Showing papers in "Information Technology Journal in 2010"

A survey of business process complexity metrics.

Abstract: Business processes have an inherent complexity which if not controlled can keep on increasing with time, thus making the processes error-prone, difficult to understand and maintain. In the last few years, several researchers have proposed a number of metrics which can be used to measure and therefore control the complexity of business processes. In this study, a survey of business process complexity metrics is conducted with the goal of investigating if there are any gaps in literature. Initially, a description of the process of metrics definition and validation is presented, followed by an analysis of business process complexity metrics that have appeared in literature in the last 5 years. The reviewers checked whether the identified metrics have any tool support, whether they have been validated and whether validation results are significant or not. Findings show that few business process complexity metrics have been proposed so far and that even fewer have been validated. In order to address these issues, some future research directions are proposed.

Ranking of influencing factors in predicting students' academic performance.

Abstract: The aim of this study was to rank influencing factors that contribute to the prediction of students’ academic performance. It is useful in identifying weak students who are likely to perform poorly in their studies. In this study, we used WEKA open source data mining tool to analyze attributes for predicting a higher learning institution’s bachelor of computer science students’ academic performance. The data set comprised of 2427 number of student records and 396 attributes of students registered between year 2000 and 2006. Preprocessing includes attribute importance analysis. We applied the data set to different classifiers (Bayes, trees or function) and obtained the accuracy of predicting the students’ performance into either first-second-upper class or second-lower-third class. A cross-validation with 10 folds was used to evaluate the prediction accuracy. Our results showed the ranking of courses that has significant impact on predicting the students’ overall academic results. In addition, we perform experiments comparing the performance of different classifiers and the result showed that Naive Bayes, AODE and RBFNetwork classifiers scored the highest percentage of prediction accuracy of 95.29%.

Compact dual band microstrip antenna for Ku-band application

Abstract: A new design of dual band compact microstrip antenna is proposed for Ku-band applications. Dual band is achieved using three pairs of thin slits from the sides of a rectangular patch and feeding with a microstrip feedline. The antenna has a compact structure and the total size is 9.50 by 10 by 0.254 mm. The result shows that the return loss of-23.83 dB is achieved at the first resonant frequency of 12.54 GHz and-14.04 dB is obtained at the second resonant frequency of 14.15 GHz. The antenna gives a stable radiation performance with gain greater than 4 dBi over the frequency band.

Mining web navigation profiles for recommendation systems

Abstract: This study explores web usage mining, for which many data mining techniques such as clustering, classification and pattern discovery have been applied to web server logs. The output is a set of discovered patterns which form the main input to the recommendation systems which in return predict the next web navigations. Most of the recommendation systems are user-centered which make a prediction list to the users based on their long term navigation history, user’s databases or full user’s profiles. Companies wish to attract anonymous users, directed them at the early stages of their visits and get them involved with their websites. Learning and mining the web navigation profiles followed by enhanced classification to the similar activities of previous users will provide an appropriate model to recommend to the current anonymous active user with short term navigation. Using CTI dataset, the experimental results show better prediction accuracy than the previous works. An adaptive profiling to save time is a key factor for future works.

Complexity Metrics for Executable Business Processes

Abstract: In this study, seven metrics are proposed for measuring the complexity of Executable Business Processes (EBP). The metrics are either derived from existing business process metrics or adapted from software metrics. Evaluation was carried out in three case studies with the goal of finding out if the metrics are theoretically sound and at the same time intuitional. In case 1, metrics values were computed from three processes and then analyzed to check whether they agree with reality. In case 2, the metrics were grouped into two categories of length and complexity and then separately checked for their conformance to Briand’s framework. In case 3, all the metrics were treated under one complexity category and then checked for their conformance to Weyuker’s properties. Results indicate that the new metrics are intuitional and are good if used in their respective categories, or when used together to complement each other in order to give a fuller view of process complexity.