Name
Abstract | ||
|---|---|---|
Recently, data mining has become more attractive for researchers as a technique to analyze and transform raw data into useful information that would help with decision support. Over the last decade, many data mining applications have been proposed in various research areas such as medicine, agriculture, and finance. Data classification is one of the data mining processes, which is a supervised learning task that analyzes the past data to predict future data. Particle swarm optimization (PSO) is one of the most popular swarm intelligence methods that simulates the behavior of bird flocking whereby the best source of food in a certain area is sought. In this paper, a new approach for data classification based on PSO abbreviated as CPSO is proposed. The main idea of CPSO is to find the optimal centroid and the standard deviation for each target label and then use the normal distribution probability density function and the probability of each target label to classify unseen data. The performance of CPSO was tested using ten data sets and was compared to twelve classification algorithms. The experimental results show that the CPSO algorithm is competitive compared to other classification algorithms. In addition, the algorithm can be efficiently used for data classification. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/SSCI.2018.8628926 | 2018 IEEE Symposium Series on Computational Intelligence (SSCI) |
Keywords | Field | DocType |
Classification,Particle Swarm Optimization | Particle swarm optimization,Data mining,Data set,Computer science,Swarm intelligence,Raw data,Supervised learning,Data classification,Cluster analysis,Statistical classification | Conference |
ISBN | Citations | PageRank |
978-1-5386-9277-6 | 0 | 0.34 |
References | Authors | |
12 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jamil Al-Sawwa | 1 | 0 | 0.34 |
| Simone A Ludwig | 2 | 1309 | 179.41 |