检索结果-南通市图书馆

Novel Apriori-Based Multi-Label Learning Algorithm by Exploiting Coupled Label Relationship

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 Beijing Institute of Technology 2017年第2期26卷 206-214页

作者： Zhenwu Wang Longbing Cao department of computer science and Technology China University of Mining and Technology(Beijing) The Advanced Analytics Institute University of TechnologySydney

It is a key challenge to exploit the label coupling relationship in multi-label classification（MLC）*** previous work focused on label pairwise relations,in which generally only global statistical information is used to analyze the coupled label *** this work,firstly Bayesian and hypothesis testing methods are applied to predict the label set size of testing samples within their k nearest neighbor samples,which combines global and local statistical information,and then apriori algorithm is used to mine the label coupling relationship among multiple labels rather than pairwise labels,which can exploit the label coupling relations more accurately and *** experimental results on text,biology and audio datasets shown that,compared with the state-of-the-art algorithm,the proposed algorithm can obtain better performance on 5 common criteria.

关键词： multi-label classification hypothesis testing k nearest neighbor apriori algorithm label coupling

Classification by ALH-Fast Algorithm

在线全文

学校读者我要写书评

暂无评论

Tsinghua science and Technology 2010年第3期15卷 275-280页

作者： Tao Yang Vojislav Kecman Longbing Cao Faculty of Engineering and Information Technology University of Technology Sydney Sydney 2007 Australia department of computer science The Virginia Commonwealth University (VCU) Richmond VA 23284-3068 USA

The adaptive local hyperplane （ALH） algorithm is a very recently proposed classifier, which has been shown to perform better than many other benchmarking classifiers including support vector machine （SVM）, K-nearest neighbor （KNN）, linear discriminant analysis （LDA）, and K-local hyperplane distance nearest neighbor （HKNN） algorithms. Although the ALH algorithm is well formulated and despite the fact that it performs well in practice, its scalability over a very large data set is limited due to the online distance computations associated with all training instances. In this paper, a novel algorithm, called ALH-Fast and obtained by combining the classification tree algorithm and the ALH, is proposed to reduce the computational load of the ALH algorithm. The experiment results on two large data sets show that the ALH-Fast algorithm is both much faster and more accurate than the ALH algorithm.

关键词： classification adaptive local hyperplane (ALH) decision tree

A Real-Time Pedestrian Social Distancing Risk Alert System for COVID-19

在线全文

学校读者我要写书评

暂无评论

computer Systems science & Engineering 2023年第10期47卷 937-954页

作者： Zhihan Liu Xiang Li Siqi Liu Wei Li Xiangxu Meng Jing Jia College of computer science and Technology Harbin Engineering UniversityHarbin150001China department of Clinical Laboratory Harbin Medical University Cancer HospitalHarbinHeilongjiang150081China Faculty of Arts Design and ArchitectureSchool of Built EnvironmentThe University of New South WalesSydneyNSW 2052Australia

The COVID-19 virus is usually spread by small droplets when talking,coughing and sneezing,so maintaining physical distance between people is necessary to slow the spread of the *** World Health Organization(WHO)recommends maintaining a social distance of at least six *** this paper,we developed a real-time pedestrian social distance risk alert system for COVID-19,whichmonitors the distance between people in real-time via video streaming and provides risk alerts to the person in charge,thus avoiding the problem of too close social distance between pedestrians in public *** design a lightweight convolutional neural network architecture to detect the distance between people more *** addition,due to the limitation of camera placement,the previous algorithm based on flat view is not applicable to the social distance calculation for cameras,so we designed and developed a perspective conversion module to reduce the image in the video to a bird’s eye view,which can avoid the error caused by the elevation view and thus provide accurate risk indication to the *** selected images containing only person labels in theCOCO2017 dataset to train our *** experimental results show that our network model achieves 82.3%detection accuracy and performs significantly better than other mainstream network architectures in the three metrics of Recall,Precision and mAP,proving the effectiveness of our system and the efficiency of our technology.

关键词： Convolutional neural network pedestrian detection social distancing COVID-19

Behavioral Feature and Correlative Detection of Multiple Types of Node in the Internet of Vehicles

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2020年第8期64卷 1127-1137页

作者： Pengshou Xie Guoqiang Ma Tao Feng Yan Yan Xueming Han School of computer and Communications Lanzhou University of TechnologyLanzhou730050China department of Computing Faculty of Science and EngineeringMacquarie UniversitySydneyNSW 2109Australia

