|
|
Chess Program for Bughouse Variant
Staňa, Marek ; Křena, Bohuslav (referee) ; Rozman, Jaroslav (advisor)
This thesis describes process of creating a chess program playing Bughouse variant allowing to play against human or other programs. Firstly explains difference in Bughouse rules from classic chess, main part is about artificial intelligence. It compares individual methods used for making chess programs and adapts them to Bughouse variant.
|
|
|
Chess Program for Various Chess Variations
Jadrníček, Zbyněk ; Křena, Bohuslav (referee) ; Rozman, Jaroslav (advisor)
This thesis describes process of creating chess program allowing human play against computer. First part explains chess rules, next parts are about artificial intelligence. Thesis deals with nontraditional chess variants and also with changes, which were made in implementation in comparasion with classical game. It compares usual chessboard representations in computer, methods of playing games and techniques of evaluation chessboard state. The aim was to achieve high artificial intelligence by using of effective algorithms.
|
|
|
Use of selected artificial intelligence methods for finding small watersheds most at risk of flash floods
Ježík, Pavel ; Fošumpaur, Pavel (referee) ; Hlavčová,, Kamila (referee) ; Starý, Miloš (advisor)
In our region, heavy rains may occur virtually everywhere. Nowadays there are instruments to predict these events in sufficient advance, but without precise localisation, which is a problem. Present instruments for searching endangered watersheds are focused on operative evaluation of meteorological situation and actual precipitation forecast processing (nowcasting). The thesis brings quite different approach. Potentially endangered areas are detected with evaluation of long-term statistical variables (N-year discharges and rain characteristics) and properties of specific watershed. The whole issue is handled out of situation of actual danger, this attitude is so called off-line solution. The thesis describes a model based on selected artificial intelligence methods. The model forms the core of final map application. The use of model and final application is supposed to be used in area of preventive flood protection, and related investment decision-making. The model focuses on heavy rains and flash floods.
|
|
|
Application for Recognition of People by Face
Svoboda, Jakub ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Person identification has in the recent years gained notoriety as one of the most powerful ways of extracting information from image data. This thesis is focused on the task of human identification from facial photographs. To solve this task, we employ algorithms based on neural networks, which produce more robust results than traditional algorithms. In this thesis, we studied the common approaches for solving this problem and based on the gathered knowledge we created an architecture of a neural network trained to tackle the task of human identification and verification based on facial photographs. We have then further improved the model architecture and the training process by performing various experiments and observing the results. The final model has reached an accuracy comparable to other state-of-the-art models. Furthermore, we created a desktop application to demonstrate the results visually and to enable easier manipulation with the identity database. The knowledge gathered in this thesis can be used for improvements of current identification models or models modified for solving similar tasks.
|
|
|
Expert systems
Veselovský, Michal ; Konečný, Pavel (referee) ; Dvořák, Jiří (advisor)
Expert systems (ES) are commercially one of the most succesfull use of artificial intelligence (AI) - since eighties of the 20th century. They are often used in medicine, industry, science, trade, banking etc. Expert system is a software using knowledge of human experts for solving very complicated tasks and problems, which would otherwise require participating or consultation of one or more specialists on these issues. This software simulates decision-making of human expert in solving complicated tasks, and tries to reach the most probable result, ideally same as the expert´s opinion. Typical feature of expert systems, differencing it from usual software, is separating of decision making engine (inference engine) and knowledge base – same expert system with different knowledge base may serve for different purposes. This feature is used for creating empty expert systems – shells. Other features, which may not occur at all ES, are ability to make decision with uncertainty, and ability to explain the decision. Goal of this work is to describe basic principles of ES, using freely available information sources, and then describe and analyze resources for creating of these systems, using mainly information from official web sites.
