检索结果-内蒙古大学图书馆

arXiv 2019年

作者： An, Shan Che, Guangfu Zhou, Fangru Liu, Xianglong Ma, Xin Chen, Yu AR/VR department *** Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Control Science and Engineering Shandong University Jinan China

Visual loop closure detection, which can be considered as an image retrieval task, is an important problem in SLAM (Simultaneous Localization and Mapping) systems. The frequently used bag-of-words (BoW) models can achieve high precision and moderate recall. However, the requirement for lower time costs and fewer memory costs for mobile robot applications is not well satisfied. In this paper, we propose a novel loop closure detection framework titled 'FILD' (Fast and Incremental Loop closure Detection), which focuses on an on-line and incremental graph vocabulary construction for fast loop closure detection. The global and local features of frames are extracted using the Convolutional Neural Networks (CNN) and SURF on the GPU, which guarantee extremely fast extraction speeds. The graph vocabulary construction is based on one type of proximity graph, named Hierarchical Navigable Small World (HNSW) graphs, which is modified to adapt to this specific application. In addition, this process is coupled with a novel strategy for real-time geometrical verification, which only keeps binary hash codes and significantly saves on memory usage. Extensive experiments on several publicly available datasets show that the proposed approach can achieve fairly good recall at 100% precision compared to other state-of-the-art methods. The source code can be downloaded at https://***/AnshanTJU/FILD for further studies. Copyright © 2019, The Authors. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Data mining-based model and risk prediction of colorectal cancer by using secondary health data:A systematic review

引用

Chinese Journal of Cancer Research 2020年第2期32卷 242-251页

作者： Hailun Liang Lei Yang Lei Tao Leiyu Shi Wuyang Yang Jiawei Bai Da Zheng Ning Wang Jiafu Ji School of Public Administration and Policy Renmin University of ChinaBeijing 100872China Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education/Beijing) Beijing Office for Cancer Prevention and ControlPeking University Cancer Hospital&InstituteBeijing 100142China Departm ent of Public Policy City University of Hong KongHong Kong SAR999077China Johns Hopkins Primary Care Policy Center BaltimoreMD 21205USA Ddepartment of Neurosurgery Johns Hopkins MedicineBaltimoreMD 21205USA Department of Biostatistics Johns Hopkins Bloomberg School of Public HealthBaltimoreMD 21205USA Department of Computer Science Johns Hopkins Whiting School of EngineeringBaltimoreMD 21205USA Key Laboratory of Carcinogenesis and Translational Research(Ministiy of Education/Beijing) Center of Gastrointestinal SurgeryPeking University Cancer Hospital&InstituteBeijing 100142China

Objective:Prevention and early detection of colorectal cancer(CRC)can increase the chances of successful treatment and reduce *** data mining technologies have been utilized to strengthen the early detection of CRC in primary *** synthesis on the model’s effectiveness is *** systematic review synthesizes studies that examine the effect of data mining on improving risk prediction of ***:The PRISMA framework guided the conduct of this *** obtained papers via Pub Med,Cochrane Library,EMBASE and Google *** appraisal was performed using Downs and Black’s quality *** evaluate the performance of included models,the values of specificity and sensitivity were comparted,the values of area under the curve(AUC)were plotted,and the median of overall AUC of included studies was ***:A total of 316 studies were reviewed for full *** articles were *** studies implement techniques including artificial neural networks,Bayesian networks and decision *** articles reported the overall model ***,the median AUC is 0.8243[interquartile range(IQR):0.8050-0.8886].In the two articles that reported comparison results with traditional models,the data mining method performed better than the traditional models,with the best AUC improvement of 10.7%.Conclusions:The adoption of data mining technologies for CRC detection is at an early *** numbers of included articles and heterogeneity of those studies implied that more rigorous research is expected to further investigate the techniques’effects.

关键词： Systematic review colorectal cancer disease detection data mining

来源：评论

学校读者我要写书评

暂无评论

Multi-representational learning for offline signature verification using multi-loss snapshot ensemble of CNNs

arXiv

引用

arXiv 2019年

作者： Masoudnia, Saeed Mersa, Omid Araabi, Babak Nadjar Vahabie, Abdol-Hossein Sadeghi, Mohammad Amin Ahmadabadi, Majid Nili Machine Learning and Computational Modelling Lab Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Tehran Iran Cognitive System Lab Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran

