This thesis presents a procedure to collect, process, and analyse data for use in machine learning models within the rifle marksmanship domain. The machine learning model, features, and analysis presented in this thesis provide a first step towards models that can provide automated assistance for rifle marksmanship practice.A quasi-experiment is designed with eye movement and rifle handling as independent variables, and shooting result as dependent variable. The data is collected by letting 14 participants with different levels of marksmanship experience perform a rifle shooting exercise. Eye movement data is gathered using a Tobii Pro Glasses 3 eye tracker, and rifle handling data is gathered using an iCubeX Orient3D IMU. Analysis from the data shows a stratification of participant rifle marksmanship experience into five classes. The highest performing group, to a larger degree than the other groups, aimed with both eyes open, has a faster rifle acceleration, has a lower time between peak motion and shot, and are overall more consistent with their shots. A prototype random forest classification model trained to predict these classes shows a Cohen’s Kappa of 0.526, balanced accuracy of 0.599 and a one-vs-all AUC between 0.83 and 0.95 for the classes.

The theoretical part of this thesis deals with the description of sensory processes, human eye and visual perception. The following are traffic participant and get data using the method of eye tracking. The practical part consisted in the evaluation of driving video recordings describing the driver's observation. The frequency and length of the pedestrian observation was evaluated, and the graphical processing was performed depending on whether the pedestrian actually crossed the road or simulated walking on the side of the roadway.

Eye tracking is an increasingly more popular research method in software engineering and can be used to study how programmers process and comprehend source code. This study investigated the possibility to perform such studies remotely with the use of eye-tracking algorithms and consumer grade webcams. A practical experiment was set up to remotely gather gaze-data from programmers. Several processing steps were applied to the gaze-data to establish the adequacy of the procedure. Two main problems with the webcam eye-tracking technology were found. The first was the lack of a fixation detection algorithm developed specifically for low frequency webcam data. This makes isolation of eye-movements more difficult and the results possibly unreliable. The second was the lack of support for dealing with head movements when predicting the gaze-position. Online experiments are unsupervised and there is no guarantee a subject will keep their head still even if instructed to do so. This was thought to be the reason behind spatial shifts observed within the collected datasets. Positive trends in the data were also identified. Like the consistent dispersions of gaze-points, and certain recognisable reading trends. While deemed unsuited for the task. Ultimately, the positive trends provided optimism for the technology to be usable to study code reading in the future.

This thesis deals with influence of advertisements on driver´s attention. Within the theoretical part are summarize findings in field of influence of advertisements on driver´s attention, it also clarified the idea of recording driver´s eye movement, which were used during the measurement. The analytical part draws from video records with driving tests provided by the Institute of Forensic Engineering of Brno University of Technology. Obtained data were processed and analyze in order to determine the durations of views on advertising devices in area of roads.

The dissertation thesis is concentrated on newsletter creation and its productivity evaluation. According to the information analysis from the field of email marketing, advertisement psychology and other knowledge, new proposals of new newsletter have been developed. These proposals went through testing using eye cameras - the eye tracking. Out of the partial proposals has been made a final newsletter which was sent out to customers by the company and the results have been evaluated in comparison with the previous one. The thesis also serves as a guideline for companies working on newsletter creation and its use.

Pervasive computing sa zameriava odstránenie zložitostí pri interakcii s výpočtovou technikou a zvýšenie efektivity pri jej každodennom používaní. Ale i po viac ako 15 rokoch od sformulovania hlavných cieľov Pervasive computingu existujú aspekty interakcie ktoré stále nie sú súčasťou užívateľskej skúsenosti s dnešnou technológiou. Bezproblémová integrácia s prostredím vedúca k technologickej neviditeľnosti, alebo interakcia naprieč rôznymi zariadeniami predstavujú stále veľkú výzvu. Hlavným cieľom tejto práce je prispieť k tomu, aby sa ciele Pervasive computingu priblížili k realizovaniu tým, že predstavíme spôsob intuitívneho zdieľania informácií medzi osobným a verejne umiestneným zariadením. Predstavili sme tri interakčné techniky, ktoré podporujú intuitívnu výmenu obsahu medzi osobným zariadením a zdieľaným displejom. Tieto techniky sú založené na prenose videa, rozšírenej realite a analýze pohľadových dát. Okrem interakčných techník sme tiež predstavili mechanizmus pre získavanie, prenos a rekonštrukciu aplikačného stavu na cieľovom zariadení.

