Robust Local Feature Weighting Hard C-Means Clustering Algorithm

2012 ◽  
pp. 591-598
Author(s):  
Xiaobin Zhi ◽  
Jiulun Fan ◽  
Feng Zhao
Keyword(s):  
Clustering Algorithm ◽  
Feature Weighting ◽  
Local Feature

Robust local feature weighting hard c-means clustering algorithm

2014 ◽  
Vol 134 ◽  
pp. 20-29 ◽  
Author(s):  
Xiao-bin Zhi ◽  
Jiu-lun Fan ◽  
Feng Zhao
Keyword(s):  
Clustering Algorithm ◽  
Feature Weighting ◽  
Local Feature

Laplacian-based 3D mesh simplification with feature preservation

2019 ◽  
Vol 10 (02) ◽  
pp. 1950002 ◽  
Author(s):  
Wei Lyu ◽  
Wei Wu ◽  
Lin Zhang ◽  
Zhaohui Wu ◽  
Zhong Zhou
Keyword(s):  
Clustering Algorithm ◽  
Shape Descriptor ◽  
Mesh Simplification ◽  
Feature Weighting ◽  
Laplacian Operator ◽  
Geometric Features ◽  
Error Statistics ◽  
3D Mesh ◽  
Surface Meshes ◽  
Improving Accuracy

We propose a novel Laplacian-based algorithm that simplifies triangle surface meshes and can provide different preservation ratios of geometric features. Our efficient and fast algorithm uses a 3D mesh model as input and initially detects geometric features by using a Laplacian-based shape descriptor (L-descriptor). The algorithm further performs an optimized clustering approach that combines a Laplacian operator with K-means clustering algorithm to perform vertex classification. Moreover, we introduce a Laplacian weighted cost function based on L-descriptor to perform feature weighting and error statistics comparison, which are further used to change the deletion order of the model elements and preserve the saliency features. Our algorithm can provide different preservation ratios of geometric features and may be extended to handle arbitrary mesh topologies. Our experiments on a variety of 3D surface meshes demonstrate the advantages of our algorithm in terms of improving accuracy and applicability, and preserving saliency geometric features.

scholarly journals Retraction Note to: Local Feature Weighting for Data Classification

2017 ◽  
pp. E1-E1
Author(s):  
Gengyun Jia ◽  
Haiying Zhao ◽  
Zhigeng Pan ◽  
Liangliang Wang
Keyword(s):  
Data Classification ◽  
Feature Weighting ◽  
Local Feature

AUTOMATIC IMAGE ANNOTATION BASED ON SEMI-SUPERVISED CLUSTERING AND MEMBERSHIP-BASED CROSS MEDIA RELEVANCE MODEL

2012 ◽  
Vol 26 (06) ◽  
pp. 1255009 ◽  
Author(s):  
MOHAMED MAHER BEN ISMAIL ◽  
OUIEM BCHIR
Keyword(s):  
Clustering Algorithm ◽  
Image Annotation ◽  
Feature Weighting ◽  
Training Data ◽  
Automatic Image Annotation ◽  
Data Set ◽  
Cross Media ◽  
Training Images ◽  
Possibilistic Clustering ◽  
Main Components

In this paper, we propose a system for automatic image annotation that has two main components. The first component consists of a novel semi-supervised possibilistic clustering and feature weighting algorithm based on robust modeling of the generalized Dirichlet (GD) finite mixture. This algorithm is used to group image regions into prototypical region clusters that summarize the training data and can be used as the basis of annotating new test images. The constraints consist of pairs of image regions that should not be included in the same cluster. These constraints are deduced from the irrelevance of all concepts annotating the training images to help in guiding the clustering process. The second component of our system consists of a probabilistic model that relies on the possibilistic membership degrees, generated by the clustering algorithm, to annotate unlabeled images. The proposed system was implemented and tested on a data set that include thousands of images using four-fold cross validation.

Distance measure adaptation based on local feature weighting

2012 ◽  
Author(s):  
Mohammad Reza Moosavi ◽  
Zahra Yeganehfard ◽  
Alireza Kazemi ◽  
Mohammad Hadi Sadreddini ◽  
Mansoor Zolghadri Jahromi
Keyword(s):  
Distance Measure ◽  
Feature Weighting ◽  
Local Feature

scholarly journals A survey on feature weighting based K-Means algorithms

2020 ◽  
Author(s):  
Renato Cordeiro de Amorim
Keyword(s):  
Machine Learning ◽  
Empirical Evidence ◽  
Real World ◽  
Clustering Algorithm ◽  
Machine Learning Algorithms ◽  
Feature Weighting ◽  
Future Research ◽  
Real World Data ◽  
Data Set ◽  
Partitional Clustering

In a real-world data set there is always the possibility, rather high in our opinion, that different features may have different degrees of relevance. Most machine learning algorithms deal with this fact by either selecting or deselecting features in the data preprocessing phase. However, we maintain that even among relevant features there may be different degrees of relevance, and this should be taken into account during the clustering process. With over 50 years of history, K-Means is arguably the most popular partitional clustering algorithm there is. The first K-Means based clustering algorithm to compute feature weights was designed just over 30 years ago. Various such algorithms have been designed since but there has not been, to our knowledge, a survey integrating empirical evidence of cluster recovery ability, common flaws, and possible directions for future research. This paper elaborates on the concept of feature weighting and addresses these issues by critically analysing some of the most popular, or innovative, feature weighting mechanisms based in K-Means

RETRACTED CHAPTER: Local Feature Weighting for Data Classification

2017 ◽  
pp. 293-302 ◽  
Author(s):  
Gengyun Jia ◽  
Haiying Zhao ◽  
Zhigeng Pan ◽  
Liangliang Wang
Keyword(s):  
Data Classification ◽  
Feature Weighting ◽  
Local Feature
Sign in / Sign up

Export Citation Format

Share Document