This thesis deals with CT data segmentation using convolutional neural nets and describes the problem of training with limited training sets. User interaction is suggested as means of improving segmentation quality for the models trained on small training sets and the possibility of using transfer learning is also considered. All of the chosen methods help improve the segmentation quality in comparison with the baseline method, which is the use of automatic data specific segmentation model. The segmentation has improved by tens of percents in Dice score when trained with very small datasets. These methods can be used, for example, to simplify the creation of a new segmentation dataset.

<div>With more and more videos taken from dash cams on thousands of cars, retrieving these videos and searching for important information is a daunting task. The purpose of this work is to mine some key road and vehicle motion attributes in a large-scale driving video data set for traffic analysis, sensing algorithm development and autonomous driving test benchmarks. Current sensing and control of autonomous cars based on full-view identification makes it difficult to maintain a high-frequency with a fast-moving vehicle, since computation is increasingly used to cope with driving environment changes.</div><div><br></div><div>A big challenge in video data mining is how to deal with huge amounts of data. We use a compact representation called the road profile system to visualize the road environment in long 2D images. It reduces the data from each frame of image to one line, thereby compressing the video clip to the image. This data dimensionality reduction method has several advantages: First, the data size is greatly compressed. The data is compressed from a video to an image, and each frame in the video is compressed into a line. The data size is compressed hundreds of times. While the size and dimensionality of the data has been compressed greatly, the useful information in the driving video is still completely preserved, and motion information is even better represented more intuitively. Because of the data and dimensionality reduction, the identification algorithm computational efficiency is higher than the full-view identification method, and it makes the real-time identification on road is possible. Second, the data is easier to be visualized, because the data is reduced in dimensionality, and the three-dimensional video data is compressed into two-dimensional data, the reduction is more conducive to the visualization and mutual comparison of the data. Third, continuously changing attributes are easier to show and be captured. Due to the more convenient visualization of two-dimensional data, the position, color and size of the same object within a few frames will be easier to compare and capture. At the same time, in many cases, the trouble caused by tracking and matching can be eliminated. Based on the road profile system, there are three tasks in autonomous driving are achieved using the road profile images.</div><div><br></div><div>The first application is road edge detection under different weather and appearance for road following in autonomous driving to capture the road profile image and linearity profile image in the road profile system. This work uses naturalistic driving video data mining to study the appearance of roads, which covers large-scale road data and changes. This work excavated a large number of naturalistic driving video sets to sample the light-sensitive area for color feature distribution. The effective road contour image is extracted from the long-time driving video, thereby greatly reducing the amount of video data. Then, the weather and lighting type can be identified. For each weather and lighting condition obvious features are I identified at the edge of the road to distinguish the road edge. </div><div><br></div><div>The second application is detecting vehicle interactions in driving videos via motion profile images to capture the motion profile image in the road profile system. This work uses visual actions recorded in driving videos taken by a dashboard camera to identify this interaction. The motion profile images of the video are filtered at key locations, thereby reducing the complexity of object detection, depth sensing, target tracking and motion estimation. The purpose of this reduction is for decision making of vehicle actions such as lane changing, vehicle following, and cut-in handling.</div><div><br></div><div>The third application is motion planning based on vehicle interactions and driving video. Taking note of the fact that a car travels in a straight line, we simply identify a few sample lines in the view to constantly scan the road, vehicles, and environment, generating a portion of the entire video data. Without using redundant data processing, we performed semantic segmentation to streaming road profile images. We plan the vehicle's path/motion using the smallest data set possible that contains all necessary information for driving.</div><div><br></div><div>The results are obtained efficiently, and the accuracy is acceptable. The results can be used for driving video mining, traffic analysis, driver behavior understanding, etc.</div>

This work deals with the text-dependent speaker recognition in systems, where just a few training samples exist. For the purpose of this recognition, the voice imprint based on different features (e.g. MFCC, PLP, ACW etc.) is proposed. At the beginning, there is described the way, how the speech signal is produced. Some speech characteristics important for speaker recognition are also mentioned. The next part of work deals with the speech signal analysis. There is mentioned the preprocessing and also the feature extraction methods. The following part describes the process of speaker recognition and mentions the evaluation of the used methods: speaker identification and verification. Last theoretically based part of work deals with the classifiers which are suitable for the text-dependent recognition. The classifiers based on fractional distances, dynamic time warping, dispersion matching and vector quantization are mentioned. This work continues by design and realization of system, which evaluates all described classifiers for voice imprint based on different features.

