Nearest Prototype Classification of Special School Families Based on Hierarchical Compact Sets Clustering

-Cuban Schools for children with AffectiveBehavioral Maladies (SABM) have as goal to accomplish a major change in children behavior, to insert them effectively into society. One of the key elements in this objective is to give an adequate orientation to the children's families; due to the family is one of the most important educational contexts in which the children will develop their personality. The family orientation process in SABM involves clustering and classification of mixed type data with non-symmetric similarity functions. To improve this process, this paper includes some novel characteristics in clustering and prototype selection. The proposed approach uses a hierarchical clustering based on compact sets, making it suitable for dealing with non-symmetric similarity functions, as well as with mixed and incomplete data. The proposal obtains very good results on the SABM data, and over repository databases.

show abstract

“…This section introduces a prototype selection algorithm (figure 4) based on Compact Sets structuralization [6].…”

Section: B Nearest Prototype Selection Based On Compact Setsmentioning

confidence: 99%

Improving the family orientation process in Cuban Special Schools trough Nearest Prototype classification

Villuendas-Rey¹,

Benguría²,

Caballero³

et al. 2013

IJIMAI

View full text Add to dashboard Cite

show abstract

“…Instead of using a classical prototype selection strategy, this paper introduces the idea of structuralize the majority class by means of compact sets, and then obtain the desired number of prototypes. Compact sets have been used successfully for prototype selection in mixed and incomplete data, and also for clustering [8,9]. A compact set is a connected component of a Maximum Similarity Graph.…”

Section: Compact Sets Based Data Balancing By Under-samplingmentioning

confidence: 99%

Mixed Data Balancing through Compact Sets Based Instance Selection

Villuendas-Rey

García-Lorenzo

2013

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

Self Cite

View full text Add to dashboard Cite

Learning in datasets that suffer from imbalanced class distribution is an important problem in Pattern Recognition. This paper introduces a novel algorithm for data balancing, based on compact set clustering of the majority class. The proposed algorithm is able to deal with mixed, as well as incomplete data, and with arbitrarily dissimilarity functions. Numerical experiments over repository databases show the high quality performance of the method proposed in this paper according to area under the ROC curve and imbalance ratio.

show abstract

“…This type of object description is per say a challenge for any algorithm [11][12][13]. The lacking of a metric space makes impossible the definition of a sum operator and also the scalar multiplication [14][15][16][17][18][19][20][21][22][23]. In the same way, numeric attributes often have a large amount of values, each with low frequency.…”

Section: Introductionmentioning

confidence: 99%

Clustering mixed data using an Artificial Bee Colony

Cabrera-Venegas*,

Chávez-Castilla

2019

IJITEE

View full text Add to dashboard Cite

 Abstract: In this paper, we have proposed a clustering technique which optimizes the total compactness and separation (measured using the Silhouette index) of the clusters. The proposed algorithm uses an Artificial Bee Colony (ABC) based optimization method as the underlying optimization criterion. We used similarity based prototypes as cluster centers. The proposed clustering technique is able to suitably handle mixed and incomplete data types in such a way that the original characteristics of the data are preserved. Assignment of points to different clusters is done based on a dissimilarity function rather than the Euclidean distance. Results on real-life data sets show that the proposed technique is well-suited to detect true partitioning from data sets. Results are compared with those obtained by four existing clustering techniques, one genetic algorithm based clustering technique (AGKA), the k-Prototypes (KP) algorithm, well-known based K-means clustering technique for similarity functions (KMSF) and a newly developed algorithm with dissimilarity based clustering technique (AD2011).

show abstract

Nearest Prototype Classification of Special School Families Based on Hierarchical Compact Sets Clustering

Cited by 6 publications

References 7 publications

Improving the family orientation process in Cuban Special Schools trough Nearest Prototype classification

Improving the family orientation process in Cuban Special Schools trough Nearest Prototype classification

Mixed Data Balancing through Compact Sets Based Instance Selection

Clustering mixed data using an Artificial Bee Colony

Contact Info

Product

Resources

About