|
Similar Photo Searching
Rosa, Štěpán ; Mlích, Jozef (referee) ; Beran, Vítězslav (advisor)
This paper describes the way to realization such an application, where a user chooses a photo database to working with and enters a photo into the system. The system using a visual vocabulary finds the most similar photos from the database and offers tags of the searched photo with a suitable form based on the tag statistical analysis of this photo.
|
|
Extension of User Profiles for Targeted Advertising Purposes
Hadač, Filip ; Burgetová, Ivana (referee) ; Zendulka, Jaroslav (advisor)
This thesis is devoted to designation and realisation of the extension of user profiles for improvement targeted advertising purposes. Web scraping is used for acquirement of new data information. Extracted data comes from two servers, ČSFD and Recepty. Data from ČSFD are film genres. Data from Recepty are categories of recepies. Streaming applications are used for processing of data and saving them to databases of user profiles. Preprocessing and machine learning classification algorithms are used for benefit evaluation of new informations for profiles in advertising campaigns. Evaluation of experiments shows that new informations have slight benefit in improvement advertising campaigns.
|
|
Verification And Adjustment Of Hf-Ecg
Preprocessing In Experimental Cardiology
Novotna, Petra
The aim of this article is to propose an approach to High-Frequency ECG (HF-ECG) preprocessing with an intention to verify the settled methods of signal preprocessing in the perspective of the new requirements and possibilities in the area of signal processing. The method using Butterworth filters is often used. Nevertheless, for the presented type of analysis is not suitable. FIR filtering alongside with clustering and signal averaging were used for preprocessing of data from isolated rabbit hearts. Frequency bands for further analysis were chosen according to the estimated SNR (signal-to-noise ratio).
|
|
Machine Learning Text Classifier for Short Texts Category Prediction
Drápela, Karel ; Křena, Bohuslav (referee) ; Šimková, Hana (advisor)
This thesis deals with categorization of short spam texts from SMS messages. First part summarizes current methods for text classification and~it's followed by description of several commonly used classifiers. In following chapters test data analysis, program implementation and results are described. The program is able to predict text categories based on predefined set of classes and also estimate classification accuracy on training data. For the two category types, that I designed, classifier reached accuracy of 82% and 92% . Both preprocessing and feature selection had a positive impact on resulting accuracy. It is possible to improve this accuracy further by removing portion of samples, which are difficult to classify. With 80\% recall it is possible to increase accuracy by 8-10%.
|
|
Machine Learning Optimization of KPI Prediction
Haris, Daniel ; Burget, Radek (referee) ; Bartík, Vladimír (advisor)
This thesis aims to optimize the machine learning algorithms for predicting KPI metrics for an organization. The organization is predicting whether projects meet planned deadlines of the last phase of development process using machine learning. The work focuses on the analysis of prediction models and sets the goal of selecting new candidate models for the prediction system. We have implemented a system that automatically selects the best feature variables for learning. Trained models were evaluated by several performance metrics and the best candidates were chosen for the prediction. Candidate models achieved higher accuracy, which means, that the prediction system provides more reliable responses. We suggested other improvements that could increase the accuracy of the forecast.
|
|
Basic fingerprint liveness detection
Horák, Tomáš ; Smital, Lukáš (referee) ; Kašpar, Jakub (advisor)
This work focuses on recognizing fingerprints liveness based purely on software-methods evaluating symptoms from just one fingerprint image. At first in this work was described the issue of biometry as such, comparing the advantages and disadvantages of such systems. Next part deal with more detailed process of fingerprint biometry including papillary lines and overall fingerprints as such. In the next phase, the problems and utilization of both software and hardware methods are discussed, including principles of individual approaches. This part is followed by a selection of used fingertip symptoms. This is followed by the practical part and the LivDet 2011 database, which was used for finger recognition. In the practical part is also described the used neural network capturing minor differences in fingerprints according to 13 symptoms.
|
|
Plagiarism Detection in Program Codes Using Mapping Technique
Kašpar, Jakub
The aim of this paper is to introduce the problem of plagiarism and propose a method for plagiarism detection in program codes. In the first part of this paper the basic definition of plagiarism is described. Further in the paper the principle of preprocessing and localization process for signs of plagiarism is introduced. The last part of this paper presents an algorithm for comparison of the detected signs to get the best results possible. The detector was tested on student projects from the BTBIO study program.
|
|
Basic fingerprint liveness detection
Horák, Tomáš ; Smital, Lukáš (referee) ; Kašpar, Jakub (advisor)
Biometric data is unique, safe and often used to protect information. Even in some cases, detectors can be fooled, and therefore liveness is needed to check. This work focuses on the basic recognition of the liveliness of the fingerprint. Only one finger image is used. For perfect recognition, you need to compare the prints, so have more than one print, and that's why this detection is very demanding. Pre-processing was done with a binary segmentation mask. Methods using gray scale ratios, mean, standard deviations or histogram equalization were also used. All the methods were done on the LivDet 2011 database, in the Matlab environment and the goal was to recognize a live fingerprints from a false ones.
|
|
Prediction of energy load profiles
Bartoš, Samuel ; Fink, Jiří (advisor) ; Van Leeuwen, Richard (referee)
Prediction of energy load profiles is an important topic in Smart Grid technologies. Accurate forecasts can lead to reduced costs and decreased dependency on commercial power suppliers by adapting to prices on energy market, efficient utilisation of solar and wind energy and sophisticated load scheduling. This thesis compares various statistical and machine learning models and their ability to forecast load profile for an entire day divided into 48 half-hour intervals. Additionally, we examine various preprocessing methods and their influence on the accuracy of the models. We also compare a variety of imputation methods that are designed to reconstruct missing observation commonly present in energy consumption data.
|
| |