Global ETD Search

31	Rozpoznávání a klasifikace emocí na základě analýzy řeči / Emotional State Recognition and Classification Based on Speech Signal Analysis Černý, Lukáš January 2010 (has links) The diploma thesis focuses on classification of emotions. Thesis deals about parameterization of sounds files by suprasegment and segment methods with regard for next used of these methods. Berlin database is used. This database includes many of sounds records with emotions. Parameterization creates files, which are divided to two parts. First part is used for training and second part is used for testing. Point of interest is self-organization network. Thesis includes Matlab´s program which can be used for parameterization of any database. Data are classified by self-organization network after parameterization. Results of hits rates are presented at the end of this diploma thesis.
32	Návrh sanace stokové sítě vybrané části urbanizovaného celku / Design of sewer network rehabilitation of choice parts of urbanized areas Horák, Ondřej January 2013 (has links) The thesis approaches the problem of design of sewer network rehabilitation of urbanized area named Kamenná čtvrť. The thesis is divided into several parts. In the first part of the thesis there is the accompaying report, which describs characteristics of the area as a whole. The second part of the thesis is about describing each part of the network, clasification of defects according to the ČSN EN 13508 -2 and fothcoming TNV 75 6905 and photographs from network camera survey. In the third part of this thesis there is a chart with all defects located on the network. Also there is an evaluation of each part of network according to prepared TNV 75 6905. The fourth part of the thesis talks about evaluation of each part of the network as a whole. In the fifth part of the thesis we design possible choises of reahabilitation on the network. The sixth part of the thesis contains the economic aspects of possible alternatives and their comparsion. Last part of the thesis contains a hydrotechnical calculation, which means calculation of the current situation and the possible alternatives. There is an individual evaluation of the calculation and if its necessary optimizations of the network.
33	Založení a rozvoj školicího střediska / Creating and developing of training centre Žídek, Marek January 2008 (has links) Document describes foundation and development of computer training center. It introduces the reader to the development process and the structure of business plan in the beginning. The process starts with SLEPTE analysis, customer research and simple financial analysis. The result of previous three analyses is SWOT analysis. SWOT analysis recommends author to continue in the business plan development. Therefore, documents describe more accurate and detailed analyses specialized to computer professional courses in the region of Brno and surrounding cities. Next, it describes company strategy according to the results of analyses. Marketing and financial parts of the strategy are the most stressed ones. The reader is very deeply familiarized with company product and their price policy. The last pages of document present steps required to successfully implement company strategy.
34	Dolování dat z databází / Data Mining Slezák, Milan January 2011 (has links) The thesis is focused on an introduction of data mining. Data mining is focused on finding of a hidden data correlation. Interest in this area is dated back to the 60th the 20th century. Data analysis was first used in marketing. However, later it expanded to more areas, and some of its options are still unused. One of methodologies is useful used for creating of this process. Methodology offers a concise guide on how you can create a data mining procedure. The data mining analysis contains a wide range of algorithms for data modification. The interest in data mining causes that number of data mining software is increasing. This thesis contains overviews some of this programs, some examples and assessment.
35	AUGMENTATION AND CLASSIFICATION OF TIME SERIES FOR FINDING ACL INJURIES Johansson, Marie-Louise January 2022 (has links) This thesis addresses the problem where we want to apply machine learning over a small data set of multivariate time series. A challenge when classifying data is when the data set is small and overfitting is at risk. Augmentation of small data sets might avoid overfitting. The multivariate time series used in this project represent motion data of people with reconstructed ACLs and a control group. The approach was pairing motion data from the training set and using Euclidean Barycentric Averaging to create a new set of synthetic motion data so as to increase the size of the training set. The classifiers used were Dynamic Time Warping -One Nearest neighbour and Time Series Forest. In our example we found this way of increasing the training set a less productive strategy. We also found Time Series Forest to generally perform with higher accuracy on the chosen data sets, but there may be more effective augmentation strategies to avoid overfitting. computer science machine learning motion analysis reconstructed ACL anterior cruciate ligament time series forest dynamic time wapring ACL multivariate time series clasification MTSC time series classification TSC euclidean barycentric average euclidean barycentric averaging autmentation of time series augmentation of multivariate time series data augmentation augmentation Computer Sciences Datavetenskap (datalogi)

Page generated in 0.4975 seconds