Browsing by Author "Liu, DR"

Now showing 1 - 20 of 31

A hypergraph based approach to declustering problems
(2001)
Liu, DR
;
Wu, MY
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Parallelizing I/O operations via effective declustering of data is becoming essential to scale up the performance of parallel databases or high performance systems. Declustering has been shown to be a NP-complete problem in some contexts. Some heuristic methods have been proposed to solve this problem. However, most methods are not effective in several cases such as queries with different access frequencies or data with different sizes. In this paper, we propose a hypergraph model to formulate the declustering problem. Several interesting theoretical results are achieved by analyzing the proposed model. The proposed approach will allow modeling a wide range of declustering problems. Furthermore, the hypergraph declustering model is used as the basis to develop new heuristic methods, including a greedy method and a hybrid declustering method. Experiments show that the proposed methods can achieve better performance than several declustering methods.
A logical approach to fuzzy data analysis
(1999)
Liau, CJ
;
Liu, DR
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
In this paper, we investigate the extraction of fuzzy rules from data tables based on possibility theory. A possibilistic decision language is used to represent the extracted fuzzy rules. The algorithm for rule extraction is presented and the complexity analysis is carried out. Since the results of the rule induction process strongly depend on the representation language, we also discuss some approach for dynamic adjustment of the language based on the data.
A possibilistic decision logic with applications
(2001-05-01)
Liau, CJ
;
Liu, DR
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
In this paper, we investigate a knowledge representation formalism in the context of fuzzy data tables. A possibilistic decision logic incorporating linguistic terms is proposed for representing and reasoning about knowledge in fuzzy data tables. Two applications based on the logic are described. The first is the extraction of fuzzy rules from general fuzzy data tables. In this application, the knowledge in the tables may be made explicit by the formulas of the logic or used implicitly in decision-making. The second is for the fuzzy quantization problem of precise data tables. It can be viewed as a special case of the first, however, due to some special properties of the problem, a polynomial time rule extraction process can be obtained. Finally, the relationship of the logic with some works for handling uncertain information in data tables is also discussed.
An agent-based approach to flexible commerce in intermediary - centric electronic markets
(2004-01-01)
Liu, DR
;
Hwang, TF
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
The growth of electronic-markets (e-markets) necessitates the processing of many commerce protocols (processes). Each protocol handles different messages and flows of transactions among customers, merchants and intermediaries. Developing applications for each commerce protocol is costly and impractical. Accordingly, developing a flexible model of Internet commerce to support various commerce protocols is important. Moreover, the emergence of intermediaries is inevitable as e-markets grow. This work analyzes various trading processes and the roles of intermediaries, and proposes a flexible agent-based model of intermediary-centric commerce. The proposed model applies basic transaction functions to compose various commerce protocols. Agent technology and an event-driven approach are employed to process flexibly the complex trading interactions among the participants. The agent-based approach enhances scalability and makes complex trading interactions more tractable. Furthermore, an agent-based prototype system is deployed. The novel system is extensible and facilitates flexible trading interactions to support various commerce protocols in e-markets. (C) 2004 Elsevier Ltd. All rights reserved.
Arrow decision logic
(2005)
Fan, TF
;
Liu, DR
;
Tzeng, GH
;
科技管理研究所
;
資訊管理與財務金融系註：原資管所+財金所
In this paper, we propose arrow decision logic (ADL), which combines the main features of decision logic and arrow logic. Decision logic represents and reasons about knowledge extracted from decision tables based on rough set theory, while arrow logic is the basic modal logic of arrows. The semantic models of ADL are pairwise comparison tables, which are useful in rough set-based multicriteria analysis. Consequently, ADL can represent preference knowledge induced from multicriteria decision tables.
Business-to-business workflow interoperation based on process-views
(2004-12-01)
Liu, DR
;
Shen, MX
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
When cooperating with each other, enterprises must closely monitor internal processes and those of partners to streamline business-to-business (B2B) workflows. This work applies the process-view model, which extends beyond conventional activity-based process models, to design workflows across multiple enterprises. A process-view is an abstraction of an implemented process. An enterprise can design various process-views for different partners based on diverse commercial relationships and, in doing so, establish an integrated process that consists of internal processes and process-views that each partner provides. Participatory enterprises can obtain appropriate progress information from their own integrated processes, allowing them to collaborate effectively. Furthermore, B2B workflows are coordinated through virtual states of process-views. This work develops a uniform approach to manage state mappings between internal processes and process-views. The proposed approach enhances prevalent activity-based process models adaptable to collaborative environments. (C) 2003 Elsevier B.V. All rights reserved.
