Time filter

Source Type

Liang H.,Jilin University | Liang H.,Changchun Taxation College | Zuo W.,Jilin University | Zuo W.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | And 2 more authors.
Journal of Software | Year: 2010

Search engines and web crawlers can not access the Deep Web directly. The workable way to access the hidden database is through query interfaces. Automatic extracting attributes from query interfaces and translating queries is a solvable way for addressing the current limitations in accessing Deep Web. However, the query interface provides semantic constraints, some attributes are co-occurred and the others are exclusive sometimes. To generate a valid query, we have to reconcile the key attributes and semantic relation between them. We design a framework to automatically extract attributes from query interfaces taking full advantage of instances information and enrich the attribute sets embedded in the semantic query interface by Ontology technique. Each attribute is extended into a candidate attribute expressed by a hierarchy tree and describes the semantic relation of the attributes. We carry out our experiments in the real-world domain and results showed the validation of query translation framework. © 2010 ACADEMY PUBLISHER.


Peng T.,Jilin University | Peng T.,University of Illinois at Urbana - Champaign | Peng T.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | Liu L.,Jilin University | Liu L.,University of Illinois at Urbana - Champaign
Applied Soft Computing Journal | Year: 2015

As a data mining method, clustering, which is one of the most important tools in information retrieval, organizes data based on unsupervised learning which means that it does not require any training data. But, some text clustering algorithms cannot update existing clusters incrementally and, instead, have to recompute a new clustering from scratch. In view of above, this paper presents a novel down-top incremental conceptual hierarchical text clustering approach using CFu-tree (ICHTC-CF) representation, which starts with each item as a separate cluster. Term-based feature extraction is used for summarizing a cluster in the process. The Comparison Variation measure criterion is also adopted for judging whether the closest pair of clusters can be merged or a previous cluster can be split. And, our incremental clustering method is not sensitive to the input data order. Experimental results show that the performance of our method outperforms k-means, CLIQUE, single linkage clustering and complete linkage clustering, which indicate our new technique is efficient and feasible. © 2014 Elsevier B.V. All rights reserved.


Zhang J.,Jilin University | Zhang J.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | Jia X.,Jilin University | Li J.,Jilin University
Journal of Intelligent and Fuzzy Systems | Year: 2015

In order to detect lane rapidly and accurately, the integration of scanning and image processing algorithms (SIP) based on the fuzzy method is proposed. Further, combination of the proposed algorithm with an adaptive threshold value for image binarization, the least-square method and Bessel curve algorithm are proposed for detection and to fit the lane. The proposed SIP algorithm was evaluated by various tests. The experimental results indicate that the average time consumed for the detection of lane in each frame is 16.7639 ms, and the accuracy of lane detection is 95. The proposed algorithm demonstrates good robustness, and can be used as the core algorithm for further application in lane departure warning systems. © 2015 - IOS Press and the authors. All rights reserved.


Chen K.,Jilin University | Chen K.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | Zhao J.,Zhengzhou University of Light Industry | Zuo W.,Jilin University | And 2 more authors.
Journal of Convergence Information Technology | Year: 2010

This paper proposed a complex ontology evolution based method of extracting data, and also completely designed an extraction system, which consists of four important components: Resolver, Extractor, Consolidator and the ontology construction components. The system gives priority to the construction of mini-ontology. When the user submits query keywords to the deep web query interface, the returned result will pass through the prior three components; after that, the final execution result will be returned to user in a unified form. This paper adopted an extraction method that is different from the general ontology extraction. More specifically, the ontology used in extraction here is dynamic evolution, which can adapt various data source better. Experimental results proved that this method could effectively extract the data in the query result pages.


Chen Y.,Jilin University | Chen Y.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | Zuo W.,Jilin University | He F.,Jilin University | Chen K.,Jilin University
Journal of Convergence Information Technology | Year: 2010

Chip Multi-Processor (CMP) could support more than two threads to execute simultaneously, and some executing units are owned by each core. Because threads share various resources of CMP, such as L2-Cache, among many threads, CMP system is inherently different from multiprocessors system and, CMP is also different from simultaneously multithreading (SMT). In this paper a novel and complete approach on how to parallelism for relational database multithreaded query execution that strives for maximum resource utilization for both CPU and disk activities. The focus of this approach is on how to use the multithreaded parallel technique to optimize and process queries based on multi-core architecture. A set of algorithms for implementing and optimizing the best query plan, such as the algorithms for scheduling and parallel executing the query plan, the algorithms for allocating thread to sub-query and memory to the buffers between operations in pipelining execution, are proposed in this method. Additionally this paper analysis and optimize the implementation of parallel buffers and multithread. In the experiments, this paper evaluates performance of the parallel buffers and tests the coordination of the multithread.


