|
|
Neural Cell Segmentation from Fluorescent Microscopy Images of Mouse Brains
Studna, Martin ; Šikudová, Elena (advisor) ; Bída, Michal (referee)
Our objective is to propose a neural cell segmentation algorithm for fluorescent mi- croscopic images of mice brains. We received a dataset from the Laboratory of Neu- rochemistry, Institute of Physiology of the Czech Academy of Sciences in Prague. We conducted various image segmentation experiments to identify a method that can most accurately segment neural cells. Our thesis will present the challenges linked with the segmentation of biological images. Then, we will describe the details of our experiments and the evaluation metrics used for measuring our methods' accuracy. 1
|
|
|
GPU Accelerated Adversarial Search
Brehovský, Martin ; Bošanský, Branislav (advisor) ; Bída, Michal (referee)
General purpose graphical processing units were proven to be useful for accelerating computationally intensive algorithms. Their capability to perform massive parallel computing significantly improve performance of many algorithms. This thesis focuses on using graphical processors (GPUs) to accelerate algorithms based on adversarial search. We investigate whether or not the adversarial algorithms are suitable for single instruction multiple data (SIMD) type of parallelism, which GPU provides. Therefore, parallel versions of selected algorithms accelerated by GPU were implemented and compared with the algorithms running on CPU. Obtained results show significant speed improvement and proof the applicability of GPU technology in the domain of adversarial search algorithms.
|
|
|
Generating life episodes for the purpose of testing of episodic memory models
Běhan, Zdeněk ; Kadlec, Rudolf (advisor) ; Bída, Michal (referee)
The goal of this work is to create a generator that provides a corpora of input episodes in the specified format, which can be used as an input to test episodic memory models. More specifically, the methods used should ensure the scope to be in years up to a possible lifetime of a typical human agent. It also attempts to verify this on an actual episodic memory model, and test if the generated data has high enough quality to be used for testing psychological paradigms on memory models.
|
|
|
Platform for spatial navigation research in virtual reality
Galajda, Martin ; Bída, Michal (advisor) ; Gemrot, Jakub (referee)
The Department of Neurophysiology of the Memory of the Academy of Sciences of the Czech Republic (UAV) has for several years been researching experiments to monitor the impact of various stages of Alzheimer's disease on patients' cognitive abilities. For this purpose, SpaNav was developed almost 9 years ago in cooperation of the UAV with the MFF UK. The system currently hits its technical limits given by possibilities of the time when it was created. The aim of this work is to introduce a new system that will remove the limits of the original system and allow research to continue. Powered by TCPDF (www.tcpdf.org)
|
|
|
Artificial Intelligence in Strategy Computer Games
Jirout, David ; Ježek, Pavel (advisor) ; Bída, Michal (referee)
Strategy war games are a genre of computer games with the key element being control and navigation of units on the map. Despite having different approach to unit management, even the best-selling titles usually feature troubles during unit collisions solving with the collisions occurring either among units or between a unit and a natural obstacle. The library being developed in this thesis unifies all the types of approach to unit management being used nowadays and offers generic formation system, prediction, avoidance and/or solving of unit collisions on all levels and furthermore unit pathfinding on the map with both the nature and height profile of the path taken into account. Powered by TCPDF (www.tcpdf.org)
|
|
|
Použití plánovacích technik pro generování sportovního komentáře pro dvojici virtuálních agentů
Gregor, Ivan ; Brom, Cyril (advisor) ; Bída, Michal (referee)
Virtual agents are essential representatives of multimodal user interfaces. This thesis presents the IVAN system (Intelligent Interactive Virtual Agent Narrators) that generates affective commentary on a tennis game that is given as an annotated video in real-time. The system employs two distinguishable virtual agents that have different roles (TV com- mentator, expert), personality profiles, and positive, neutral, or negative attitudes to the players. The system uses an HTN planner to generate dialogues which enables to plan large dialogue contributions and generate alternative plans. The system can also interrupt the current discourse if a more important event happens. The current affect of the virtual agents is conveyed by lexical selection, facial expression, and gestures. We have focused on the dialogue planning, knowledge processing, and behaviour control of the virtual agents. Commercial products have been used as the audio-visual component of the system.
|
|
|
The Spider Game
Ziegler, Martin ; Plch, Tomáš (advisor) ; Bída, Michal (referee)
We discuss the process of designing and of the following realization of our computer game Spider. We talk about the means that the game design uses to accomplish the goals that we have set for the game. We discuss the game's implementation architecture that uses the OGRE library to render the 3D scene, the Awesomium and NaviLibrary libraries to render the 2D user interface that is described in HTML and the Lua library for scripting purposes. We show the technical solution that we have used to extend the Lua library, so that the scripts can start their execution automatically based on the events in the game world, and so that the scripts can pause their execution on demand.
|
|
|
Role of communication in team-oriented FPS games
Tuma, Vojtěch ; Gemrot, Jakub (advisor) ; Bída, Michal (referee)
Communicaton in computer games is used to coordinate a team strategy and for sharing knowledge. The role of communication was examined in this thesis by creating several teams of bots for CTF mode of the Unreal Tournament 2004 computer game. As a base for implementation served the Pogamut platform and an existing deathmatch bot adjusted for CTF mode. For comparison three teams were made: the first was without any communication, the second used knowledge sharing and the third team - apart from knowledge sharing - used active communication for group movement. After several comparing experiments a conclusion was made that the team without communication is not worse than teams using communication. The difference is small and may have been affected during experiments or by specific implementation in this thesis. 1
|
|
| |
|
|
Pogamut and USARSim integration
Vejman, Martin ; Bída, Michal (advisor) ; Obdržálek, David (referee)
In this work we integrate the USARSim simulator with the Pogamut platform in order to facilitate the development of USARSim virtual robots. We present a set of robots solving simple task as a proof-of-concept. We also provide an aerial robot solving more complicated task. This robot will be used to evaluate the suitability of reactive planner POSH for controlling robots in USARSim. Two versions of the robot will be created and compared qualitatively. The first version will use pure Java, the second version will use reactive planner POSH.
|
guest ::
