Partitional clustering methods such as C-Means classify all samples into clusters. Even a noise sample that is distant from any cluster is assigned to one of the clusters. Noise samples included in clusters bias the clustering result and tend to produce meaningless clusters. Our clustering method repeats to extract mutually close samples as a cluster and leave isolated noises unclustered. Thus,...

Data mining has became a familiar tool for mining stored value from the large scale databases that are known as Sequential Database. These databases has large number of itemsets that can arrive frequently and sequentially, it can also predict the users behaviors. The evaluation of user behavior is done by using Sequential pattern mining where the frequent patterns extracted with several limitat...

In this thesis, we study scalable and general purpose methods for mining frequent sequences that satisfy a given subsequence constraint. Frequent sequence mining is a fundamental task in data mining and has many real-life applications like information extraction, market-basket analysis, web usage mining, or session analysis. Depending on the underlying application, we are generally interested i...

In this study, the problem of unstructured information extraction has been analyzed and the need for a new Information Extraction algorithm is justified. We propose an Intelligent Information Extraction using Java Agent Development Environment (JADE) to be an optimal solution for intelligent information extraction. This proposed algorithm first assigns intelligent agents to gathering data, whic...