|
|
Machine Learning Optimization of KPI Prediction
Haris, Daniel ; Burget, Radek (referee) ; Bartík, Vladimír (advisor)
This thesis aims to optimize the machine learning algorithms for predicting KPI metrics for an organization. The organization is predicting whether projects meet planned deadlines of the last phase of development process using machine learning. The work focuses on the analysis of prediction models and sets the goal of selecting new candidate models for the prediction system. We have implemented a system that automatically selects the best feature variables for learning. Trained models were evaluated by several performance metrics and the best candidates were chosen for the prediction. Candidate models achieved higher accuracy, which means, that the prediction system provides more reliable responses. We suggested other improvements that could increase the accuracy of the forecast.
|
|
|
Implementation of Algorithms Based on Decision Trees in C#
Grolig, Lukáš ; Pešek, Martin (referee) ; Stríž, Rostislav (advisor)
This bachelor thesis is focused on selection of data mining algorithms based on decision trees for an analytical system developed under the project System for the Internet security increase based on malware spreading analysis. Selected algorithms are described in greater detais, as well as their implementation in the C# language. These algorithms are then tested with regards to their training speed and classification accuracy. Finally, this thesis presents further conclusions and recommendations based on performed experiments.
|
|
| |
|
|
Android Music Player with the Song Selection by a Device Context
Chmelařová, Gabriela ; Burget, Radek (referee) ; Rychlý, Marek (advisor)
Tato práce pojednává o vytvoření mobilní aplikace zvažující kontext zařízení, která vybírá a doporučuje hudební skladby dle aktuálního stavu kontextu zařízení. Kontext je získáván na základě naměřených hodnot, které jsou získány z vestavěných senzorů mobilního zařízení a z ostatních systémových hodnot zařízení. Výběr konkrétní skladby je poté založen na výstupu modelu strojového učení, který klasifikuje kontext na základě aktuálních získaných dat a následně zvolí skladbu připadající k danému kontextu.
|
|
|
Comparison of Heuristic and Conventional Statistical Methods in Data Mining
Bitara, Matúš ; Žák, Libor (referee) ; Bednář, Josef (advisor)
The thesis deals with the comparison of conventional and heuristic methods in data mining used for binary classification. In the theoretical part, four different models are described. Model classification is demonstrated on simple examples. In the practical part, models are compared on real data. This part also consists of data cleaning, outliers removal, two different transformations and dimension reduction. In the last part methods used to quality testing of models are described.
|
|
|
Tissue characterisation in spectral CT data
Poláková, Veronika ; Jan, Jiří (referee) ; Jakubíček, Roman (advisor)
This bachelor thesis deals with tissue characterisation in virtual monoenergetic images (VMI). Firstly, literature survey presents spectral CT which allows reconstructing VMI. Secondly, statistical evaluation of tissue CT numbers was made for all energies of VMI which were reconstructed. It was found that with growing energy of VMI CT number increases or decreases with different steepness depending on a type of tissue. As a consequence, the suitable VMI offer better contrast resolution between selected pairs of tissues, which enables better tissue segmentation and classification in these images.
|
|
|
Sentiment Analysis of Czech and Slovak Social Networks and Web Discussions
Sojka, Matěj ; Dočekal, Martin (referee) ; Smrž, Pavel (advisor)
Thanks to digitalization, the spread of opinions in the population has accelerated sharply in the recent years, however the need to understand them has not changed. The goal of this thesis was to create a system for automatic data collection from social media and web discussions and sentiment analysis in Czech and Slovak language. The system has a web interface for visualizing results and configuring data analysis. The system is capable of offering topics to the user that it considers to occur in the selected data and group posts based on user-defined opinions.
|
|
|
Tool for Classification of Lifestyle Traits Based on Metagenomic Data from the Large Intestine
Kubica, Jan ; Hon, Jiří (referee) ; Smatana, Stanislav (advisor)
This thesis deals with analysis of human microbiome using metagenomic data from large intestine. The main focus is placed on bacteria composition in a sample on different taxonomic levels regarding the lifestyle traits of an individual. For this purpose, a tool for classification of several attributes was created. It considers attributes like diet type and eating habits (vegetarian, vegan, omnivore), gluten and lactose intolerance, body mass index, age or sex. From range of machine learning perspectives considering K Nearest Neighbours (kNN), Random Forest (RF) and Support Vector Machines (SVM) were used. Datasets for training and final evaluation of the classifier were taken from American Gut project. The thesis also focuses on particular problems with metagenomic datasets like its multidimensionality, sparsity, compositional character and class imbalance.
|
|
|
Protein Classification Techniques
Dekrét, Lukáš ; Zendulka, Jaroslav (referee) ; Burgetová, Ivana (advisor)
Main goal of classifying proteins into families is to understand structural, functional and evolutionary relationships between individual proteins, which are not easily deducible from available data. Since the structure and function of proteins are closely related, determination of function is mainly based on structural properties, that can be obtained relatively easily with current resources. Protein classification is also used in development of special medicines, in the diagnosis of clinical diseases or in personalized healthcare, which means a lot of investment in it. I created a new hierarchical tool for protein classification that achieves better results than some existing solutions. The implementation of the tool was preceded by acquaintance with the properties of proteins, examination of existing classification approaches, creation of an extensive data set, realizing experiments and selection of the final classifiers of the hierarchical tool.
|
|
|
Genetic Programming in Prediction Tasks
Machač, Michal ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
This thesis introduces various machine learning algorithms which can be used in prediction tasks based on regression. Tree genetic programming and linear genetic programming are explained more thoroughly. Selected machine learning algorithms (linear regression, random forest, multilayer perceptron and tree genetic programming) are compared on publicly available datasets with the use of scikit-learn and gplearn libraries. A core part of this project is a new implementation of linear genetic programming which was developed in C++, tested on common symbolic regression problems and then evaluated on real datasets. Results obtained with the proposed system are compared with the results obtained with gplearn.
|
guest ::
