Fuzzy Semantic Retrieval for Traffic Information Based on Fuzzy Ontology and RDF on the Semantic Web

758 JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009 Fuzzy Semantic Retrieval for Traffic Information Based on Fuzzy Ontology and RDF on the Seman...
Author: Herbert Woods
5 downloads 0 Views 372KB Size
758

JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009

Fuzzy Semantic Retrieval for Traffic Information Based on Fuzzy Ontology and RDF on the Semantic Web Jun Zhai, Yan Chen, Yi Yu, Yiduo Liang and Jiatao Jiang School of Management, Dalian Maritime University, Dalian 116026, P. R. China [email protected]

Abstract—Information retrieval is the essential task for Traffic Information Service System in Intelligent Transportation Systems (ITS). There a lot of fuzzy traffic information derived from human factor. To achieve fuzzy semantic retrieval, this paper proposes an approach using Resource Description Framework (RDF) and fuzzy ontology. First, we apply RDF data model to represent traffic information on the Semantic Web. Then we present fuzzy linguistic variable ontology models and its formal representation with RDF. Introducing new data type referred as fuzzy linguistic variables to RDF data model, the semantic query expansions in SeRQL query language are constructed by order relation, equivalence relation, inclusion relation and complement relation between fuzzy concepts defined in linguistic variable ontologies. Examples show that the extended query can return all results which satisfy research requirement at semantic level without upgrading current main search algorithm, and this research facilitates the semantic retrieval of traffic information through fuzzy concepts for ITS on the Semantic Web. Index Terms—semantic retrieval, fuzzy ontology, ontology, traffic information, the Semantic Web

I. INTRODUCTION Traffic Information Service System is one of the key components in urban Intelligent Transportation Systems (ITS) [1]-[2]. Several extremely important aspects describe the current problems relating to the access and distribution of information [3]: (1) A great amount of traffic information is distributed among different web sites. (2) It is only possible to obtain as a result information that has been explicitly detailed in advance, since it is no possible to make inferences. The main problem, searching for and obtaining information in keeping with the user’s requirements, is still the main obstacle to overcome. However, the traditional information retrieval technique has been criticized as deeply flawed; the main reason is that the existing search technique is mainly based on the keyword match [4]-[5]. In other words, users input keywords which they want to search, then retrieval system return Manuscript received January 26, 2009; accepted February 10, 2009. Corresponding author is Jun Zhai.

© 2009 ACADEMY PUBLISHER doi:10.4304/jsw.4.7.758-765

the matching document to users. Because of synonyms and polysemy, it’s very difficult to understand user exact needs by keyword. Often the initial keywords do not get the results they want, the mildly relevant or irrelevant documents were also retrieved. Therefore, the use of ontologies to overcome the limitations of keyword-based search has been put forward as one of the motivations of the Semantic Web since its emergence in the late 1990s [6]. Ontology, with the excellent concept hierarchy and appropriately supporting for logic reasoning, is used widely in information retrieval, especially in the semantic retrieval. For the emphasizing of matching based on knowledge and semantic, semantic information retrieval has good performance in recall and precision [7]. Ontology-based traffic information retrieval has also been studied [8]. At the same time, ITS lays stress on the relationship between human, vehicle and road. There a lot of fuzzy phenomenon derived from human factor [9]-[10]. For instance, in traffic information service domain, people pay attention to message such as weather information, road information, accident information and gas station information etc. It is sufficient for travelers to obtain some message in fuzzy linguistic values rather than in accurate numeric values, such as weather information, road information etc. Linguistic values for weather include “overcast”, “cloudy”, “fine”, “rainy”, “snow” etc, and linguistic values for road surface condition include “dryness”, “dampness”, “seeper”, “firn” etc. These linguistic values considered as fuzzy concepts have uncertainty. To handle uncertainty of information and knowledge, one possible solution is to incorporate fuzzy theory into ontology. Then we can generate fuzzy ontologies, which contain fuzzy concepts and fuzzy memberships. Sanchez studied several connections between Fuzzy Logic, the Semantic Web, and its components (Ontologies, Description Logics) and introduced a Fuzzy Ontology structure, Lexicon and Knowledge Base [11]. Lau presented a fuzzy domain ontology for business knowledge management [12]. Lee et al. proposed an algorithm to create fuzzy ontology and applied it to news summarization [13]. Tho et al. proposed a Fuzzy Ontology Generation Framework (FOGA) for fuzzy ontology generation on uncertainty information [14]. This framework is based on the idea of fuzzy theory and

JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009

Formal Concept Analysis (FCA). Abulaish et al. proposed a fuzzy ontology framework in which a concept descriptor is represented as a fuzzy relation which encodes the degree of a property value using a fuzzy membership function [15]. Calegari and Ciucci presented the fuzzy OWL language [16]. Jiang et al. studied the fuzzy description logic for fuzzy ontology [17]. But, current fuzzy ontology models do not focus on essential semantic relationships between fuzzy concepts, which lead difficulty to search information at fuzzy semantic level. To achieve fuzzy semantic retrieval for traffic information, this paper proposes a new kind of fuzzy ontology models. The rest of this paper is organized as follows: Section 2 gives traffic information model with RDF and RDFS. Section 3 introduces fuzzy linguistic variable ontology models. Section 4 proposes formal representation for linguistic variables ontology using RDF. Section 5 studies the semantic retrieval for traffic information in SeRQL query language. Finally, section 6 concludes the paper. II. TRAFFIC INFORMATION MODEL BASED ON RDF AND RDFS The idea of Semantic Web came from Tim BemersLee in his vision to move the web into a new generation, where the web resources are annotated with meaning in a form that machines can understand [5]. This will open up vast opportunities for automated processing of the rich knowledge resources available on the web to applications in information search and filtering, knowledge mining, coordination and collaborative processing by intelligent agents. The Semantic Web is to be realized through a shared infrastructure consisting of languages and tools for knowledge representation and processing. The basic knowledge representation format is the Resource Description Framework (RDF) [18]-[19] and RDF Schema (RDFS) [20]. RDF provides a data model that supports fast integration of data sources by bridging semantic differences. To achieve semantic retrieval for ITS, it is necessary to represent traffic information through RDF model. The RDF data model vaguely resembles an object-oriented data model. It consists of entities,

represented by unique identifiers, and binary relationships, or statements, between those entities. In a graphical representation of an RDF statement, the source of the relationship is called the subject, the labeled arc is the predicate (also called property), and the relationship’s destination is the object. Both statements and predicates are first-class objects, which means they can be used as the subjects or objects of other statements. The RDF data model distinguishes between resources, which are object identifiers represented by URIs, and literals, which are just strings. The subject and the predicate of a statement are always resources, while the object can be a resource or a literal. In RDF diagrams, resources are always drawn as ovals, and literals are drawn as boxes. Fig.1 shows an example of RDF data model graph for traffic accident information, which means as following: (1) The resource “ex: traffic accident No. T101” has a property “ex: driver” the value of which is the resource “ex: driver No. D000033”. (2) The resource “ex: traffic accident No. T101” has a property “ex: vehicle” the value of which is the resource “ex: vehicle No. V9006”. (3) The resource “ex: driver No. D000033” has a property “ex: age” with value “middle-aged” (a literal and a fuzzy concept). (4) The resource “ex: vehicle No. V9006”. has a property “ex: speed” with value “fast” (a literal and a fuzzy concept). (5) The resource “ex: vehicle No. V9006”. has a property “ex: performance of detent” with value “terrible” (a literal and a fuzzy concept). The part of RDF statements is as following: middle-aged fast terrible

ex: driver No. D000033

ex: driver

ex: traffic accident No. T101

759

ex: vehicle

ex: speed

ex: age middle-aged

ex: vehicle No. V9006 ex: performance of detent

fast

Figure 1. RDF data model graph for traffic accident information

© 2009 ACADEMY PUBLISHER

terrible

760

JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009

A mass of information about traffic accident is distributed among the Semantic Web. So it is meaning and difficult to retrieve relevant information. RDFS allows one to define so-called “RDF Schemas” or “ontologies”, similar to object-oriented data models. The inheritance model of RDFS exhibits the following peculiarities: (1) Resources can be classified in different classes that are not related in the class hierarchy. (2) The class hierarchy can be cyclic so that all classes on the cycle are “subclass equivalent”. (3) Properties are first-class objects. (4) RDF does not describe which properties can be associated with a class, but instead the domain and range of a property. Based on an RDFS schema, “inference rules” can be specified, for instance the transitivity of the class hierarchy, or the type of an untyped resource that has a property associated with a known domain. Fig.2 shows the RDFS graph for traffic ontology. As shown in Fig. 1, people often use fuzzy concepts to describe entity property. But, due to the lack of relationships between fuzzy concepts in current RDF model, it is difficult to search information at semantic level of fuzzy concepts. Consequently, we propose the fuzzy linguistic variables ontology models. III. FUZZY LINGUISTIC VARIABLE ONTOLOGY MODELS The fuzzy linguistic variables proposed by Zadeh are the basic of fuzzy knowledge and fuzzy system [21]. A linguistic variable is a variable whose value is not a number but a word. Each linguistic value is associated with a fuzzy set, each of which has a defined membership function. A membership function describes these linguistic values in terms of numerals. The linguistic variables and their membership functions allow fuzzy logic to perform the imprecise and non-numerical reasoning performed by humans.

