineering Medicine Beijing Institute of TechnologyBeijing 100081China

The release of AlphaFold2 has sparked a rapid expansion in protein model *** protein structure retrieval is crucial for the analysis of structure models,while measuring the similarity between structures is the key challenge in structural *** existing structure alignment algorithms can address this challenge,they are often ***,the state-of-the-art approach involves converting protein structures into three-dimensional(3D)Zernike descriptors and assessing similarity using Euclidean ***,the methods for computing 3D Zernike descriptors mainly rely on structural surfaces and are predominantly web-based,thus limiting their application in studying custom *** overcome this limitation,we developed FP-Zernike,a user-friendly toolkit for computing different types of Zernike descriptors based on feature *** simply need to enter a single line of command to calculate the Zernike descriptors of all structures in customized ***-Zernike outperforms the leading method in terms of retrieval accuracy and binary classification accuracy across diverse benchmark *** addition,we showed the application of FP-Zernike in the construction of the descriptor database and the protocol used for the Protein Data Bank(PDB)dataset to facilitate the local deployment of this tool for interested *** demonstration contained 590,685 structures,and at this scale,our system required only 4-9 s to complete a *** experiments confirmed that it achieved the state-of-the-art accuracy ***-Zernike is an open-source toolkit,with the source code and related data accessible at https://***/biocode/tools/BT007365/releases/0.1,as well as through a webserver at http://***/.

关键词： Zernike descriptor Structure alignment PDB dataset Open-source Retrieval system

A survey on intelligence-endogenous network:Architecture and technologies for future 6G

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent and Converged Networks 2024年第1期5卷 53-67页

作者： Lanlan Li the School of Communication and information Engineering Shanghai Technical Institute of Electronics&InformationShanghai 201141China

With the maturity of 5G technology and global commercialization,scholars in institutions and industrial circles began to research 6G *** important innovation of 6G technology is to integrate artificial intelligence(AI)technology and communication technology to build a highly endogenous intelligent communication *** paper investigates the process of AI technology introduced into the field of communication and reviews the use cases of the simulation and application of AI algorithms being discussed in 3GPP meetings in industry *** this research report,we first investigate the progress of AI technology in 5G network architecture and then discuss the requirements of endogenous intelligent 6G networks,which leads to the possible network *** work aims to provide enlightening guidance for subsequent research of intelligence-endogenous 6G network.

关键词： 5G 6G intelligence-endogenous artificial intelligence

Facile intercalation of alkali ions in WO_(3)for modulated electronic and optical properties:Implications for artificial synapses and chromogenic application

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(Physics,Mechanics & Astronomy) 2024年第2期67卷 149-160页

作者： Changmeng Huan Zihan Lu Silin Tang Yongqing Cai Qingqing Ke School of Microelectronics Science and Technology Sun Yat-sen UniversityZhuhai 519082China Guangdong Provincial Key Laboratory of Optoelectronic information processing Chips and Systems Sun Yat-sen UniversityZhuhai 519082China institute of Applied Physics and Materials Engineering University of MacaoTaipaMacao 999078China

Tungsten oxides(WO_(3))are widely recognized as multifunctional systems owing to the existence of rich *** diverse phases exhibit distinct octahedra-tilting patterns,generating substantial tunnels that are ideally suited for ***,a quantitative comprehension regarding the impact of distinct phases on the kinetics of intercalated conducting ions remains ***,we employ first-principles calculations to explore the spatial and orientational correlations of ion transport inγ-and h-WO_(3),shedding light on the relationship between diffusion barriers and the size of the conducting *** findings reveal that different types and concentrations of alkali-metals induce distinct and continuous lattice distortions in WO_(3)***,γ-WO_(3)is more appropriate to accommodate Li+ions,exhibiting a diffusion barrier and coefficient of 0.25 eV and 9.31×10^(-8)cm^(2)s^(-1),***,h-WO_(3)features unidirectional and sizeable tunnels that facilitate the transport of K+ions with an even lower barrier and a high coefficient of 0.11 e V and 2.12×10^(-5)cm^(2)s^(-1),***,the introduction of alkali-metal into WO_(3)tunnels tends to introduce n-type conductivity by contributing s-electrons to the unoccupied W 5d states,resulting in enhanced conductivity and tunable electronic *** alkali metals in WO_(3)tunnels are prone to charge transfer,forming small polaronic states and modulating the light absorption in the visible and nearinfrared *** tunable electronic and optical properties,combined with the high diffusion coefficient,underscore the potential of WO_(3)in applications such as artificial synapses and chromogenic devices.

