Prepoznavanje mikroba uporabom obrade signala i lokalno osjetljivog raspršenog adresiranja

master's thesis

• Title (english): Microbe Detection Using Signal Processing and Locality Sensitive Hashing
• Author: Mate Paulinović
• Mentor: Mile Šikić (mentor)
• Committee member: Mile Šikić (predsjednik povjerenstva)
• Committee member: Damir Seršić (član povjerenstva)
• Committee member: Krešimir Križanović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Naše spoznaje o interakcijama ljudi i mikroskopskih organizama se nepresetano razvijaju.
Iz tog razloga izrazito je važno moći ih prepoznati i identificirati.
Cilj ovog rada bio je razviti rješenje za detekciju mikroba koristeći obradu signala i lokalno osjetljivo raspršeno adresiranje.
Predstavljamo rješenje koje se sastoji od detekcije događaja, kontinuirane valićne transformacije, kombinatornog raspršenog adresiranja i MinHash lokalno osjetljivog raspršenog adresiranja.
Rješenje je testirano na generiranom skupu podataka sa svrhom utvrđivanja kako tip i dužina signala utječu na izvođenje te na podskupu javno dostupnog Zymo mock community standard skupa podataka.

Abstract (english)

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.

• Keywords: bioinformatika; metagenomika; valićna transformacija; lokalno osjetljivo raspršeno adresiranje; minhash; obrada signala
• Keywords (english): bioinformatics; metagenomics; wavelet transform; locality sensitive hashing; minhash; signal processing
• Language: english
• URN:NBN: urn:nbn:hr:168:163546
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 13:24:26