Undoubtedly,uncooperative or malicious nodes threaten the safety of Internet of Vehicles(IoV)by destroying routing or *** this end,some researchers have designed some node detection mechanisms and trust calculating algorithms based on some different feature parameters of IoV such as communication,data,energy,etc.,to detect and evaluate vehicle ***,it is difficult to effectively assess the trust level of a vehicle node only by message forwarding,data consistency,and energy *** order to resolve these problems,a novel mechanism and a new trust calculating model is proposed in this ***,the four tuple method is adopted,to qualitatively describing various types of nodes of IoV;Second,analyzing the behavioral features and correlation of various nodes based on route forwarding rate,data forwarding rate and physical location;third,designing double layer detection feature parameters with the ability to detect uncooperative nodes and malicious nodes;fourth,establishing a node correlative detection model with a double layer structure by combining the network layer and the perception ***,we conducted simulation experiments to verify the accuracy and time of this detection method under different speed-rate topological conditions of *** results show that comparing with methods which only considers energy or communication parameters,the method proposed in this paper has obvious advantages in the detection of uncooperative and malicious nodes of IoV;especially,with the double detection feature parameters and node correlative detection model combined,detection accuracy is effectively improved,and the calculation time of node detection is largely reduced.

关键词： IoV behavioral feature double layer detection feature correlation analysis correlative detection model

Balance Control of a Biped Robot on a Rotating Platform Based on Efficient Reinforcement Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第4期6卷 938-951页

作者： Ao Xi Thushal Wijekoon Mudiyanselage Dacheng Tao Chao Chen the department of Mechanical and Aerospace Engineering Monash UniversityClaytonVIC 3800Australia IEEE Monash university ClaytonVIC 3800Australia the UBTECH sydney Artificial Intelligence Centre and the School of computer science the Faculty of Engineeringthe University of SydneyNSW 2008Australia

In this work,we combined the model based reinforcement learning(MBRL)and model free reinforcement learning(MFRL)to stabilize a biped robot(NAO robot)on a rotating platform,where the angular velocity of the platform is unknown for the proposed learning algorithm and treated as the external *** Gaussian processes normally require a large number of training data points to deal with the discontinuity of the estimated *** some improved method such as probabilistic inference for learning control(PILCO)does not require an explicit global model as the actions are obtained by directly searching the policy space,the overfitting and lack of model complexity may still result in a large deviation between the prediction and the real ***,none of these approaches consider the data error and measurement noise during the training process and test process,*** propose a hierarchical Gaussian processes(GP)models,containing two layers of independent GPs,where the physically continuous probability transition model of the robot is *** to the physically continuous estimation,the algorithm overcomes the overfitting problem with a guaranteed model complexity,and the number of training data is also *** policy for any given initial state is generated automatically by minimizing the expected cost according to the predefined cost function and the obtained probability distribution of the ***,a novel Q(λ)based MFRL method scheme is employed to improve the *** results show that the proposed RL algorithm is able to balance NAO robot on a rotating platform,and it is capable of adapting to the platform with varying angular velocity.

关键词： Biped robot Gaussian processes(GP) reinforcement learning temporal difference

Real-Time and Intelligent Flood Forecasting Using UAV-Assisted Wireless Sensor Network

在线全文

学校读者我要写书评

暂无评论

computers, Materials & Continua 2022年第1期70卷 715-738页

作者： Shidrokh Goudarzi Seyed Ahmad Soleymani Mohammad Hossein Anisi Domenico Ciuonzo Nazri Kama Salwani Abdullah Mohammad Abdollahi Azgomi Zenon Chaczko Azri Azmi Centre for Artificial Intelligent(CAIT) Universiti Kebangsaan MalaysiaBangi43600Malaysia School of computer Engineering Iran University of Science and TechnologyResalat Sq.16846-13114TehranIran School of Computing Faculty of Engineering Universiti Teknologi MalaysiaJohorMalaysia School of computer science and Electronic Engineering University of EssexColchester CO43SQUnited Kingdom department of Electrical Engineering and Information Technologies University of Naples“Federico II”Naples80125Italy Razak Faculty of Technology and Informatics Universiti Teknologi MalaysiaKuala Lumpur54100Malaysia School of Electrical and Data Engineering University of Technology SydneyUltimoNSWAustralia

The Wireless Sensor Network(WSN)is a promising technology that could be used to monitor rivers’water levels for early warning flood detection in the 5G ***,during a flood,sensor nodes may be washed up or become faulty,which seriously affects network *** address this issue,Unmanned Aerial Vehicles(UAVs)could be integrated with WSN as routers or data mules to provide reliable data collection and flood *** light of this,we propose a fault-tolerant multi-level framework comprised of a WSN and a UAV to monitor river *** framework is capable to provide seamless data collection by handling the disconnections caused by the failed nodes during a ***,an algorithm hybridized with Group Method Data Handling(GMDH)and Particle Swarm Optimization(PSO)is proposed to predict forthcoming floods in an intelligent collaborative *** proposed water-level prediction model is trained based on the real dataset obtained fromthe Selangor River *** performance of the work in comparison with other models has been also evaluated and numerical results based on different metrics such as coefficient of determination(R2),correlation coefficient(R),RootMean Square Error(RMSE),Mean Absolute Percentage Error(MAPE),and BIAS are provided.