The process of locating moving objects through video sequences is a fundamental computer vision problem. This process is referred to as video tracking and has a broad range of applications. Even though video tracking is an open research topic that have received much attention during recent years, developing accurate and robust algorithms that can handle complicated tracking tasks and scenes is still challenging. One challenge in computer vision is to develop systems that like humans can understand, interpret and recognize visual information in different situations. In this master thesis work, a tracking algorithm based on eye tracking data is proposed. The aim was to compare the tracking performance of the proposed algorithm with a state-of-the-art video tracker. The algorithm was tested on gaze signals from five participants recorded with an eye tracker while the participants were exposed to dynamic stimuli. The stimuli were moving objects displayed on a stationary computer screen. The proposed algorithm is working offline meaning that all data is collected before analysis. The results show that the overall performance of the proposed eye tracking algorithm is comparable to the performance of a state-of-the-art video tracker. The main weaknesses are low accuracy for the proposed eye tracking algorithm and handling of occlusion for the video tracker. We also suggest a method for using eye tracking as a complement to object tracking methods. The results show that the eye tracker can be used in some situations to improve the tracking result of the video tracker. The proposed algorithm can be used to help the video tracker to redetect objects that have been occluded or for some other reason are not detected correctly. However, ATOM brings higher accuracy.

Language is a multimodal process with visual and auditory cues playing important roles in understanding speech. A well-controlled paradigm with audiovisually matched and mismatched syllables is often used to capture audiovisual (AV) speech processing. The ability to detect and integrate mismatching cues shows large individual variability across development and is linked to later language in typical development (TD) and social abilities in autism spectrum disorder (ASD). However, no study has used a multimethod approach to better understand AV speech processing in early development. The studies’ aims were to examine behavioral performance, gaze patterns, and neural indices of AV speech in: 1) TD preschoolers (N=60; females=35) and 2) infants at risk for developing ASD (high-risk, HR; N=37; females=10) and TD controls (low-risk, LR; N=42; females=21). In Study 1, I investigated preschoolers’ gaze patterns and behavioral performance when presented with matched and mismatched AV speech and visual-only (lipreading) speech. As hypothesized, lipreading abilities were associated with children’s ability to integrate mismatching AV cues, and children looked towards the mouth when visual cues were helpful, specifically in lipreading conditions. Unexpectedly, looking time towards the mouth was not associated with the children’s ability to integrate mismatching AV cues. Study 2 examined how visual cues of AV speech modulated auditory event-related potentials (ERPs), and associations between ERPs and preschoolers’ behavioral performance during an AV speech task. As hypothesized, the auditory ERPs were attenuated during AV speech compared to auditory-only speech. Additionally, individual differences in their neural processing of auditory and visual cues predicted which cue the child attended to in mismatched AV speech. In Study 3, I investigated ERPs of AV speech in LR and HR 12-month-olds and their association with language abilities at 18-months. Unexpectedly, I found no group differences: all infants were able to detect mismatched AV speech as measured through a more negative ERP response. As hypothesized, more mature neural processing of AV speech integration, measured as a more positive ERP response to fusible AV cues, predicted later language across all infants. These results highlight the importance of using multimethod approaches to understand variability in AV speech processing at two developmental stages. / 2021-11-12T00:00:00Z

According to the seductive details (SD) effect, interesting, but irrelevant information in learning materials reduces learning outcomes. Basic research suggests that subjects in positive mood are more distractible by task‐irrelevant stimuli than subjects in negative mood. Hence, mood could moderate the SD effect. We tested this assumption by comparing eye movements to seductive pictures in participants in positive versus negative mood. As expected, participants in positive mood fixated pictures longer and more frequently than participants in negative mood, which can be interpreted in terms of mood‐based higher distractibility. However, this did not translate to a more pronounced SD effect in the learning test. Unexpectedly, there was no SD effect in either mood condition. We discuss implications of the eye‐tracking data as well as potential reasons for the nonexistent SD effect in our study.

Night eating syndrome (NES) is characterized by excessive evening and/or nocturnal eating episodes. Studies indicate an attentional bias towards food in other eating disorders. For NES, however, evidence of attentional food processing is lacking. Attention towards food and non-food stimuli was compared using eye-tracking in 19 participants with NES and 19 matched controls without eating disorders during a free exploration paradigm and a visual search task. In the free exploration paradigm, groups did not differ in initial fixation position or gaze duration. However, a significant orienting bias to food compared to non-food was found within the NES group, but not in controls. A significant attentional maintenance bias to non-food compared to food was found in both groups. Detection times did not differ between groups in the search task. Only in NES, attention to and faster detection of non-food stimuli were related to higher BMI and more evening eating episodes. The results might indicate an attentional approach-avoidance pattern towards food in NES. However, further studies should clarify the implications of attentional mechanisms for the etiology and maintenance of NES.