Spelling suggestions: "subject:"verver"" "subject:"cerver""
1041 |
Forexový automatický obchodní systém založený na neuronových sítích / Forex automated trading system based on neural networksKačer, Petr January 2015 (has links)
Main goal of this thesis is to create forex automated trading system with possibility to add trading strategies as modules and implementation of trading strategy module based on neural networks. Created trading system is composed of client part for MetaTrader 4 trading platform and server GUI application. Trading strategy modules are implemented as dynamic libraries. Proposed trading strategy uses multilayer neural networks for prediction of direction of 45 minute moving average of close prices in one hour time horizon. Neural networks were able to find relationship between inputs and output and predict drop or growth with success rate higher than 50%. In live demo trading, strategy displayed itself as profitable for currency pair EUR/USD, but it was losing for currency pair GBP/USD. In tests with historical data from year 2014, strategy was profitable for currency pair EUR/USD in case of trading in direction of long-term trend. In case of trading against direction of trend for pair EUR/USD and in case of trading in direction and against direction of trend for pair GBP/USD, strategy was losing.
|
1042 |
Umělá inteligence ve hře Bang! / Artificial Intelligence in Bang! GameKolář, Vít January 2010 (has links)
The goal of this master's thesis is to create an artificial intelligence for the Bang! game. There is a full description of the Bang! game, it's entire rules, player's using strategy principles and game analysis from UI point of view included. The thesis also resumes methods of the artificial intelligence and summarizes basic information about the domain of game theory. Next part describes way of the implementation in C++ language and it's proceeding with use of Bayes classification and decision trees based on expert systems. Last part represent analysis of altogether positive results and the conclusion with possible further extensions.
|
1043 |
Využití PDA pro distribuci informací v rámci uzavřených sítí / Usage of PDA for Distribution of Information in Closed NetRyšánek, Vojtěch Unknown Date (has links)
The task of this project is to build application for managing of multimedia data in enclosed wireless networks and to present this data to the user. In model case it can be for example city guide - on position given by GPS are presented information about surrounding scene. Application must be capable of downloading data into Pocket PC - PDA and present them to the user as user friendly application.
|
1044 |
Webová aplikace zprostředkovávající výsledky testování výkonu platformy JBoss / Test Result Repository with Web User InterfaceVlasák, Jaroslav January 2013 (has links)
This thesis deals with the development of a client-server application for Red Hat company. Client participates in testing process of JBoss platform and gets user-defined performance data which sends during testing to the server application by platform independent communication. The server application allows to analyze the received data which can be also compared by several perspectives. These services for data analysis and comparison are accessible for server users using the web client. The server application supports the import of the performance data stored in the XML file and also their export for qVue portal. The client part of the application is implemented in Java and the server application is based on Java EE platform.
|
1045 |
Dolování periodických vzorů / Periodic Patterns MiningStríž, Rostislav January 2012 (has links)
Data collecting and analysis are commonly used techniques in many sectors of today's business and science. Process called Knowledge Discovery in Databases presents itself as a great tool to find new and interesting information that can be used in a future developement. This thesis deals with basic principles of data mining and temporal data mining as well as with specifics of concrete implementation of chosen algorithms for mining periodic patterns in time series. These algorithms have been developed in a form of managed plug-ins for Microsoft Analysis Services -- service that provides data mining features for Microsoft SQL Server. Finally, we discuss obtained results of performed experiments focused on time complexity of implemented algorithms.
|
1046 |
Dolování sekvenčních vzorů / Sequential Pattern MiningTisoň, Zdeněk January 2012 (has links)
This master's thesis is focused on knowledge discovery from databases, especially on methods of mining sequential patterns. Individual methods of mining sequential patterns are described in detail. Further, this work deals with extending the platform Microsoft SQL Server Analysis Services of new mining algorithms. In the practical part of this thesis, plugins for mining sequential patterns are implemented into MS SQL Server. In the last part, these algorithms are compared on different data sets.
|
1047 |
Datalogger s rozhraním Ethernet / Datalogger with EthernetOrávik, Tomáš January 2016 (has links)
Thesis deals with Datalogger with Ethernet interface controlled by Raspberry Pi 2. Datalogger is equipped with eight digital inputs and three analogue inputs. It allows storage of measured data into the database on the microSD card. It communicates over an Ethernet interface on the Raspberry Pi. The administration and control of the datalogger is possible trought a web server.
|
1048 |
Implementace nových koncových uzlů do firmy a jejich management / Implementation of New Terminal Nodes to the Company and it’s ManagementLukeš, Pavel January 2016 (has links)
This thesis deals with analysis of company’s MBG, spol. s r.o. problems, following with teoretical basis for these problems and in the end, it suggests the solutions. These problems are insufficient monitoring, any of used technology are old and absent of any information security management system. The first part is focused on a teoretical basis for the described problems, the second part will completely analyze all mentioned problems of a company. Final part will contain a solution for every company’s problem, based on theory and analysis with taking care about company’s demand too.
|
1049 |
Model třídicí linky v systému Tecnomatix Process Simulate / Sorting line model implemented by Tecnomatix Process SimulateProkop, Michal January 2017 (has links)
This master‘s thesis is about how to create a virtual model of a sorting line by using Tecnomatix Process Simulate program. In this master‘s thesis is describe non-robotics operation as a controlling conveyor, material flow, working with sensors and simulaton of manufactory process. In the second part of my master’s thesis I realise virtual commissioning for this model of sorting line. I made program for real PLC and conected with model of sorting line via OPC server. I made SCADA aplication for users too. This model will be used in lessons and students will program PLC for controlling. In master’s thesis I explain, how to work in simulation environment Tecnomatix Process Simulate too.
|
1050 |
A Client-Server Solution for Detecting Guns in School Environment using Deep Learning TechniquesOlsson, Johan January 2019 (has links)
Att använda maskininlärning för att detektera vapen eliminerar en konstant mänsklig övervakning, vilket också kan leda till en lägre responstid till polis. I den här rapporten undersöks hur en vapendetektor kan konstrueras och byggas som en del av en klient-server-lösning. / With the progress of deep learning methods the last couple of years, object detectionrelated tasks are improving rapidly. Using object detection for detecting guns in schoolsremove the need for human supervision and hopefully reduces police response time. Thispaper investigates how a gun detection system can be built by reading frames locally andusing a server for detection. The detector is based on a pre-trained SSD model and throughtransfer learning is taught to recognize guns. The detector obtained an Average Precisionof 51.1% and the server response time for a frame of size 1920 x 1080 was 480 ms, but couldbe scaled down to 240 x 135 to reach 210 ms, without affecting the accuracy. A non-gunclass was implemented to reduce the number of false positives and on a set of 300 imagescontaining 165 guns, the number of false positives dropped from 21 to 11.
|
Page generated in 0.0271 seconds