Zasnova in razvoj aplikacije za napovedovanje vremena z uporabo strojnega učenja

Bec, Klemen

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Zasnova in razvoj aplikacije za napovedovanje vremena z uporabo strojnega učenja
Authors:	ID Bec, Klemen (Author) ID Podgorelec, Vili (Mentor) More about this mentor... ID Karakatič, Sašo (Comentor)
Files:	VS_Bec_Klemen_2018.pdf (1,90 MB) MD5: DACC61B48860D89830929B0589A9EB24 PID: 20.500.12556/dkum/c0e12251-6431-4ded-aa51-6a4e00f4e55b
Language:	Slovenian
Work type:	Bachelor thesis/paper
Typology:	2.11 - Undergraduate Thesis
Organization:	FERI - Faculty of Electrical Engineering and Computer Science
Abstract:	Zaradi sodobne tehnologije, kot so npr. računalniki in internet imamo, v današnjem času, na voljo zelo veliko podatkov. To je tudi eden izmed glavnih razlogov, zakaj je postalo strojno učenje tako popularno. Med podatki so tudi podatki o vremenu, ki jih pridobivamo s satelitov, zračnih balonov in vremenskih postaj na Zemlji. Zato sem se odločil, da bom izdelal aplikacijo, ki bo s pomočjo teh podatkov in strojnega učenja napovedala vreme. V diplomskem delu je približno četrtina vsebine namenjena teoriji. Na kratko je predstavljeno napovedovanje vremena in strojno učenje. Opisano je, kako sta ta dva področja med sabo povezana v praksi. V zadnjem delu teorije so opisane uporabljene metode strojnega učenja in merila kakovosti. Predstavljeni so tudi uporabljeni programi in tehnologije. Predvsem pa je diplomsko delo osredotočeno na izdelavo aplikacije za napovedovanje vremena. Na koncu je predstavljena uporaba aplikacije. Podani so končni rezultati in zapisane so ugotovitve.
Keywords:	strojno učenje, nevronske mreže, priprava podatkov, vremenska napoved, linearna regresija, LSTM, scikit-learn, keras
Place of publishing:	[Maribor
Publisher:	K. Bec
Year of publishing:	2018
PID:	20.500.12556/DKUM-72150
UDC:	004.777:004.8(043.2)
COBISS.SI-ID:	21788950
NUK URN:	URN:SI:UM:DK:FOFQCRVW
Publication date in DKUM:	08.10.2018
Views:	2252
Downloads:	211
Metadata:
Categories:	KTFMB - FERI
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	12.09.2018

Secondary language

Language:	English
Title:	Design and development of an application for weather prediction using machine learning
Abstract:	Because of modern technology, such as computers and the Internet we have a lot of data available today. This is also one of the main reasons why machine learning has become so popular. There is also a lot of weather data obtained from satellites, airborne balloons and weather stations on the ground. That's why I decided to create an application that will predict weather using this data and machine learning. In the diploma thesis, approximately a quarter of the content is devoted to theory. In brief, weather forecasting and machine learning are presented. It is described how these two areas are interconnected in practice. The last part of the theory describes used machine learning methods and quality metrics. There is also presentation of used programs and technologies. Above all, the thesis focuses on creating an application for weather forecasting. Finally, the use of the application is presented. The final results are given and the findings are recorded.
Keywords:	machine learning, neural network, data preparation, weather report, linear regression, LSTM, scikit-learn, keras

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back