National Taichung University of Science and Technology
Taichung, Taiwan
Time filter
Source Type

Chen C.-C.,Tunghai University | Huang T.-C.,National Taichung University of Science and Technology
Computers and Education | Year: 2012

Context-awareness techniques can support learners in learning without time or location constraints by using mobile devices and associated learning activities in a real learning environment. Enrichment of context-aware technologies has enabled students to learn in an environment that integrates learning resources from both the real world and the digital world. Although learning outside of the traditional classroom is an innovative teaching approach, the two main problems are the lack of proper learning strategies and the capacity to acquire knowledge on subjects effectively. To manage these problems, this study proposes a context-aware ubiquitous learning system (CAULS) based on radio-frequency identification (RFID), wireless network, embedded handheld device, and database technologies to detect and examine real-world learning behaviors of students. A case study of an aboriginal education course was conducted in classrooms and at the Atayal u-Museum in Taiwan. Participants included elementary school teachers and students. We also designed and used a questionnaire based on the Unified Theory of Acceptance and Use of Technology (UTAUT) theory to measure the willingness for adoption or usage of the proposed system. The experimental results demonstrated that this innovative approach can enhance their learning intention. Furthermore, the results of a posttest survey revealed that most students' testing scores improved significantly, further indicating the effectiveness of the CAULS. © 2012 Elsevier Ltd. All rights reserved.

Lin H.-Y.,National Taichung University of Science and Technology
Knowledge-Based Systems | Year: 2013

Feature selection is an essential problem for pattern classification systems. This paper studies how to provide systems with the most characterizing features for ordinal multi-class classification task. The integration of cluster analyses and variability analyses advances a novel feature selection scheme with efficiency. The Huang-index method using fuzzy c-means is employed to enhance cluster validity and optimizes a consistent number of clusters among the features. A new entropy-based feature evaluation method is formulated for the authentication of relevant features. Then, multivariate statistical analyses are utilized to solve the redundancy between relevant features. Experimental results show that our new feature selection scheme sifts successfully a compact subset of characterizing features for classification problems with multiple classes. © 2012 Elsevier B.V. All rights reserved.

Chen M.-Y.,National Taichung University of Science and Technology
Future Generation Computer Systems | Year: 2014

Recently, many fuzzy time series models have already been used to solve nonlinear and complexity issues. However, first-order fuzzy time series models have proven to be insufficient for solving these problems. For this reason, many researchers proposed high-order fuzzy time series models and focused on three main issues: fuzzification, fuzzy logical relationships, and defuzzification. This paper presents a novel high-order fuzzy time series model which overcomes the drawback mentioned above. First, it uses entropy-based partitioning to more accurately define the linguistic intervals in the fuzzification procedure. Second, it applies an artificial neural network to compute the complicated fuzzy logical relationships. Third, it uses the adaptive expectation model to adjust the forecasting during the defuzzification procedure. To evaluate the proposed model, we used datasets from both the Taiwanese stock index from 2000 to 2003 and from the student enrollment records of the University of Alabama. The results of our study show that the proposed model is able to obtain an accurate forecast without encountering conventional fuzzy time series issues. © 2013 Elsevier B.V. All rights reserved.

Chien Y.-H.,National Taichung University of Science and Technology
IEEE Transactions on Reliability | Year: 2012

This paper presents the effects of a renewing free-replacement warranty (RFRW) on the age-replacement policy in a discrete time process. Consider a product that should be operating over an indefinitely long operation cycle n(n=1,2,⋯); under the discrete age-replacement policy, a product is replaced at cycle N(N=1,2,⋯) after its installation, or at failure, whichever occurs first. The cost models from the customer's perspective are developed for both warranted, and non-warranted products. The corresponding optimal replacement age N* (i.e., the optimal number of operation cycles for a preventive replacement) is derived such that the long-run expected cost rate is minimized. Under the assumption of the discrete time increasing failure rate, the existence and uniqueness of the optimal N* are shown, and the impacts of a RFRW on the optimal replacement policies are investigated analytically. The optimal N* for a warranted product is closer to the end of the warranty period than for a non-warranted product. Finally, a numerical example is demonstrated for the optimal policy illustration and verification. The observations from the technical analysis and numerical results provide valuable information for a buyer (user) to adjust the optimal age-replacement policy if a product is operating in discrete time under a RFRW. © 2012 IEEE.

Lin H.-Y.,National Taichung University of Science and Technology
Decision Support Systems | Year: 2012

Classification problems have become more complex and intricate in modern applications in the face of continuous data explosion. In addition to great quantities of features and large numbers of instances, modern classification applications are continuously developed with multiple classes (objectives). The ever-increasing growth in data quantity and computation complexity has largely deteriorated the performance and accuracy of classification models. In order to deal with such situations, multivariate statistical analyses are adopted in this paper. Multivariate statistical analyses have two advantages. First, they can explore the relationships between variables and find the most characterizing features of the observed data. Second, they can solve problems which are stalled by high dimensionality. In this paper, the first advantage is applied to the selection of relevant features and the second is employed to generate the multivariate classifier. Experimental results show that our model can significantly improve classification training time by combining a compact subset of relevant features without the loss of accuracy in multi-class classification problems. In addition, the discrimination degree of our classifier outperforms other conventional classifiers. © 2012 Elsevier B.V. All rights reserved.

