检索结果-南通市图书馆

Grasp Detection with Hierarchical Multi-Scale Feature Fusion and Inverted Shuffle Residual

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 244-256页

作者： Wenjie Geng Zhiqiang cao Peiyu guan Fengshui Jing Min Tan Junzhi yu State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Department of Advanced Manufacturing and Robotics College of EngineeringPeking UniversityBeijing 100871China

Grasp detection plays a critical role for robot *** pixel-wise grasp detection networks with encoder-decoder structure receive much attention due to good accuracy and ***,they usually transmit the high-level feature in the encoder to the decoder,and low-level features are *** is noted that low-level features contain abundant detail information,and how to fully exploit low-level features remains ***,the channel information in high-level feature is also not well ***,the performance of grasp detection is *** solve these problems,we propose a grasp detection network with hierarchical multi-scale feature fusion and inverted shuffle *** low-level and high-level features in the encoder are firstly fused by the designed skip connections with attention module,and the fused information is then propagated to corresponding layers of the decoder for in-depth feature *** a hierarchical fusion guarantees the quality of grasp ***,an inverted shuffle residual module is created,where the high-level feature from encoder is split in channel and the resultant split features are processed in their respective *** such differentiation processing,more high-dimensional channel information is kept,which enhances the representation ability of the ***,an information enhancement module is added before the encoder to reinforce input *** proposed method attains 98.9%and 97.8%in image-wise and object-wise accuracy on the cornell grasping dataset,respectively,and the experimental results verify the effectiveness of the method.

关键词： grasp detection hierarchical multi-scale feature fusion skip connections with attention inverted shuffle residual

circulating RNA ZFR promotes hepatocellular carcinoma cell proliferation and epithelial-mesenchymal transition process through miR-624-3p/WEE1 axis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Hepatobiliary & Pancreatic Diseases International 2024年第1期23卷 52-63页

作者： Li Zhang Sai He Hao guan yao Zhao Di Zhang Department of General Surgery the Second Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710004China Department of Breast cancer Shaanxi Provincial Cancer HospitalXi’an 710000China

Background:Hepatocellular carcinoma(Hcc),the most common type of primary liver cancer,is the fourth leading cause of cancer-related deaths *** evidence shows that the expression of circulating RNA ZFR(circZFR)is upregulated in Hcc ***,the molecular mechanism of circZFR in Hcc is ***:Quantitative reverse transcriptase polymerase chain reaction(qRT-PcR)was employed to detect the expression of circZFR,microRNA-624-3p(miR-624-3p)and WEE1 in Hcc tissues and *** R assay and actinomycin D treatment assay were used to analyze the characteristics of *** functional analysis,the capacities of colony formation,cell proliferation,cell apoptosis,migration and invasion were assessed by colony formation assay,5-ethynyl-2-deoxyuridine(EdU)assay,flow cytometry assay and transwell *** blot was used to examine the protein levels of WEE1 and epithelial-mesenchymal transition(EMT)-related *** interactions between miR-624-3p and circZFR or WEE1 were validated by dual-luciferase reporter assay and RNA immunoprecipitation(RIP)*** models were established to determine the role of circZFR in ***:circZFR and WEE1 were upregulated,while miR-624-3p expression was reduced in Hcc tissues and *** could sponge miR-624-3p,and WEE1 was a downstream gene of *** of circZFR significantly reduced the malignant behaviors of Hcc and that co-transfection with miR624-3p inhibitor restored this *** of WEE1 abolished the inhibitory effect of miR624-3p mimic on Hcc ***,circZFR acted as a competitive endogenous RNA(ceRNA)to regulate WEE1 expression by targeting ***,in vivo studies have illustrated that circZFR knockdown inhibited tumor ***:circZFR knockdown reduced Hcc cell proliferation,migration and invasion and promoted apoptosis by regulating the miR-624-3p/WEE1 axis,suggesting that the circZFR/miR-624-3p/WEE1 axis might

关键词： Hepatocellular carcinoma circZFR miR-624-3p WEE1 Liver cancer

How Does Urban Shrinkage Affect Land Use Efficiency?A case Study of Shrinking cities in Northeast china

在线全文

学校读者我要写书评

暂无评论

chinese Geographical Science 2024年第1期34卷 34-51页

作者： XIE Mingke FENG Zhangxian SONG yang guan Haoming WANG Shijun School of Geographical Sciences Northeast Normal UniversityChangchun130024China

The effect of urban shrinkage has gradually become a new ***,urban shrinkage may exert great influence on land use efficiency(LUE)through various urban subsystems,but there is currently limited research examining these *** the Super-SBM-Undesirable model and the Structural Equation Model(SEM),this study calculates the LUE of shrinking cities in Northeast china and simulates the process of urban shrinkage affecting *** quantify the process of urban shrinkage affecting LUE,three mediation variables,namely the economy,public services,and innovation,are used as latent variables to apply *** results show that urban shrinkage will affect LUE through a direct path and indirect *** the direct path,urban shrinkage leads to an improvement in *** the indirect paths,the economy and innovation will transmit the negative effect of urban shrinkage on LUE,while public services will reverse this *** important contribution of this study is that it quantifies the paths of urban shrinkage affecting LUE,thereby expanding the understanding of urban shrinkage effect and laying a foundation for the sustainable development of shrinking cities.

