A novel ICA-based clustering algorithm for heart arrhythmia diagnosis
| Autor: | Emad Naseri, Ali Ghaffari, Majid Abdollahzade |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Optimization problem
Computer science Correlation clustering Imperialist competitive algorithm 020207 software engineering 02 engineering and technology computer.software_genre ComputingMethodologies_PATTERNRECOGNITION Artificial Intelligence CURE data clustering algorithm Genetic algorithm Simulated annealing 0202 electrical engineering electronic engineering information engineering Canopy clustering algorithm 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Data mining Cluster analysis computer |
| Zdroj: | Pattern Analysis and Applications. 22:285-297 |
| ISSN: | 1433-755X 1433-7541 |
| DOI: | 10.1007/s10044-017-0628-5 |
| Popis: | Thousands of people around the world are suffered from heart diseases; however, a considerable amount of them can have a chance of survival if there is an accurate and accessible diagnosis method. This paper introduces a new method for clustering of Holter electrocardiogram QRS complexes based on imperialist competitive optimization algorithm (ICA) which is the main contribution of this paper to raise the accuracy of diagnosis and find the methods for heart disease accessible machine diagnosis. The procedure of clustering is carried out using a mathematical modeling based on defining a cost function which is the ratio between the distance of each pattern’s features within each cluster (DWC) and the distance between the clusters. Hence, the clustering problem is reduced to an optimization process. The recently introduced optimization algorithm of ICA, inspired by imperialistic competition, is applied to solve the resulting optimization problem and to find the appropriate weighting factors. To demonstrate the effectiveness of the proposed clustering method, it was implemented on 5 set of MIT records obtained from MIT-BIH Arrhythmia Database records and also on hand-designed datasets (HDD). HDDs developed by selecting and combining some sets of computer-based simulated QRS complexes developed by CVRG group. To compare the effectiveness of the proposed approach, simulated annealing and genetic algorithm were also employed as other optimization algorithms. The results were promising and showed the ability of the proposed method for the clustering applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink