Nature-inspired algorithms for hyperparameter optimization : magistrsko deloFilip Glojnarić
, 2019, master's thesis
Abstract: This master thesis is focusing on the utilization of nature-inspired algorithms for hyperparameter optimization, how they work and how to use them. We present some existing methods for hyperparameter optimization as well as propose a novel method that is based on six different nature-inspired algorithms: Firefly algorithm, Grey Wolf Optimizer, Particle Swarm Optimization, Genetic algorithm, Differential Evolution, and Hybrid Bat algorithm. We also show the optimization results (set of hyperparameters) for each algorithm and we present the plots of the accuracy for each combination and handpicked one. In discussion of the results, we provide the answers on our research questions as well as propose ideas for future work.
Keywords: artificial intelligence, artificial neural networks, machine learning, nature-inspired algorithms, evolutionary algorithms
Published in DKUM: 09.12.2019; Views: 1258; Downloads: 97
Full text (969,13 KB)
FORMULATION, PREPARATION AND CHARACTERIZATION OF NANOEMULSIONS FOR PARENTERAL NUTRITION : doctoral disertationDušica Mirković
, 2019, doctoral dissertation
Abstract: The aim of this doctoral research was to develop and optimize parenteral nanoemulsions as well as the total parenteral nutrition (TPN) admixture containing a nanoemulsion obtained in the course of the optimization process (hereinafter referred to as optimal nanoemulsion), and to examine their physicochemical and biological quality as well. In addition, the quality of the prepared nanoemulsions was compared with the quality of the industrial nanoemulsion (Lipofundin® MCT/LCT 20%), and, in the end, the TPN admixture initially prepared was also compared with the admixture into which the industrial emulsion was incorporated.
Parenteral nanoemulsions that were considered in this dissertation were prepared by the high-pressure homogenization method. This method is the most widely applied method for the production of nanoemulsions due to the shortest length of homogenization time, the best-obtained homogeneity of the product and the smallest droplet diameter.
For the nanoemulsion formulation, preparation and optimization purposes, by using, firstly, the concept of the computer-generated fractional design, and, after that, the full experimental design, the assessment of both direct effects of different formulation and process parameters (the oil phase type, the emulsifier type and concentration, a number of homogenization cycles and the pressure under which homogenization was carried out) as well as the effects of their interactions on the characteristics of prepared nanoemulsions was performed.
Monitoring the nanoemulsion physical and chemical stability parameters was carried out immediately after their preparation, and then after 10, 30 and 60 days. It included the visual inspection, the measurement of the droplet diameter (the mean and volume droplet diameter), the polydispersity index, the ζ-potential, the pH value, the electrical conductivity, and the peroxide number. After the preparation and after 60 days, the biological evaluation (the sterility test and the endotoxic test) of the prepared nanoemulsions was carried out. As far as the characterization of the TPN admixture is concerned, it included practically the same parameters. The dynamics of monitoring the characteristics of the TPN admixture was determined on the basis of practical needs of hospitalized patients (0h, 24h and 72h).
The scope and comprehensiveness of this issue indicated the need to divide the doctoral dissertation into three basic stages. The first stage was preliminary. Using the 24-1 fractional factorial design, nanoemulsions for the parenteral nutrition were prepared. They contained either a combination of soybean and fish oil, or a combination of medium chain triglycerides and fish oil. In addition, the type and the amount of an emulsifier used, a number of high-pressure homogenization cycles, and the homogenization pressure, were also varied. The measurement of the above-mentioned parameters for the industrial nanoemulsion was parallely carried out (Lipofundin® MCT/LCT 20%). The objective of this part of the research was to identify critical numerical factors having the most significant effect on the characteristics that define the prepared parenteral nanoemulsions. Parameters that were singled out as the result of this stage of the research (the emulsifier concentration and a number of homogenization cycles) were used as independent variables in the second stage of the research.
Keywords: nanoemulsions, total parenteral nutrition admixtures, high pressure homogenization, design of experiments, optimization, analysis of variance, artificial neural networks
Published in DKUM: 07.06.2019; Views: 11391; Downloads: 10
Full text (2,82 MB)
The accuracy of the germination rate of seeds based on image processing and artificial neural networksUroš Škrubej
, Črtomir Rozman
, Denis Stajnko
, 2015, original scientific article
Abstract: This paper describes a computer vision system based on image processing and machine learning techniques which was implemented for automatic assessment of the tomato seed germination rate. The entire system was built using open source applications Image J, Weka and their public Java classes and linked by our specially developed code. After object detection, we applied artificial neural networks (ANN), which was able to correctly classify 95.44% of germinated seeds of tomato (Solanum lycopersicum L.).