|
|
|
Artificial intelligence in internet communication
Merzliakov, Evgeniy ; Rujbrová, Šárka (referee) ; Jašková, Jana (advisor)
Rozvoj takových technologií jako cloud computing, big data a deep learning způsobuje to, ze uměla inteligence se pomalu stává časti běžného života. Tato bakalářská práce popisuje základní systémy s umelou inteligenci, které už mohou být používané i v dnešní době, například Smart Home a virtuální asistenti. Zároveň je popsaná krátká historie podobných systémů a jejich vliv na komunikaci. Navíc jsou popsané základní principy umělých neuronových sítí. Taky v dane prací jsou porovnané tři různé virtuální asistenti (Google Asistent, Apple Siri a Amazon Alexa). Z výsledku patří, že Google Asistent je lepší než ostatní, ale rozdíl mezi nejlepším a nejhorším z porovnaných je 13 %.
|
|
|
Image classification using deep learning
Hřebíček, Zdeněk ; Přinosil, Jiří (referee) ; Mašek, Jan (advisor)
This thesis deals with image object detection and its classification into classes. Classification is provided by models of framework for deep learning BVLC/Caffe. Object detection is provided by AlpacaDB/selectivesearch and belltailjp/selective_search_py algorithms. One of results of this thesis is modification and usage of deep convolutional neural network AlexNet in BVLC/Caffe framework. This model was trained with precision 51,75% for classification into 1 000 classes. Then it was modified and trained for classification into 20 classes with precision 75.50%. Contribution of this thesis is implementation of graphical interface for object detction and their classification into classes, which is implemented as aplication based on web server in Python language. Aplication integrates object detection algorithms mentioned abowe with classification with help of BVLC/Caffe. Resulting aplication can be used for both object detection (and classification) and for fast verification of any classification model of BVLC/Caffe. This aplication was published on server GitHub under license Apache 2.0 so it can be further implemented and used.
|
|
|
Machine Learning-based Anomaly Detection in Industrial Control Systems
Tsymbal, Kateryna ; Holasová, Eva (referee) ; Pospíšil, Ondřej (advisor)
The main goal of this thesis is to design a system for anomaly and intrusion detection in industrial control systems using machine learning. The theoretical part of the thesis provides a basic theoretical overview of industrial control systems and their security. Furthermore, knowledge about anomaly detection techniques and potential challenges in this area are discussed. Lastly, the theoretical part has reviewed various solutions for anomaly detection in industrial control systems using machine learning. In the practical part, machine learning algorithms are applied to the selected HAI dataset. Finally, the findings on the suitability of the used algorithms and the possibilities for further research are summarized. The purpose of this thesis is to improve the security of industrial control systems, and the results can serve as a basis for the future development of more effective methods for anomaly detection in this area.
|
|
|
Application for Recognition of People by Face
Svoboda, Jakub ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Person identification has in the recent years gained notoriety as one of the most powerful ways of extracting information from image data. This thesis is focused on the task of human identification from facial photographs. To solve this task, we employ algorithms based on neural networks, which produce more robust results than traditional algorithms. In this thesis, we studied the common approaches for solving this problem and based on the gathered knowledge we created an architecture of a neural network trained to tackle the task of human identification and verification based on facial photographs. We have then further improved the model architecture and the training process by performing various experiments and observing the results. The final model has reached an accuracy comparable to other state-of-the-art models. Furthermore, we created a desktop application to demonstrate the results visually and to enable easier manipulation with the identity database. The knowledge gathered in this thesis can be used for improvements of current identification models or models modified for solving similar tasks.
|
|
|
Artificial intelligence in internet communication
Merzliakov, Evgeniy ; Rujbrová, Šárka (referee) ; Jašková, Jana (advisor)
Rozvoj takových technologií jako cloud computing, big data a deep learning způsobuje to, ze uměla inteligence se pomalu stává časti běžného života. Tato bakalářská práce popisuje základní systémy s umelou inteligenci, které už mohou být používané i v dnešní době, například Smart Home a virtuální asistenti. Zároveň je popsaná krátká historie podobných systémů a jejich vliv na komunikaci. Navíc jsou popsané základní principy umělých neuronových sítí. Taky v dane prací jsou porovnané tři různé virtuální asistenti (Google Asistent, Apple Siri a Amazon Alexa). Z výsledku patří, že Google Asistent je lepší než ostatní, ale rozdíl mezi nejlepším a nejhorším z porovnaných je 13 %.
|
guest ::
