2013 | OriginalPaper | Buchkapitel
Similar or Not Similar: This Is a Parameter Question
verfasst von : Andrey Araujo Masiero, Flavio Tonidandel, Plinio Thomaz Aquino Junior
Erschienen in: Human Interface and the Management of Information. Information and Interaction Design
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
There is much information of users to be analyzed to develop a personalized project. To perform an analysis, it is necessary to create clusters in order to identify features to be explored by the project designer. In general, a classical clustering algorithm called K-Means is used to group users features. However, K-Means reveals some problems during the cluster process. In fact, K-Means does not guarantee to find Quality-Preserved Sets (QPS) and its randomness let the entire process unpredictable and unstable. In order to avoid these problems, a novel algorithm called Q-SIM (Quality Similarity Clustering) is presented in this paper. The Q-SIM algorithm has the objective to keep a similarity degree among all elements inside the cluster and guarantee QPS for all sets. During the tests, Q-SIM demonstrates that it is better than
k
-means and it is more appropriate to solve the problem for user modeling presented in this paper.