|
|
Optimization methods for perfusion parameters estimation.
Bali-Jenčíková, Kateřina ; Kozumplík, Jiří (referee) ; Mézl, Martin (advisor)
The content of this bachelor thesis is research the principles of ultrasound imaging, description of mathematical models that are used to estimate perfusion parameters of concentration curves. Thesis also includes a theoretical analysis of genetic algorithms. In the practical part, solves the realization of global optimization methods and their subsequent evaluation. Implementation was solved by in Matlab.
|
|
|
Design optimization of packed bed for thermal energy storage
Krist, Thomas ; Charvát, Pavel (referee) ; Klimeš, Lubomír (advisor)
Tato diplomová práce se zabývá tématem výměny tepla v zásobníku tepla typu ”packed bed”. Cílem je popsat přenos tepla v zásobníku tepla obsahující kamínky malých průměrů, skrz který proudí horký vzduch. Toto je modelováno v prostředí MATLAB. Na začátku je krátký úvod do problematiky zahrnující ukládání tepla a jeho možné využití. Dále je uveden krátký přehled o základech přenosu tepla, typech přenosu tepla a termofyzikální vlastnosti systému vzduch-kámen. Ve třetí kapitole je představen zásobník tepla typu ”packed bed” a rozličné modely a dané podmínky jsou vysvětleny. Další kapitola se zabývá s numerickými metodami, převážně s metodou konečných diferencí použitou v této práci. Pátá kapitola se zaměřuje na obecnou optimalizaci daného problému přenosu tepla. Populačně založený metaheuristický optimalizační algoritmus zvaný Genetický algoritmus je popsán. Sestavení modelu je ukázáno v šesté kapitole, stejně jako prezentace výsledků získaných z programu MATLAB. V poslední kapitole je pak diskutován závěr a doporučení.
|
|
|
Smart Home Control
Fučík, Jan ; Beran, Vítězslav (referee) ; Zemčík, Pavel (advisor)
This thesis summarizes the subject of intelligent homes and describes commonly used standards and commercial solutions on the market. The thesis covers the design of a low-cost and easy to use smart home system which can be managed over the internet, uses a genetic algorithm for heating regulation optimization and its central computing unit is a low-cost, embedded device with low power consumption. The functionality of the system is verified on a practical application of heating regulation in a house. The efficacy of the system for energy savings is shown; it is based on measured data statistics.
|
|
|
Coalition Formation in Multiagent Systems Using Genetic Algorithms
Kučera, Tomáš ; Uhlíř, Václav (referee) ; Zbořil, František (advisor)
This thesis discusses the basics of software agents and the way they form the multiagent coalitions. Genetic algorithms are introduced as one of the methods of solving the coalition formation problem. MAPC 2018 competition is introduced, which inspired the final design and implementation of the solution by using the tools described. A demo project was created, in which agents communicate with the MASSim server and gather data which is then used as an input into the genetic algorithm. Its purpose is to assign the agents to the tasks based on the input data, so that the tasks can be accomplished in the most effective manner possible. The results of this algorithm are evaluated in experiments which are focused on the quality of the solutions found as well as the time required for the calculation.
|
|
|
Artificial Intelligence
Ragas, Luděk ; Žouželková Bartošová, Marie (referee) ; Sedláček, Pavel (advisor)
Cílem této bakalářské práce je poskytnout náhled do rozsáhlého oboru umělé inteligence. Téze nejprve poskytuje definici umělé inteligence a krátký přehled její historie. Poté práce stručně popisuje technologie umělé inteligence, jako jsou neuronové sítě, expertní systémy a genetické algoritmy. Na závěr téze popisuje vliv umělé inteligence na společnost a její pozici v ní.
|
|
|
Coevolutionary Algorithms Statistical Analysis Tool
Urban, Daniel ; Zachariášová, Marcela (referee) ; Drahošová, Michaela (advisor)
This bachelor thesis contains a theoretical basis that introduces evolutionary algorithms, genetic programming, coevolutioanary algorithms and methods for statistical evaluation. Furthermore, this work deals with the design and implementation of tool with graphical user interface, which allows the analysis of coevolutioanary algorithm for various parameters and also its statistical evaluation. The functionality of the implemented tool has been tested on data obtained from an external program performing evolutionary design of image filters with the use of the coevolution of tness predictors. The resulting graphs and statistics allow easy comparison of the progress and results for each program run.
|
|
|
Optimization of a small induction machine’s slots
Šišák, David ; Janda, Marcel (referee) ; Mach, Martin (advisor)
This master thesis deals with optimization of the shape of the stator and rotor slots of induction motor with focusing on increasing efficiency. The theoretical part introduces the principles of optimization algorithms. Another part is devoted to design the shape of slots and its influence on the shape of slots on machine. On the models of motor was conducted the optimized shape of slots by using a genetic algorithm. Firstly, it was performed by using the analytical calculation in the RMxprt program, then by using the finite element method on two different models, whose difference simulates the influence of the production technology on the efficiency of the motor. Laboratory measurement was made on a real machine as well. The results of the measurement, calculations and optimizations are compared in the work.
|
|
|
Evolution algorithms for ultrasound perfusion analysis
Kolářová, Jana ; Odstrčilík, Jan (referee) ; Mézl, Martin (advisor)
This master´s thesis is focused on the application of evolutionary algorithms for interleaving data obtained by ultrasound scanning of tissue. The interleaved curve serves to estimate perfusion parameters, thus allowing to detect possible pathophysiology in the scanned area. The theoretical introduction is devoted to perfusion and its parameters, contrast agents for ultrasonic application, ultrasonic modality scanning, optimization, evolutionary algorithms in general and two selected evolutionary algorithms - genetic algorithm and bee algorithm. These algorithms were tested on noisy data obtained from clinical images of mice with tumor. The final part summarizes the results of the practical part and provides suggestions and recommendations for further possible development.
|
|
| |
|
|
Effective evaluation of losses to buildings affected by flood
Tuscher, Martin ; Schneiderová-Heralová,, Renáta (referee) ; Kocanda,, Pavel (referee) ; Zeleňáková,, Martina (referee) ; Hanák, Tomáš (advisor)
This doctoral thesis deals with the valuation of damage to buildings affected by floods. In its individual parts, it researches floods as a risk, focuses on the damage caused by this natural phenomenon and examines the methods used to assess the damages caused by floods. With the beginnings of human settlement, the vicinity of rivers has been inhabited for the many befits that watercourses bring. However, there are many dangers associated with this, especially the ones associated with the spillage of riverbeds – with floods. This phenomenon causes considerable damage to property, the environment or human health and lives. There are many measures to eliminate the risk of flooding, or at least mitigate its effects. This work further researches the mitigating of impacts – it examines the methods of determining the amount of damage to buildings caused by floods, looks for factors and parameters influencing the amount of damage and focuses on streamlining these methods. The aim of the thesis is to find a suitable methodology/model that can automate the calculation of the amount of damage, or in other words, to find a quick and at the same time sufficiently accurate solution to this problem. The main output of the thesis is the equation of the damage curve and a model for the amount of damage calculation based on the principle of damage curves using the hybrid genetic algorithm. Another output is a practical tool that works on the basis of the said algorithm and automatically calculates the amount of damage to the building when entering very basic information about the damaged object.
|
guest ::
