Parallel framework based gene signature-hierarchical random forest cluster for predicting human diseases
Gene is not responsible for many Human Diseases and instead, diseases occur by different or group of genomes interacting together and cause diseases. Hence it is need to analyse and associate the complete genome sequences to understand or predict various possible human diseases. This research work focused i. Hierarchical-Random Forest based Clustering (HRF-Cluster), ii. Genetic Algorithm-Gene Associa-tion Classifier (GA-GA) and iii. Weighted Common Neighbor Classifier (wCN). These Classifiers were implemented and studied thor-oughly in terms of Prediction Accuracy, Memory Utilization, Memory Usage and Processing Time. To improve the performances of the Gene Classifiers / Predictors further, this research work was proposed and implemented Gene Signature based HRF Cluster, G-HR. Re-sults show that that the performances of the proposed Classifier G-HR is outperforming as compared with the identified three Classifiers in terms of Disease Pattern Prediction, Processing Time, Memory Usage and Classification Accuracy. To improve the performance of the system further in term of Processing Time, the proposed model G-HR 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 de-creases considerably which will improve the performance of the Proposed Model.