关键词： WO_(3)polymorphs ion insertion kinetic activity tunable electronic and optical properties iontronics

Experimental study of 3D printed carbon fibre sandwich structures for lightweight applications

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第6期36卷 71-77页

作者： Solaiprakash Vellaisamy Raguraman Munusamy Department of Mechanical Engineering Indian Institute of Information Technology Design and ManufacturingKancheepuramChennai600127India School of Interdisciplinary Design and Innovation Indian Institute of Information Technology Design and ManufacturingKancheepuramChennai600127India

Honeycomb sandwich structures are widely used in lightweight ***,these structures are subjected to extreme loading conditions,leading to potential failures due to delamination and debonding between the face sheet and the honeycomb ***,the present study is focused on the mechanical characterisation of honeycomb sandwich structures fabricated using advanced 3D printing *** continuous carbon fibres and ONYX-FR matrix materials have been used as raw materials for 3D printing of the specimens needed for various mechanical characterization testing;ONYX-FR is a commercial trade name for flame retardant short carbon fibre filled nylon filaments,used as a reinforcing material in Morkforged 3D *** and flatwise compression tests have been conducted for different configurations of honeycomb sandwich structures,fabricated by varying the face sheet thickness and core cell size,while keeping the core cell thickness and core height *** on these tests,the proposed structure with face sheet thickness of 3.2 mm and a core cell size of 12.7 mm exhibited the highest energy absorption and prevented delamination and debonding ***,3D printing technology can also be considered as an alternative method for sandwich structure ***,detailed parametric studies still need to be conducted to meet various other structural integrity criteria related to the lightweight applications.

关键词： 3D printed composite Honeycomb sandwich Edgewise compression Flatwise compression Lightweight

RGB-guided hyperspectral image super-resolution with deep progressive learning

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第3期9卷 679-694页

作者： Tao Zhang Ying Fu Liwei Huang Siyuan Li Shaodi You Chenggang Yan School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina Satellite information Intelligent processing and Application Research Laboratory Beijing Institute of Remote SensingBeijingChina Key Laboratory of Spectral Imaging Technology Xi'an Institute of Optics and Precision Mechanics of Chinese Academy of SciencesXi'anChina institute of Informatics University of AmsterdamAmsterdamNetherlands School of Communication Engineering Hangzhou Dianzi UniversityHangzhouChina

Due to hardware limitations,existing hyperspectral(HS)camera often suffer from low spatial/temporal ***,it has been prevalent to super-resolve a low reso-lution(LR)HS image into a high resolution(HR)HS image with a HR RGB(or mul-tispectral)image *** approaches for this guided super-resolution task often model the intrinsic characteristic of the desired HR HS image using hand-crafted ***,researchers pay more attention to deep learning methods with direct supervised or unsupervised learning,which exploit deep prior only from training dataset or testing *** this article,an efficient convolutional neural network-based method is presented to progressively super-resolve HS image with RGB image ***-ically,a progressive HS image super-resolution network is proposed,which progressively super-resolve the LR HS image with pixel shuffled HR RGB image ***,the super-resolution network is progressively trained with supervised pre-training and un-supervised adaption,where supervised pre-training learns the general prior on training data and unsupervised adaptation generalises the general prior to specific prior for variant testing *** proposed method can effectively exploit prior from training dataset and testing HS and RGB images with spectral-spatial *** has a good general-isation capability,especially for blind HS image *** experimental results show that the proposed deep progressive learning method out-performs the existing state-of-the-art methods for HS image super-resolution in non-blind and blind cases.

关键词： computer vision deep neural networks image processing image resolution unsupervised learning

Simulation and fabrication of in vitro microfluidic microelectrode array chip for patterned culture and electrophysiological detection of neurons

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nanotechnology and Precision Engineering 2024年第2期7卷 1-10页

作者： Yan Yang Shihong Xu Yu Deng Yaoyao Liu Kui Zhang Shiya Lv Longze Sha Qi Xu Xinxia Cai Jinping Luo State Key Laboratory of Transducer Technology Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100190China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of medical Molecular Biology Institute of Basic Medical SciencesChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijing 100005China

