Filters








26,528 Hits in 10.5 sec

The K-Means Algorithm Evolution [chapter]

Joaquín Pérez-Ortega, Nelva Nely Almanza-Ortega, Andrea Vega-Villalobos, Rodolfo Pazos-Rangel, Crispín Zavala-Díaz, Alicia Martínez-Rebollar
2019 Clustering [Working Title]  
The solution to the K-means clustering problem is NP-hard, which justifies the use of heuristic methods for its solution.  ...  Finally, it is considered that the main improvements may inspire the development of new heuristics for K-means or other clustering algorithms.  ...  an algorithm for partitioning an instance into a set of clusters whose variance was small for each cluster.  ... 
doi:10.5772/intechopen.85447 fatcat:oyidqzjs4zdinopc3pvjl6rn6a

Partitioning Biological Networks into Highly Connected Clusters with Maximum Edge Coverage

Falk Huffner, Christian Komusiewicz, Adrian Liebtrau, Rolf Niedermeier
2014 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
The data reduction typically identifies 75 % of the edges that are deleted for an optimal solution; the column generation method can then optimally solve protein interaction networks with up to 6 000 vertices  ...  A popular clustering algorithm for biological networks which was proposed by Hartuv and Shamir [IPL 2000] identifies nonoverlapping highly connected components.  ...  We also thank Andrea Kappes (Karlsruhe Institute of Technology) for pointing out a flaw in a previous version of the column generation algorithm.  ... 
doi:10.1109/tcbb.2013.177 pmid:26356014 fatcat:aonwphzqcrhobnuwlrxaigf6my

Partitioning Biological Networks into Highly Connected Clusters with Maximum Edge Coverage [chapter]

Falk Hüffner, Christian Komusiewicz, Adrian Liebtrau, Rolf Niedermeier
2013 Lecture Notes in Computer Science  
The data reduction typically identifies 75 % of the edges that are deleted for an optimal solution; the column generation method can then optimally solve protein interaction networks with up to 6 000 vertices  ...  A popular clustering algorithm for biological networks which was proposed by Hartuv and Shamir [IPL 2000] identifies nonoverlapping highly connected components.  ...  We also thank Andrea Kappes (Karlsruhe Institute of Technology) for pointing out a flaw in a previous version of the column generation algorithm.  ... 
doi:10.1007/978-3-642-38036-5_13 fatcat:65xq7e7fazcovlayv4qnqusity

A novel clustering method for breaking down the symmetric multiple traveling salesman problem

Basma Hamdan, Hamdi Bashir, Ali Cheaitou
2021 Journal of Industrial Engineering and Management  
A comparison with the k-means++ clustering algorithm, one of the most popular clustering algorithms, was made to evaluate the performance of the proposed method in terms of four objective criteria.Findings  ...  : Computational results and comparison on 63 problems revealed that the proposed method is promising for producing quality clusters and thus for enhancing the performance of heuristic optimization algorithms  ...  The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.  ... 
doi:10.3926/jiem.3287 fatcat:r45z6thlpvgcbiigddg4kh6ngi

DASH: Dynamic Approach for Switching Heuristics [article]

Giovanni Di Liberto and Serdar Kadioglu and Kevin Leo and Yuri Malitsky
2013 arXiv   pre-print
Experiments on a highly heterogeneous collection of MIP instances show significant gains over the pure algorithm selection approach that for a given instance uses only a single heuristic throughout the  ...  Recently, portfolio algorithms have taken the process a step further, trying to predict the best heuristic for each instance at hand.  ...  Experiments on a highly heterogeneous collection of MIP instances show significant gains over the pure algorithm selection approach that for a given instance uses only a single heuristic throughout the  ... 
arXiv:1307.4689v1 fatcat:zrrbmbeewrhk7ph36jbntvx45y

Enhanced Evolutionary Computing Assisted K-Means Clustering Algorithm for BigData Analytics

Sarada B
2020 International Journal of Advanced Trends in Computer Science and Engineering  
In addition, the use of AGA assisted K-Means clustering algorithm has accomplished computationally efficient and reliable clustering for efficient Big Data analytics purposes.  ...  The computational efficacy of AGA-K-Means can strengthen MapReduce to be used for real-time Big Data analytics applications.  ...  Unlike classical K-Means clustering algorithm, we applied an enhanced EC concept named AGA for K-Means clustering centroid estimation, which is highly related to the classification accuracy and hence the  ... 
doi:10.30534/ijatcse/2020/268942020 fatcat:ua3hekruc5gkfk6iipilwrw2xq

Analysis and Algorithms for Stemming Inversion [chapter]

Ingo Feinerer
2010 Lecture Notes in Computer Science  
We present efficient heuristic algorithms for practical application in information retrieval and test our approach on real data.  ...  Stemming is a fundamental technique for processing large amounts of data in information retrieval and text mining.  ...  This work is supported by the Vienna Science and Technology Fund (WWTF), project ICT08-032.  ... 
doi:10.1007/978-3-642-17187-1_28 fatcat:q53zjgk2jngcfk4qkz4k5hx2wi

The Context of Knowledge and Data Discovery in Highly Dense Data Points Using Heuristic Approach

