Browsing by Author "Tseng, Judy C. R."

Now showing 1 - 4 of 4

A hybrid linear text segmentation algorithm using hierarchical agglomerative clustering and discrete particle swarm optimization
(2014)
Wu, Ji-Wei
;
Tseng, Judy C. R.
;
Tsai, Wen-Nung
;
資訊工程學系
;
Department of Computer Science
Linear text segmentation plays an important role in many natural language processing tasks. Many algorithms have been proposed and shown to improve the performance of linear text segmentation. However, the previous studies often suffer from either lower segmentation accuracy or higher computational complexity. Moreover, parameter setting is another critical problem in some algorithms. Although manual assignment is an approach to solve this problem, it may increase the user's burden, and the parameters provided may not always be suitable to reflect the real metadata of a text. In this paper, a hybrid algorithm, TSHAC-DPSO, is proposed to tackle these problems. A novel linear Text Segmentation algorithm based on Hierarchical Agglomerative Clustering (TSHAC) is proposed to rapidly generate a satisfactory solution without an auxiliary knowledge base, parameter setting, or user involvement; then an efficient evolutional algorithm, Discrete Particle Swarm Optimization (DPSO), is adopted to generate the global optimal solution by refining the solution created by TSHAC. TSHAC-DPSO fully utilizes the merits of both algorithms which not only improve the accuracy of linear text segmentation, but also make the execution more efficient and flexible. The experimental results show that TSHAC-DPSO provides comparable segmentation accuracy with several well-known linear text segmentation algorithms.
An integrated proactive knowledge management model for enhancing engineering services
(2012-07-01)
Wu, Ji-Wei
;
Tseng, Judy C. R.
;
Yu, Wen-Der
;
Yang, Jyh-Bin
;
Lee, Shun-Min
More and more construction organizations have adopted Knowledge Management (KM) to enhance their engineering services. However, most of the traditional KM methods suffer from their "reactive mode" of problem solving. To cope with this problem, a newly developed model, the Integrated Proactive Knowledge Management Model (IPKMM), is proposed in this paper. A leading engineering consulting firm in Taiwan was selected as a case study to implement the proposed model. The system implementation of IPKMM, the Integrated Proactive Knowledge Management System (IPKMS), is verified with real world cases. A novel Business Intelligence Index (BII) is also proposed in this paper to evaluate the relative competitiveness of different KM models. It is confirmed from the case study that IPKMM can significantly improve the efficiency of problem-solving and the competitiveness of an engineering consulting firm in the service market. This study demonstrates that IPKMM has great potential in enhancing emergent problem-solving for engineering consultants. (C) 2012 Elsevier B.V. All rights reserved.
Benefit Analysis of Knowledge Management System for Engineering Consulting Firms
(2014-07-01)
Yang, Jyh-Bin
;
Yu, Wen-Der
;
Tseng, Judy C. R.
;
Chang, Chia-Shin
;
Chang, Pei-Lun
Engineering consulting (EC) firms in the construction industry are knowledge-intensive and experience-based organizations. As the knowledge accumulated from previous experiences is the essential asset for wining and managing future projects, many EC firms have developed diversified knowledge management systems (KMSs) to accumulate and retain this essential knowledge. However, evaluation methods and results regarding the benefit analysis of KMSs are rarely found in literature. To evaluate the performances of KMSs, most previous studies have adopted qualitative approaches. This paper, on the other hand, presents a ratio-based approach for evaluating the benefits of KMSs. The proposed approach is tested using one of the KMSs from a study EC firm: the proposal preparation assistant (PPA) system. Based on a test of two real cases, this study found that a 48.7% time reduction in data collection and 25.3% staff-hour savings can be achieved when using the PPA system to prepare service proposal drafts. The results revealed in this study not only prove the usability of the proposed ratio-based benefit analysis approach, but also provide convincing and inspiring information for knowledge management practitioners as they plan their future works. (C) 2014 American Society of Civil Engineers.
Proactive problem-solver for construction
(2010-10-01)
Yu, Wen-der
;
Yang, Jyh-bin
;
Tseng, Judy C. R.
;
Liu, Shen-jung
;
Wu, Ji-wei
Construction is an experience-based discipline. Knowledge or experience accumulated from previous projects plays a very important role in successful performance of new works. More and more construction organizations have adopted commercial Knowledge Management Systems (KMSs) to develop their own Knowledge Management (KM) functionalities. Most of the existing KMSs adopt Communities of Practice (CoPs) for knowledge sharing and exchange. Such an approach is found on the reactive problem-solver (RPS); that is, the problem raised by the questioner in the CoP has to "wait" for the "solution knower" to respond (or reply). Previous research indicated that the RPS approach may suffer in poor time and cost effectiveness. This paper proposes a Proactive Problem-Solver (PPS) approach for the problems encountered in construction engineering and management. Unlike RPS, the PPS proactively solves the problem based on lessons learned from previous projects. Should the solution be not available; the PPS dispatches the problem to the most appropriate domain experts so that the problem can be tackled timely and efficiently. A case A/E consulting firm is selected for implementation of the proposed PPS to demonstrate its applicability. It is shown that the proposed PPS improves more than 89.5% of efficiency both for timeliness and cost-saving of problem-solving. The proposed PPS demonstrates great potentials for improvement of emergent problem solving and enhancement of market competitiveness of a construction organization. (C) 2010 Elsevier B.V. All rights reserved.