To enable the detection and modulation of modularized neural networks in vitro,this study proposes a microfluidic microelectrode array chip for the cultivation,compartmentalization,and control of neural *** chip was designed based on the specific structure of neurons and the requirements for detection and ***-element analysis of the chip’s flow field was conducted using the COMSOL Multiphysics software,and the simulation results show that the liquid within the chip can flow smoothly,ensuring stable flow fields that facilitate the uniform growth of neurons within the microfluidic *** employing MEMS technology in combination with nanomaterial modification techniques,the microfluidic microelectrode array chip was fabricated *** hippocampal neurons were cultured on the chip,forming a well-defined neural *** electrical activity of the detected neurons was recorded,exhibiting a 23.7%increase in amplitude compared to neuronal discharges detected on an open-field microelectrode *** study provides a platform for the precise detection and modulation of patterned neuronal growth in vitro,potentially serving as a novel tool in neuroscience research.

关键词： Microfluidic Microelectrode array In vitro Neural chip

Non-destructive electroluminescence inspection for LED epitaxial wafers based on soft single-contact operation

在线全文

学校读者我要写书评

暂无评论

Photonics Research 2024年第08期12卷 1776-1784页

作者： HAO SU JIAWEN QIU JUNLONG LI RONG CHEN JIANBI LE XIAOYANG LEI YONGAI ZHANG XIONGTU ZHOU TAILIANG GUO CHAOXING WU School of Physics and information Engineering Fuzhou University Fujian Science and Technology Innovation Laboratory for Optoelectronic information of China Fujian Inspection and Research institute for Product Quality

Non-destructive and accurate inspection of gallium nitride light-emitting diode(Ga N-LED) epitaxial wafers is important to Ga N-LED technology. However, the conventional electroluminescence inspection, the photoluminescence inspection, and the automated optical inspection cannot fulfill the complex technical requirements. In this work, an inspection method and an operation system based on soft single-contact operation, namely, single-contact electroluminescence(SC-EL) inspection, are proposed. The key component of the SC-EL inspection system is a soft conductive probe with an optical fiber inside, and an AC voltage(70Vpp, 100 k Hz) is applied between the probe and the ITO electrode under the LED epitaxial wafer. The proposed SC-EL inspection can measure both the electrical and optical parameters of the LED epitaxial wafer at the same time, while not causing mechanical damage to the LED epitaxial wafer. Moreover, it is demonstrated that the SC-EL inspection has a higher electroluminescence wavelength accuracy than photoluminescence inspection. The results show that the non-uniformity of SC-EL inspection is 444.64%, which is much lower than that of photoluminescence inspection. In addition, the obtained electrical parameters from SC-EL can reflect the reverse leakage current(Is) level of the LED epitaxial wafer. The proposed SC-EL inspection can ensure high inspection accuracy without causing damage to the LED epitaxial wafer, which holds promising application in LED technology.

关键词： Gallium nitride light emitting diodes Indium tin oxide Light emitting diodes Near eye displays Optical fibers Optical inspection

Polymer-encapsulated metal complex catalysts:An emerging and efficient platform for electrochemical CO_(2) reduction

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2024年第5期172卷 33-50页

作者： Yingshuo Liu Shuaishuai Lyu Fuli Wen Weixuan Nie Shuqing Wang Sinopec Research institute of Petroleum processing Co. Ltd.Beijing 100083China School of Engineering Westlake UniversityHangzhou 310024China

Over the past decade,electrocatalytic reduction of CO_(2)has gained substantial ***,hardly any of the previous reviews have focused on the systematic discussion of polymer-molecular catalyst composites as an emerging system for the electrochemical transformation of CO_(2)to value-added *** this review,we first give a brief overview of the general features of solid-state and molecular catalysts,and then advance the discussion to polymer-catalyst composite systems,with particular emphasis on polymer-encapsulated molecular catalysts,where the coordination environment surrounding molecular catalysts can be modified via polymer encapsulation to promote the overall performance of CO_(2)*** elucidation of the possible reaction mechanisms of this emerging electrocat-alytic system along with proposed optimization strategies is also summarized and discussed based on recently published reports,followed by the challenges and prospects of their industrial applications at the end of this *** this review,we hope the audience can gain a comprehensive understanding of the electrocatalytic mechanism of the coordinating polymers and valuable insights into engineering the microenvironment surrounding the metal complexes for potential future research directions.

关键词： Polymer-molecular catalyst composite Polymer encapsulation Coordination environment CO_(2)electrocatalysis Electrocatalytic mechanism