National Repository of Grey Literature 35 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Signature verification using neural network-based algorithms
Čírtek, Petr ; Kiac, Martin (referee) ; Myška, Vojtěch (advisor)
Signature is one of the most used biometrics in banking and contracting therefore is important to verificate signature authenticity. Verification can be done with the help of a forensic specialist or, thanks to the rise of advanced technology, with the help of a computing technology. The purpose of this thesis is to develop methods for signature verification using neural networks for Czech type of signature and to find out if adding manual extracted features to convolutional analysis could improve these methods. Neural networks seek to replicate the functioning of human brain, consisting of input neurons, several hidden layers and output neurons. Neural networks are one of the most popular artificial intelligence technologies for image analysis and classification. The proposed methods in this thesis work on the principles of convolutional networks. The first proposed method consist of three convolutional layers which extract important features from image of signature and pass them to fully connected classifier layer. This determines whether the signature is genuine or forgery. Also for this method there were created two functions which can interpret it's decision-making. The second method, siamese neural network, unlike the first, does not work with signatures independently, but uses a reference signature image to determine authenticity. The basis of this method is to extract features with convolutional analysis from both the reference signature and the signature to be authenticated. These features are then concatenated and passed to the clasificator. A Czech dataset was created to train models that would verify the Czech type of signatures. From the experiments, it was found that the addition of manualy extracted features has the potential to improve the prediction accuracy of methods based on convolutional image analysis. 3 models were trained, which can verify the Czech type of signatures with an accuracy higher than 80 \%, namely: the model of the convolutional neural network method with discrete wavelet transformation feature, which was trained on the Czech dataset, the model of the same method trained on the CEDAR dataset with number of strokes as added feature and a siamese convolutional neural network method model trained on the Czech dataset of signatures with the tri-surface feature.
COVID-19 disease classification based on analysis of chest X-rays
Šteflík, Dominik ; Kiac, Martin (referee) ; Myška, Vojtěch (advisor)
This diploma thesis addresses the development and evaluation of artificial intelligence algorithms for classifying COVID-19 disease from chest X-ray images. Given the severity and impact of the COVID-19 pandemic on the global population, the ability to rapidly and accurately diagnose diseases from radiographic images has become critical. This study synthesizes current advancements in image processing and deep learning to evaluate the application of several novel classification methods in practice. Using a dataset obtained from a Czech medical environment, these methods are analyzed and validated in order to examine their effectiveness and accuracy in real life scenarios. The methods chosen for this study, COVID-Net, DarkCovidNet, and CoroNet, were selected due to their availability, widespread use and proven effectiveness in the field. The core of the thesis is the design of a convolutional neural network tailored to extract and learn from the subtle features present in X-ray images indicative of COVID-19. This initiative confronted significant challenges posed by variable acquisition parameters of X-ray images, which can substantially affect diagnostic accuracy. The uniformity of these parameters is crucial for reliable analysis, underscoring the importance of rigorous preprocessing techniques. In response, advanced normalization, contrast adjustment, and augmentation procedures were implemented to standardize the input data. The convolutional network itself employs a series of convolutional, pooling, and fully connected layers, optimized to handle the nuanced variations present in medical imaging data. Notably, the network architecture incorporates an attention mechanism, implemented through a Squeeze-and-Excitation block, to dynamically adjust the importance of different channels in the input image. By integrating these elements, the network model is trained to focus on significant features within the X-ray images, allowing it to distinguish subtle indicators of COVID-19 effectively. Furthermore, this work discusses the potential of integrating these AI-driven diagnostic tools into existing healthcare infrastructures to enhance early detection and treatment of COVID-19. The findings indicate that leveraging artificial intelligence in medical imaging can substantially aid in managing and controlling disease outbreaks, ultimately contributing to better health outcomes.
Image data segmentation using deep neural networks
Hrdý, Martin ; Myška, Vojtěch (referee) ; Kiac, Martin (advisor)
The main aim of this master’s thesis is to get acquainted with the theory of the current segmentation methods, that use deep learning. Segmentation neural network that will be capable of segmenting individual instances of the objects will be proposed and created based on theoretical knowledge. The main focus of the segmentation neural network will be segmentation of electronic components from printed circuit boards.
