Abstract Computational approaches can be applied to solve different biology challenges. Tools based on traditional computation methods have shown, however, to be limited to approach complex biological problems in many situations. In the present study, a machine learning environment (GASNP), based on Genetic Algorithms, is proposed as a tool to extract classification rules from biological dataset. The main goal of the... Computational approaches can be applied to solve different biology challenges. Tools based on traditional computation methods have shown, however, to be limited to approach complex biological problems in many situations. In the present study, a machine learning environment (GASNP), based on Genetic Algorithms, is proposed as a tool to extract classification rules from biological dataset. The main goal of the proposed approach is to allow the discovery of concise, and accurate, biological high-level rules which can be used as a classification system. More than focusing only on the classification accuracy, the proposed GASNP model aims at balancing prediction precision, comprehensibility and interpretability. The obtained results show that the suggested approach has great potential and is capable of extracting useful high-level knowledge that could not be extracted by traditional classification methods such as Decision Trees, One R, Single Conjunctive Rule Learner, BFTree, Decision Table, JRIP, PART, among others, using the same dataset. Read More Read Less

Abstract This paper describes the features of an adaptive e-learning system from the perspectives of content adaptation and generation architecture, which includes three models: the domain model, the learning models and the adaptation model. We have used in our study, the rule base of the personalized e-learning system. We have documented that most students consider the personalized e-learning system useful for... This paper describes the features of an adaptive e-learning system from the perspectives of content adaptation and generation architecture, which includes three models: the domain model, the learning models and the adaptation model. We have used in our study, the rule base of the personalized e-learning system. We have documented that most students consider the personalized e-learning system useful for learning basic Java programming. Read More Read Less

Abstract Automatic learning systems now consider the time as the significatnt component and it has good impact and hence it should be considered while developing these systems. Many studies have addressed this issue and one amont them is the Allen’s temporal interval, based on a set of 13 relations that may hold between two time intervals. We in our study have... Automatic learning systems now consider the time as the significatnt component and it has good impact and hence it should be considered while developing these systems. Many studies have addressed this issue and one amont them is the Allen’s temporal interval, based on a set of 13 relations that may hold between two time intervals. We in our study have kept the principal notion of identifying the several of temporal relations from data, using an inductive logic programming (ILP) system. This work addresses a series of automatic learning investigations. This study shows the following: The exploration of the impact of the negative training patterns on the induced relation, evidencing the necessary background knowledge for inducing the exact expression of the target concept and investigate the viability of ILP as a learning mechanism in real-time systems. Read More Read Less

Abstract Due to an increase of several data mining techniques, selection of an appropriate data mining technique to use is one of the important steps when undertaking a data mining project. Data miners used to test various numbers of techniques to work out which one will give them the best results every time they have new data, this is costly and... Due to an increase of several data mining techniques, selection of an appropriate data mining technique to use is one of the important steps when undertaking a data mining project. Data miners used to test various numbers of techniques to work out which one will give them the best results every time they have new data, this is costly and time consuming. They can solve this problem by understanding the main objective of mining, strength and weaknesses of the techniques and the features of the data they have, to determine the best technique to use without testing numbers of techniques. Testing different techniques shows that, there is a confusion of what data mining technique will be most appropriate for them than other techniques. Therefore, this paper discus different strength and weaknesses of four different data mining techniques and compare their performance on different features of the datasets by four different evaluation metrics. The summary was theoretically applied to the retail dataset to decide on the most appropriate technique for customer retention as a case study. Thus, users can use the summary provided in this paper to select the most appropriate data mining technique. Read More Read Less

Abstract In this paper is described an agile process for Web development based on the use of User Stories. The main objective of this study is to have a greater integration between the disciplines of software development process, i.e. to have a closer relationship between requirements and the final product, and all stages between these two extremes. In addition, the process... In this paper is described an agile process for Web development based on the use of User Stories. The main objective of this study is to have a greater integration between the disciplines of software development process, i.e. to have a closer relationship between requirements and the final product, and all stages between these two extremes. In addition, the process incorporates the use of acceptance tests. The User Stories try to be a snapshot as faithful as possible of User’s needs. It will be used both in manuscript form (in cards) for requirements specification and in an executable format to guide the coding and serve as acceptance tests. Other artifacts, such as Class Diagram, Architecture Model and Product Backlog also will be created. Read More Read Less