关键词： Unmanned aerial vehicles wireless sensor networks group method data handling particle swarm optimization river flow prediction

SELECTED PAPERS FROM IEEE/CIC ICCC 2017

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2018年第4期15卷 I0003-I0005页

作者： Cheng-Xiang Wang Guoqiang Mao Ekram Hossain Xiaotian Zhou Heriot-Watt university the university of Technology sydney department of Electrical and computer Engineering at university of Manitoba school of Information science and Engineering Shandong University

The IEEE/CIC International Conference on Communication in China(ICCC)has been globally recognized as one of the important annual international conference held by the IEEE Communication Society(Com Soc)and China Institute of Communication(CIC)in *** sixth IEEE/CIC ICCC 2017 was held in the magnificent city of Qingdao,China,22-24 October,

关键词：国际会议计算中心报纸 IEEE 中国通讯研究所

Colouring of COVID-19 Affected Region Based on Fuzzy Directed Graphs

在线全文

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第7期68卷 1219-1233页

作者： Rupkumar Mahapatra Sovan Samanta Madhumangal Pal Jeong-Gon Lee Shah Khalid Khan Usman Naseem Robin Singh Bhadoria department of Applied Mathematics with Oceanology and computer Programming Vidyasagar UniversityMidnapore721102India department of Mathematics Tamralipta MahavidyalayaTamluk721636India Division of Applied Mathematics Wonkwang UniversityIksan-SiJeonbuk54538Korea School of Engineering RMIT UniversityMelbourne3001Australia School of computer science University of Sydney Sydney2006Australia department of computer science&Engineering Birla Institute of Applied Sciences(BIAS)BhimtalUttarakhand263136India

Graph colouring is the system of assigning a colour to each vertex of a *** is done in such a way that adjacent vertices do not have equal *** is fundamental in graph *** is often used to solve real-world problems like traffic light signalling,map colouring,scheduling,***,social networks are prevalent systems in our ***,the users are considered as vertices,and their connections/interactions are taken as *** users follow other popular users’profiles in these networks,and some don’t,but those non-followers are connected directly to the popular *** means,along with traditional relationship(information flowing),there is another relation among *** depends on the domination of the relationship between the *** type of situation can be modelled as a directed fuzzy *** the colouring of fuzzy graph theory,edge membership plays a vital *** membership is a representation of flowing information between end nodes of the *** from the communication relationship,there may be some other factors like domination in *** influence of power is captured *** this article,the colouring of directed fuzzy graphs is defined based on the influence of *** with this,the chromatic number and strong chromatic number are provided,and related properties are *** application regarding COVID-19 infection is presented using the colouring of directed fuzzy graphs.

关键词： Graph colouring chromatic index directed fuzzy graphs

Graph-Based Chinese Word Sense Disambiguation with Multi-Knowledge Integration

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2019年第7期61卷 197-212页

作者： Wenpeng Lu Fanqing Meng Shoujin Wang Guoqiang Zhang Xu Zhang Antai Ouyang Xiaodong Zhang School of computer science and Technology Qilu University of Technology(Shandong Academy of Sciences)Jinan250353China School of Information science and Engineering Zaozhuang UniversityZaozhuang277160China department of Computing Macquarie UniversitySydneyNSW 2109Australia Centre for Audio Acoustics and VibrationUniversity of Technology SydneySydneyNSW 2006Australia School of computer science and Engineering Shandong University of Science and TechnologyQingdao266590China Jinan Intellectual Property Information Center Jinan250099China

Word sense disambiguation(WSD)is a fundamental but significant task in natural language processing,which directly affects the performance of upper ***,WSD is very challenging due to the problem of knowledge bottleneck,i.e.,it is hard to acquire abundant disambiguation knowledge,especially in *** solve this problem,this paper proposes a graph-based Chinese WSD method with multi-knowledge ***,a graph model combining various Chinese and English knowledge resources by word sense mapping is ***,the content words in a Chinese ambiguous sentence are extracted and mapped to English words with ***,English word similarity is computed based on English word embeddings and knowledge *** word similarity is evaluated with Chinese word embedding and HowNet,*** weights of the three kinds of word similarity are optimized with simulated annealing algorithm so as to obtain their overall similarities,which are utilized to construct a disambiguation *** graph scoring algorithm evaluates the importance of each word sense node and judge the right senses of the ambiguous *** experimental results on SemEval dataset show that our proposed WSD method significantly outperforms the baselines.

关键词： Word sense disambiguation graph model multi-knowledge integration word similarity