A new Centroid-Based Classification model for text categorization

Liu, Chuan; Wang, Wenyong; Tu, Guang-hui; Xiang, Yu; Wang, Siyang; Lv, Fengmao

doi:10.1016/j.knosys.2017.08.020

Cited by 31 publications

(30 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also possible to apply a different formula proposed in [ 17 ], which replaces the reciprocal of the square of the distance

with the similarity function

, according to this Equation (4):

…”

Section: Methodsmentioning

confidence: 99%

“…Based on the data gravity force values determined in such way between the atomic data particle

and all

data particles belonging to the feature space

, the data particle

, for which the data gravity force was the highest, is selected [ 17 ], which is expressed by the following relationship, as shown in Equation (5):

…”

Section: Methodsmentioning

confidence: 99%

“…Two algorithms for determining the mass of a data particle—Stochastic Learning Algorithm (GM SLA) and Batch-update Learning Algorithm (GM BLA) were proposed in 2017 [ 17 ]. It was then emphasized that the effectiveness of centroid-based algorithms depends on the characteristics of the data set.…”

Section: Methodsmentioning

confidence: 99%

“…In the evaluation process of the proposed method,

-Fold Cross-Validation was used. It was also used to evaluate the models in many new publications [ 17 , 24 ]. The application of

-Fold Cross-Validation enables avoiding the model overfitting and improves the model’s generalization property [ 24 ].…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations

A Geometrical Divide of Data Particle in Gravitational Classification of Moons and Circles Data Sets

Rybak¹,

Dudczyk²

2020

Entropy

View full text Add to dashboard Cite

Thus far, the Universal Law of Gravitation has found application in many issues related to pattern classification. Its popularity results from its clear theoretical foundations and the competitive effectiveness of the classifiers based on it. Both Moons and Circles data sets constitute distinctive types of data sets that can be found in machine learning. Despite the fact that they have not been formally defined yet, on the basis of their visualization, they can be defined as sets in which the distribution of objects of individual classes creates shapes similar to circles or semicircles. This article makes an attempt to improve the gravitational classifier that creates a data particle based on the class. The aim was to compare the effectiveness of the developed Geometrical Divide method with the popular method of creating a class-based data particle, which is described by a compound of 1 ÷ 1 cardinality in the Moons and Circles data sets classification process. The research made use of eight artificially generated data sets, which contained classes that were explicitly separated from each other as well as data sets with objects of different classes that did overlap each other. Within the limits of the conducted experiments, the Geometrical Divide method was combined with several algorithms for determining the mass of a data particle. The research did also use the k-Fold Cross-Validation. The results clearly showed that the proposed method is an efficient approach in the Moons and Circles data sets classification process. The conclusion section of the article elaborates on the identified advantages and disadvantages of the method as well as the possibilities of further research and development.

show abstract

“…It is also possible to apply a different formula proposed in [ 17 ], which replaces the reciprocal of the square of the distance

with the similarity function

, according to this Equation (4):

…”

Section: Methodsmentioning

confidence: 99%

“…Based on the data gravity force values determined in such way between the atomic data particle

and all

data particles belonging to the feature space

, the data particle

, for which the data gravity force was the highest, is selected [ 17 ], which is expressed by the following relationship, as shown in Equation (5):

…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…In the evaluation process of the proposed method,

-Fold Cross-Validation was used. It was also used to evaluate the models in many new publications [ 17 , 24 ]. The application of

-Fold Cross-Validation enables avoiding the model overfitting and improves the model’s generalization property [ 24 ].…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A Geometrical Divide of Data Particle in Gravitational Classification of Moons and Circles Data Sets

Rybak¹,

Dudczyk²

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…NCC has been used in many field for classification purpose. Several studies using NCC methods are [5], which perform feature selection as preprocessing, [6] used NCC for DNA classification, [7] is about vehicle routing problems, [8] use a centroidbased classifier for text classification, [9] use a centroid-based classifier for intrusion detection, and [4] are used for music genre classification. In related studies [4][5] [6] [7][8] [9], there are no data cleaning process as a preprocessing for the NCC method.…”

Section: Introductionmentioning

confidence: 99%

Nearest Centroid Classifier with Outlier Removal for Classification

Bawono

Bahtiar

Supianto

2020

JITeCS

View full text Add to dashboard Cite

Classification is a part of data mining which is very useful for many purpose. There are so many method to classify, however a classification process need good source of data to deliver good performance. In the real world, not all data is good. Some of the data contains noise and outlier that can reduce classification performance. However, there are few research of classification with an outlier removal process, especially for Nearest Centroid Classifier Method. Nearest Centroid Classifier is a good yet simple classification method. However, Nearest Centroid Classifier suffers performance loss like the other classification method. The proposed methodology consists of two stages. First, preprocess the data with outlier removal, removes points which are far from the corresponding centroids, the center point of a class. Second, classify the outlier removed data or cleaned data. The experiment covers six data sets which have different characteristic. The results indicate that outlier removal as preprocessing method provide better result by 0.76% to 3.16% for improving Nearest Centroid Classifier performance on most data set.

show abstract

Optimal weighted hybrid pattern for content based medical image retrieval using modified spider monkey optimization

Darapureddy

Karatapu²,

Battula

2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The current approaches for image retrieval are more concentrating on numerous image features. Texture, shape, spatial information, and color are the fundamental features to deal with flexible image datasets. This paper aims to develop new Content-Based Image Retrieval System based on Optimal Weighted Hybrid Pattern. Two relevant patters like Local Vector Pattern and Local Derivative Pattern are intended to develop a novel Content-Based Image Retrieval system. The optimal weighted hybrid pattern is implemented to derive a new feature vector, so that the weight is optimized by a modified optimization algorithm called Improved Local Leader-based Spider Monkey Optimization to maximize the precision and recall of the retrieved images. The retrieval of the image is done by measuring the similarity based on Mean Square Distance between the features of query image as well as training image. Finally, the performance comparison of the proposed and the traditional patterns shows its reliable performance. K E Y W O R D S content-based medical image retrieval, improved local leader-based spider monkey optimization, local derivative pattern, local vector pattern, machine learning-based classification, novel descriptors, optimal weighted hybrid pattern

show abstract

A new Centroid-Based Classification model for text categorization

Cited by 31 publications

References 45 publications

A Geometrical Divide of Data Particle in Gravitational Classification of Moons and Circles Data Sets

A Geometrical Divide of Data Particle in Gravitational Classification of Moons and Circles Data Sets

Nearest Centroid Classifier with Outlier Removal for Classification

Optimal weighted hybrid pattern for content based medical image retrieval using modified spider monkey optimization

Contact Info

Product

Resources

About