This master’s thesis describes the design and implementation of the application that created the basis set pieces "puzzle" according to the shape of the folded edges of the original image. This application is developed using Matlab. The work also describes how to create a database of actual pieces of the puzzle composite photo image. Closer was also focused on finding the characteristic section points, their segmentation and appropriate description. There is dismantled procedure for selecting the types of symptoms and their extraction. On the basis of suitably described pieces of segmented parts is designed and implemented the algorithm of comparing and grouping into clusters. Using the proposed method of visualization is then displayed in the resulting composite picture puzzle.

This master’s thesis describes the design and implementation of the application that created the basis set pieces "puzzle" according to the shape of the folded edges of the original image. This application is developed using Matlab. The work also describes how to create a database of actual pieces of the puzzle composite photo image. Closer was also focused on finding the characteristic section points, their segmentation and appropriate description. There is dismantled procedure for selecting the types of symptoms and their extraction. On the basis of suitably described pieces of segmented parts is designed and implemented the algorithm of comparing and grouping into clusters. Using the proposed method of visualization is then displayed in the resulting composite picture puzzle.

Tato práce popisuje problematiku návrhu a vývoje aplikace pro rekonstrukci 3D modelů z 2D obrazových dat, označované jako bundle adjustment. Práce analyzuje proces 3D rekonstrukce a důkladně popisuje jednotlivé kroky. Prvním z kroků je automatizované získání obrazové sady z internetu. Je představena sada skriptů pro hromadné stahování obrázků ze služeb Flickr a Google Images a shrnuty požadavky na tyto obrázky pro co nejlepší 3D rekonstrukci. Práce dále popisuje různé detektory, extraktory a párovací algoritmy klíčových bodů v obraze s cílem najít nejvhodnější kombinaci pro rekonstrukci budov. Poté je vysvětlen proces rekonstrukce 3D struktury, její optimalizace a jak je tato problematika realizovaná v našem programu. Závěr práce testuje výsledky získané z implementovaného programu pro několik různých datových sad a porovnává je s výsledky ostatních podobných programů, představených v úvodu práce.

In my thesis, I focus on the task of recognizing human iris from an image.In the beginning, the work deals with a question of biometrics, its importance and basic concepts, which are necessary for use in following text. Subsequently process of human Iris detection is described together with theory of evolution algorithms. In the implementation part, is described the design of implemented solution, which uses evolution algorithms, where is emphasis on correct pupil and iris boundary detection.

Keyword spotting is one of the many applications of automatic speech recognition. Its purpose is determining spots in given utterance in which some of the specified words were spoken. Keyword spotting has a great potential to enhance performance of new applications as well as the existing ones. An example could be a mobile phone voice control. Due to OS Symbian's coming to the market it is even possible for end user to implement a keyword spotting for a mobile phone on his or her own. The thesis describes theoretical prerequisites for keyword spotting and its implementation. Firstly the OS Symbian is presented with respect to the given task. Secondly each step of keyword spotting process is described. Finally the object design of keyword spotter is presented followed by implementation description. The thesis concludes with results review and notes on possible improvements.