Offline Signature Verification (OSV) is a challenging pattern recognition task, especially in the presence of skilled forgeries that are not available during training. This study aims to tackle its challenges and meet the substantial need for generalization for OSV by examining different loss functions for Convolutional Neural Network (CNN). We adopt our new approach to OSV by asking two questions: 1. which classification loss provides more generalization for feature learning in OSV?, and 2. How integration of different losses into a unified multi-loss function lead to an improved learning framework? These questions are studied based on analysis of three loss functions, including cross entropy, Cauchy-Schwarz divergence, and hinge loss. According to complementary features of these losses, we combine them into a dynamic multi-loss function and propose a novel ensemble framework for simultaneous use of them in CNN. Our proposed Multi-Loss Snapshot Ensemble (MLSE) consists of several sequential trials. In each trial, a dominant loss function is selected from the multi-loss set, and the remaining losses act as a regularizer. Different trials learn diverse representations for each input based on signature identification task. This multi-representation set is then employed for the verification task. An ensemble of SVMs is trained on these representations, and their decisions are finally combined according to the selection of most generalizable SVM for each user. We conducted two sets of experiments based on two different protocols of OSV, i.e., writer-dependent and writer-independent on three signature datasets: GPDS-Synthetic, MCYT, and UT-SIG. Based on the writer-dependent OSV protocol, On UT-SIG, we achieved 6.17% Equal Error Rate (EER) which showed substantial improvement over the best EER in the literature, 9.61%. Our method surpassed state-of-the-arts by 2.5% on GPDS-Synthetic, achieving 6.13%. Our result on MCYT was also comparable to the best previous results. The

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: Google’s new AI technology detects cardiac issues using retinal scan

引用

Applied Nanoscience 2022年第4期13卷 3137-3137页

作者： Borra, Surya Prasada Rao Sumathy, B. Ismail, B. Mohammed Kumar, S. Naresh Phasinam, Khongdet Ramesh, R. Prasad V. Potluri Siddhartha Institute of Technology Vijayawada India Instrumentation and Control Engineering Srisairam Engineering College Chennai India Department of Information Technology Kannur University Kannur India School of Computer Science and Artificial Intelligence SR University Warangal India School of Agricultural and Food Engineering Faculty of Food and Agricultural Technology Pibulsongkram Rajabhat University Phitsanulok Thailand Department of Science and Humanities Sri Krishna College of Engineering and Technology Coimbatore India

来源：评论

学校读者我要写书评

暂无评论

On the performance of dual-hop systems over mixed FSO/mmWave fading channels

arXiv

引用

arXiv 2020年

作者： Zhang, Yan Zhang, Jiayi Yang, Liang Ai, Bo Alouini, Mohamed-Slim School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China Thuwal Makkah Province Saudi Arabia

Free-space optical (FSO) links are considered as a cost-efficient way to fill the backhaul/fronthaul connectivity gap between millimeter wave (mmWave) access networks and optical fiber based central networks. In this paper, we investigate the end-to-end performance of dual-hop mixed FSO/mmWave systems to address this combined use. The FSO link is modeled as a Gamma-Gamma fading channel using both heterodyne detection and indirect modulation/direct detection with pointing error impairments, while the mmWave link experiences the fluctuating two-ray fading. Under the assumption of both amplify-and-forward and decode-and-forward relaying, we derive novel closed-form expressions for the outage probability, average bit error probability (BER), ergodic capacity, effective capacity in terms of bivariate Fox’s H-functions. Additionally, we discuss the diversity gain and provide other important engineering insights based on the high signal-to-noise-ratio analysis of the outage probability and the average BER. Finally, all our analytical results are verified using Monte Carlo simulations. Copyright © 2020, The Authors. All rights reserved.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Workload Allocation Based on User Mobility in Mobile Edge Computing

引用

Journal on Big Data 2020年第3期2卷 105-115页

作者： Tengfei Yang Xiaojun Shi Yangyang Li Binbin Huang Haiyong Xie Yanting Shen National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data(NEL-PSRPC) BeijingChina National Computer Network Emergency Response Technical Team Coordination Center of China BeijingChina Department of Science and Technology China Electronics Technology Group CorporationBeijingChina School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhouChina University of Science and Technology of China HefeiChina

Mobile Edge Computing(MEC)has become the most possible network architecture to realize the vision of interconnection of all *** offloading compute-intensive or latency-sensitive applications to nearby small cell base stations(sBSs),the execution latency and device power consumption can be reduced on resource-constrained mobile ***,computation delay of Mobile Edge Network(MEN)tasks are neglected while the unloading decision-making is studied in *** this paper,we propose a workload allocation scheme which combines the task allocation optimization of mobile edge network with the actual user behavior activities to predict the task allocation of single *** obtain the next possible location through the user's past location information,and receive the next access server according to the grid ***,the next time task sequence is calculated on the base of the historical time task sequence,and the server is chosen to preload the *** the experiments,the results demonstrate a high accuracy of our proposed model.