Definition 1 (Fuzzy linguistic variable) – A fuzzy linguistic variable is a 4-tuple ( X , T , M , U ) , where: (1) X is the name of fuzzy linguistic variable, e.g. “age” or “speed” etc. (2) T is the set of terms which is the value of fuzzy linguistic variable, e.g. T ={fast, middle, slow,…}. (3) M is the mapping rules which map every term of T to fuzzy set at U . (4) U is the universe of discourse. Gruber defines ontology as an explicit specification of a conceptualization, i.e. an abstract and simplified representation of real-world entities [22]. An ontology organizes domain knowledge in terms of concepts, properties, relations and axioms. Definition 2 (Ontology) – An ontology is a 4-tuple O = (C , P, R, A) , where: (1) C is a set of concepts defined for the domain. A concept is often considered as a class in an ontology. (2) P is a set of concept properties. A property p ∈ P is defined as an instance of a ternary relation of

p(c, v, f ) , where c ∈ C is an ontology concept, v is a property value associated with c and f defines restriction facets on v . Some of the restriction facets are type ( f t ), cardinality ( f c ), and range ( f r ). The type facet f t may be any one from the standard data types supported by ontology editors, i.e. f t ∈ {boolean, the form

integer, float, string, symbol, instance, class, …}. The cardinality facet f c defines the upper and lower limits on the number of values for the property. The range facet f r specifies a range of values that can be assigned to the property. (3) R = {r | r ⊆ C × C} is a set of binary semantic relations defined between concepts in C . Basic relations rdfs: Property

rdfs: Resource

rdfs: Class

rdf: type

rdfs: subClassOf

ex: traffic accident

ex: driver

rdfs: domain

rdf: type

rdfs: domain

rdfs: range

ex: driver

Figure 2. RDF schema graph for traffic ontology

© 2009 ACADEMY PUBLISHER

ex: age

rdfs: range

rdfs: Literal

JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009

761

(4) I ⊆ Q × C F is a binary relation from Q to C F .

are defined as {synonym of, kind of, part of, instance of, property of} ⊂ R . (4) A is a set of axioms. An axiom is a real fact or reasoning rule. Introducing semantic relationships between fuzzy concepts, we obtain the fuzzy ontology models. Definition 3 (Fuzzy linguistic variable ontology) – A fuzzy linguistic variable ontology is a 6-tuple OF = (c a , C F , R, F , S , U ) , where:

compose a composition fuzzy concept. To simplify the transform from fuzzy linguistic variables to fuzzy ontology, we introduce the basic fuzzy ontology model as follows. Definition 5 (Basic fuzzy ontology) – A basic fuzzy ontology is a 4-tuple O F = (c a , C F , F , U ) , where

(1) c a is a concept on the abstract level, e.g. “age”,

c a , C F , F , U have same interpretations as defined in

“speed” etc. The corresponding element of c a is

X in

definition 1. (2) C F is the set of fuzzy concepts which describes all

T in definition 1, but C F has certain structure or relations R . (3) R = {r | r ⊆ C F × C F } is a set of binary relations between concepts in C F . A kind of relation is set relation RS = {inclusion ( i.e. ⊆ ), intersection, values of c a . The corresponding element of C F is

disjointness, complement ( i.e. ┐ )}, and the other relations are the order relation and equivalence relation RO = {≤, ≥, =} . C F and an order relation

r compose the ordered structure < C F , r > . (4) F is the set of membership functions at U , which is isomorphic to C F . The corresponding element of F is M in definition 1, but F has also certain structure or relations. (5) S = {s | s : C F × C F → C F } is a set of binary operators at C F . These binary operators form the mechanism of generating new fuzzy concepts. Basic operators are the “union”, “intersection”, “reversion” and “complement” etc., i.e. S = {∨,∧, ¬, L} . C F and

S compose the algebra structure < C F , S > . (6) U is the universe of discourse.