<p>A wide range of optoelectronic applications demand semiconductors optimized for purpose.</p> <p>My research focused on data-driven identification of ABX3 Halide perovskite compositions for optimum photovoltaic absorption in solar cells.</p> <p>I trained machine learning models on previously reported datasets of halide perovskite band gaps based on first principles computations performed at different fidelities.</p> <p>Using these, I identified mixtures of candidate constituents at the A, B or X sites of the perovskite supercell which leveraged how mixed perovskite band gaps deviate from the linear interpolations predicted by Vegard's law of mixing to obtain a selection of stable perovskites with band gaps in the ideal range of 1 to 2 eV for visible light spectrum absorption.</p> <p>These models predict the perovskite band gap using the composition and inherent elemental properties as descriptors.</p> <p>This enables accurate, high fidelity prediction and screening of the much larger chemical space from which the data samples were drawn.</p> <p><br></p> <p>I utilized a recently published density functional theory (DFT) dataset of more than 1300 perovskite band gaps from four different levels of theory, added to an experimental perovskite band gap dataset of \textasciitilde{}100 points, to train random forest regression (RFR), Gaussian process regression (GPR), and Sure Independence Screening and Sparsifying Operator (SISSO) regression models, with data fidelity added as one-hot encoded features.</p> <p>I found that RFR yields the best model with a band gap root mean square error of 0.12 eV on the total dataset and 0.15 eV on the experimental points.</p> <p>SISSO provided compound features and functions for direct prediction of band gap, but errors were larger than from RFR and GPR.</p> <p>Additional insights gained from Pearson correlation and Shapley additive explanation (SHAP) analysis of learned descriptors suggest the RFR models performed best because of (a) their focus on identifying and capturing relevant feature interactions and (b) their flexibility to represent nonlinear relationships between such interactions and the band gap.</p> <p>The best model was deployed for predicting experimental band gap of 37785 hypothetical compounds.</p> <p>Based on this, we identified 1251 stable compounds with band gap predicted to be between 1 and 2 eV at experimental accuracy, successfully narrowing the candidates to about 3% of the screened compositions.</p>

Radar signals are used for estimating location, speed and direction of an object. Some radars emit pulses, while others emit a continuous wave. Both types of radars emit signals according to some pattern; a pulse radar, for example, emits pulses with a specific time interval between pulses. This time interval may either be stable, change linearly, or follow some other pattern. The interval between two emitted pulses is often referred to as the pulse repetition interval (PRI), and the pattern that defines the PRI is often referred to as the modulation. Classifying which PRI modulation is used in a radar signal is a crucial component for the task of identifying who is emitting the signal. Incorrectly classifying the used modulation can lead to an incorrect guess of the identity of the agent emitting the signal, and can as a consequence be fatal. This work investigates how a long short-term memory (LSTM) neural network performs compared to a state of the art feature extraction neural network (FE-MLP) approach for the task of classifying PRI modulation. The results indicate that the proposed LSTM model performs consistently better than the FE-MLP approach across all tested noise levels. The downside of the proposed LSTM model is that it is significantly more complex than the FE-MLP approach. Future work could investigate if the LSTM model is too complex to use in a real world setting where computing power may be limited. Additionally, the LSTM model can, in a trivial manner, be modified to support more modulations than those tested in this work. Hence, future work could also evaluate how the proposed LSTM model performs when support for more modulations is added. / Radarsignaler används för att uppskatta plats, hastighet och riktning av objekt. Vissa radarer sänder ut signaler i form av pulser, medan andra sänder ut en kontinuerlig våg. Båda typer av radarer avger signaler enligt ett visst mönster, till exempel avger en pulsradar pulser med ett specifikt tidsintervall mellan pulserna. Detta tidsintervall kan antingen vara konstant, förändras linjärt, eller följa ett annat mönster. Intervallet mellan två pulser benämns ofta pulsrepetitionsintervall (PRI), och mönstret som definierar PRIn benämns ofta modulering. Att klassificera vilken PRI-modulering som används i en radarsignal är en viktig del i processen att identifiera vem som skickade ut signalen. Felaktig klassificering av den använda moduleringen kan leda till en felaktig gissning av identiteten av agenten som skickade ut signalen, vilket kan leda till ett dödligt utfall. Detta arbete undersöker hur väl det framtagna neurala nätverket som består av ett långt korttidsminne (LSTM) kan klassificera PRI-modulering i förhållande till en modern modell som använder särskilt utvalda beräknade särdrag från data och klassificerar dessa särdrag med ett neuralt nätverk. Resultaten indikerar att LSTM-modellen konsekvent klassificerar med högre träffsäkerhet än modellen som använder särdrag, vilket gäller för alla testade brusnivåer. Nackdelen med LSTM-modellen är att den är mer komplex än modellen som använder särdrag. Framtida arbete kan undersöka om LSTM-modellen är för komplex för att använda i ett verkligt scenario där beräkningskraften kan vara begränsad. Dessutom skulle framtida arbete kunna utvärdera hur väl LSTM-modellen kan klassificera PRI-moduleringar när stöd för fler moduleringar än de som testats i detta arbete läggs till, detta då stöd för ytterligare PRI-moduleringar kan läggas till i LSTM-modellen på ett trivialt sätt.