检索结果-内蒙古大学图书馆

Construction of extraction model for ontology concept of four diagnostics information

Journal of Computational Information Systems 2015年第7期11卷 2367-2376页

作者： Yuan, Feng Chen, Shouqiang Liu, Hong Xu, Liang School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Shandong Normal University Jinan China School of Information Engineering Shandong Management University Jinan China Center of Hear of the Second Affiliated Hospital of Shandong University of Traditional Chinese Medicine Jinan China Shandong University of Traditional Chinese Medicine Jinan China

This paper is aimed at extraction of ontology concept from four diagnostics information. Due to the diversity and complexity of the four diagnostics information, there are still some difficulties when practicing ontology learning methods for TCM medical cases, so a new concept extraction method combining composite seed extraction and extended concept extraction is proposed for four diagnostics information corpus of TCM. Composite seed extraction refers to a method in which the mutual information is used to determine the appropriateness of word formation between seed and collocations by using seeds as headword to generate concepts. Extended concept extraction refers to a method in which the membership in the domain is used set the fitness function so as to extract extended concept with the assistance of artificial bee colony (ABC) algorithm. The candidate set of concepts is built by combining composite seed concept and extended concept. Through a confirmatory experiment on four diagnostics information corpus of TCM medical cases, this method is cautiously confirmed effective for concept extraction. Hence, this method has a certain reference value for ontology construction of four diagnostics information. ©, 2015, Binary Information Press. All right reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

The population-based optimization algorithms for role modelling and path generation in group animation

Journal of Software

引用

Journal of software 2014年第1期9卷 26-36页

作者： Liu, Hong Li, Yuanyuan Yu, Hanchao School of Information Science and Engineering Shandong Normal University Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan City China School of Information Science and Engineering Shandong Normal University Jinan City China

Traditional animation by key frame techniques takes animators lots of time and vigour to model and simulate behaviours of crowds. For solving this problem, this paper presents a novel group animation generation approach based on population-based optimization algorithms. It is mainly divided into two parts. First, it puts forward a role modelling approach based on dynamic selfadaptive genetic algorithm and NURBS technology. Second, following the introduction to PSO (Particle Swarm Optimization) algorithm, a group path generative approach is presented. It simulates group behaviours, including cohesion and separation, dynamic object tracking and collision avoidance. Finally, a group of shark modelling and path generation images are exhibited as examples. © 2014 ACADEMY PUBLISHER.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

AFSA based path planning method for crowd evacuation

引用

Journal of Information and Computational Science 2014年第11期11卷 3815-3823页

作者： Lu, Dianjie Zhang, Guijuan Liu, Yiliang Wang, Dequan Liu, Hong School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China School of Computer Science Fudan University Shanghai China

Path planning is critical to the efficiency and fidelity of the crowd evacuation simulation. In this paper, we propose a new path planning method for crowd evacuation based on an improved AFSA. In our method, the crowd simulated by the artificial fish swarm and the position of the crowd in evacuation scenario can be obtained through computing the position and direction of artificial fishes. In addition, we also introduce the PSO algorithm to calculate the velocity of artificial fishes in order to make the crowd evacuation simulation more realistic. Finally, we implement our method in different scenarios on the ACIS/HOOPS platform. The simulation shows that our method can enhance the efficiency and fidelity of crowd evacuation simulation. ©2014 Binary Information Press

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

IMLNB: Multi-label Naive Bayes classification based on ICA

引用

Journal of Computational Information Systems 2014年第12期10卷 5067-5074页

作者： Zheng, Xiyuan Zhang, Huaxiang Gao, Shuang School of Information Science and Engineering Shandong Normal University Jinan 250014 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan 250014 China Jinan 250101 China

Multi-label learning is initially used to deal with the difficult text classification problems of ambiguity concept, in which each document can belong to multiple topics simultaneously. In this paper, a novel multi-label learning method named IMLNB is proposed based on the traditional Naive Bayes algorithm. IMLNB first deals with the multi-label data set by using Independent Component Analysis (ICA), and then calculates the prior probabilities of each label. After that, it estimates the Gaussian distribution parameters of each dimensionality vector and then calculates the weight of each dimensionality vector and the posteriori probabilities. IMLNB can give the label predictions using the computed posteriori probabilities. Experimental results show that IMLNB can predict the possible labels of a new instance accurately. 1553-9105/Copyright © 2014 Binary Information Press.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Bi-direction link prediction in dynamic multi-dimension networks

引用

Journal of Computational Information Systems 2014年第3期10卷 1333-1340页

作者： Wang, Hong Yuan, Weihua Yu, Xiaomei School of Information Science and Engineering Shandong Normal University Jinan 250014 China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan 250000 China School of Computer Science and Technology Shandong Jianzhu University Jinan 250101 China

Recently, many researchers have been attracted in link prediction which is an effective technique to be used in graph based models analysis. By using link prediction method can we understand associations between nodes. To the best of our knowledge, most of previous works in this area have not explored the prediction of links in dynamic Multi-dimension Networks and have not explored the prediction of links which could disappear in the future. We argue that these kinds of links are important. At least they can do complement for current link prediction processes in order to plan better for the future. In this paper, we propose a link prediction model, which is capable of predicting bi-direction links that might exist and may disappear in the future in dynamic Multi-dimension Networks. Firstly, we present the definition of multi-dimensional networks, reduction dimension networks and dynamic networks. Then we put forward some algorithms which build Multi-dimension Networks, reduction dimension networks and dynamic networks. After that, we give bi-direction link prediction algorithms in dynamic multi-dimension weighted networks. At the end, algorithms above are applied in recommendation networks. Experimental results show that these algorithms can improve the link prediction performance in dynamic multi-dimensional weighted networks. © 2014 Binary Information Press.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Application and research of improved probability matrix factorization techniques in collaborative filtering