关键词： urban shrinkage land use efficiency Super-SBM-Undesirable model Structural Equation Model(SEM) Northeast china

Joint computation offloading and parallel scheduling to maximize delay-guarantee in cooperative MEc systems

在线全文

学校读者我要写书评

暂无评论

Digital communications 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 communication *** Edge computing(MEc)is a desired paradigm to timely process the data from IoT for value *** MEc,a number of computing-capable devices are deployed at the network edge near data sources to support edge computing,such that the long network transmission delay in cloud computing paradigm could be *** an edge device might not always have sufficient resources to process the massive amount of data,computation offloading is significantly important considering the coop-eration among edge ***,the dynamic traffic characteristics and heterogeneous computing capa-bilities of edge devices challenge the *** addition,different scheduling schemes might provide different computation delays to the offloaded ***,offloading in mobile nodes and scheduling in the MEc server are coupled to determine service *** paper seeks to guarantee low delay for computation intensive applica-tions by jointly optimizing the offloading and scheduling in such an MEc *** propose a Delay-Greedy computation Offloading(DGcO)algorithm to make offloading decisions for new tasks in distributed computing-enabled mobile devices.A Reinforcement Learning-based Parallel Scheduling(RLPS)algorithm is further designed to schedule offloaded tasks in the multi-core MEc *** an offloading delay broadcast mechanism,the DGcO and RLPS cooperate 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 computing computation offloading Parallel scheduling Mobile-edge cooperation Delay guarantee

Detection and isolation of false data injection attack via adaptive Kalman filter bank

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 control and Decision 2024年第1期11卷 60-72页

作者： Xiaoyuan Luo Minggao Zhu Xinyu Wang Xinping guan School of Electrical Engineering Yanshan UniversityQinhuangdaoPeople’s Republic of China Jiangsu collaborative Innovation center for Smart Distribution Network NanjingPeople’s Republic of China School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghaiPeople’s Republic of China

Due to the integration of cyber–physical systems,smart grids have faced the new security risks caused by false data injection attacks(FDIAs).FDIAs can bypass the traditional bad data detection techniques by falsifying the process of state *** this reason,this paper studies the detection and isolation problem of FDIAs based on the adaptive Kalman filter bank(AKFB)in smart *** the covert characteristics of FDIAs into account,a novel detection method is proposed based on the designed ***,the adaptive threshold is proposed to solve the detection delay caused by a priori threshold in the current detection *** the case of multiple attacked sensor nodes,the AKFB-based isolation method is *** reduce the number of isolation iterations,a logical decision matrix scheme is ***,the effectiveness of the proposed detection and isolation method is demonstrated on an IEEE 22-bus smart grids.

关键词： Smart grids false data inject attack detection and isolation Kalman filter bank

Non-monotonic behavior of jam probability and stretchedexponential distribution in pedestrian counterflow

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9期33卷 259-266页

作者： Ze-Hao chen Zhi-Xi Wu Jian-yue guan college of Physical Science and Technology Guangxi Normal UniversityGuilin 541004China Lanzhou center for Theoretical Physics Key Laboratory of Theoretical Physics of Gansu Provinceand Key Laboratory for Quantum Theory and Applications of the Ministry of EducationLanzhou UniversityLanzhou 730000China

We adopt a floor field cellular automata model to study the statistical properties of bidirectional pedestrian flow movingin a straight corridor. We introduce a game-theoretic framework to deal with the conflict of multiple pedestrians tryingto move to the same target location. By means of computer simulations, we show that the complementary cumulative distributionof the time interval between two consecutive pedestrians leaving the corridor can be fitted by a stretched exponentialdistribution, and surprisingly, the statistical properties of the two types of pedestrian flows are affected differently by theflow ratio, i.e., the ratio of the pedestrians walking toward different directions. We also find that the jam probability exhibitsa non-monotonic behavior with the flow ratio, where the worst performance arises at an intermediate flow ratio of around0.2. Our simulation results are consistent with some empirical observations, which suggest that the peculiar characteristicsof the pedestrians may attributed to the anticipation mechanism of collision avoidance.

