1. IoT and satellite sensor data integration for assessment of environmental variables: a case study on NO2Jernej Cukjati, Domen Mongus, Krista Rizman Žalik, Borut Žalik, 2022, original scientific article Abstract: This paper introduces a novel approach to increase the spatiotemporal resolution of an arbitrary environmental variable. This is achieved by utilizing machine learning algorithms to construct a satellite-like image at any given time moment, based on the measurements from IoT sensors. The target variables are calculated by an ensemble of regression models. The observed area is gridded, and partitioned into Voronoi cells based on the IoT sensors, whose measurements are available at the considered time. The pixels in each cell have a separate regression model, and take into account the measurements of the central and neighboring IoT sensors. The proposed approach was used to assess NO2 data, which were obtained from the Sentinel-5 Precursor satellite and IoT ground sensors. The approach was tested with three different machine learning algorithms: 1-nearest neighbor, linear regression and a feed-forward neural network. The highest accuracy yield was from the prediction models built with the feed-forward neural network, with an RMSE of 15.49 ×10−6 mol/m2.
Keywords: Internet of Things, IoT, remote sensing, sensor integration, machine learning, ensemble method
Published in DKUM: 22.09.2023; Views: 5; Downloads: 0
 Full text (3,72 MB)
This document has many files! More... |
2. A framework for multi-objective optimization of virtual tree pruning based on growth simulationDamjan Strnad, Štefan Kohek, Bedrich Benes, Simon Kolmanič, Borut Žalik, 2020, original scientific article Abstract: We present a framework for multi-objective optimization of fruit tree pruning within a simulated environment, where pruning is performed on a virtual tree model, and its effects on tree growth are observed. The proposed framework uses quantitative measures to express the short-term and long-term effects of pruning, for which potentially conflicting optimization objectives can be defined. The short-term objectives are evaluated on the pruned tree model directly, while the values of long-term objectives are estimated by executing a tree growth simulation. We demonstrate the concept by using a bi-objective case, where the estimated light interceptions of the pruned tree in the current and the next season are used to define separate optimization objectives. We compare the performance of the multi-objective simulated annealing and the NSGA-II method in building the sets of non-dominated pruning solutions. The obtained Pareto front approximations correspond to diverse pruning solutions that balance between optimizing either objective to different extents, which indicates a potential for new applications of the multi-objective pruning optimization concept.
Keywords: virtual tree pruning, multi-objective oiptimization, growth simulation, simulated annealing, NSGA-II
Published in DKUM: 10.07.2023; Views: 98; Downloads: 16
Full text (1,60 MB)
This document has many files! More... |
3. Aplikacije računalniških algoritmovBorut Žalik, 2023 Abstract: Učbenik Aplikacije računalniški algoritmov je namenjen študentom prve stopnje študijskega programa računalništvo in informacijske tehnologije s ciljem, spoznati algoritme, ki jih uporabniki pri svojem delu pogosto uporabljajo. Z implementacijo teh algoritmov bodo študentje pri prepotrebno rutino za za vstop v umetnost programiranja univerzalnega stroja, to je računalnika. Učbenik prinaša naslednje vsebine: urejanje podatkov v linearnem času, iskanje vzorcev v nizih, iskanje minimalne razdalje urejanja, preproste šifrirnike, metode brezizgubnega stiskanja podatkov, metode transformacije nizov, priponska polja in priponska drevesa ter algoritme v rastrskem prostoru (verižne kode in krivulje polnjenja prostora).
Keywords: urejanje podatkov v linearnem času, iskanje vzorcev v nizih, iskanje minimalne razdalje urejanja, brezizgubno stiskanje podatkov, transformacije nizov, priponska polja in priponska drevesa, verižne kode, krivulje polnjenja prostora
Published in DKUM: 21.06.2023; Views: 188; Downloads: 48
Full text (3,01 MB)
This document has many files! More... |
4. Lossless Compression of High-frequency Intervals in Digital Audio : bachelor's thesisIvan Benc, 2022, undergraduate thesis Abstract: In this Thesis, an algorithm for lossless audio compression in a time domain is developed and implemented. The algorithm is designed to estimate the signal frequency based on the number of local extremes, and adapts the encoding to the estimated high or low- frequency intervals. As possible adaptations, fitting line segments, quadratic Bézier curves to the signal, and dictionary compression are examined. Residuals are encoded with delta encoding and compressed with binary adaptive sequential coding. The difference in the proportions of line segments and curves used in the high and low-frequency intervals have been detected, but this is not significant enough for this kind of interval discrimination to be meaningful in the current design of the algorithm.
