|
|
Implementation and Comparison of Nature-Inspired Search Algorithms
Malysák, Adam ; Husa, Jakub (referee) ; Sekanina, Lukáš (advisor)
This thesis deals with the description, implementation and comparison of genetic algorithm, genetic algorithm enhanced with local search heuristic and binary particle swarm optimization (BPSO). These are algorithms inspired by natural phenomena, specifically the evolution and movement of bird flocks or fish schools. Implemented algorithms are used to solve the 3-SAT problem, which is also described in this thesis. Algorithms are tested on 3-SAT benchmarks and compared to each other and to other papers.
|
|
|
Music composition using artificial intelligence methods
Vendrame, Katia ; Dvořák, Jiří (referee) ; Matoušek, Radomil (advisor)
Tato studie se věnuje metodám automatické kompozice hudby (AMC), s kon- krétním zaměřením na evoluční algoritmy a neuronové sítě. Potenciální dialog mezi muzikologickými teoriemi a AMC jsou analyzovány, spolu s otázkou jejího základu v hudební tradici. Byly zkoumány tři algoritmy pro tvoření krátkých jednohlasých melodií založených na stylu daného datasetu nebo požadavcích uživatele: pravdě- podobnostní gramatická evoluce, genetické algoritmy a LSTM modely. Praktická část práce představuje aplikace těchto algoritmů a výsledky testování jejich výhod a předností. Dále je představena implementace pro analýzu MIDI datasetů z hudební perspektivy. V poslední řadě jsou představeny možnosti budoucího vylepšení a roz- šiření zkoumaných algoritmů v oblasti automatické hudební analýzy a kompozice.
|
|
|
Heuristic algorithm for freight transport logistics
Hobža, Jakub ; Nevrlý, Vlastimír (referee) ; Kůdela, Jakub (advisor)
This thesis deals with the solution of a real-world optimisation problem of DS Logistics, s.r.o., where the objective is to minimise the transportation costs given by the distance travelled. At the same time, a number of company-specific requirements have to be fulfilled. The work focuses on the use of heuristic and metaheuristic algorithms, and four different solution methods are presented. At the end of the thesis, these methods are compared on several instances. The best results were obtained using simulated annealing.
|
|
|
Nature-Inspired Optimisation Algorithms
Krampla, Vojtěch ; Dvořák, Jiří (referee) ; Šeda, Miloš (advisor)
This work focuses on the description of four nature-inspired optimization algorithms. The ant colony algorithm, the grey wolf algorithm, the bee swarm algorithm, and the genetic algorithm are described. As part of this work, the genetic algorithm was implemented for an optimization task, specifically for solving the knapsack problem. The work includes an experiment with this algorithm and an evaluation of the obtained results.
|
|
|
Simulace pohybu mobilního zařízení v ruce člověka
Hák, Marek ; Polčák, Libor (referee) ; Hranický, Radek (advisor)
Web browsers give websites access to motion sensors on mobile devices such as phones and tablets. The shared sensor data can be exploited to track and identify users. The JShelter browser extension provides protection against such exploitation of motion data by passing fake values. However, these values simulate a stationary device, which can lead to detection of the simulation. The goal of this thesis is to create a simulation that will generate believable device motion in the hands of a human. Prior to the design, sensor data analysis and exploration of motion simulation methods were conducted. Sets of parameters generated by a genetic algorithm are used for motion generation. The resulting solution was incorporated into the JShelter extension and experiments showed good results and performance of the solution.
|
|
| |
|
|
Automated creation of deep neural network models for image classification
DOHNAL, Patrik
The aim of the thesis is to design and implement a system that can automatically create deep neural networks (DNN) models for image classification. Additionally, the aim is to review the current state-of-the-art and to validate the system's functionality on two different datasets. A genetic algorithm is used to find the best approximate DNN model. Additionally, several approaches to encode the genetic information of DNN models are explored. Furthermore, several experiments with the VGG-16 architecture were conducted to find the best possible system base. The thesis also includes a discussion on the practice of model training and how problems that can arise during the automatic training of DNN models are avoided. The implementation is written in Python with Tensorflow library.
|
|
| |
|
|
Portfolio Optimization Using Genetic Algorithm
Kuruc, Igor ; Hanušová, Helena (referee) ; Chvátalová, Zuzana (advisor)
This bachelor's thesis focuses on using knowledge of portfolio theory and methods of soft computing. Theoretical backgroung is provided by postmodern portfolio theory and genetic algorithms. The purpose of aplicational section is maximizing risk-return measure. The result is optimized portfolio based on required properties. All calculation are made in Matlab software
|
|
|
Implementation of Mining Modules of Data Mining System on NetBeans Platform
Stríž, Rostislav ; Bartík, Vladimír (referee) ; Šebek, Michal (advisor)
Data collecting plays an important role in many aspects of today's businesses and quality information is the key to success. Process called Knowledge Discovery in Databases makes possible to extract hidden information that can be used further in our efforts. Main goal of this thesis is to describe an addition to such Data Mining System. Main objective is to create data mining module for NetBeans application, developed for demonstrational purposes by Faculty of Information Technology. New module is going to be able to mine information from Oracle database server via unusual use of Genetic Algorithm. This thesis describes the whole process of module implementation, begining with theoretical basics through coding details to final testing and summary.
|
guest ::
