diplomsko delo
Florjan Bartol (Author), Matjaž Kukar (Mentor)

Abstract

Preverite hipotezo, da je mogoče z metodami strojnega učenja na podlagi strukturnih značilnosti spletnih strani oceniti njihovo energijsko zahtevnost med nalaganjem na mobilnem telefonu. Razvijte avtomatski merilni sistem, s katerim boste merili električni tok in napetost na telefonu med nalaganjem spletnih strani. Sistem uporabite za zbiranje podatkov o porabi množice popularnih spletnih strani in jih sestavite v učni problem združen s strukturnimi podatki o straneh. Na dobljeni množici podatkov preizkusite različne metode strojnega učenja in ovrednotite dobljene rezultate.

Keywords

merjenje porabe;avtomatsko zbiranje podatkov;mobilne spletne strani;metode strojnega učenja;računalništvo;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [F. Bartol]
UDC: 004.738.12:004.85(043.2)
COBISS: 10716244 Link will open in a new window
Views: 46
Downloads: 19
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Estimating energy consumption of web pages mith machine learning
Secondary abstract: Verify the hypothesis that it is feasible to predict web page's energy consumption based on their structural properties by utilizing machine learning methods. For this purpose develop an automated measuring system for measuring electric current and voltage on the mobile phone while web pages are loading. Use the system for collecting data on energy consumption for a set of popular web pages and combine the measurements with pages' structural properties into a learning set. On the acquired dataset experiment with various machine learning methods and qualitatively and quantitatively asses the results.
Secondary keywords: consumption measurement;automatic data collection;mobile web pages;machine learning methods;computer science;diploma;
File type: application/pdf
Type (COBISS): Undergraduate thesis
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 64 str.
ID: 24215000