关键词： Edge computing workload allocation social-LSTM context-sensitive user mobility

来源：评论

学校读者我要写书评

暂无评论

Garbage image recognition and classification based on hog feature and SVM-Boosting

引用

Journal of Physics: Conference Series 2021年第1期1966卷

作者： Wang Weifeng Zhang Baobao Wang ZhiQiang Zhang FangZhi Liu Qiang School of Safety Science and Engineering Xi'an University of Science and Technology Xi'an 710054 China School of Electrical and Control Engineering Xi'an University of Science and Technology Xi'an 710054 China School of Computer Science and Technology Xi'an University of Science and Technology Xi'an 710054 China

Due to the diversity of garbage types in our daily life, we will encounter many difficulties in the process of classification. In this regard, I combine hog features and boosting algorithm to develop a SVM classification method. Firstly, the input image is preprocessed to make the image more recognizable. Secondly, the hog algorithm is used to extract the features of the image. Finally, the classification device is trained, and the relevant information is sent to the image set. On this basis, the classification situation is detected. The final results show that the classification efficiency of the algorithm is as high as 95% or even more, which is about 10% higher than that of single SVM classification method. It can accurately classify garbage and has certain feasibility.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stochastic Link Flow Model for Signalized Traffic Networks with Uncertainty in Demand

引用

IFAC-PapersOnLine 2018年第9期51卷 458-463页

作者： Lin, S. Pan, T.L. Lam, W.H.K. Zhong, R.X. Schutter, B. De School of Computer and Control Engineering University of Chinese Academy of Sciences Key Laboratory of System Control and Information Processing Ministry of Education BeijingShanghai China Department of Civil and Structural Engineering The Hong Kong Polytechnic University Hong KongSAR Hong Kong School of Engineering Sun Yat-Sen University Guangzhou China Delft Center for Systems and Control Delft University of Technology Delft Netherlands

In order to investigate the stochastic features in urban traffic dynamics, we propose a Stochastic Link Flow Model (SLFM) for signalized traffic networks with demand uncertainties. In the proposed model, the link traffic state is described using four different link state modes, and the probability for each link state mode is determined based on the stochastic link states. The SLFM model is expressed as a finite mixture approximation of the link state probabilities and the dynamic link flow models for all the four link state modes. Using data from microscopic traffic simulator SUMO, we illustrate that the proposed model can provide a reliable estimation of the link traffic states, and as well as good estimations on the link state uncertainties propagating within a signalized traffic network. © 2018

关键词： Stochastic models Routers Stochastic systems Street traffic control Traffic signals Vehicle actuated signals Demand uncertainty Finite mixtures Stochastic features Stochastic traffic Traffic networks Traffic simulators Uncertainty in demand Urban traffic networks

来源：评论

学校读者我要写书评

暂无评论

Monitoring Model of Coal Mill in Power Plant Based on Big Data and BP Neural Network

Monitoring Model of Coal Mill in Power Plant Based on Big Da...

引用

Chinese Automation Congress (CAC)

作者： Yanping Li Liang Tian Yaokui Gao Yongping Li School of control and computer Engineering North China Electric Power University Beijing China School of control and computer Engineering North China Electric Power University Baoding China Electrical Power Design and Explore Institute of Inner Mongolia Co. Ltd Hohhot China

In order to monitor the wear condition of grinding roller of coal mill in power plant and improve the reliability of production equipment, it is necessary to establish a state monitoring model with high accuracy and good prediction effect. It has been shown that the power of coal mill can reflect the wear degree of grinding roller. If the voltage and power factor of coal mill are constant, grinding current can be used to replace the power of coal mill. In this paper, through collecting field historical operation data and data preprocessing, the current model of coal mill is established by using double hidden layers BP (Back Propagation) neural network to predict the wear state of grinding roller. The simulation results show that compared with single hidden layer, double hidden layers BP neural network can improve the performance of the network, so as to improve the prediction accuracy of the model and provide basis for the follow-up maintenance of coal mill, which has certain practical engineering significance.

关键词： Coal Neural networks Data models Predictive models Power generation Mathematical model Training

来源：评论

学校读者我要写书评

暂无评论

Research on Modeling and Simulation of Smart Substation Cyber-Physical System Considering Coupling Analysis

引用

Journal of Physics: Conference Series 2021年第1期1771卷

作者： Huifeng Yang Liandong Chen Kai Cheng Gang Li Xinying Wang State Grid Hebei Information & Telecommunication Branch Shijiazhuang Hebei China North China Electric Power University/School of Control and Computer Engineering Baoding Hebei China

With the rapid development of Internet of Things and communication technologies, substations are becoming more intelligent, which brings opportunities for cyber attacks, threatens the safety of substations, and the high coupling of equipment in substations increases the threat. This paper analyzes and studies the information-physical characteristics and equipment coupling problems of smart substations, constructs a smart substation CPS model based on the balance equation of state quantity, and designs a line fault simulation example to verify the stability of the model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：