CCAM: A connectivity-clustered access method for networks and network computations
(1997-01-01)
Shekhar, S
;
Liu, DR
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Current Spatial Database Management Systems (SDBMS) provide efficient access methods and operators for point and range queries over collections of spatial points, line segments, and polygons. However, it is not clear if existing spatial access methods can efficiently support network computations which traverse line-segments in a spatial network based on connectivity rather than geographic proximity. The expected I/O cost for many network operations can be reduced by maximizing the Weighted Connectivity Residue Ratio (WCRR), i.e., the chance that a pair of connected nodes that are more likely to be accessed together are allocated to a common page of the file. CCAM is an access method for general networks that uses connectivity clustering, CCAM supports the operations of insert, delete, create, and iind as well as the new operations, get-A-successor and get-successors, which retrieve one or all successors of a node to facilitate aggregate computations on networks. The nodes of the network are assigned to disk pages via a graph partitioning approach to maximize the WCRR. CCAM includes methods for static clustering, as well as dynamic incremental reclustering, to maintain high WCRR in the face of updates, without incurring high overheads. We also describe possible modifications to improve the WCRR that can be achieved by existing spatial access methods. Experiments with network computations on the Minneapolis road map show that CCAM outperforms existing access methods, even though the proposed modifications also substantially improve the performance of existing spatial access methods.
CCAM: A connectivity-clustered access method for networks and network computations
(1997-01-01)
Shekhar, S
;
Liu, DR
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Current Spatial Database Management Systems (SDBMS) provide efficient access methods and operators for point and range queries over collections of spatial points, line segments, and polygons. However, it is not clear if existing spatial access methods can efficiently support network computations which traverse line-segments in a spatial network based on connectivity rather than geographic proximity. The expected I/O cost for many network operations can be reduced by maximizing the Weighted Connectivity Residue Ratio (WCRR), i.e., the chance that a pair of connected nodes that are more likely to be accessed together are allocated to a common page of the file. CCAM is an access method for general networks that uses connectivity clustering, CCAM supports the operations of insert, delete, create, and iind as well as the new operations, get-A-successor and get-successors, which retrieve one or all successors of a node to facilitate aggregate computations on networks. The nodes of the network are assigned to disk pages via a graph partitioning approach to maximize the WCRR. CCAM includes methods for static clustering, as well as dynamic incremental reclustering, to maintain high WCRR in the face of updates, without incurring high overheads. We also describe possible modifications to improve the WCRR that can be achieved by existing spatial access methods. Experiments with network computations on the Minneapolis road map show that CCAM outperforms existing access methods, even though the proposed modifications also substantially improve the performance of existing spatial access methods.
Classifying video documents by hierarchical structure of video contents
(2000)
Liu, DR
;
Lin, CH
;
Hwang, JJ
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Recent advances in video database technology and increasing use of the World Wide Web allow users to access video documents on the Web. Moreover, advances in digital library technologies necessitate the storing of large quantities of video documents, Consequently, video documents must be categorized to assist the user in browsing and searching them by category. This study presents a novel approach to classifying video documents under classes in a predefined class hierarchy. Video documents are classified according to the structural weight of video contents, capturing their characteristics with respect to the hierarchical structure of the video data. Furthermore, while considering the hierarchical relationship among classes, the proposed technique strives for an appropriate balance between specificity and exhaustivity in video classification.
Coordinating interorganizational workflows based on process-views
(2001)
Shen, MX
;
Liu, DR
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
In multi-enterprise cooperation, an enterprise must monitor the progress of private processes as well as those of the partners to streamline interorganizational workflows. In this work, a process-view model, which extends beyond the conventional activity-based process model, is applied to design workflows across multiple enterprises. A process-view is an abstraction of an implemented process. An enterprise can design various process-views for different partners according to diverse commercial relationships, and establish an integrated process that is comprised of private processes as well as the process-views that these partners provide. Participatory enterprises can obtain appropriate progress information from their own integrated processes, allowing them to collaborate more effectively. Furthermore, interorganizational workflows are coordinated through virtual states of process-views. This work develops a regulated approach to map the states between private processes and process-views' The proposed approach enhances prevalent activity-based process models to be adapted in open and collaborative environments.
Data models in geographic information systems
(1997-04-01)
Shekhar, S
;
Coyle, M
;
Goyal, B
;
Liu, DR
;
Sarkar, S
Deployment of personalized e-catalogues: An agent-based framework integrated with XML metadata and user models
(2001-07-01)
Liu, DR
;
Lin, YJ
;
Chen, CM
;
Huang, YW
;
資訊管理與財務金融系註：原資管所+財金所
In e-commerce applications, supporting electronic catalogues (e-catalogues) to provide product-search services on the Internet is emerging as an important function of electronic brokers ( e-brokers). However, as the Internet expands, an increasing number of virtual stores are selling products on-line. The explosive growth of information is creating difficulties for customers searching for the product information they desire. In this work, an integrated framework is proposed to develop personalized e-catalogues. The proposed framework integrates XML-based metadata models, user models and agents. The XML-based metadata model can facilitate resource-discovery and format translation, and can flexibly model the definitions of diverse product attributes in heterogeneous data resources. The proposed user model can model a user's shopping interests to resources, categories and products. This work integrates the agent technology with the proposed metadata model and user model to develop a personalized e-catalogue system. The novel system effectively provides an integrated search for heterogeneous product information, as well as supporting personalized product search and browsing for each user based upon their profiles. (C) 2001 Academic Press.
Designing a composite e-service platform with recommendation function
(2003-05-01)
Liu, DR
;
Shen, MX
;
Liao, CT
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Enterprises make e-services available via the Internet to drive new revenue streams or create new efficiencies. Composite e-services, which consist of various e-services provided by different e-service providers, are more valuable for customers. This work presents a novel platform capable of supporting e-service metadata, and modeling and recommending composite e-services. Composite e-services are modeled by using the activity diagram of Unified Modeling Language in which Event/Condition/Action (ECA) rules are employed to control the sequence of e-services enactment and to select e-service providers. Moreover, two-level e-service metadata is designed to extend Universal Description, Discovery, and Integration (UDDI) standard to enable semantic search and selection of e-services. Finally, data mining approach is proposed to discover the frequent predicates of e-services and the frequent orderings between e-services. Based on the mining result, the proposed platform provides a recommendation of top N composite e-services to customers. (C) 2003 Elsevier Science B.V. All rights reserved.
Discovering role-relevant process-views for disseminating process knowledge
(2004-04-01)
Shen, MX
;
Liu, DR
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Workflow technology supports the management of organizational process knowledge. However, workers (representing organizational roles) cannot easily obtain a global view of a complex and large workflow. This work proposes a process-view based dissemination of process knowledge to address this problem. A process-view is an abstracted process derived from a physical process, and can provide adaptable task granularity. The relationships among tasks, roles and operations, as specified in role-based access control systems, are used to evaluate the degrees of relevance between roles and tasks. Next, a novel algorithm is proposed to generate automatically role-relevant process-views based on degrees of relevance. Knowledge management systems can thus disseminate abstracted process knowledge through process-views for those roles in a complex workflow. (C) 2003 Elsevier Ltd. All rights reserved.
Discovering role-relevant process-views for recommending workflow information
(2003)
Shen, MX
;
Liu, DR
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Workflow technology automates business processes to increase managerial efficiency. However, workers (representing organizational roles) cannot easily obtain a global view of a complex and large workflow. This work proposes a process-view based recommendation of workflow information to address this problem. A process-view is an abstracted process derived from a physical process, and can provide adaptable task granularity. The relationships among tasks, roles and operations, as specified in role-based access control systems, are used to evaluate the degrees of relevance between roles and tasks. Next, a novel algorithm is proposed to generate automatically role-relevant process-views based on degrees of relevance. Workflow systems can thus recommend abstracted workflow information through process-views for those roles in a complex workflow.
Hybrid approaches to product recommendation based on customer lifetime value and purchase preferences
(2005-08-01)
Liu, DR
;
Shih, YY
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Recommending products to attract customers and meet their needs is important in fiercely competitive environments. Recommender systems have emerged in e-commerce applications to Support the recommendation of products. Recently, a weighted RFM-based method (WRFM-based method) has been proposed to provide recommendations based on customer lifetime value, including Recency, Frequency and Monetary. Preference-based collaborative filtering (CF) typically makes recommendations based on the similarities of customer preferences. This study proposes two hybrid methods that exploit the merits of the WRFM-based method and the preference-based CF method to improve the quality of recommendations. Experiments are conducted to evaluate the quality of recommendations provided by the proposed methods, using a data set concerning the hardware retail marketing. The experimental results indicate that the proposed hybrid methods outperform the WRFM-based method and the preference-based CF method. (c) 2004 Elsevier Inc. All rights reserved.
Integrating AHP and data mining for product recommendation based on customer lifetime value
(2005-03-01)
Liu, DR
;
Shih, YY
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Product recommendation is a business activity that is critical in attracting customers. Accordingly, improving the quality of a recommendation to fulfill customers' needs is important in fiercely competitive environments. Although various recommender systems have been proposed, few have addressed the lifetime value of a customer to a firm. Generally, customer lifetime value (CLV) is evaluated in terms of recency, frequency, monetary (RFM) variables. However, the relative importance among them varies with the characteristics of the product and industry. We developed a novel product recommendation methodology that combined group decision-making and data mining techniques. The analytic hierarchy process (AHP) was applied to determine the relative weights of RFM variables in evaluating customer lifetime value or loyalty. Clustering techniques were then employed to group customers according to the weighted RFM value. Finally, an association rule mining approach was implemented to provide product recommendations to each customer group. The experimental results demonstrated that the approach outperformed one with equally weighted RFM and a typical collaborative filtering (CF) method. (C) 2004 Elsevier B.V. All rights reserved.
Integrating SET and EDI for secure healthcare commerce
(2001-11-01)
Liu, DR
;
Wu, IC
;
Hsieh, ST
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Different from conventional online goods purchases, healthcare commerce, such as purchasing prescription drugs. involves transaction steps of insurance coverage inquiries which are required to determine insurance coverage and payments. Without efficient processing of online insurance coverage inquiries, the online healthcare commerce cannot be carried out successfully. This work proposes a novel secure healthcare commerce protocol that incorporates the insurance coverage inquiries into the transaction steps of online purchases. The proposed protocol is designed based on the Secure Electronic Transaction (SET) and healthcare Electronic Data Interchange (EDI). Efficient ASC X12N interactive EDI messages are adopted to facilitate online real-time interactions of insurance coverage inquiries. The results have shown that the process of healthcare commerce is streamlined by integrating secure online purchases and online EDI interactions. (C) 2001 Elsevier Science B.V. All rights reserved.
Integrating software agents with multi-level metadata in support of heterogeneous product search
(2003-05-01)
Liu, DR
;
Pan, SC
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
As the Internet grows, more virtual stores are selling products on the Internet. With the explosive growth of product information, Customers are experiencing difficulties in searching for product information satisfying their needs. To conduct an integrated search, data translation will be a problem because virtual stores may use their own data format to store product information. The characteristics of product may also vary in different product categories. This work proposes an agent-oriented search system integrating with multilevel metadata to Support effective search for heterogeneous product information. The proposed system enables users to search product information based on the attributes of various Product categories. Moreover, the multi-level metadata is able to facilitate resource-discovery and format translation, and to flexibly model the definitions of diverse attributes for describing products in various product categories and data resources. With the multi-level metadata and the agent technology, an integrated search for heterogeneous product information located in various virtual stores can be performed effectively.
Integrating software agents with multi-level metadata in support of heterogeneous product search
(2003-05-01)
Liu, DR
;
Pan, SC
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
As the Internet grows, more virtual stores are selling products on the Internet. With the explosive growth of product information, Customers are experiencing difficulties in searching for product information satisfying their needs. To conduct an integrated search, data translation will be a problem because virtual stores may use their own data format to store product information. The characteristics of product may also vary in different product categories. This work proposes an agent-oriented search system integrating with multilevel metadata to Support effective search for heterogeneous product information. The proposed system enables users to search product information based on the attributes of various Product categories. Moreover, the multi-level metadata is able to facilitate resource-discovery and format translation, and to flexibly model the definitions of diverse attributes for describing products in various product categories and data resources. With the multi-level metadata and the agent technology, an integrated search for heterogeneous product information located in various virtual stores can be performed effectively.