izpis_h1_title_alt

Prototip sistema za zajem in klasifikacijo dojenčkovega joka
ID Saftić, Saša (Author), ID Ciglarič, Mojca (Mentor) More about this mentor... This link opens in a new window, ID Zupan, Blaž (Comentor)

.pdfPDF - Presentation file, Download (2,84 MB)
MD5: 0F2E8E447A188C5F17D4F9A36B7C8FFB
PID: 20.500.12556/rul/d5cadfb0-4b50-45ac-b7db-70ebbac02d93

Abstract
V tem delu se ukvarjamo z večrazredno klasifikacijo dojenčkovega joka in raziskovanjem povezave med starostjo dojenčka in natančnostjo klasifikacije. Prav tako se ukvarjamo z varnim shranjevanjem in obdelavo podatkov v oblaku. Primerjali smo več standarnih modelov za večrazredno klasifikacijo in klasifikacijo z rekurenčnimi nevronskimi mrežami. Natančnost klasifikacije smo preverili na podatkih različno starih otrok. Za shranjevanje in obdelavo podatkov smo uporabili Rest Django API in odptokodno oblačno platformo OpenStack. Rezultati dela kažejo, da lahko s pomočjo večrazredne klasifikacije razlikujemo med razredi joka. Povezave med starostjo otroka in natančnostjo klasifikacije nismo opazili. Django Rest API in OpenStack platformi sta se izkazali za dobro orodje za shranjevanje in obdelavo podatkov v oblaku.

Language:Slovenian
Keywords:dojenčkov jok, zajem podatkov, analiza zvoka, odkrivanje značilk, klasifikacija, obdelava podatkov v oblaku, oblačna varnost
Work type:Master's thesis/paper
Organization:FRI - Faculty of Computer and Information Science
Year:2017
PID:20.500.12556/RUL-91508 This link opens in a new window
Publication date in RUL:12.04.2017
Views:2021
Downloads:542
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:System for audio capture and classification of baby cry samples
Abstract:
We explore multiclass classification of infants' cries and the relation between the age of the infant and the accuracy of classification. Additionally we explore secure cloud storage and cloud data processing. We compare several state-of-the-art multiclass classification models with recurrent neural networks. Classification accuracy was obtained on data from infants of various ages. For data storage and processing we used the Django Rest API and the opensource cloud platform OpenStack. Multiclass classification models successfully differentiated between different classes of crying, but no age effect has been found. We have demonstrated the aptness of the Django Rest API and OpenStack platform for data storing and processing in the cloud.

Keywords:infant cry, data acquisition, audio analysis, feature extraction, classification, cloud processing, cloud security

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back