Copyright © 2018 S. Subasree et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. International Journal of Engineering & Technology, 7 (2.27) (2018) 7-11 International Journal of Engineering & Technology Website: www.sciencepubco.com/index.php/IJET Research paper EMOPS: an enhanced multi-objective pswarm based classifier for poorly understood cancer patterns S. Subasree 1 *, N. P. Gopalan 2 , N .K. Sakthivel 3 1 Research Scholar, Department of Computer Science and Engineering Bharath University, Chennai – 600 073, Tamil Nadu, India 2 Department of Computer ApplicationsNational Institute of Technology, Thiruchirappalli, Tamil Nadu, India 3 Department of Computer Science and EngineeringNehru College of Engineering and Research Centre, Thrissur, Tamil Nadu, India *Corresponding author E-mail: drssubasree@gmail.com Abstract Microarray based Cancer Pattern Classification is one of the popular techniques in Bioinformatics Research. This Research Work is noticed that for studying the expression levels through the Gene Expression profiling experiments, thousands of Genes have to be simultaneously studied to understand the patterns of the Gene Expression or Cancer Pattern. This research work proposed an efficient Cancer Pattern Clas- sifier called An Enhanced Multi-Objective Pswarm (EMOPS) and it is studied thoroughly in terms of Memory Utilization, Execution Time (Processing Time), Sensitivity, Specificity, Classification Accuracy and FScore. The results were compared with the recently proposed classifiers namely Hybrid Ant Bee Algorithm (HABA), Kernelized Fuzzy Rough Set Based Semi Supervised Support Vector Machine (KFRS-S3VM) and Multi-objective Particle Swarm Optimization (MPSO). For analyzing the performances of the proposed model, this work considered a few cancer patterns namely Bladder, Breast, Colon, Endometrial, Kidney, Leukemia, Lung, Melanoma, Mom-Hodgkin, Pancreatic, Prostate and Thyroid. From our experimental results, it was noticed that the proposed model outperforms the identified three classifiers in terms of Memory Utilization, Execution Time (Processing Time), Sensitivity, Specificity, Classification Accuracy and FScore. To improve the performance of the system further in term of Processing Time, the proposed model Enhanced Multi-Objective Pswarm (EMOPS) is implemented under Parallel Framework and evaluated. That is the model is tested with Two, Four, Eight and Sixteen Parallel Processors and from the results, it is established that the Processing Time decreases considerably which will improve the performance of the Proposed Model. Keywords: Cancer Pattern Classifications; Gene Expression; Microarray, Multi-Objective Pswarm; Parallel Framework; Support Vector Machine. 1. Introduction This Microarray is a significant technology which facilitating to study various gene expressions. The microarray data, in general, are images and these microarray images could be converted into vari- ous gene expression. These Gene Expressions have been usually used for Gene Pattern Classifications. From the available literature survey [1-6], it was noticed that the Data Mining Techniques are facilitating to classify and predict various Cancer Gene Patterns. The Classifiers are used to classify microarray samples for pattern classification. ie the normal microarray sample data set and cancer pattern samples can be classified with the help of Classifiers [12- 16]. If the samples had a few subtypes of cancer pattern, then we needed multiclass cancer pattern classifiers [1-4]. From the litera- ture survey, it was noticed that the Multi-Class Cancer Pattern Clas- sifier can be employed to improve the classification accuracy [17]. This research work identified a few popular Multi-Class Classifiers which are recently proposed for Cancer Patter Prediction/Classifi- cation and all those Classifiers were discussed below. The proposed model Enhanced Multi-Objective Pswarm (EMOPS) was implemented with Uni-Processor [1] and Parallel Processors as well. The detailed procedure of the Parallel Framework was dis- cussed in the following section. This Research paper is arranged and written as follows. The Section 2 briefly described the recently proposed Data Mining Classifiers. The proposed model, Enhanced Multi-Objective Pswarm Based Classifier (EMOPS) is implemented in Uni-Processing and Parallel Framework as well is described in Section 3. The results and strengths of the proposed model in Uni-Processing as well as Par- allel Processing is discussed at Section 4 and Conclusion was given in Section 5 2. Recently proposed data mining classifiers The characteristics and procedures of the three identified Classifiers namely i. Hybrid Ant Bee Algorithm (HABA) [4], ii. Kernelized Fuzzy Rough Set Based Semi Supervised Support Vector Machine (KFRS-S3VM) [1] and iii. Multi-objective Particle Swarm Optimi- zation (MPSO) [6], [21-24] have been discussed in the following subsections. 2.1. Hybrid ant bee algorithm (HABA) Ant Colony Optimization [1], [4], [10], [26] does maintain a colony of ants and make possible Permissible Ranges (PRs) in association with values proposed for a design model. Here, each and every ant is permitted to select a Permissible Range which will represent the path. When all ants have chosen their paths, then the discrete value asso- ciated with the selected path is taken and for all ants, this is consid- ered as candidate value. Then, the system evaluates the Artificial Bee Colony Approach by combining the candidate values of all the