Chen M.-Y.,National Taichung University of Science and Technology
Applied Soft Computing Journal | Year: 2012

Prediction of financial bankruptcy has been a focus of considerable attention among both practitioners and researchers. However, most research in this area has ignored the non-stationary nature of corporate financial structures. Specifically, financial structures do not always present consistent statistical tests at each point of time, resulting in dynamic relationships between financial structures and their predictors. This characteristic of financial bankruptcy presents a significant challenge for any single artificial prediction technique. Therefore, this paper will propose a multi-phased and dynamic evaluation model of the corporate financial structure integrating both the self-organizing map (SOM) and support vector regression (SVR) techniques. In the 1st phase, the inputs to the SOM are financial indicators derived from listed companies' public financial statements adopting the principle component analysis (PCA) to extract useful indicators with a strong influence that each year determines the company's position on the SOM. In addition, we used the SOM to visualize and cluster each corporate in the 2D map. We also investigated each cluster and classified them into healthy and bankrupt-prone ones based on their regions in visualizing the 2D map. In the 2nd phase, we drew the trajectory for the healthy and the bankrupt-prone companies for consecutive years in a 2D map. Therefore, several visualized and dynamic patterns of corporate behavior could be recognized. In the 3rd phase, we used the SVR method to forecast the future trend for corporate financial structure. In addition, this research also compared the hybrid SOM-SVR architecture with single SOM, SVR, and Learning Vector Quantization (LVQ) algorithms. The results showed that the proposed methodology outperformed the other methods in both prediction accuracy and ease of use. © 2012 Elsevier B.V.

Chiang H.-S.,National Taichung University of Science and Technology
Online Information Review | Year: 2013

Purpose - Although increasing numbers of users have begun to use social networking sites (SNSs), the user growth of a few SNSs continues to decrease. Therefore identifying factors that influence users' intention to adopt and continuously use a particular SNS is a critical issue. To explore the factors, this study aims to apply the theories of reasoned action, uses and gratifications, and innovation diffusion to explain why people continue to join SNSs. Design/methodology/approach - The study participants were members of Facebook in Taiwan. An online questionnaire was used to conduct empirical research, and the data of 348 respondents were analysed using the partial least squares regression approach. Findings - It was found that the reasons why people continuously use SNSs vary with different innovation diffusion stages. In particular attitude toward SNSs had the strongest direct effect on continuous intention while the impact of social norms was not significant in the different innovation diffusion stages. Practical implications - From a practical perspective, insights provided by the study can help SNS developers understand user motivation and thus design more effective marketing strategies. Originality/value - The proposed model provides an improved understanding of the needs of different SNS users, and testing verified the effects of the factors related to gratification and innovation diffusion. © Emerald Group Publishing Limited.

Chen Y.-K.,National Taichung University of Science and Technology
Computers and Industrial Engineering | Year: 2013

The cumulative conformance count (CCC) control chart is often employed to monitor the fraction nonconforming of high-yield processes. Traditional CCC chart is used when the items from a process are inspected one-at-a-time following the production order. In recent years, the CCC chart has been generalized to accommodate some industrial practices where items from a process are inspected sample by sample and not according to the production order. In order to increase the sensitivity of the generalized CCC (GCCC) chart to changes in fraction nonconforming, the variable sampling interval (VSI) scheme is used in this study. The output characteristic within each sample is assumed with correlation. The statistical properties of the GCCC chart with the VSI scheme are deduced using the Markov chain method. In evaluating the usefulness of the VSI feature, GCCC charts with VSI and fixed sampling interval (FSI) schemes are compared in terms of their statistical properties. The comparison results show that using the VSI scheme can improve the speed of GCCC chart in detecting changes in fraction nonconforming. Finally, according to the comparison results, a design procedure is applied to an industrial example to validate its practicability. © 2012 Elsevier Ltd. All rights reserved.

Chang H.-C.,National Taichung University of Science and Technology
International Journal of Production Economics | Year: 2013

In this study, we revisit research contributed by Burwell et al. (1997. International Journal of Production Economics 48, 141-155), where an economic lot size model for price-dependent demand under quantity and freight discounts was proposed. Specifically, for the cases of mixed discounts in which the quantity discounts are either of the incremental or all-units variety and the freight discounts are of the opposite type, we first provide counterexamples to show that adopting the existing algorithm to determine overall optimal lot size and selling price may not achieve the goal of maximizing profit. We then propose an easy to understand computational algorithm to obtain an exact solution. © 2013 Elsevier B.V. All rights reserved.

Chang H.-C.,National Taichung University of Science and Technology
International Journal of Production Economics | Year: 2013

In this note, we correct some typos that appeared in Yassine et al. {Yassine, A.; Maddah, B.; Salameh M.; Disaggregation and consolidation of imperfect quality shipments in an extended EPQ model, International Journal of Production Economics 135 (2012) 345-352}, specifically, for one of their models that considered consolidating shipments of imperfect quality items across multiple production cycles. In addition, we present a heuristic approach to find a good solution for this model. The performance of heuristic solution is illustrated with numerical examples. © 2013 Elsevier B.V.

Loading National Taichung University of Science and Technology collaborators
Loading National Taichung University of Science and Technology collaborators