Wireless robot control using mobile platform
Matuška, Jakub ; Kiac, Martin (referee) ; Přinosil, Jiří (advisor)
This bachelor’s thesis deals with design and implementation of an application for robot’s omnidirectional movement control using mobile platform. Implementation includes an Android application, used as user interface, as well as robot–side Python program for controlling movement and sending RTP stream to Android application. User can control robot’s movement using two virtual joysticks. Raspberry Pi was used as the control unit. The application has security module. Pipeline-based multimedia framework named GStreamer was used to implement RTP steaming. This paper describes necessary theory first and then introduces basic building blocks used in creation process of the application.
IoT system for gardening
Mlčák, Petr ; Kiac, Martin (referee) ; Caha, Tomáš (advisor)
The thesis deals with the design and creation of a weather station suitable for gardeners. The created device is able to measure temperature, pressure, humidity, amount of precipitation, wind speed and direction, UV index and also temperature and soil moisture at several depths. The weather station is powered by a battery with auxiliary charging from a photovoltaic panel. The thesis is divided into several parts. The theoretical part describes the individual physical principles of measurement of the considered physical quantities. Subsequently, a comparison of available sensors is made and then a final selection is made. The third part deals with the design and implementation of the hardware circuitry including the creation of the PCB. In this section, the holders of each sensor are also designed for printing on a 3D printer, which are then printed. The fourth section deals with software design issues, which is described in more detail. Finally, the whole weather station is assembled, wired and the functionality of all components is verified by sending the measured data to Thingspeak.
Real-time voice command recognition system
Šíbl, Evžen ; Kiac, Martin (referee) ; Přinosil, Jiří (advisor)
The bachelor thesis deals with the development of a system for voice command recognition. The classifier of this system was created using a neural network. In this thesis you will learn about the history and problems of speech recognition. A system has been created that detects a section in a recording containing a speech signal, which then uses the classifier to decide what word from the word table it is. Three models with the same architecture but with different training data were created. These models were then compared with each other. A simple user interface was created for the resulting system.
Intelligent beekeeping system
Hrubý, Jan ; Zeman, Václav (referee) ; Kiac, Martin (advisor)
The aim of this thesis is to design and develop an intelligent beekeeping system that can measure the frequency in the colony, the weight of the hive to monitor the loss or to inform the beekeeper if the bees are carrying honey. Furthermore, the security of the hive against theft is also being considered. Communication between multiple intelligent beekeeping systems is important for the functionality. This is why part of the work focuses on choosing the best possible communication, taking into consideration battery consumption and reliability. In this work, a many-to-one communication system of modules is used, which means that the number of hives can be freely expanded without affecting the functionality of the system. The resulting system is powered by a combination of battery and solar panels.
Mobile application for an intelligent beekeeping system
Pecár, Martin ; Myška, Vojtěch (referee) ; Kiac, Martin (advisor)
The aim of this thesis is to design and create an application which will allow beekeepers to manage their hives with a mobile phone.The reason for this is centralisation and clarification of all colected data from visits to the hive, where this data could be later used to create statistics.Furthermore, this app contains ways to notify the beekeeper that there is a need of intervention with the hive using their own alerts and statistics of selected properties of a hive. The result of this work is the previously described application.
Intelligent hatchery of poultry
Kejík, Jan ; Číka, Petr (referee) ; Kiac, Martin (advisor)
The aim of this thesis was to design and build an intelligent hatchery for poultry. The first part deals with the description of poultry hatching processes. Furthermore, the bestselling hatcheries from different manufacturers are compared and the proposed hatchery management system is described. In other parts of the work there is described the practical construction of the hatchery as it was constructed. The mechanical part of the hatchery uses largely the components printed on a 3D printer, the electronic equipment uses the components of the Arduino platform. A significant part is the description of embedded software implemented in the object-oriented programming language C++. The resulting hatchery is equipped with an user-friendly interface with the ability of control by mobile applications. As the practical use of the hatchery requires continuous reliable operation for several weeks, the hatchery had been tested for several months. During this time, practical experience was gained to help with the solving of some problematic components and to debug the resulting software.
Object detection in video using neural networks and Android application
Mikulec, Vojtěch ; Kiac, Martin (referee) ; Myška, Vojtěch (advisor)
This master’s thesis deals with the implementation of functional solution for classifying road users using mobile device with Android operating system. The goal is to create Android application which classifies vehicles in real time using rear-facing camera and saves timestamps of classification. Testing is performed mostly with own, diversely modificated dataset. Five models are trained and their performance is measured in dependence on hardware. The best classification performance is from pretrained MobileNet model where transfer learning with 6 classes of own dataset is used – 62,33 %. The results are summarized and a method for faster and more accurate traffic analysis is proposed.

National Repository of Grey Literature : 35 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.