International Journal of Data Mining and Emerging Technologies

  • Year: 2017
  • Volume: 7
  • Issue: 2

Optimized Rule Generation for Preterm Birth Prediction Using Soft Computing

1Research Scholar, Department of Computer Science & Engineering, Sathyabama University, Chennai, India

2Professor, National Institute of Technical Teachers Training & Research, Chennai, India

*(Corresponding author) email id: phd.jthomas@gmail.com,

**gkvel@gmail.com

null

Abstract

Decision-making and prediction systems have been researched actively for many decades and have got a heave in the recent past. The decision-support system has been investigated in various areas including preterm birth (PTB) analysis. In this paper, the medical decision-support system is designed for the prediction of PTB using hybrid particle swarm optimisation (PSO) and cuckoo search (CS) with Fuzzy Min–Max Neural Network (FMMNN) Here, our proposed work mainly contains two modules such as pattern classification and optimal rule extraction. In classification, we use FMMNN, and in optimal rule generation, we using Particle swarm Cuckoo Search (PCS) algorithm which is hybridisation of PSO and CS algorithm. The experimentation is carried out using the PTB dataset and implemented using MATLAB. The evaluation metric used is the accuracy, and we have also compared with existing methods. From the results, it can be seen that our proposed technique has achieved better accuracy value (90%) which shows the effectiveness of the proposed technique.

Keywords

Preterm birth prediction, PCS, Cuckoo search, PSO, Fuzzy Min–Max Neural Network, Rule optimization, Soft computing