Keywords: image processing, artificial neural networks, seeds, tomato
Published in DKUM: 14.11.2017; Views: 1166; Downloads: 389
Full text (353,43 KB)
This document has many files! More...
Prediction of wine sensorial quality by routinely measured chemical propertiesAdriána Bednárová
, Roman Kranvogl
, Darinka Brodnjak-Vončina
, Tjaša Jug
, 2014, original scientific article
Abstract: The determination of the sensorial quality of wines is of great interest for wine consumers and producers since it declares the quality in most of the cases. The sensorial assays carried out by a group of experts are time-consuming and expensive especially when dealing with large batches of wines. Therefore, an attempt was made to assess the possibility of estimating the wine sensorial quality with using routinely measured chemical descriptors as predictors. For this purpose, 131 Slovenian red wine samples of different varieties and years of production were analysed and correlation and principal component analysis were applied to find inter-relations between the studied oenological descriptors. The method of artificial neural networks (ANNs) was utilised as the prediction tool for estimating overall sensorial quality of red wines. Each model was rigorously validated and sensitivity analysis was applied as a method for selecting the most important predictors. Consequently, acceptable results were obtained, when data representing only one year of production were included in the analysis. In this case, the coefficient of determination (R2) associated with training data was 0.95 and that for validation data was 0.90. When estimating sensorial quality in categorical form, 94 % and 85 % of correctly classified samples were achieved for training and validation subset, respectively.
Keywords: overall sensorial quality, prediction, Slovenian wine, artificial neural networks, multivariate data analysis
Published in DKUM: 03.04.2017; Views: 1172; Downloads: 363
Full text (1,02 MB)
This document has many files! More...
Navzkrižno testiranje simboličnih in konektivističnih pristopov strojnemu učenju na specializiranih bazah akutnega vnetja slepičaMilan Zorman
, Sandi Pohorec
, Bojan Butolen
, Bojan Žlahtič
, Peter Kokol
, 2012, original scientific article
Keywords: acute appendicitis, decision trees, artificial neural networks, machine learning, cross-testing, medica informatics
Published in DKUM: 30.12.2015; Views: 1208; Downloads: 22
Link to full text
Tool cutting force modeling in ball-end milling using multilevel perceptronUroš Župerl
, Franc Čuš
, 2004, original scientific article
Abstract: This paper uses the artificial neural networks (ANNs) approach to evolve an efficient model for estimation of cutting forces, based on a set of input cutting conditions. A neural network algorithms are developed for use as a direct modeling method, to predict forces for ball-end milling operation. Supervised neural networks are used to successfully estimate the cutting forces developed during end milling process. The training of the networks is preformed with experimental machining data. The predictive capability of using analytical and neural network approaches are compared using statistics, which showed that neural network predictions for three cutting force components were for 4% closer to the experimental measurements, compared to 11% using analytical method. Exhaustive experimentation is conduced to develop the model and to validate it. The milling experiments prove that this model can predict accurately the cutting forces in three Cartesian directions.The force model can be used for simulation purposes and for defining threshold values in cutting tool condition monitoring system.
Keywords: ball end milling, cutting forces, modelling, artificial intelligence, neural networks
Published in DKUM: 01.06.2012; Views: 2025; Downloads: 103
Link to full text
The use of artificial neural networks for colour prediction in textile printingDarko Golob
, Jure Zupan
, Đurđica Parac-Osterman
, 2008, published scientific conference contribution
Abstract: An attempt of using artificial neural networks for the prediction of dzes in textile printing paste preparation is presented. An existing collection of printed samples served as the basis for neural network training. It consists of 1340 samples printed using either a single dze or a combination of two dzes. First the proper combination of dzes was determined, because in most cases onlz two dzes are combined in the printing paste. Then the necessarz concentration of each dze was predicted. The reflectance value, and the colourvalues L*, a*, b* serve as input data and the known combination and concentrations of dzes for each sample were the targets. Some variations of neural network were tested, as well as various numbers of neurons in the hidden lazer. In addition, the influence of the training set organisation was examined, together with the number of learning epochs on the learning success.
Keywords: artificial neural networks, textile printing, colour recipe prediction
Published in DKUM: 31.05.2012; Views: 1627; Downloads: 57
Link to full text