Naslov
Microbe Detection Using Signal Processing and Locality Sensitive Hashing

Autori
Paulinović, Mate

Vrsta, podvrsta i kategorija rada
Ocjenski radovi, diplomski rad, diplomski

Fakultet
Fakultet elektrotehnike i računarstva

Mjesto
Zagreb

Datum
13.07

Godina
2020

Stranica
53

Mentor
Šikić, Mile

Ključne riječi
bioinformatics ; metagenomics ; wavelet transform ; locality sensitive hashing ; minhash ; signal processing

Sažetak
Our knowledge of the interaction between humans and the microscopic lifeforms is constantly evolving. For this reason, our ability to detect and identify them is of paramount importance. The goal of this thesis was to develop a microbe detection solution using signal processing and locality sensitive hashing. We present a solution consisting of event detection, the continuous wavelet transform, combinatorial hashing and MinHash locality sensitive hashing. This solution was tested on a generated dataset to determine how signal types and signal lengths impact its performance as well as a subset of the publicly available Zymo mock community standard dataset.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA