Browsing by Author "Lee, Jia-Huei"

Now showing 1 - 3 of 3

An Online Activity Recommendation Approach based on the Dynamic Adjustment of Recommendation Lists
(2017-01-01)
Liu, Duen-Ren
;
Chen, Kuan-Yu
;
Chou, Yun-Cheng
;
Lee, Jia-Huei
;
資訊管理與財務金融系註：原資管所+財金所
This research investigates an online recommendation method for new types of online news websites. Cross-domain analysis on user browsing news and the attending activities is conducted to predict user preferences on activities based on non-negative Matrix Factorization (NMF) and Latent Dirichlet Allocation (LDA) topic model. A novel approach is proposed for the dynamic adjustment of recommendation lists in order to tackle the issue of limited recommendation layouts. The existing studies have not addressed this issue. The proposed approach is implemented on an online news website and evaluated for online recommendations. The experiment results demonstrate that our method can predict user preferences on recommended activities and enhance the effectiveness of recommendations.
Bootstrapping comparison on availability of parallel systems with non-identical components
(2008)
Ke, Jau-Chuan
;
Chu, Yunn-Kuang
;
Lee, Jia-Huei
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
Purpose - In order to develop a feasible and efficient method to acquire the long-run availability of a parallel system with distribution-free up and down times, the purpose of this paper is to perform the simulation comparisons on the interval estimations of system availability using four bootstrapping methods. Desigri/methodology/approach - By using four bootstrap methods; standard bootstrap (SB) confidence interval, percentile bootstrap (PB) confidence interval, bias-corrected percentile bootstrap (BCPB) confidence interval, and bias-corrected and accelerated (BCa) confidence interval. A numerical simulation study is carried out in order to demonstrate performance of these proposed bootstrap confidence intervals. Especially, we investigate the accuracy of the four bootstrap confidence intervals by calculating the coverage percentage, the average length, and the relative coverage of confidence intervals. Findings - Among the four bootstrap confidence intervals, the PB method has the largest relative coverage in most situations. That is, the PB method is the best one made by practitioners who want to obtain an efficient interval estimation of availability. Originality/value - It is the first time that the relative coverage is introduced to evaluate the performance of estimation method, which is more efficient than the existing measures.
Online recommendations based on dynamic adjustment of recommendation lists
(2018-12-01)
Liu, Duen-Ren
;
Chen, Kuan-Yu
;
Chou, Yun-Cheng
;
Lee, Jia-Huei
;
資訊管理與財務金融系註：原資管所+財金所
The flourishing of the Internet has increasingly promoted the rise of new types of online news websites with e-commerce portals. Online news websites provide specific information on such topics as lifestyle, fashion news, and a variety of other activities. The provision of online recommendation of activities associated with online news websites has the potential to attract more users and create more benefits. Such online recommendations represent an important online trend. Furthermore, dynamically adjusting recommendation lists to increase users' click-through rates is important for limited online recommendation layouts; however, existing studies have not addressed this online recommendation issue. This research proposes a novel approach for the dynamic adjustment of recommendation lists to tackle the issue of limited recommendation layouts, and then develops novel online recommendation methods. This research designs novel methods based on non-negative matrix factorization (NMF) and latent Dirichlet allocation (LDA) to predict user preferences for activities, using analysis of browsing news and attending activities. We propose a novel online activity recommendation approach, taking into consideration the interest scores and push scores, for dynamically adjusting the recommendation list. The Most Frequently Pushed (MFP) strategy gives priority to replacing the most frequently pushed activity, while the Not Frequently Clicked (NFC) strategy gives priority to replacing the not frequently clicked activity. We implement our proposed approach on an online news website and evaluate its online recommendation performance. The results of our experiment demonstrate that our proposed approach can enhance the effectiveness of recommendations. (C) 2018 Elsevier B.V. All rights reserved.