Definition 3 is more complex than definition 1 in order to describe the semantic information. Modeling the linguistic qualifiers, we extend the fuzzy linguistic variable ontology as follows. Definition 4 (Extended fuzzy ontology) – An extended fuzzy ontology is a 9-tuple OF = (c a , C F , R, F , S , Q, O, I ,U ) , where:

< q, c F >∈ I means that q ∈ Q and c F ∈ C F can

definition 3, which satisfy the following conditions: (1) C F = {c1 , c 2 , L , c n } is a limited set. (2) Only one relation of set, the relation of disjointness, exists in C F , and C F is complete at U . In the other words, C F is a fuzzy partition of U . (3) C F has an ordered relation ≤ , and < C F , ≤> is a complete ordered set, i.e. all concepts in C F constitute a chain c1 ≤ c 2 ≤ L ≤ c n . (4) F is optional element of ontology. An example of basic fuzzy ontology is OF = ( c a = speed of vehicle, C F = {slow, middle, fast},

U = [0,200] ), where “slow” ≤ “middle” ≤ “fast”, and the membership functions are shown in Fig 3. Another fuzzy ontology model can be derived from linguistic labels, which have been studied and applied in a wide variety of areas, including engineering, decision making, artificial intelligence, data mining, and soft computing [23]. Definition 6 (Linguistic labels ontology) – A linguistic labels ontology is a 4tuple O F = (c a , C F , F , U ) , where c a , C F , F , U have same interpretations as defined in definition 3, which satisfy the following conditions: (1) C F = {c 0 , c1 , c 2 , L , c n } is a limited set, whose cardinality value is odd, such as 7 and 9, where the mid term represents an assessment of approximately 0.5 and with the rest of the terms being placed symmetrically around it. (2) C F is ordered: ci ≥ c j iff i ≥ j . (3) The reversion operator is defined: reversion

(ci ) = c j such that i + j = n .

(1) c a , C F , R, F , S , U have same interpretations as

slow

middle

fast

100

200

defined in definition 3. (2) Q is the set of the linguistic qualifiers, e.g.

Q ={very, little, close to, …}. An qualifier q ∈ Q and a fuzzy concept c F ∈ C F compose a composition fuzzy concept that can be the value of c a , e.g. “very cheap”. (3) O is the set of fuzzy operators at U , which is isomorphic to Q . © 2009 ACADEMY PUBLISHER

0

Figure 3. Membership functions in fuzzy ontology

762

(4)

JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009

U = [0,1] .

An example of linguistic labels ontology is OF =

= degree of loyalty, C F = {c0 = none, c1 = very low, c 2 = low, c3 = medium, c 4 = high, c5 = very high, c6 = perfect } ). ( ca

To incorporate fuzzy ontology into the RDF model, we give formal representation for linguistic variable ontology in the next section. IV. FORMAL REPRESENTATION FOR LINGUISTIC VARIABLES ONTOLOGY USING RDF In traffic information service domain, the main fuzzy linguistic variable ontologies to describe traffic accident information are as following: O1= (age, {old, middle-aged, midlife, youth, youngster, adult}); O2= (speed, {fast, middle, slow, very slow, very fast}); O3= (performance of detent, {bad, good, terrible}); O4= (road surface condition, {dryness, dampness, seeper, firn, …}); O5= (weather, {overcast, cloudy, fine, rainy, snow, …}) . O6=(loss, {little, low, middle, high, …}). There is a lot of semantic relation between fuzzy concepts. For instance: • “middle-aged” = “midlife”, “old” ⊆ “adult”, “middle-aged” ⊆ “adult”, “youth” ⊆ “adult”; • “very slow” ≤“slow” ≤ “middle” ≤ “fast” ≤ “very fast”; • “terrible” ≤ “bad” ≤ “good” ; • “dryness” ≤ “dampness”≤ “seeper” ≤ “firn”; • “little” ≤ “low”≤ “middle” ≤ “high”; • ┐“good”= {“bad”, “terrible”}; • reversion (“bad”) = “good”, reversion (“slow”)= “fast”, etc. Fig. 4 shows the RDF graph for linguistic variable ontology O1 which includes a set of fuzzy concepts and their semantic relation. The part of RDF statements is as following:

© 2009 ACADEMY PUBLISHER

……………………………… Each fuzzy concept is associated with a membership function. There are many types of membership functions. Some of the common ones are: (1) Triangular. A triangular shaped curve can be described by three points, namely: (x1, 0), (x2, 1), and (x3, 0). The RDF statements are as following: (2) Trapezoidal. A trapezoidal shaped curve can be described by four points, namely: (x1, 0), (x2, 1), (x3,1), and (x4, 0). The RDF statements are as following: Combining Fig. 1 with Fig. 4, we introduce new data type referred as fuzzy linguistic variables to RDF data model, such as “age”, “speed” and “performance of detent” etc. Using semantic relation defined in fuzzy linguistic variable ontologies between fuzzy concepts which can be the value of linguistic variables, fuzzy semantic information retrieval can be achieved.

JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009

763

ex: age

rdf: Seq rdf: Type

ex: linguistic values include rdf_1

rdf_2

rdf_3

rdf_4

ex: ≤

ex: youngster

ex: youth

ex: old

ex: midlife

ex: ≤

ex: ≤ ex: =

ex: ⊆

ex: ⊆

ex: ⊆

ex: adult

ex: middle-aged ex: ⊆ Figure 4. RDF graph for linguistic variable ontology

V. SEMANTIC RETRIEVAL FOR TRAFFIC INFORMATION IN SERQL Semantic retrieval or conceptual search, i.e., search based on meaning rather than just character strings, has been a hotspot in the information retrieval (IR) field along with the Semantic Web. One way to view a semantic search engine is as a tool that gets formal ontology-based queries (e.g., in SeRQL [24], RDQL [25], RQL [26], etc.) from a client, executes them against a knowledge base (KB), and returns tuples of ontology values that satisfy the query. SeRQL (Sesame RDF Query Language) is a new RDF/RDFS query language that is currently being developed by Aduna as part of Sesame. It combines the best features of other (query) languages (RQL, RDQL, etc.) and adds some of its own. The SeRQL query language supports SELECT queries which include six clauses: SELECT, FROM, WHERE, LIMIT, OFFSET and USING NAMESPACE. In a SELECT clause, one can specify which variable values should be returned and in what order. The FROM clause is optional and always contains path expressions, which define the paths in an RDF graph that are relevant to the query. The WHERE clause is optional and can contain additional (Boolean) constraints on the values in the path expressions. One of the most prominent parts of SeRQL is path expressions. Path expressions are expressions that match specific paths through an RDF graph. The parts surrounded by curly brackets represent the nodes in the RDF graph; the parts between these nodes represent the edges in the graph. The direction of the arcs (properties) in SeRQL path expressions is always from left to right. The nodes and edges in the path expressions can be variables, URIs and literals. Also, a node can be left empty in case one is not interested in the value of that node.

© 2009 ACADEMY PUBLISHER

Using the following query statements to RDF graph shown in Fig.1, the return result will be “ex: traffic accident No. T101”: SELECT traffic accident FROM {traffic accident } ex: vehicle {} ex: speed {speed} WHERE speed = “fast” The search engine handle “speed” as an ordinary variable with data type “literal”. Current RDF and SeRQL cannot handle the fuzzy concepts as values of properties and do not support fuzzy semantic retrieval. To achieve fuzzy semantic retrieval, “age”, “speed” etc. are considered as a fuzzy linguistic variable and their values are defined in ontologies “O1”, “O2” etc. For instance, we can retrieve “traffic accident” information through property “speed of vehicle” by the query statements: SELECT traffic accident FROM {traffic accident } ex: vehicle {} ex: speed {speed} WHERE speed ≤ “fast” Using the “order relation” defined in fuzzy linguistic variable ontology: “very slow” ≤ “slow” ≤ “middle” ≤ “fast” ≤ “very fast” , the search engine can transform the above query statements to: SELECT traffic accident FROM {traffic accident } ex: vehicle {} ex: speed {speed} WHERE speed = “very slow” OR speed = “slow” OR speed = “middle” OR speed = “fast” For the query statements: SELECT traffic accident FROM {traffic accident } ex: vehicle {} ex: speed {speed} WHERE speed =REVERSION (“slow”) Using the “reversion relation” defined in fuzzy linguistic variable ontology: reversion (“slow”) = “fast”, we can transform the above query statements to:

