Please use this identifier to cite or link to this item: http://dspace.dtu.ac.in:8080/jspui/handle/repository/19884
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMANGLA, MAYANK-
dc.date.accessioned2023-06-14T05:41:01Z-
dc.date.available2023-06-14T05:41:01Z-
dc.date.issued2023-05-
dc.identifier.urihttp://dspace.dtu.ac.in:8080/jspui/handle/repository/19884-
dc.description.abstractBioinformatics data is treated as high-dimensional data by nature, which requires great computational demands. Scientists around the world have proposed many computing solutions such as Field-Programmable Gate Arrays (FPGAs) and Graphics Processing Units (GPUs). In order to meet these high computational demands, a feature wherein we can alter some specific areas in the chip proves to be very helpful and resourceful, from which FPGAs are benefiting. FPGAs enable flexible, reconfigurable computing, as most enable the user to reprogram the hardware circuit with different logic functions. Applying classification machine learning algorithms to the bioinformatics data set on a conventional PC to get the desired result proves to be a very time-consuming task. This is where the FPGAs come into the picture and help in drastically reducing this computational time. In this project, we have implemented the above approach using an FPGA board and executed its software-based implementation on a CPU to compare them on the grounds of timing. The hardware implementation of the algorithm is done using Verilog and for the software-based implementation we have used Python. Furthermore, in this project we have done a comparative analysis by adopting different sorting technique which plays a vital role in the KNN classification algorithm implemented. These algorithms also are one of the pivotal factors for the speed and hardware utilization requirement for implementing the algorithm on the FPGA board.en_US
dc.language.isoenen_US
dc.relation.ispartofseriesTD-6446;-
dc.subjectBIOINFORMATICSen_US
dc.subjectDATA CLASSIFICATIONen_US
dc.subjectFIELD-PROGRAMMABLE GATE ARRAYSen_US
dc.titleBIO-INFORMATICS DATA CLASSIFICATION USING KNN ON FPGA BOARDen_US
dc.typeThesisen_US
Appears in Collections:M.E./M.Tech. Electronics & Communication Engineering

Files in This Item:
File Description SizeFormat 
MAYANK MANGLA-mtech-thesis.pdf1.22 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.