C. S. Sasireka, P. Raviraj
2013 Journal of Signal and Information Processing  
To overcome the above mentioned issues, we plan to present an Optimal Model-Selection Clustering for image data point analysis in the context of knowledge and data discovery in highly dense data points  ...  Considering image data, partitioning approaches seems to be computationally complex due to large data size, and uncertainty of number of clusters.  ...  The k-means process falls beneath the group of dividing methods for clustering. Hierarchical methods of clustering generate a hierarchy of clusters.  ... 
doi:10.4236/jsip.2013.41011 fatcat:suvof3d4qvgdxcnqadxubtluym

Heuristics for dynamically adapting propagation in constraint satisfaction problems

Kostas Stergiou
2009 AI Communications  
An important line of research towards this goal is concerned with ways to dynamically adapt the propagation method applied on the constraints of the problem during search.  ...  Then we present simple heuristics that exploit this clustering to efficiently switch between different local consistencies on individual constraints during search.  ...  We show that the most efficient heuristics can be up to an order of magnitude faster than MAC, i.e. the standard search algorithm for binary CSPs, on hard instances.  ... 
doi:10.3233/aic-2009-0450 fatcat:d4quqgs3qvdjzm5hftzgqgth5e

Solving the Clustered Traveling Salesman Problem via TSP methods [article]

Yongliang Lu, Jin-Kao Hao, Qinghua Wu
2020 arXiv   pre-print
For this purpose, we first investigate a technique to convert a CTSP instance to a TSP and then apply popular TSP solvers (including exact and heuristic solvers) to solve the resulting TSP instance.  ...  We want to answer the following questions: How do state-of-the-art TSP solvers perform on clustered instances converted from the CTSP?  ...  Sets 1 and 2 (35 instances): These instances belong to the following six types: (1) instances taken from the TSPLIB [32] where the clusters are generated by using a k-means clustering algorithm; (2)  ... 
arXiv:2007.05254v2 fatcat:ris6blbhpbcqbjs3poiehq5trq

Introducing Hybrid model for Data Clustering using K-Harmonic Means and Gravitational Search Algorithms

Anuradha D.Thakare, Rohini S Hanchate
2014 International Journal of Computer Applications  
To overcome this drawback, an improved algorithm called K-Harmonic Mean (KHM) was proposed, which is independent of cluster center initialization.  ...  K-Means is well known clustering algorithm but it easily converge to local optima.  ...  ACAKHM, PSOKHM method which performs clustering efficiently, used K-Harmonic Means as the objective function.  ... 
doi:10.5120/15445-4002 fatcat:uznkvxk2yfhfxb5pbcmw37qj4y

A Comprehensive Survey on Centroid Selection Strategies for Distributed K-means Clustering Algorithm

Poonam Ghuli, Maanas Prabhakar, Rajashree Shettar
2015 International Journal of Computer Applications  
K-means due to its gradient descent nature is highly sensitive to the initial placement of the cluster centers.  ...  In this paper, effort has been made to tweak in changes to the existing K-means algorithm so as to work in parallel using MapReduce paradigm.  ...  for K-Means clustering algorithm on Hadoop, an open source implementation of Mapreduce paradigm.  ... 
doi:10.5120/ijca2015905919 fatcat:oqz57aovlvcbxhyl4pzqifnmie

Characterization of neighborhood behaviours in a multi-neighborhood local search algorithm [article]

Nguyen Thi Thanh Dang, Patrick De Causmaecker
2016 arXiv   pre-print
In this work, we propose a systematic method to characterize each neighborhood's behaviours, representing them as a feature vector, and using cluster analysis to form similar groups of neighborhoods.  ...  Given a set of instances, off-line tuning of the algorithm's parameters can be done by automated algorithm configuration tools (e.g., SMAC).  ...  We would like to thank Túlio Toffolo for his great support during the course of this research, Thomas Stützle and Jan Verwaeren for their valuable remarks.  ... 
arXiv:1603.06459v1 fatcat:ojrotfpwdrf4hnbmn4gs645ct4

Scaling up data mining algorithms: review and taxonomy

Nicolás García-Pedrajas, Aida de Haro-García
2012 Progress in Artificial Intelligence  
In many cases, the demands of the algorithm in terms of the running time are very large, and mining methods cannot be applied when the problem grows.  ...  Thus, for many problems, especially when dealing with very large datasets, the only way to deal with the aforementioned problems is to scale up the data mining algorithm.  ...  Acknowledgments This work was supported in part by the Grant TIN2008-03151 of the Spanish "Comisión Interministerial de Ciencia y Tecnología" and the Grant P09-TIC-4623 of the Regional Government of Andalucía  ... 
doi:10.1007/s13748-011-0004-4 fatcat:o53sri33rbf5dmjazaexfwvxeq

Optimization of Multiple Vehicle Routing Problems using Approximation Algorithms [article]

R. Nallusamy, K. Duraiswamy, R. Dhanalaksmi, P. Parthiban
2010 arXiv   pre-print
We used a methodology of clustering the given cities depending upon the number of vehicles and each cluster is allotted to a vehicle. k- Means clustering algorithm has been used for easy clustering of  ...  applied to the cluster and iterated to obtain the most optimal value of the distance after convergence takes place.  ...  k-means clustering Simply speaking k-means clustering is an algorithm to classify or to group the objects based on attributes/features into k number of group. k is a positive integer number.  ... 
arXiv:1001.4197v1 fatcat:w75jtmrzy5eh3fkjvhk2m6xexa
« Previous Showing results 1 — 15 out of 26,528 results