关键词： traffic and crowd dynamics evolutionary game theory

Microstructure evolution,mechanical properties and fracture behavior of Al-xSi/AZ91D bimetallic composites prepared by a compound casting

在线全文

学校读者我要写书评

暂无评论

Journal of Magnesium and Alloys 2024年第5期12卷 1944-1964页

作者： guangyu Li Wenming Jiang Feng guan Junwen Zhu yang yu Zitian Fan State Key Laboratory of Materials Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China

In this paper,the effect of the Si content on microstructure evolution,mechanical properties,and fracture behavior of the Al-xSi/AZ91D bimetallic composites prepared by compound casting was investigated *** obtained results showed that all the Al-xSi/AZ91D bimetallic composites had a metallurgical reaction layer(MRL),whose thickness increased with increasing Si content for the hypoeutectic Al-Si/AZ91D composites,while the hypereutectic Al-Si/AZ91D composites were *** MRL included eutectic layer(E layer),intermetallic compound layer(IMc layer)and transition region layer(T layer).In the IMc layer,the hypereutectic Al-Si/AZ91D composites contained some Si solid solution and flocculent Mg_(2)Si+Al-Mg IMcs phases not presented in the hypoeutectic Al-Si/AZ91D ***,increasing Si content,the thickness proportion of the T layer increased,forming an inconsistent preferred orientation of the *** shear strengths of the Al-xSi/AZ91D bimetallic composites enhanced with increasing Si content,and the Al-15Si/AZ91D composite obtained a maximum shear strength of 58.6 MPa,which was 73.4% higher than the Al-6Si/AZ91D *** fractures of the Al-xSi/AZ91D bimetallic composites transformed from the T layer into the E layer with the increase of the Si *** improvement of the shear strength of the Al-xSi/AZ91D bimetallic composites was attributed to the synergistic action of the Mg_(2)Si particle reinforcement,the reduction of oxidizing inclusions and the ratio of Al-Mg IMcs as well as the orientation change of the MRL.

关键词： Al/Mg bimetallic composites Si content Mg_(2)Si reinforcement Microstructure Mechanical properties Fracture behavior

Grating-free autofocus for single-pixel microscopic imaging

在线全文

学校读者我要写书评

暂无评论

Photonics Research 2024年第6期12卷 1313-1321页

作者： guan WANG HUAXIA DENG yU cAI MENGcHAO MA XIANG ZHONG XINGLONG GONG cAS Key Laboratory of Mechanical Behavior and Design of Materials Department of Modern MechanicsUniversity of Science and Technology of ChinaHefei 230027China School of Instrument Science and Opto-electronics Engineering Hefei University of TechnologyHefei 230009China

As a computational technology,single-pixel microscopic imaging(SPMI)transfers the target’s spatial information into a temporal *** traditional focusing method of imaging before evaluation is not applicable to the SPMI *** propose a grating-free autofocus strategy derived from the physical mechanism of optical *** the amplitude information of just one high-frequency point in the spectrum is all that is needed to achieve fast autofocus with the SPMI ***,only four patterns need to be cyclically projected,enabling efficient localization of the focal plane based on the measurement *** demonstrate SPMI autofocus experiments at micrometer and even nanometer depths of *** proposed method can be extended to achieve SMPI autofocus with invisible optical pattern illumination.

关键词： optical system illumination

construction personnel dress code detection based on yOLO framework

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 709-721页

作者： yunkai Lyu Xiaobing yang Ai guan Jingwen Wang Leni Dai college of Information Engineering China Jiliang UniversityHangzhouChina college of Integrated circuit Science and Engineering Nanjing University of Posts and TelecommunicationsNanjingChina china Jiliang University HangzhouZhejiangChina Department of Mathematics University of California San DiegoLa JollaCaliforniaUSA

It is important for construction personnel to observe the dress code,such as the correct wearing of safety helmets and reflective vests is conducive to protecting the workers'lives and safety of construction.A yOLO network-based detection algorithm is proposed for the construction personnel dress code(yOLO-cPDc).Firstly,Multi-Head Self-Attention(MHSA)is introduced into the backbone network to build a hybrid back-bone,called convolution MHSA Network(cMNet).The cMNet gives the model a global field of view and enhances the detection capability of the model for small and obscured ***,an efficient and lightweight convolution module is *** is named Ghost Shuffle Attention-conv-BN-SiLU(GSA-cBS)and is used in the neck *** GSANeck network reduces the model size without affecting the ***,the SIoU is used in the loss function and Soft NMS is used for *** results on the self-constructed dataset show that yOLO-cPDc algorithm has higher detection accuracy than current ***-cPDc achieves a mAP50 of 93.6%.compared with the yOLOv5s,the number of parame-ters of our model is reduced by 18%and the mAP50 is improved by 1.1%.Overall,this research effectively meets the actual demand of dress code detection in construction scenes.

关键词： artificial intelligence computer vision deep learning deep neural networks