|
|
Re-identification of Objects in Video Stream using Data Analytics
Smrž, Dominik ; Skopal, Tomáš (advisor) ; Lokoč, Jakub (referee)
The wide usage of surveillance cameras provides data that can be used in various areas, such as security and urban planning. An important stepping stone for useful information extraction is matching the seen object across different points in time or different cameras. In this work, we focus specifically on this part of the video processing, usually referred to as re-identification. We split our work into two stages. In the first part, we focus on the spatial and temporal information regarding the detected objects. In the second part, we combine this metadata with the visual information. For the extraction of useful descriptors from the images, we use methods based on the color distribution as well as state-of-the-art deep neural networks. We also annotate a dataset to provide a comprehensive evaluation of our approaches. Additionally, we provide a custom tool we used to annotate the dataset. 1
|
|
|
Electrophoretical determination of corrosion inhibitors in engine coolants
Smrž, Dominik ; Kubíčková, Anna (advisor) ; Coufal, Pavel (referee)
A determination of corrosion inhibitors in engine coolants represent a difficult analytical problem due to their different physicochemical properties. Nowadays a lot of instrument methods are needed to determine them. The aim of this work was the development of methods for their determination using only one instrumentation. Capillary zone electrophoreses was chosen as a suitable technique. Three electrophoretic methods for three groups of corrosion inhibitors were developed. Firstly, method for determination of inorganic anions was developed in range from 5 to 50 ppm with limit of detection around 1 ppm. Background electrolyte contains sodium chromate, CTAB and CHES solution. Analytes were detected indirectly at 450 nm. Another method was for determination of organic acids anions. They were determined in range from 5 to 500 ppm. Limit of detection for each analyte was around 1 ppm. Measurement was made with PDC a CTAC water solution. Indirect detection was used for this determination at 350 nm. Last developed method can be use for determination of aryltrizoles in range from 5 to 500 ppm. Limit of detection was around 1 ppm. As a background electrolyte was used sodium tetraborate solution. The developed methods were validated and their suitability for determination of corrosion inhibitors in real...
|
|
|
Feature extraction from Android application packages and its usage in machine learning for malware classification
Smrž, Dominik ; Bálek, Martin (advisor) ; Kofroň, Jan (referee)
In this Thesis, we propose a machine-learning based classification algorithm of applications for a popular mobile phone operating system Android that can dis- tinguish malicious samples from benign ones. Feature extraction for the machine learning is based on static analysis of the application's bytecode with focus on API and method calls. We show various ways to transform the most frequent API and method calls into numeric (histogram-based) features. We further examine the specifics of the extracted features and discuss their importance. The dataset used for experiments in this Thesis contains more than 200,000 samples with approxi- mately half of them malicious and half of them benign. Further, multiple machine learning algorithms are examined and their performance is evaluated. The size of our dataset prevents overfitting and hence provides a reliable basis for training of classification models. The results of the experiments show that the proposed algo- rithm achieves very low false positive rate under 2.9% while preserving specificity over 93.6%. 1
|
|
|
Determination of Engine Coolants by UHPLC
Smrž, Dominik ; Kubíčková, Anna (advisor) ; Sobotníková, Jana (referee)
4 Abstract Nowadays, there is no standard method for determination of organic corrosion inhibitors in engine coolant. Due to that the aim of this bachelor thesis is to develop a rapid and effective method for their determination by UHPLC method in all commercially available engine coolants. The method was developed and optimized. The optimal separation conditions are: core-shell column Poroshell 120 SB-AQ, gradient elution programme of methanol and 0.05% (v/v) trifluoracetic acid solution mixture (concentration of methanol changes from 40 to 65 % (v/v)), dosed volume 1 µl, detection at wavelength 211 nm. All analyzes were performed at 25 řC. The analysis duration is 6.5 min. Calibration dependences were measured from 0.25 to 4.0 g l-1 for 2-ethylhexanoic, 3,5,5-trimethylhexanoic, nonanoic and decandioic acid, in range 0.025 - 0.400 g l-1 for imidazole, benzotriazole, methylbenzotriazole, benzothiazole-2-thiol and benzoic acid. The calibration curves are linear in whole range of detector for all chosen corrosion inhibitors. Key words engine coolants, organic acids, aryltrizoles, UHPLC, Core-Shell columns
|
guest ::
RSS feed.