764

JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009

SELECT traffic accident FROM {traffic accident } ex: vehicle {} ex: speed {speed} WHERE speed =“fast” For the query statements: SELECT traffic accident FROM {traffic accident } ex: vehicle {} ex: performance of detent {performance of detent } WHERE performance of detent ≠ “good” Using the “complement relation” defined in fuzzy linguistic variable ontology: ┐ “good” = {“bad”, “terrible”}, the search engine can transform the above query statements to: SELECT traffic accident FROM {traffic accident } ex: vehicle {} ex: performance of detent {performance of detent } WHERE performance of detent = “bad” OR performance of detent = “terrible” For the query statements: SELECT traffic accident FROM {traffic accident } ex: driver {} ex: age {age} WHERE age = “middle-aged” Using equivalence relation: “middle-aged”= “midlife”, we can transform the above query statements to: SELECT traffic accident FROM {traffic accident } ex: driver {} ex: age {age} WHERE age = “middle-aged” OR age= “midlife” For the query statements: SELECT traffic accident FROM {traffic accident } ex: driver {} ex: age {age} WHERE age = “adult” Using inclusion relation: “old” ⊆ “adult”, “middle-aged” ⊆ “adult” and “youth” ⊆ “adult”, we can transform the above query statements to: SELECT traffic accident FROM {traffic accident } ex: driver {} ex: age {age} WHERE age = “adult” OR age= “old” OR age= “middle-aged” OR age= “midlife” OR age= “youth” Obviously, extended query statements can return all results which satisfy research requirement at semantic level without upgrading current main search algorithm. VI. CONCLUSION The Semantic Web is a scheme to extend the current Web from documents linked to each other, into a Web

© 2009 ACADEMY PUBLISHER

that recognizes the meaning of information in these documents. Ontology-based semantic information retrieval is one of the motivations of the Semantic Web. To achieve fuzzy semantic retrieval for traffic information, this paper proposes an approach using RDF and fuzzy ontology. We have applied RDF data model to represent traffic accident information on the Semantic Web. Then we have presented fuzzy linguistic variable ontology and its formal representation with RDF. Introducing new data type referred as fuzzy linguistic variables to RDF data model, the semantic query expansion in SeRQL query language is constructed by semantic relations between fuzzy concepts. Examples show that the semantic retrieval of traffic information through fuzzy concepts for ITS can be achieved. ACKNOWLEDGMENT This work was supported in part by the Research Project of the Educational Department of Liaoning Province (Leading Laboratory Project) under Grant 20060083. REFERENCES [1] Y. Q. Shi, C. G. Yan, C. G. Jiang, and Y. Fang, “Resource integration and information services in urban ITS supported by grid technology,” in: Proceedings of 5th World Congress on Intelligent Control and Automation, Hangzhou, China, 2004, pp. 5283-5256. [2] Z. H. Wu, S. G. Deng, J. Wu, and H. J. Chen, “DartGrid II: a semantic grid platform for ITS,” IEEE Intelligent Systems, vol. 20, no. 3, 2005, pp. 12-15. [3] J. Javier Samper, Vicente R. Tomás, J. José Martinez, and Leo van den Berg, “An ontological infrastructure for traveler information systems,” in: Proceedings of 2006 IEEE Intelligent Transportation Systems Conf., Toronto, Canada, 2006, pp. 1197-1202. [4] T. Berners-Lee, “Semantic web road map, W3C design issues”, http://www.w3.org/DesignIssues/Semantic.html, 1998. [5] T. Berners-Lee, J. Hendler, and O. Lassila, “The Semantic Web,” Scientific American, vol. 284, no. 5, 2001, pp. 3443. [6] P. Castells, M. Fernandez, and D. Vallet, “An adaptation of the vector-space model for ontology-based information retrieval,” IEEE Transactions on Knowledge and Data Engineering, vol.19, no. 2, 2007, pp. 261-272. [7] J. Li, J. Y. Song, and H. Zhong, “Ontology-based query division and reformulation for heterogeneous information integration,” Journal of Software, vol.18, no.10, 2007, pp. 2495−2506. (in Chinese) [8] X.J. Yang, J. Zhai, and Y. Chen, “Ontology-based information retrieval for city intelligent public traffic,” in: Proceedings of First International Conference of Transportation Engineering (Volume Three), Chengdu, China, 2007, pp. 2374-2379. [9] A. G. Evsukoff, and N. E. F. Ebecken, “Mining fuzzy rules for a traffic information system,” in: KES 2003, LNAI 2773, Springer Berlin Heidelberg, 2003, pp. 237-243. [10] J. Zhai, Y. Chen, and L. X. Shen, “Knowledge modeling for Intelligent Transportation System based on fuzzy ontology models,” Journal of Dalian Maritime University, vol. 34, no. 2, 2008, pp. 91-94. (in Chinese)

