|
|
Comparison of machine learning models in outdoor temperature sensing by commercial microwave link
Pospisil, Ondrej ; Musil, Petr ; Fujdiak, Radek
The main objective of this work is to focus on outdoor temperature prediction using machine learning based on parameters from commercial microwave links. This information can be used to refine the weather information at a given link location. Three machine learning models (random forest, linear regression, and lasso) are used for prediction using a combination of two datasets (ERA5 weather dataset and CML monitoring database dataset). The results were evaluated based on two evaluation metrics (R^2 and mean absolute error (MAE)). In this work, the ERA5 outdoor temperature was found to be correlated with the temperature of the microwave link unit, and results were obtained with an accuracy of 0.87144 based on the MAE metric. Thus, the results can fairly well predict actual outdoor temperatures in the microwave link area based on the microwave link unit temperature.
|
|
| |
|
|
Dispersion and survival of Moorhen (Gallinula choloropus) in urban habitats
Vodičková, Barbora ; Musil, Petr (advisor) ; Reif, Jiří (referee)
Presence of Common Moorhen (Gallinula chloropus) in Prague is a long known fact. Mapping and data collecting of this species during winter is on a low level, so there is not many information about its winter behavior. Present climate change brings not only a change in climate, but in combination with rapid urbanization, also big changes in environment. Wintering locations are moving to the north due to higher temperatures, and also to the cities. This could be fatal for many individuals. Weather is unpredictable and during wintering season of 2016/2017 and 2017/2018 there were very unorthodox winter conditions, which had a significant impact on bird population in Prague. During winter 2016/2017 there were extermely low temperatures with median deep below zero degrees Celsius in combination with large snow coverage. Winter 2017/2018 was overall good for surviving. Reason for great decline in numbers was caused not only by climate and weather conditions, but also by wrongly chosen wintering location. Unique locality of Zoological garden of Prague in Troja district, offers safe shelter even during extreme weather conditions such as freezing cold temperatures. According to statistics , this location is best suited for survival. Keywords: wintering, Common Moorhen, weather, still waters, rivers,...
|
|
|
Acceleration of Particles Tracking on CBM Experiment
Roth, Michael ; Kolář, Martin (referee) ; Musil, Petr (advisor)
The focus of this work is to research various methods of particle track reconstruction in the CBM experiment, and the problem of hardware acceleration of these methods. The advantages and disadvantages of the extended methods were discussed and a reconstruction method based on cellular automata and Kalman filters was selected for further study. In particular, the thesis details the development of a simulation model suitable for generating test data to facilitate future implementation of the selected tracking algorithm. Two different particle simulators have been developed and will be used in the following work to calculate the prediction step of the extended Kalman filter and to test the quality of the implemented reconstruction method.
|
|
|
Food competition between waterbirds and fish
Bečvář, Viktor ; Hořák, David (advisor) ; Musil, Petr (referee)
Food competition between waterbirds and fish can be a crucial factor in todays wetland ecosystems. In certain situations it can be decisive if a specific site is still suitable for waterbirds or not. Large aquatic invertebrats are often shared food resource. Situations where specific waterbirds and fish compete for this resource were described in many wetland habitats. Fish are often much more effective in acquiring food to the point when this relationship can be described as asymetrical competition. The level of competition can be also influenced by various envirometal factors or different attributes of waterbird and fish populations. The knowledge obtained by studing this relationship can be then used in management of protected areas and comercially used waterbodies.
|
|
|
Recognizing and Classification of Traffic Situations
Zbořil, Jiří ; Musil, Petr (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to identify and classify dangerous situations from surveillance cameras, monitoring traffic. An example of such situations is dangerous standing near by the road and car crash, on which this work focuses. The created system uses object detector, analyzing average images in given interval, K nearest neighbor and K Means algorithm and re-detection of enlarged local area in a frame to select anomaly candidates. Detected objects, that do not belong on the road are eliminated by attaching created road mask. At the very last phase, the interval, together with the classification is determined. Calculated F1 score is 0.645, S4 score 0.535 and precision of classification 80 %.
|
|
|
Predicting Trajectories of Vehicles and Pedestrians for Driving Assistent Systems
Mudroň, Marek ; Musil, Petr (referee) ; Smrž, Pavel (advisor)
This bachelor thesis deals with representation of a traffic scene by processing monocular video sequence. I try to predict a trajectory of detected vehicles in a short time horizon, based on created representation. Current approaches use multiple expensive sensors to gather instant information of environment. In the thesis I introduce technique, which is able to extract data from an environment by image processing techniques without the need of expensive sensors. The result of this work is a system creating opportunity to reduce the sensor costs of a system for scene representation and trajectory prediction of vehicles in the scene. In addition, comparison of models trained on differently processed data is provided, as well as data about how my system approximates the most reliable prediction models.
|
|
|
Gateway for monitoring maritime transport
Fučík, Stanislav ; Číž, Radim (referee) ; Musil, Petr (advisor)
This thesis addressed the monitoring of maritime traffic. The aim was to evaluate current solutions in the field of maritime traffic monitoring and to design and create new solution. The proposed solution is powered by solar panels and Li-Ion batteries. For sending data, satellite and mobile connections is be used. As a source of information about position GPS is used. The monitoring unit is equipped with sensors for measuring temperature, humidity, acceleration, intrusion of into the container and a detector of the opening door. The unit is resistant to the atmospheric influences prevailing sea and is operational long-term at sea.
|
|
|
Web and mobile application for meteorological data collection and visualisation
Šturala, Martin ; Musil, Petr (referee) ; Caha, Tomáš (advisor)
The thesis deals with the development of a web application in .NET 5 and a mobile application for the Android operating system. The applications were created for the collection and visualization of data from the weather station, which was developed in previous years within the diploma thesis of Ing. Petr Mlčák. The web application provides a REST API for collecting data from the weather station and sending data for the mobile application, it also provides a user web interface for visualizing data from the weather station and managing it. The first part describes the quantities that the weather station measures and sends to the server. The second part describes the design of a database structure for data storage. The third part of the work is focused on the development of a web application in ASP.NET, its parts and structure. The functions and their meaning in the web interface are also described. The fourth part describes the design and development of a mobile application and the principles used for data acquisition and display. In the end, the results of the work and the method of testing applications are evaluated.
|
|
|
Automated area measurement of precipitation intensity via a network of microwave links
Bubniak, Milan ; Pospíšil, Ondřej (referee) ; Musil, Petr (advisor)
Point-to-point microwave links can be utilized as a large sensor network to measure rainfall. This work deals with the application of this procedure in practice. The first part of the thesis deals with atmospheric precipitation in general and standard methods of their measurement; and the propagation of the microwave signal and various causes of its attenuation, focusing on the attenuation caused by rain and the recommendation ITU-R P.838. This is followed by a state of the art summarization of the measurement of rainfall by microwave links. In the second part of the work, a manual procedure for calculating rainfall from microwave link data is performed, taking wet antenna attenuation into account. Then the creation of a support tool in the C# language is being described, which supply the data to the functions of the RAINLINK rainfall calculation library. Several rainfall calculations that are validated by physical rain gauges are performed. Furthermore, the own Telcorain application for rainfall calculation is created in the Python language, based on the pycomlink library. It has a graphical user interface created in PyQt. Several rainfall calculations validated by rain gauges are performed again, and the results are compared with the RAINLINK library.
|
guest ::