Keywords: lossless audio compression, delta encoding, binary adaptive sequential coding, greedy method
Published in DKUM: 07.11.2022; Views: 359; Downloads: 32
Full text (1,90 MB) |
5. |
6. Primerjava dinamičnega programiranja in požrešne metode pri optimizaciji brezizgubnega stiskanja avdia s prileganjem krivulj : diplomsko deloLuka Železnik, 2022, undergraduate thesis Abstract: V diplomski nalogi je najprej opravljen pregled brezizgubnih algoritmov za stiskanje avdia, nato pa sledi prestavitev nove lastne metode, ki temelji na prileganju daljic in Bézierovih krivulj 2. reda avdiosignalu. Opisani sta dve inačici algoritma, zasnovani s strategijama požrešne metode in dinamičnega programiranja. Sledi še primerjava obeh inačic med seboj in z obstoječimi brezizgubnimi algoritmi.
Keywords: računalništvo, algoritem, Bézierova krivulja, Riceovo kodiranje, prilagodljivo binarno zaporedno kodiranje
Published in DKUM: 20.10.2022; Views: 282; Downloads: 17
Full text (1,46 MB) |
7. Ugotavljanje podobnosti rastrskih slik z vgnezdenimi 3D izbočenimi lupinami : diplomsko deloŽiga Pečar, 2022, undergraduate thesis Abstract: V diplomskem delu smo izdelali metodo, ki s pomočjo 3D vgnezdenih izbočenih lupin ugotavlja podobnost med slikami. Najprej smo podali opis štirih že znanih metod za ugotavljanje podobnosti slik. Implementirana metoda prejme sivinsko rastrsko sliko, ki jo redči s Sobelovo zaznavo robov in nato sestavi 3D vgnezdene izbočene lupine te slike. Na podlagi teh izračuna cenilko, katere vrednost uporabimo za ugotavljanje podobnosti slik. Metodo smo testirali nad štirimi slikami in ovrednotili ustreznost rezultatov.
Keywords: algoritem, računalniška geometrija, hitra izbočena lupina, zaznava robov, sivinske slike
Published in DKUM: 20.10.2022; Views: 274; Downloads: 24
Full text (1,71 MB) |
8. |
9. Algoritem SA-IS za tvorbo priponskega polja : diplomsko deloDaniel Kvar, 2022, undergraduate thesis Abstract: Priponsko polje je podatkovna struktura, ki nam zelo učinkovito pomaga, kadar želimo izvajati določene operacije nad nizi, kot recimo: iskanje vzorca v nizu, iskanje najdaljšega ponavljajočega se niza in podobne. Obstaja več algoritmov za tvorbo priponskega polja. Algoritem SA-IS obljublja njegovo konstrukcijo v linearnem času, majhno prostorsko zahtevnost in hitrost v praksi. V diplomskem delu bomo najprej analizirali delovanje algoritma, sledila bo implementacija, testiranje in merjenje časa CPU ter porabo pomnilnika implementiranega algoritma.
Keywords: računalništvo, algoritem, podatkovna struktura, priponska polja, inducirano razvrščanje, časovna zahtevnost
Published in DKUM: 25.08.2022; Views: 836; Downloads: 156
Full text (1,37 MB) |
10. Algoritem LZW in njegove izboljšave : diplomsko deloMario Močnik, 2021, undergraduate thesis Abstract: V diplomskem delu smo opazovali, kako implementacija slovarja z razpršilno tabelo vpliva
na čas stiskanja algoritma Lempel–Ziv–Welch. Primerjali smo algoritem LZW z njegovimi
izboljšavami nadzora slovarja. Ugotovili smo, da najboljše razmerje stiskanja dosežemo z
algoritmom LZC. Algoritem SLZW, ki kombinira pristop statističnega stiskanja in stiskanja s
slovarjem, pa je bil najslabši.
Keywords: algoritmi, razpršilna tabela, brezizgubno stiskanje, stiskanje s slovarjem, razmerje stiskanja
Published in DKUM: 18.10.2021; Views: 860; Downloads: 127
Full text (188,63 KB) |
