K-Means Initialization Methods for Improving Clustering by Simulated Annealing

Perim, Gabriela Trazzi; Wandekokem, Estefhan Dazzi; Varejão, Flávio Miguel

doi:10.1007/978-3-540-88309-8_14

Cited by 14 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These include methods based on hierarchical clustering [72], genetic algorithms [73], simulated annealing [74,75], multiscale data condensation [76], and kd-trees [77]. Other interesting methods include the global k-means method [78], Kaufman and Rousseeuw's method [79], and the ROBIN method [80].…”

Section: Initializing the K-means Algorithmmentioning

confidence: 99%

Improving the performance of k-means for color quantization

Celebi

2011

Image and Vision Computing

157

View full text Add to dashboard Cite

Color quantization is an important operation with many applications in graphics and image processing. Most quantization methods are essentially based on data clustering algorithms. However, despite its popularity as a general purpose clustering algorithm, k-means has not received much respect in the color quantization literature because of its high computational requirements and sensitivity to initialization. In this paper, we investigate the performance of k-means as a color quantizer. We implement fast and exact variants of k-means with several initialization schemes and then compare the resulting quantizers to some of the most popular quantizers in the literature. Experiments on a diverse set of images demonstrate that an efficient implementation of k-means with an appropriate initialization strategy can in fact serve as a very effective color quantizer.

show abstract

Section: Initializing the K-means Algorithmmentioning

confidence: 99%

Improving the performance of k-means for color quantization

Celebi

2011

Image and Vision Computing

157

View full text Add to dashboard Cite

show abstract

“…Pipeline hybridization means that algorithm “A” runs fully and its results are taken to algorithm B as inputs. This type of hybridization has been investigated in several papers concerning Kmeans and SA algorithms [ 18 , 44 , 45 ]. The clustering algorithm (Kmeans) will take all the points (messages) and cluster them based on their high similarities with the corresponding classes.…”

Section: Resultsmentioning

confidence: 99%

“…Kmeans can still get stuck into local optima. In the literature, several papers addressed how SA can be used for optimal selection of initial Kmeans points [ 37 , 38 ]. The output of these results is that metaheuristics can solve the initialization problem of Kmeans, but the problem of converging into local optima is still not solved.…”

Section: Methodsmentioning

confidence: 99%

Sequence diagram refactoring using single and hybridized algorithms

Baqais

Alshayeb

2018

PLoS ONE

View full text Add to dashboard Cite

Data mining and search-based algorithms have been applied to various problems due to their power and performance. There have been several studies on the use of these algorithms for refactoring. In this paper, we show how search based algorithms can be used for sequence diagram refactoring. We also show how a hybridized algorithm of Kmeans and Simulated Annealing (SA) algorithms can aid each other in solving sequence diagram refactoring. Results show that search based algorithms can be used successfully in refactoring sequence diagram on small and large case studies. In addition, the hybridized algorithm obtains good results using selected quality metrics. Detailed insights on the experiments on sequence diagram refactoring reveal that the limitations of SA can be addressed by hybridizing the Kmeans algorithm to the SA algorithm.

show abstract

“…In K-means clustering, the clusters are formed by minimizing the within cluster variance of the observations in each cluster [48]. Given a data set represented by [50]. If it is not chosen properly, then the algorithm may converge towards a local optimal solution for the objective function.…”

Section: A Formation Of Retail Zones Using K-means Clusteringmentioning

confidence: 99%

Facility Selection Model for BOPS Service for an Omnichannel Retail Chain

Jain

Darbari

Kaul

et al. 2022

IEEE Trans. Eng. Manage.

View full text Add to dashboard Cite

Retail sector around the world is going through a transition due to digitalization. Customers now demand convenience of online channel with instant fulfilment of offline channel. As a result, the concept of omni-channel retailing has come into existence. In omni-channel retailing, both the channels of a firm are fully or partially integrated. There are many strategies that may be developed by retailers for efficient functioning of the omni-channel retail chain. The choice of such a strategy depends upon the comparative benefits that can be derived from them. One such strategy gaining immense attention of retailers is the Buy Online Pickup in Store (BOPS) strategy. In order to understand this BOPS, we conducted a detail case study of an Indian multi-channel retail chain who is considering the option of launching BOPS option in few of its retail stores. The focus is to evaluate and select a fixed number of operational retail stores to also act as pickup points for online deliveries. K-means clustering is utilized for formation of retail zones as per the number of retail stores to be selected. The retail stores in each zone are evaluated on the basis of a number of criteria such as demand, inventory carrying capacity, cost, and population characteristics using Analytical Hierarchy Process (AHP) and Complex Proportional Assessment-Grey (COPRAS-G). Based on these evaluations the best suitable retail store is selected for expansion from each zone. The result implications drawn in the study can provide an understanding of the future strategies that can be developed by the decision makers of the firm for launching the BOPS option. The study can also be beneficial to other Indian retail firms who can derive meaningful insights from the findings.

show abstract

K-Means Initialization Methods for Improving Clustering by Simulated Annealing

Cited by 14 publications

References 11 publications

Improving the performance of k-means for color quantization

Improving the performance of k-means for color quantization

Sequence diagram refactoring using single and hybridized algorithms

Facility Selection Model for BOPS Service for an Omnichannel Retail Chain

Contact Info

Product

Resources

About