FPGA-based urinalysis for urinary tract infection detection using principal component analysis

Date of Publication

2016

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Electronics and Communications Engineering

College

Gokongwei College of Engineering

Department/Unit

Electronics and Communications Engineering

Thesis Adviser

Cesar A. Llorente

Defense Panel Chair

Maria Antonette C. Roque

Defense Panel Member

Roderick Yao Yap

Argel A. Bandala

Abstract/Summary

Urinalysis is considered to be a common test performed in laboratory in order to diagnose Urinary Tract Infection (UTI). It undergoes three stages, which include macroscopic, dipstick, and microscopic analysis. This paper discusses about a new way of performing urinalysis for UTI detection through a Field Programmable Gate Array (FPGA) and with the use of five different sensors that measure five different components specifically sodium, nitrate, potassium, and pH level of a urine sample. The designed system has an accuracy of 94.13% for the urinalysis. To be able to detect the presence of UTI in urines, an outlier detection method, Principal Component Analysis (PCA), was used. PCA is a tool used in reducing multidimensional data to lesser dimensions while keeping all the information. The selection of the parameters to be measured is important in order to increase the accuracy of detection. Because of this, the group compared the accuracy of UTI detection when the pH sensor was used and if it was removed. The accuracy of the designed system for UTI detection increased to 83.33% when pH sensor is removed. This paper also discusses about the implementation of PCA on an FPGA. The computed principal component by the FPGA was compared to be computed principal components by MATLAB and has an accuracy of 99.917%.

Abstract Format

html

Language

English

Format

Print

Accession Number

TU21504

Shelf Location

Archives, The Learning Commons, 12F, Henry Sy Sr. Hall

Physical Description

366 leaves : colored illustrations ; 28 cm.

Keywords

Urine--Analysis; Urinary tract infections; Field programmable gate arrays; Principal components analysis

This document is currently not available here.

Share

COinS