National Repository of Grey Literature 192 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
Multiagentní systém pro řízení subsystému Smart Home
Pločica, Peter ; Zbořil, František (referee) ; Janoušek, Vladimír (advisor)
In today’s world, technology has become an essential part of practically every person’s life. The development in technology has led to the creation of Smart Home. The advancement in artificial intelligence has resulted in the emergence of multi-agent systems, which is the focus of this work. The aim of this work was to create a multi-agent system to control the subsystem of Smart Home, which can lead to better integration of devices from different companies and better handling of more demanding operations. The work includes topic of Smart Home, which is related to the concept of ambient intelligence and the topic of multi-agent systems. Furthermore, the work includes the design of this system and a detailed description of its implementation, specifically the agents in the system. Finally, the functionality of the system is tested and the results are also part of the work.
Multiagentní systém pro řízení subsystému Smart Home
Pločica, Peter ; Zbořil, František (referee) ; Janoušek, Vladimír (advisor)
In today’s world, technology has become an essential part of practically every person’s life. The development in technology has led to the creation of Smart Home. The advancement in artificial intelligence has resulted in the emergence of multi-agent systems, which is the focus of this work. The aim of this work was to create a multi-agent system to control the subsystem of Smart Home, which can lead to better integration of devices from different companies and better handling of more demanding operations. The work includes topic of Smart Home, which is related to the concept of ambient intelligence and the topic of multi-agent systems. Furthermore, the work includes the design of this system and a detailed description of its implementation, specifically the agents in the system. Finally, the functionality of the system is tested and the results are also part of the work.
Code Generation from Object Oriented Petri Nets
Frlička, Eduard ; Janoušek, Vladimír (referee) ; Kočí, Radek (advisor)
PNtalk is a language used for modelling of object-oriented Petri nets. The existing simu- lator implemented in Smalltalk language is used mainly for modelling and debugging. For practical use, however, a more efficient representation of Petri net models is needed. This work presents a C++ representation of object-oriented Petri nets.
Multiagentní systém učící se maximalizovat komfort uživatelů v rámci Smart Home
Čábela, Radek ; Zbořil, František (referee) ; Janoušek, Vladimír (advisor)
This thesis comes with a solution, how to work with feedback, Smart Home devices and "agents" in a way that minimizes direct Smart Home parameters changes coming from house inhabitants and therefore increases their comfort. Resulting simulation demonstrating the funcionality of the system design is focused on problematics regarding changing temperature inside of a house.
Development of Combine Tool
Nováček, Pavel ; Janoušek, Vladimír (referee) ; Smrčka, Aleš (advisor)
This thesis deals with the reimplementation of the web tool Combine, which generates combinatorial test sets satisfying user-specified parameters and constraints using the IPOG algorithm. The thesis is a part of Testos platform, which aims at software testing automation. The goal of this thesis is to analyze the current state of the tool, identify its errors and deficiencies, discuss suitable extensions to its functionality, and based on these findings, create a new design and implementation of the Combine tool. The new solution preserves all the functionality of the previous tool and at the same time expands it on all levels of the architecture. The tool is not only more manageable thanks to a more user-friendly web interface but also offers new possibilities for test set generation. More suitable technologies have been chosen for its implementation, making the tool portable and significantly faster in generating test sets compared to the previous implementation, capable of competing with existing solutions for combinatorial test set generation.
Editor for City Traffic Simulator
Mariani, Juraj ; Janoušek, Vladimír (referee) ; Rozman, Jaroslav (advisor)
This thesis looks into modification of geographical data from the OpenStreetMap database represented in an XML format. The software serves mainly for editing traffic signals and road properties, e.g. the speed limit or the number of available lanes. I solved the selected problem by extracting relevant input data and by subsequent intersection detection. The apperance and properties of roads and intersections can be modified at will in a graphical user interface. The created software is aimed to enable modification of road and intersection features by easy-to-use and intuitive controls, without the need to remember feature names and format. The output data are stored back to a file in an XML format and are compatible with city traffic simulators working with OSM data.
Adaptive Pet Monitoring System within Smart Home
Ďurina, Michal ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
The aim of this thesis is to create an intelligent system that monitors and evaluates the behavior of a pet using image processing from a camera. The thesis will also focus on training existing models in order to improve the accuracy of animal detection. The application will run on the embedded Raspberry Pi system and, in addition to observation, performs specific actions based on the unwanted behavior of the animal using connected hardware (ultrasound, actuators, nebulizers, etc.), which has the task of influencing the animal’s behavior. Based on this monitoring and implementation of the action, the success of preventing the animal from moving to a predetermined unwanted area will be evaluated with regard to their safety. These actions will be optimized by experimentation and validation of results during development based on animal behavior. Part of the work is also a review of existing applications of Ambient intelligence in Smart Home, finding similar solutions used in practice.
Sequence Diagram Generation from Object-Oriented Petri Nets
Hoffmann, Michael ; Janoušek, Vladimír (referee) ; Kočí, Radek (advisor)
This diploma thesis aims to design and implement the mechanism of transformation of Object Oriented Petri Nets (OOPN) models into the form of sequence diagrams, as they are defined in the UML language. The OOPN formalism combines object-oriented language Smalltalk and Petri nets and is described by the PNtalk language. The resulting implementation will become part of the existing editor of Object-oriented Petri nets, where it will be possible to generate a sequence diagram from edited models.
Data Analysis for Predictive Maintenance of a Robotic Arm
Žitný, Roland ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
The Mitsubishi MELFA robotic arms used in modern factories work almost without interruption and produce sensory data about their operation. Various analysis techniques can be applied to such data for predictive maintenance, which provide information on the condition and maintenance needs of such robotic arms. The proposed predictive maintenance process consists of a sensory data acquisition system using the slmpclient and mitsubishi-monitor libraries, an analysis method system with anomaly detection using a convolutional autoencoder, anomaly classification using convolutional neural networks, and data segmentation into segments of individual robot actions using hidden Markov models. Such analysis techniques provide information on the severity, type, and location of emerging faults and abnormalities in behavior, which then determine the time required to perform the required maintenance. This work presents a created chain of predictive maintenance processes, where the obtained findings provide valuable insights into the application of predictive maintenance of Mitsubishi MELFA robotic arms in an industrial environment.
Multiagentní systém učící se maximalizovat komfort uživatelů v rámci Smart Home
Bednařík, Radim ; Zbořil, František (referee) ; Janoušek, Vladimír (advisor)
This thesis is focused on creating a multi-agent system for a smart home heating subsystem that tries to learn user patterns, using a reinforcement learning algorithm. The thesis further describes the creation of the necessary modules, which are a digital thermostatic valve, which appears in the system as an end agent, and a module for detecting the presence of people. The created system was deployed in a real environment and is functional.

National Repository of Grey Literature : 192 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.