Unsupervised Learning Aided by Clustering and Local-Global Hierarchical Analysis in Knowledge Exploration

Yihao Zhang; Orgun, Mehmet A.; Weiqiang Lin
August 2007
Journal of Digital Information Management;Aug2007, Vol. 5 Issue 4, p237
Academic Journal
Unsupervised learning plays an important role in the knowledge exploration discovery. The basic task of unsupervised learning is to find latent variables or relationships in a given dataset without any assumed regularities or patterns. In this paper we apply two advanced models, clustering analysis and hierarchical analysis to accomplish unsupervised learning. K-Means clustering presents its strength in large scale clustering. The original data can be preprocessed and the potential variables are targeted. Correlations among these variables are explored in the subsequent sets by Local Global Hierarchical Analysis (LGHA) assisted by three main steps. In the first step, we use a structural approach to find qualititative patterns from the given variables. Then, the second step applies a quantitative based algorithm to find quantitative patterns from those variables. The and last step generated global hybrid patterns by combining the local patterns obtained from the first two steps based on a certain criterion. Both of the K-Means and Local Global Hierarchical Analysis (LGHA) models are applied in experiments with real world longitutional medical datasets.


Related Articles

  • A Novel Model-Based Approach in Classification Using Extension Distance. Hai-Tao Zhang; Bin-Jun Wang // Applied Mechanics & Materials;2014, Issue 644-650, p2009 

    In order to solve the low efficiency problem of KNN or K-Means like algorithms in classification, a novel extension distance of interval is proposed to measure the similarity between testing data and the class domain. The method constructs representatives for data points in shorter time than...

  • Notes on Vertex Classification Problem in Hypergraph Setting. Li Yan; Junsheng Li; Wei Gao // Information Technology Journal;2013, Vol. 12 Issue 18, p3309 

    Classification algorithm is classical learning problem in computer science. Hypergraph, as a knowledge representation model, has widely used in finance, biology and information science. In this study, we extend some graph vertex classification analysis results to hypergraph. Specifically, we use...

  • Imitation learning of car driving skills with decision trees and random forests. Cichosz, Paweł; Pawełczak, Łukasz // International Journal of Applied Mathematics & Computer Science;Sep2014, Vol. 24 Issue 3, p579 

    Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a...

  • Representación del conocimiento y aprendizaje. Teoría de los Conceptos Nucleares. Casas García, Luis M.; Luengo González, Richard // Revista Española de Pedagogía;2004, Issue 227, p59 

    The present investigation approached the problem of the concept of angle and the techniques needed to represent how pupils construct that concept in their cognitive structure during their years in school. We used the Pathfinder Associative Networks. This technique provided us with the data of...

  • The Tactics and Knowledge Representations Used by Blind Students in Learning from Texts. Hoz, Ron; Alon, Asnat // Journal of Visual Impairment & Blindness;May2001, Vol. 95 Issue 5, p304 

    Presents a study on the learning tactics and knowledge representations used by visually impaired students attempting to learn from texts. Types of knowledge representations; Methodology used; Results and discussion.

  • Performance evaluation of clustering techniques for image segmentation. Ouali, Mohammed; Aitnouri, Elmehdi // Computer Science Journal of Moldova;2010, Vol. 18 Issue 3, p271 

    In this paper, we tackle the performance evaluation of two clustering algorithms: EFC and AIC-based. Both algorithms face the cluster validation problem, in which they need to estimate the number of components. While EFC algorithm is a direct method, the AIC-based is a verificative one. For a...

  • Dunn's index for cluster tendency assessment of pharmacological data sets. Rivera-Borroto, Oscar Miguel; Rabassa-Gutiérrez, Mónica; Grau-Ábalo, Ricardo del Corazón; Marrero-Ponce, Yovani; García-de la Vega, José Manuel // Canadian Journal of Physiology & Pharmacology;Apr2012, Vol. 90 Issue 4, p425 

    Cluster tendency assessment is an important stage in cluster analysis. In this sense, a group of promising techniques named visual assessment of tendency (VAT) has emerged in the literature. The presence of clusters can be detected easily through the direct observation of a dark blocks structure...

  • Image Compression Using Partitioning Around Medoids Clustering Algorithm. Nikam, V. B.; Kadam, Vinod J.; Meshram, B. B. // International Journal of Computer Science Issues (IJCSI);Nov2011, Vol. 8 Issue 6, p399 

    Clustering is a unsupervised learning technique. This paper presents a clustering based technique that may be applied to Image compression. The proposed technique clusters all the pixels into predetermined number of groups and produces a representative color for each group. Finally for each...

  • Affinity Propagation Clustering Based on Grey Relational Analysis. Guo Kun; Zhang Qishan // Journal of Grey System;2010, Vol. 22 Issue 2, p147 

    Affinity propagation (AP) is a clustering algorithm based on the similarities between data points and is proved to be a fast and efficient clustering method for large-scale data sets. But for some data sets with complex cluster structures, it cannot produce good clustering results. In this...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics