<p>The present dissertation investigated the impact of scales / scoring methods and prompt linguistic features on the meausrement quality of L2 English elicited imitation (EI). Scales / scoring methods are an important feature for the validity and reliabilty of L2 EI test, but less is known (Yan et al., 2016). Prompt linguistic features are also known to influence EI test quaity, particularly item difficulty, but item discrimination or corpus-based, fine-grained meausres have rarely been incorporated into examining the contribution of prompt linguistic features. The current study addressed the research needs, using item response theory (IRT) and random forest modeling.</p><p>Data consisted of 9,348 oral responses to forty-eight items, including EI prompts, item scores, and rater comments, which were collected from 779 examinees of an L2 English EI test at Purdue Universtiy. First, the study explored the current and alternative EI scales / scoring methods that measure grammatical / semantic accuracy, focusing on optimal IRT-based measurement qualities (RQ1 through RQ4 in Phase Ⅰ). Next, the project identified important prompt linguistic features that predict EI item difficulty and discrimination across different scales / scoring methods and proficiency, using multi-level modeling and random forest regression (RQ5 and RQ6 in Phase Ⅱ).</p><p>The main findings were (although not limited to): 1) collapsing exact repetition and paraphrase categories led to more optimal measurement (i.e., adequacy of item parameter values, category functioning, and model / item / person fit) (RQ1); there were fewer misfitting persons with lower proficiency and higher frequency of unexpected responses in the extreme categories (RQ2); the inconsistency of qualitatively distinguishing semantic errors and the wide range of grammatical accuracy in the minor error category contributed to misfit (RQ3); a quantity-based, 4-category ordinal scale outperformed quality-based or binary scales (RQ4); sentence length significantly explained item difficulty only, with small variance explained (RQ5); Corpus-based lexical measures and phrase-level syntactic complexity were important to predicting item difficulty, particularly for the higher ability level. The findings made implications for EI scale / item development in human and automatic scoring settings and L2 English proficiency development.</p>

<div> <div> <div> <p>For pedestrians and autonomous vehicles (AVs) to co-exist harmoniously and safely in the real-world, AVs will need to not only react to pedestrian actions, but also anticipate their intentions. In this thesis, we propose to use rich visual and pedestrian-environment interaction features to improve pedestrian crossing intention prediction from the ego-view. We do so by combining visual feature extraction, graph modeling of scene objects and their relationships, and feature encoding as comprehensive inputs for an LSTM encoder-decoder network. </p> <p>Pedestrians react and make decisions based on their surrounding environment, and the behaviors of other road users around them. The human-human social relationship has already been explored for pedestrian trajectory prediction from the bird’s eye view in stationary cameras. However, context and pedestrian-environment relationships are often missing in current research into pedestrian trajectory, and intention prediction from the ego-view. To map the pedestrian’s relationship to its surrounding objects we use a star graph with the pedestrian in the center connected to all other road objects/agents in the scene. The pedestrian and road objects/agents are represented in the graph through visual features extracted using state of the art deep learning algorithms. We use graph convolutional networks, and graph autoencoders to encode the star graphs in a lower dimension. Using the graph en- codings, pedestrian bounding boxes, and human pose estimation, we propose a novel model that predicts pedestrian crossing intention using not only the pedestrian’s action behaviors (bounding box and pose estimation), but also their relationship to their environment. </p> <p>Through tuning hyperparameters, and experimenting with different graph convolutions for our graph autoencoder, we are able to improve on the state of the art results. Our context- driven method is able to outperform current state of the art results on benchmark dataset Pedestrian Intention Estimation (PIE). The state of the art is able to predict pedestrian crossing intention with a balanced accuracy (to account for dataset imbalance) score of 0.61, while our best performing model has a balanced accuracy score of 0.79. Our model especially outperforms in no crossing intention scenarios with an F1 score of 0.56 compared to the state of the art’s score of 0.36. Additionally, we also experiment with training the state of the art model and our model to predict pedestrian crossing action, and intention jointly. While jointly predicting crossing action does not help improve crossing intention prediction, it is an important distinction to make between predicting crossing action versus intention.</p> </div> </div> </div>

Studien fick en förståelse över hur Greta Thunberg har blivit representerad i de utvalda svenska nyhetstidningarna (Dagens Nyheter &amp; Aftonbladet), vilka karaktärsdrag som tillskrivits henne och vilka värderingar som använts om henne. Frågeställningarna har varit; Hur ser representationen av Greta Thunberg ut i svenska nyhetstidningar? Vilka värderingar finns det i texten? Vilka karaktärsdrag används om Greta Thunberg? Texterna har analyserats genom representationsteorin av Stuart Hall och gestaltningfunktioner av Vladimir Propp och metoden som användes var en kvalitativ innehållsanalys. Studien fann att Greta Thunberg har blivit representerad både på ett positivt och negativt sätt, hon stereotypiseras och tillskrivs en hel del karaktärsdrag genom värderingar utöver de tre som studien har valt att fokusera på. / The aim of the study is to get an understanding of how Greta Thunberg was represented in the Swedish newspapers (Dagens Nyheter &amp; Aftonbladet), what characteristic features that was given to her and the values used about her. The framing of questions is: How is the representation of Greta Thunberg in Swedish newspapers? What values can be seen in the text? What characteristic features are given to Greta Thunberg? The  representation theory of Stuart Hall  and Vlademir Propp's design features was used and qualitative content analysis for helping discover these things. The Study found that Greta Thunberg has been represented in both a positive and a negative way in the chosen written media. She is stereotyped and has been given more characteristic features than this study has chosen to focus on.

This thesis deals with the image object detection using Haar--like features and AdaBoost algorithm. The text describes methods how to train and test an object detector. The main contributon of this thesis consists in creation image object detector in Java programming language. Created algorithms were integrated as plugin into the RapidMiner tool, which is widely used and known worldwide as tool for data mining. The thesis contains the instructions for created operators and few exaples for executing in RapidMiner tool. The functionality of image object detector was demonstrated on selected medical images.

Diploma’s thesis is focused on determining person’s height from spoken utterance. First part of the work evaluates present situation and refers to the published studies. Knowledge gained in these studies was used in this thesis. Study with the best results according to estimated height of the speakers was chosen. The experiment realized in the chosen study was performed in this work. The system for the estimation of the height of the speakers based on the speech signal was created. This system was successfully tested by using several acoustic features on spoken utterances from TIMIT database.

This work deals with analysis of phonation in patients with Parkinson’s disease (PD). Approximately 90% of patients with Parkinson’s disease suffer from speech motor dysfunction called hypokinetic dysarthria. System for Parkinson’s disease analysis from speech signals is proposed and several types of features are examined. Czech Parkinson’s speech database called PARCZ is used for classification. This dataset consists of 84 PD patients and 49 healthy controls. Results are evaluated in two ways. Firstly, features are individually analysed by Spearman correlation, mutual information and Mann-Whitney U test. Classification is based on random forests along with leave-one-out validation. Secondly, SFFS algorithm is employed for feature selection in order to get the best classification result. Proposed system is tested for each gender individually and both genders together as well. Best result for both genders together is expressed by accuracy 89,47 %, sensitivity 91,67% and specificity 85,71 %. Results of this work showed that the most important vowel realizations for phonation analysis are sustained vowels pronounced with maximum or minimum intensity (not whispering).

This work deals with medical image analysis, using variety of statisic and numeric methods implemented in Eclipse and Rapidminer environments in Java programming language. Sets of images (slices), which are used here, are the results of magnetic resonance brain examination of several subejcts. Segments in this 3D image are analyzed and some local features are computed, based on which data sets for use in training algorythms are generated. The ability of successful identification of healthy or unhealthy tissues is then practically tested using available data.

This paper describes the manifestations of ischemia in the ECG signals and summarizes some methods allowing automatic detection of ischemia. Morphological features were then calculated from ECG signals available from UBMI and statistically evaluated to select features appropriate for further automatic classification. Multilayer feedforward neural network was used for classification of heart beats. The neural network was designed in Matlab. Classification performance up to 99.9% was obtained on available dataset.

This thesis focuses on modification of feature extraction and multiview object detection learning process. We add new channels to detectors based on the "Aggregate channel features" framework. These new channels are created by filtering the picture by kernels from autoencoders followed by nonlinear function processing. Experiments show that these channels are effective in detection but they are also more computationally expensive. The thesis therefore discusses possibilities for improvements. Finally the thesis evaluates an artificial car dataset and discusses its small benefit on several detectors.

Tato práce popisuje systém pro sledování obrazovky počítače v reálném čase a určení pozice uživatelova pohledu na tuto obrazovku s využitím dat z eye-trackovacích brýlí a Uniform Marker Fields. Vytvořený systém lokalizuje obrazovku počítače ve snímcích z kamery umístěné na eye-trackeru snímající scénu před uživatelem. V této scéně je detekován marker zobrazený na monitoru počítače. Po jeho úspěšné detekci je marker skryt a ke sledování pozice obrazovky jsou dále využívány významné body detekované ve snímku z kamery ležící na obrazovce, případně z celého snímku. Pokud sledování významných bodů selže, marker je znovu zobrazen a systém je znovu inicializován pomocí detekovaného markeru. Aby byl marker pro uživatele co nejméně nápadný a obtěžující, jsou využity data z eye-trackeru k tomu, aby byl marker zobrazen co nejdále od oblasti uživatelova zájmu. Pro vyhodnocení výkonu a přesnosti vytvořeného systému a rušivosti markeru pro uživatele bylo provedeno několik experimentů a testování s uživateli.