JOURNAL OF SOFTWARE, VOL. 4, NO. 7, SEPTEMBER 2009

[11] E. Sanchez, and T. Yamanoi, “Fuzzy ontologies for the Semantic Web,” in: Flexible Query Answering System (FQAS 2006), Springer Berlin Heidelberg, 2006, pp. 691699. [12] Raymond Y.K. Lau, “Fuzzy domain ontology discovery for business knowledge management,” IEEE Intelligent Informatics Bulletin, vol.8, no.1, 2007, pp. 29-41. [13] C. S. Lee, Z. W. Jian, and L. K. Huang, “A fuzzy ontology and its application to news summarization,” IEEE Transactions on Systems, Man and Cybernetics (Part B), vol.35, no.5, 2005, pp. 859- 880. [14] Q. T. Tho, S. C. Hui, A. C. M. Fong, and T. H. Cao, “Automatic fuzzy ontology generation for semantic web,” IEEE Transactions on Knowledge and Data Engineering, vol.18, no.6, 2006, pp. 842- 856. [15] Muhammad Abulaish, and Lipika Dey, “Interoperability among distributed overlapping ontologies – a fuzzy ontology framework,” in: Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence, Hong Kong, 2006, pp.397-403. [16] Calegari Silvia, and Ciucci Davide, “Fuzzy ontology and fuzzy-OWL in the KAON project,” in: Proceedings of 2007 IEEE International Conference on Fuzzy Systems Conference, London, UK, 2007, pp.1-6. [17] Y. C. Jiang, Z. Z. Shi, Y. Tang, and J. Wang, “Fuzzy description logic for semantics representation of the Semantic Web,” Journal of Software, vol. 18, no. 6, 2007, pp. 1257−1269. (in Chinese) [18] D. Beckett, and B. McBride, “RDF/XML syntax specification,” W3C, 2004, URL http://www.w3.org/TR/rdf-syntax-grammar/. [19] John W.T. Lee, and Alex K.S. Wong, “Information retrieval based on semantic query on RDF annotated resources,” in: Proceedings of the 2004 IEEE International

© 2009 ACADEMY PUBLISHER

765

[20]

[21] [22]

[23]

[24]

[25]

[26]

Conference on Systems, Man and Cybernetics, 2004, pp. 3220-3225. D. Brickley, R. Guha, and B. McBride, “RDF vocabulary description language 1.0: RDF schema,” W3C, 2004, URL http://www.w3.org/TR/rdf-schema/. L. A. Zadeh, and J. Kacprzyk, Fuzzy logic for the management of uncertainty, John Wiley & Sons, Inc, 1992. T. R. Gruber, “A Translation Approach to Portable Ontology Specification,” Knowledge Acquisition, vol.5, no.2, 1993, pp. 199-220. Z. S. Xu, “Linguistic aggregation operators: an overview,” in: Fuzzy Sets and Their Extensions: Representation, Aggregation and Models, H. Bustince et al., (eds.), Springer, 2008, pp. 163-181. B. V. Aduna, “The SeRQL query language,” http: //www.openrdf.org/doc/sesame/users/ch06.html#d0e1977, 2002. P. Haase, J. Broekstra, A. Eberhart, and R. Volz, “A comparison of RDF query languages,” in: ISWC 2004, LNCS 3298, Springer-Verlag Berlin Heidelberg, 2004, pp. 502–517. T. Furche, B. Linse, F. Bry, D. Plexousakis, and G. Gottlob, “RDF querying: language constructs and evaluation methods compared,” in: Reasoning Web 2006, LNCS 4126, Springer-Verlag Berlin Heidelberg, 2006, pp. 1–52.

Jun Zhai was born in Changchun, P.R. China, on Sep. 19, 1969. He graduated from the Harbin Institute of Technology, Ph.D, and studied at the Dalian Maritime University, associate professor. He is now a post-doctoral scholar and his research interests include knowledge management and its application in Electronic Commerce and transport system.

Suggest Documents