Kerui C.,Jilin University | Kerui C.,Key Laboratory of Symbol Computation and knowledge Engineering of the Ministry of Education | Jinchao Z.,Zhengzhou University of Light Industry | Wanli Z.,Jilin University | And 3 more authors.
International Journal of Digital Content Technology and its Applications | Year: 2011

Deep web could automatically produce web pages according to the query criteria of users. The report found most query result page store data information using table form. Knowledge management, information retrieval, Web mining, abstract extraction and so on were benefited from automatically understanding of table forms. The study web forms on the web information extraction and integration have important significance. This paper proposed a domain-specific ontology based strategy for integration tables, and this method could independent the structure of table. Experimental results confirm that this method could effectively improve the accuracy of integration.


Chen K.,Jilin University | Chen K.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | Zuo W.,Jilin University | Zuo W.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | And 4 more authors.
Communications in Computer and Information Science | Year: 2011

Schema matching is the process of identifying semantic mappings, or correspondences, between two or more schemas. Schema matching is a first step and critical part of data integration. For schema matching of deep web, most researches only interested in query interface, while rarely pay attention to abundant schema information contained in query result pages. This paper proposed a mixed schema matching technique, which combines attributes that appeared in query structures and query results of different data sources, and mines the matched schemas inside. Experimental results prove the effectiveness of this method for improving the accuracy of schema matching. © Springer-Verlag Berlin Heidelberg 2011.


Dong X.,Jilin University | Dong X.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | Ouyang D.,Jilin University | Ouyang D.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | And 6 more authors.
3rd International Conference on Knowledge Discovery and Data Mining, WKDD 2010 | Year: 2010

In this paper, we present a novel deterministic heuristic and a new genetic algorithm to solve the problem of optimal triangulation of Bayesian networks. The heuristic, named MinFillWeight, aims to select variables minimizing the multiplication of the weights on nodes of fill-in edges. The genetic algorithm, named GA-MFW, uses a new rankreserving crossover operator and a 2-fold mutation mechanism utilizing the MinFillWeight heuristic. Experiments on representative benchmark show that the deterministic heuristic and the stochastic algorithm have good performance and stability to various problems. © 2010 IEEE.


Zhang Y.-G.,Jilin University | Zhang Y.-G.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | Zhang S.-B.,Jilin University | Zhang S.-B.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | And 2 more authors.
Tongxin Xuebao/Journal on Communications | Year: 2015

The traditional backtracking algorithm was less efficient on solving large-scale constraint satisfaction problem, and more difficult to be solved within a reasonable time. In order to overcome this problem, many incompleteness algorithms based on heuristic search have been proposed. Two improvements based on ant colony optimization meta-heuristic constraint solving algorithm were presented: First, arc consistency checks was done to preprocess before exploring the search space, Second, a new parameter setting scheme was proposed for ant colony optimization to improve the efficiency of the search. Finally, the improved algorithm is applied to solve random problems and combinatorial optimization problems. The results of the experiment have showed its superiority. ©, 2015, Editorial Board of Journal on Communications. All right reserved.


Zhang J.,Jilin University | Zhang J.,Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education | Jia X.,Jilin University | Zhou Z.,Jilin University
Optik | Year: 2015

To tackle the string stability problem of a vehicle platoon, an efficient collision prevention pre-compensation control algorithm called CPPC is proposed in this paper. In the algorithm, acceleration, speed, location, communication delay and spacing errors are introduced. The safe distance between vehicles is used to keep driving safety. We evaluate our algorithm experimentally using simulation method and compared it with the no string stability control algorithm. It reveals very encouraging simulation results indicate effectiveness of the proposed approach. © 2015 Elsevier GmbH.

Loading Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education collaborators
Loading Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education collaborators