IITI Computer Science & Engineering, Big Data Lab is equipped with a small Apache Spark cluster setup version 2.4.0 with Hadoop version 2.7.3.
The Spark cluster consists of six nodes (clusters); Master Node configuration: Dell precision Tower 5810, RAM: 32 GB, 4 cores, Slave Nodes configuration: Intel(R) Core(TM) i7-77000 CPU @ 3.60 GHZ, 1TB storage (each node).
HDFS is used for storing data across the cluster and Spark standalone for resource management.
HPC System Specification: Total number of cores: 32, Total memory: 187 GB. Total disk: 12 TB.
HPC server machine is used for preprocessing of raw genome data. HPC system is added into cluster for feature extraction of huge genome data.
Outcomes: The setup is established to check the performance of developed scalable fuzzy clustering algorithms for handling big data in various domains of pattern recognition like genomics ( to increase the productivity of next generation plants based on the conserved region of plants), Stock exchange, disease diagnosis etc.
HPC server machines is established to check the performance of develop machine learning/artificial intelligence algorithms, like softcomputing/datamining, clustering, hybrid quantum fuzzy neural network, evolutionary optimization techniques, One-class Classification, Kernel Learning, Online Learning, Non-iterative Approaches in Learning, Multi-label Classification etc.