International Journal of Control and Automation

引用

International Journal of Control and Automation 2014年第8期7卷 79-92页

作者： Zhang, Zhijun Liu, Hong School of Information Science and Engineering Shandong Normal University Jinan Shandong 250014 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Jinan Shandong 250014 China School of Computer Science and Technology Shandong Jianzhu University Jinan Shandong 250101 China

The matrix factorization algorithms such as the matrix factorization technique (MF), singular value decomposition (SVD) and the probability matrix factorization (PMF) and so on, are summarized and compared. Based on the above research work, a kind of improved probability matrix factorization algorithm called MPMF is proposed in this paper. MPMF determines the optimal value of dimension D of both the user feature vector and the item feature vector through experiments. The complexity of the algorithm scales linearly with the number of observations, which can be applied to massive data and has very good scalability. Experimental results show that MPMF can not only achieve higher recommendation accuracy, but also improve the efficiency of the algorithm in sparse and unbalanced data sets compared with other related algorithms. © 2014 SERSC.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Efficient routing in wireless sensor networks with multiple sessions

引用

Sensors and Transducers 2014年第5期171卷 99-105页

作者： Lu, Dianjie Zhang, Guijuan Han, Ren Zheng, Xiangwei Liu, Hong School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China

Wireless Sensor Networks (WSNs) are subject to node failures because of limited energy and link unreliability which makes the design of routing protocols in such networks a challenging task. The multipath routing scheme is an optimal alternative to address this problem which splits the traffic across multiple paths instead of routing all the traffic along a single path. However, using more paths introduces more contentions which degrade energy efficiency. The problem becomes even more difficult in the scenario of multiple sessions since different source-destination pairs may pass the same link which makes the flow distribution of each link uncertain. Our goal is to minimize the energy cost and provide the robust transmission by choosing the optimal paths. We first study the problem from a theoretical standpoint by mapping it to the multi-commodity network design problem. Since it is hard to build a global addressing scheme due to the great number of sensor nodes, we propose a distributed Energy Efficient Routing protocol (D2ER). In D2ER, we employ the transportation method which can optimize the flow distribution with minimal energy consumption. Simulation results demonstrate that our optimal algorithm can save energy drastically. © 2014 IFSA Publishing, S. L.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Hybrid collaborative filtering recommendation based on time and diversity

引用

ICIC Express Letters, Part B: Applications 2015年第9期6卷 2539-2545页

作者： Wang, Hong Sun, Yanshen Yu, Xiaomei Wang, Jihua School of Information Science and Engineering Shandong Normal University No. 88 East Wenhua Road Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology No. 88 East Wenhua Road Jinan China School of Earth Sciences Zhejiang University No. 388 Yuhangtang Road Hangzhou China

Many researchers have been attracted in personalized recommendation which is considered as one of the most effective methods to solve the problem of information overloading. We propose a hybrid collaborative filtering recommendation method based on time and diversity in this paper. Firstly, we construct a personalized recommendation model by using an improved frequent item mining method and an improved visibility graph, thus making us obtain user-item networks and user-user networks. Secondly, we define concepts of similarity and similarity index and then put forward a revised recommendation algorithm in the user-user networks based on link mining and diversity. Finally, we apply our methods to four classic datasets in order to evaluate the performance of our algorithms. Experimental results show that our methods do better than traditional collaborative filtering methods and content based recommendation methods in precision, recall and time. © 2015 ISSN 2185-2766

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

New adaptations of classic algorithm for mining frequent itemsets from uncertain data 5

New adaptations of classic algorithm for mining frequent ite...

引用

5th International Conference on Computing Communication and Networking Technologies, ICCCNT 2014

作者： Yu, Xiaomei Wang, Hong Zheng, Xiangwei School of Information Science and Engineering Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Shandong Normal University Jinan Shandong China

ISBN: (纸本)9781479926961

Mining frequent itemsets from traditional database is an important research topic in data mining and researchers achieved tremendous progress in this field. However, with the emergence of new applications, the traditional way of mining frequent itemsets is not available in uncertain environment. In the past ten years, researchers proposed different solutions in extending the conventional techniques into uncertainty environment. In this paper, we review the previous algorithms based on the two definitions of frequent itemsets, then we improve the traditional classic algorithm for mining frequent itemsets in uncertain databases under the definition of frequent probability. Finally, we tested our algorithm on a number of uncertain data sets. The experiments on both sythetic and real data have shown that the new adaptation of classic algorithm is efficient and gain better results on accuracy. © 2014 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A visualization method in virtual educational system

A visualization method in virtual educational system

引用

5th International Symposium on IT in Medicine and Education, ITME 2013

作者： Zhang, Guijuan Lu, Dianjie Liu, Hong School of Information Science and Engineering Shandong Normal University Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan China

ISBN: (纸本)9789400776173

We present a visualization-based knowledge expression approach for virtual educational system in this paper. Our method allows teachers and students to understand complex algorithms and procedures more intuitively and conveniently during the process of teaching and learning. We take the decision tree and the random forest algorithm in the field of Data mining as examples in this paper. In our method, the decision tree is represented by a virtual 3D tree model that both the structure and the classification results can be showed clearly. In addition, random forest is represented by a group of virtual 3D trees and their positions denote the similarity between the decision trees. We also provide several user-interaction tools in our system. The tools help users to browse the forest, select a tree, delete a tree and even see the detail information of the decision tree. The effective and understandable results show the feasibility of applying visualization method in virtual educational system. © Springer Science+Business Media Dordrecht 2014.

关键词： Visualization

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：