Classification of Diabetes Mellitus using Modified Particle Swarm Optimization and Least Squares Support Vector Machine
Journal Title: INTERNATIONAL JOURNAL OF COMPUTER TRENDS & TECHNOLOGY - Year 2014, Vol 8, Issue 1
Abstract
Diabetes Mellitus is a major health problem all over the world. Many classification algorithms have been applied for its diagnoses and treatment. In this paper, a hybrid algorithm of Modified-Particle Swarm Optimization and Least Squares-Support Vector Machine is proposed for the classification of type II DM patients. LS-SVM algorithm is used for classification by finding optimal hyper-plane which separates various classes. Since LS-SVM is so sensitive to the changes of its parameter values, Modified-PSO algorithm is used as an optimization technique for LS-SVM parameters. This will Guarantee the robustness of the hybrid algorithm by searching for the optimal values for LS-SVM parameters. The pro-posed Algorithm is implemented and evaluated using Pima Indians Diabetes Data set from UCI repository of machine learning databases. It is also compared with different classifier algorithms which were applied on the same database. The experimental results showed the superiority of the proposed algorithm which could achieve an average classification accuracy of 97.833%.
Authors and Affiliations
Omar S. Soliman , Eman AboElhamed
Keywords
Related Articles
- EP ID EP147256
- DOI -
- Views 138
- Downloads 0
Implementation of E-mail Access for Vision Impaired Person Using Speech Synthesizer
Developments in technology over the last twenty years have enhanced the possibilities for learning and working for people with vision impairments. Computers with speech or Braille output peripherals, or portable speech-o...
WiFiPos: An In/Out-Door Positioning Tool
Geographical location solutions have a wide diversity of applications, ranging from emergency services to access to tourist and entertainment services. GPS (Global Positioning System) is the most widely used system for o...
Database Based Validation of Union of Two Multigranular Rough Sets
Most of the traditional tools for undertaking modeling, reasoning and other computing are found not only crisp but also highly deterministic and more precise in character which usually limits their applicability in real...
Novel Sensing Approach for Predicting SLA Violations
Customer contentment plays a vital role in business environment. Service level agreements (SLA’s) are signed between the service provider and the customer where SLA violation acts as a major constraint. SLA Violation is...
Design an Algorithm for Data Encryption and Decryption Using Pentaoctagesimal SNS
Encryption is the most effective way of computer science concerned with developing schemes and formula to achieve data and information security through the use of codes. Today the privacy is the main issue to sending inf...