Predviđanje vremenskih profila relativne vlažnosti i svježine zraka u prostoriji korištenjem strojnog učenja

undergraduate thesis

• Title (english): Prediction of relative humidity and air freshness in a room by using machine learning
• Author: Danijel Bošnjak
• Mentor: Mario Vašak (mentor)
• Committee member: Mario Vašak (predsjednik povjerenstva)
• Committee member: Vinko Lešić (član povjerenstva)
• Committee member: Anita Banjac (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-02-23, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Strojno učenje je učenje računala prepoznavanju uzoraka koji se ponavljaju u setu za treniranje kojeg smo mu poslali, da bi prema njima mogao predvidjeti izlazne rezultate, tj. neko buduće ponašanje.. Model se uči na danom setu za treniranje, nakon kojih može uspješno procesuirati i nove, nepoznate podatke te predvidjeti stanja. U strojnom učenju postoji velik broj tipova modela, od kojih smo odabrali linearnu regresiju. Najprije podatke razvrstavamo na set za treniranje i testiranje, zatim popunjavamo praznine u podatcima interpolacijom, skaliramo varijable, obavljamo linearnu regresiju, inverzno skaliramo te na kraju računamo srednju kvadratnu grešku i grafički prikazujemo izlaznu varijablu.

Abstract (english)

Machine learning is defined as learning a computer to recognize repetitive patterns in a training set that we send it, so that it can predict the output, ie some future behavior. The model is trained on a given training set, after which it can successfully process new, unknown data and predict conditions. In machine learning, there is a large number of types of models, from which we have chosen linear regression. We first sort the data into a training and testing set, then fill in the gaps in the data by interpolation, scale the variables, perform linear regression, inversely scale, and finally calculate the mean square error and graphically display the output variable.

• Keywords: strojno učenje; model; linearna regresija; set za treniranje i testiranje; srednja kvadratna greška; skaliranje
• Keywords (english): machine learning; model; linear regression; training and test set; mean square error; scaling
• Language: croatian
• URN:NBN: urn:nbn:hr:168:546822
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 14:36:08