Among the age competition, more and more companies know how to provide fine, humane benefit cares, in order to obtain satisfactory outcome and secure good employees. Therefore, companies should know employees¡¦ diverse needs in being cared. The purposes of the employees¡¦ benefit committee devoting to promote benefit cares are to lift working spirits, to raise working efficiency, and to increase the enterprise overall profits. The best method to evaluate employees¡¦ feelings toward the benefit of cares is to measure their satisfaction. At the customer-oriented new economy age, most companies realize that having satisfied employees can eventually bring in customer satisfaction. The main purposes of this study are to explore the degrees of satisfaction and importance, respectively, of the employees toward the care items proposed by the Taiwan Sugar Corporation Employee¡¦s Benefit Committee and to provide suggestions and ways of improving. We randomly draw 5¢H employees from the Taiwan Sugar Corporation and they are the subjects of this study. Totally 210 copies of questionnaires are given away and 188 copies deemed effective are retrieved. There are 34 survey questions in the questionnaire. The Likert scale is adopted and SPSS for Windows is used as the tool for statistical analysis. This paper tries to figure out the top five satisfactory/unsatisfactory, important/unimportant benefit care items. The benefit care items are categorized into four groups. They are the group with balanced demand and supply, the group with excess demand, the group with excess supply, and the group with wasted resources. The result can be a reference for Taiwan Sugar Corporation Employee¡¦s Benefit Committee to improve their benefit care items. This study finds that there is a difference between the degrees of satisfaction and the degrees of the importance and employees with different personal backgrounds are different toward the perception of satisfaction and importance.

No description available.

No description available.

Quality of life is an important yet often unmeasured variable in assessing places to live. Maintaining and promoting a high quality of life is critical for communities striving to sustain and expand their current economic bases. This study presents a format for measuring quality of life and an adaptation of the importance-performance analytical technique for evaluating results. Using results from a quality of life survey, the study demonstrates how policy implications may be suggested from the analysis.

Variable importance measures for random forests have been receiving increased attention as a means of variable selection in many classification tasks in bioinformatics and related scientific fields, for instance to select a subset of genetic markers relevant for the prediction of a certain disease. We show that random forest variable importance measures are a sensible means for variable selection in many applications, but are not reliable in situations where potential predictor variables vary in their scale level or their number of categories. This is particularly important in genomics and computational biology, where predictors often include variables of different types. Simulation studies are presented illustrating that, when random forest variable importance measures are used with data of varying types, the results are misleading because suboptimal predictor variables may be artificially preferred in variable selection. The two mechanisms underlying this deficiency are biased variable selection in the individual classification trees used to build the random forest on one hand, and effects induced by bootstrap sampling with replacement on the other hand. We propose to employ an alternative implementation of random forests, that provides unbiased variable selection in the individual classification trees. When this method is applied using subsampling without replacement, the resulting variable importance measures can be used reliably for variable selection even in situations where the potential predictor variables vary in their scale level or their number of categories. The usage of both random forest algorithms and their variable importance measures in the R system for statistical computing is illustrated and documented thoroughly in an application re-analysing data from a study on RNA editing. Therefore the suggested method can be applied straightforwardly by scientists in bioinformatics research. (author's abstract) / Series: Research Report Series / Department of Statistics and Mathematics

Student Number : 9804484F MSc dissertation - School of Statistics and Acturial Science - Faculty of Science / This dissertation conducts a comprehensive and up to date review of measures of component and module importance within monotone systems, where it is assumed that components work independent of each other. The dissertation traces the development of these important measures from the initial definition of Birnbaum importance right through to the definition of Meng's criticality importance. Furthermore, the dissertation draws a distinction between time independent measures and time dependent measures (such as the Barlow-Proschan measures). The dissertation demonstrates how such measures may be implemented in analysing the importance of components within the monotone systems by evaluating these measures for a well known bridge structure example. This evaluation also reveals how each defined measure can be compared to each other. In conclusion, the dissertation describes how these measures can be extended to non-monotone systems or systems with dependent components.

The present study investigated the extent to which importance ratings (i.e., a measure of perceived importance for driving-related concepts) are a viable alternative to traditional mental model assessment methods in predicting driving performance. Although mental models may predict driving–related outcomes—crash involvement and moving violations—common mental model assessment techniques are associated with administrative limitations and challenges, which can affect how valid mental models are as assessments of knowledge structure. Importance ratings, as a measure of driving-related knowledge that may be associated with fewer administrative limitations, were hypothesized to provide equal predictive validity for driving–related performance outcomes in a sample of undergraduate students. To investigate the extent to which the measurement of mental models and importance ratings contribute to the prediction of driving crashes and moving violations, students completed Pathfinder, a common computer-based mental model assessment method, and paper-and-pencil importance ratings. In addition, students completed a test of driving knowledge and reported driving behaviors and outcomes including at-fault crashes and moving violations that occurred over the past five years (i.e., from 2005 to 2009). A group of expert drivers completed mental model and importance ratings assessments as well. Data across expert raters were combined and analyzed for appropriateness to serve as referent scores for each assessment. Students' mental model accuracy as well as importance rating accuracy was based on the extent to which student mental models and ratings agreed with those provided by the group of expert drivers. The results suggest that importance rating and mental model accuracy predicted crash involvement and moving violations. Whereas mental model accuracy was a stronger predictor of the number of moving violations, importance rating accuracy predicted the number of at-fault crashes slightly better than mental models. Although inconclusive, these results suggest that importance ratings may be a viable alternative to traditional mental model assessment in predicting some driving outcomes. Future research is warranted on importance ratings and other alternative mental model assessments.

People preserve memories of events such as birthdays, weddings, or vacations by capturing photos, often depicting groups of people. Invariably, some individuals in the image are more important than others given the context of the event. This work analyzes the concept of the importance of individuals in group photographs. We address two specific questions - Given an image, who are the most important individuals in it? Given multiple images of a person, which image depicts the person in the most important role? We introduce a measure of importance of people in images and investigate the correlation between importance and visual saliency. We find that not only can we automatically predict the importance of people from purely visual cues, incorporating this predicted importance results in significant improvement in applications such as im2text (generating sentences that describe images of groups of people). / Master of Science

This thesis develops a generalized form of Monte Carlo integration called Resampled Importance Sampling. It is based on the importance resampling sample generation technique. Resampled Importance Sampling can lead to significant variance reduction over standard Monte Carlo integration for common rendering problems. We show how to select the importance resampling parameters for near optimal variance reduction. We also combine RIS with stratification and with Multiple Importance Sampling for further variance reduction. We demonstrate the robustness of this technique on the direct lighting problem and achieve up to a 33% variance reduction over standard techniques. We also suggest using RIS as a default BRDF sampling technique.

We propose a new measure, called the Container Port Connectivity Index (CPCI), to more accurately reflect the relative importance of container ports within the global network of container shipping. This index is based on both economics and network topology, where the strength of a port is based on its position within the global structure of shipping network and not just on local information, such as the number of TEUs handled or direct links to other ports. As the CPCI produces two separate scores for each inbound and outbound connectivity, we can use them to analyze the economic roles played by each port independently. We also propose a framework for evaluating market stability of a logistics hub in a competitive environment. In particular, we build a model, called the Liner Shipping Cooperative Model, to predict how the community of liners calling at a hub might develop as the result of actions by competitors. We use such a model to study the behavior of shipping lines, as well as the resulting trade-flow changes, as the system gradually moves toward new equilibrium defined by the grand coalition. With this piece of information, a port authority would be able to quantify threats posed by competitors and, consequently, devise counter strategies to safeguard its business against competing ports.