National Repository of Grey Literature 120 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
Classification of high frequency oscillations in intracranial EEG
Macíčková, Magda ; Vítek, Martin (referee) ; Ronzhina, Marina (advisor)
This Master’s thesis deals with investigation of high-frequency oscillations in intracranial electroencephalography in patients with pharmacoresistant epilepsy. It describes individual types of oscillations with respect to their frequency definition, examines their physiological differences and occurrence. In addition to conventional high-frequency oscillations (up to about 600 Hz), it also focuses on oscillations with a frequency component above 1kHz. According to recent studies, these oscillations could have higherspecificity for the determination of pathological tissue in the epileptic brain. The data for this work was obtained by manual labeling and categorization of approximately 1500 sections of the stereoencephalographic record signals of patients undergoing surgical removal of the epileptic foci and subsequently monitored for success in the operation. Differences between individual groups of oscillations and resected or unresected tissues are investigated in this work by methods using calculations of entropy signals or cross frequency coupling. The most significant results were achieved for the classification group (FR + vFR) vs. uFR, methods frequency-amplitude coupling and sample entropy 1. When categorizing according to information about channel resection, the Shannon entropy is the most successful classification parameter.
Stress detection
Jindra, Jakub ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
Stress detection based on non-EEG physiological data can be useful for monitoring drivers, pilots, and also for monitoring of people in ordinary situation, where standard EEG monitoring is unsuitable. This work uses Non-EEG database freely available from Physionet. The database contains records of heart rate, saturation of blood oxygen, motion, a conductance of skin and temperature recorded for 3 type of stress alternated with relax state. Two final models were created in this thesis. First model for Binary classification stress/relax, second for classification of 4 different type of psychical state. Best results were reached using model created by decision tree algorithm with 8 features for binary classification and with 8 features for classification of 4 psychical state. Accuracy of final models is aproximately 95 % for binary model and 99 % for classification of 4 psychical state. All algorithms were implemented in Python.
ECG signal quality annotation
Waloszek, Vojtěch ; Smíšek, Radovan (referee) ; Vítek, Martin (advisor)
This thesis gives basic information summary about electrophysiology of heart and electrocardiography and overview of several signal quality assessment methods. It also presents a new method for evaluating ECG quality, shows how signal quality indices are extracted and how the quality annotation is performed. It also gives test results of how the signal quality indices reflect the presence of corresponding noise and whether the quality annotation is correct.
Detection of similarity in program codes
Maťašová, Kristýna ; Vítek, Martin (referee) ; Kašpar, Jakub (advisor)
The Bachelor introduces the concept of plagiarism and possible kinds of plagiarism. It focuses on the problem of detecting the similarity of source codes, especially with graphical interfaces in the MATLAB environment. It also describes already existing detectors. The practical part of thesis is focused on finding appropriate flags for detection of similarity in source codes and introduces the metric of detected flags. It also describes the internal logic of created detector of similarity and discusses the results of its testing.
Pedometer and fall detection
Vraňáková, Sofia ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
This work is focused on the issue of human activity sensing using inertial sensors built into intelligent devices and followed by detection of walk, detection of steps and fall from the accelerometer-scanned signal in the smartphone. The walk detection is performed by using signal envelope, a first signal difference and a standard deviation of the signal. The step detection is implemented by using the method of searching local maximum values and the customized filtering method. Fall detection is realized by using the method of searching maximum and minimum values and using the appropriate threshold values.
Classification of free living data
Rychtárik, Martin ; Vítek, Martin (referee) ; Smíšek, Radovan (advisor)
The topic of this bachelor thesis is classification of free living data, captured by the accelerometer sensor of a smart phone. The first part of the thesis deals with the possibilities of recording daily activity using accelerometer and subsequent classification by neural network. In the next section, the data of eight different daily activities were recorded on ten people. An algorithm containing a neural network was created for the data in the MATLAB programming environment to automatically identify the activities. In the last part of the work the algorithm classification was compared with manually recorded reference and the results were statistically evaluated.
Delineation of ECG signals using phasor transform
Koupil, Michal ; Vítek, Martin (referee) ; Maršánová, Lucie (advisor)
TThis project deals with delineation of ECG signals using phasor transform. This method is rather new in the field of automatic delineation of ECG and it is not widely used in practice yet. In the theoretical part, the relation between heart activity and ECG is described. A phasor transform is also described. In the practical part, a program was implemented in the computing environment of MATLAB. Its purpose is to delineate the signals. At first, it detects waves’ peaks, then its beginning and starting points. In the next part, analysis of the results is done, as well as comparison with other authors. The testing was performed on the QT signals from the Physionet database.
Plagiarism detection in programme codes
Skoupilová, Alena ; Vítek, Martin (referee) ; Kašpar, Jakub (advisor)
The main goal of this thesis is to introduce the meaning of plagiarism and its types and occuration in academic field in form of textual plagiarism and mainly source-code plagiarism. Thesis also introduces principals and types of source-code plagiarism detection and introduces existing detecting tools. A detector for computing source-code similarity based on detection and counting chosen attributes is being realized and described. Reability of the detector is tested within students’ projects database.
Noise suppression in ECG signal based on the empirical mode decomposition
Hemzalová, Zuzana ; Vítek, Martin (referee) ; Kozumplík, Jiří (advisor)
This thesis is focused on signal-filtering method based on empirici mode decomposition. The proposed EMD-based method is able power line interference to remove with minimum signal distortion.
Gait detection and step counting using smartphone
Kočendová, Kateřina ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
The focus of this thesis is the detection of walking and running, followed by a step count. Testing is performed on signals of regular daily human activity that involve sections of running, walking or no activity. Those signals are logged using accelerometer in smartphone. The exact type of physical activity performed is distinguished by an average, variation coefficient and wave transformation methods. Basics statistic methods are used to quantify the number of steps taken during either walking or running. Algorithm for activity detection and algorithm for step counting are optimized and tested by a set of signals.

National Repository of Grey Literature : 120 records found   1 - 10nextend  jump to record:
See also: similar author names
4 VÍTEK, Martin
2 Vítek, Matouš
7 Vítek, Michal
2 Vítek, Milan
3 Vítek, Miroslav
Interested in being notified about new results for this query?
Subscribe to the RSS feed.