Using Representative-Based Clustering for Nearest Neighbor Dataset Editing

Eick, Christoph F.; Zeidat, Nidal; Vilalta, Ricardo

doi:10.1109/icdm.2004.10044

Cited by 20 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Selecting a set of examples that generates a template with the best accuracy, for example. The algorithm chosen for this work is the SCE (Supervised Clustering Editing) [4]. The SCE uses the second method mentioned.…”

Section: B Nearest Neighbor Editing (Prototype Selection)mentioning

confidence: 99%

Performance Comparison between Edited kNN and MQ-RBFN for Regression and Classification Tasks

Maia

Laboreiro²,

Chaves³

et al. 2016

Anais Do 11. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

Abstract-Supervised learning techniques can be roughly grouped into lazy learning or eager learning. Lazy learning and eager learning have very different properties and are suitable for different applications. In this paper we evaluate properties of the two types of learning using a representative distance based algorithm for each class, namely, kNN (k-nearest neighbors) and RBFN (Radial Basis Function Network). In addition, an edition algorithm (SPAM -Supervised Partitioning Around Medoids) is used to reduce the labeled dataset. Our experiments for classification and regression tasks, using 12 public datasets show that prototype selection algorithms typically used with kNN are good alternatives for selection of centers of RBFN when to optimize the number of centers is not the relevant criterion. The experiments also show that the RBFN generally perform better than Edited kNN.

show abstract

Section: B Nearest Neighbor Editing (Prototype Selection)mentioning

confidence: 99%

Performance Comparison between Edited kNN and MQ-RBFN for Regression and Classification Tasks

Maia

Laboreiro²,

Chaves³

et al. 2016

Anais Do 11. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…Algorithm Improvements The nearest neighbor classification algorithm [7] is one of the most famous prototype classifier. It is suitable for circumstances where all the samples has been obtained before training, and performs well in dealing with a large number of sample data, but its main disadvantage is that if the training samples are melt with some noise, the performance of the classifier will be greatly reduced.…”

Section: )mentioning

confidence: 99%

Incremental learning based on the nearest neighbor classifier

Liu

2015

2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

View full text Add to dashboard Cite

In many practical applications, it is difficult to obtain the complete sample set and the categories may be variable with time. This paper introduces an online incremental learning algorithm based on the nearest neighbor algorithm to increase model or category during the process of recognition. Calculating the matching degree between new input sample and model samples, the algorithm finds the best and second best matching degrees and compares them with the threshold. The comparative results decide whether it increases samples' amount or adds a new category to realize incremental learning. The algorithm is applied to segment data set and experiment of vehicle type recognition. The experiments prove the algorithm efficient. Also, more experiments are conducted to analyze and verify how standard sample amount and matching degree threshold affect the final results.

show abstract

“…Kullanılan kalp veri kümesinin sınıflandırılmasına yönelik literatürde farklı çalışmalar bulunmaktadır [13,14]. Kullanılan veri kümesinde, iki sınıf, 13 öznitelik değeri ve toplamda 270 örnek bulunmaktadır.…”

Section: Metotunclassified

The optimum fuzzy logic approach for biomedical data classification

Polat

2010

2010 15th National Biomedical Engineering Meeting

View full text Add to dashboard Cite

ÖzetçeBu çalışmada farklı biyomedikal verilerin sınıflandırılması amaçlı kullanılabilecek bir bulanık mantık tekniğinin performansını arttırmak için optimizasyon işlemi gerçekleştirilmiştir. Optimizasyon işleminde eşik kabulü algoritması kullanılmıştır. Önerilen metot kalp veri kümesi üzerinde denenmiş ve simülasyon sonuçlarında optimize edilmiş bulanık mantık yaklaşımının sınıflandırma başarısının optimize edilmemiş yapıya göre daha yüksek olduğu görülmüştür. AbstractIn this study, a fuzzy logic technique for classification of different biomedical dataset is optimized for improving performance. Threshold acceptance algorithm is used for optimization process. The proposed method is tested on heart data set and simulation results show that the optimized fuzzy logic approach provides higher classification accuracy compare with that of unoptimized fuzzy logic structure.

show abstract

Using Representative-Based Clustering for Nearest Neighbor Dataset Editing

Cited by 20 publications

References 6 publications

Performance Comparison between Edited kNN and MQ-RBFN for Regression and Classification Tasks

Performance Comparison between Edited kNN and MQ-RBFN for Regression and Classification Tasks

Incremental learning based on the nearest neighbor classifier

The optimum fuzzy logic approach for biomedical data classification

Contact Info

Product

Resources

About