Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published September 1, 2017 | Version v1
Journal article Open

A MEMORY EFFICIENT HARDWARE BASED PATTERN MATCHING AND PROTEIN ALIGNMENT SCHEMES FOR HIGHLY COMPLEX DATABASES

  • 1. Faculty of Electronics and Communication Department, vel tech, Chennai, India.
  • 2. UG Students of Electronics and Communication Department, vel tech , Chennai, India.

Description

Protein sequence alignment to find correlation between different species, or genetic mutations etc. is the most computational intensive task when performing protein comparison. To speed-up the alignment, Systolic Arrays (SAs) have been used. In order to avoid the internal-loop problem which reduces the performance, pipeline interleaving strategy has been presented. This strategy is applied to an SA for Smith Waterman (SW) algorithm which is an alignment algorithm to locally align two proteins. In the proposed system, the above methodology has been extended to implement a memory efficient FPGA-hardware based Network Intrusion Detection System (NIDS) to speed up network processing. The pattern matching in Intrusion Detection Systems (IDS) is done using SNORT to find the pattern of intrusions. A Finite State Machine (FSM) based Processing Elements (PE) unit to achieve minimum number of states for pattern matching and bit wise early intrusion detection to increase the throughput by pipelining is presented.

Files

10.21307_ijssis-2017-239.pdf

Files (727.4 kB)

Name Size Download all
md5:28308ab0f344361a0e99aa2889886f64
727.4 kB Preview Download