• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 20
  • 5
  • 4
  • 4
  • 4
  • 3
  • 3
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • Tagged with
  • 54
  • 54
  • 11
  • 10
  • 9
  • 7
  • 7
  • 7
  • 6
  • 6
  • 6
  • 6
  • 6
  • 5
  • 5
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
51

Self-calibrating eye tracker using imagesaliency : Självkalibrerande ögonspårare medhjälp av image saliency / Självkalibrerande ögonspårare medhjälp av image saliency : Self-calibrating eye tracker using imagesaliency

Vega, Gabriel January 2022 (has links)
Self-calibrating eye tracker using image saliency. / Självkalibrerande ögonspårare med hjälp av image saliency.
52

Real-Time Pupillary Analysis By An Intelligent Embedded System

Hasanzadeh, Mujtaba, Hengl, Alexandra January 2019 (has links)
With no online pupillary analysis methods today, both the medical and the research fields are left to carry out a lengthy, manual and often faulty examination. A real-time, intelligent, embedded systems solution to pupillary analysis would help reduce faulty diagnosis, speed-up the analysis procedure by eliminating the human expert operator and in general, provide a versatile and highly adaptable research tool. Therefore, this thesis has sought to investigate, develop and test possible system designs for pupillary analysis, with the aim for caffeine detection. A pair of LED manipulator glasses have been designed to standardize the illumination method across testing. A data analysis method of the raw pupillary data has been established offline and then adapted to a real-time platform. ANN was chosen as classification algorithm. The accuracy of the ANN from the offline analysis was 94% while for the online classification the obtained accuracy was 17%. A realtime data communication and synchronization method has been developed. The resulting system showed reliable and fast execution times. Data analysis and classification took no longer than 2ms, faulty data detection showed consistent results. Data communication suffered no message loss. In conclusion, it is reported that a real-time, intelligent, embedded solution is feasible for pupillary analysis.
53

Détection et amélioration de l'état cognitif de l'apprenant

Ghali, Ramla 12 1900 (has links)
Cette thèse vise à détecter et améliorer l’état cognitif de l’apprenant. Cet état est défini par la capacité d’acquérir de nouvelles connaissances et de les stocker dans la mémoire. Nous nous sommes essentiellement intéressés à améliorer le raisonnement des apprenants, et ceci dans trois environnements : environnement purement cognitif Logique, jeu sérieux LewiSpace et jeu sérieux intelligent Inertia. La détection de cet état se fait essentiellement par des mesures physiologiques (en particulier les électroencéphalogrammes) afin d’avoir une idée sur les interactions des apprenants et l’évolution de leurs états mentaux. L’amélioration des performances des apprenants et de leur raisonnement est une clé pour la réussite de l’apprentissage. Dans une première partie, nous présentons l’implémentation de l’environnement cognitif logique. Nous décrivons des statistiques faites sur cet environnement. Nous avons collecté durant une étude expérimentale les données sur l’engagement, la charge cognitive et la distraction. Ces trois mesures se sont montrées efficaces pour la classification et la prédiction des performances des apprenants. Dans une deuxième partie, nous décrivons le jeu Lewispace pour l’apprentissage des diagrammes de Lewis. Nous avons mené une étude expérimentale et collecté les données des électroencéphalogrammes, des émotions et des traceurs de regard. Nous avons montré qu’il est possible de prédire le besoin d’aide dans cet environnement grâce à ces mesures physiologiques et des algorithmes d’apprentissage machine. Dans une troisième partie, nous clôturons la thèse en présentant des stratégies d’aide intégrées dans un jeu virtuel Inertia (jeu de physique). Cette dernière s’adapte selon deux mesures extraites des électroencéphalogrammes (l’engagement et la frustration). Nous avons montré que ce jeu permet d’augmenter le taux de réussite dans ses missions, la performance globale et par conséquent améliorer l’état cognitif de l’apprenant. / This thesis aims at detecting and enhancing the cognitive state of a learner. This state is measured by the ability to acquire new knowledge and store it in memory. Focusing on three types of environments to enhance reasoning: environment Logic, serious game LewiSpace and intelligent serious game Inertia. Physiological measures (in particular the electroencephalograms) have been taken in order to measure learners’ engagement and mental states. Improving learners’ reasoning is key for successful learning process. In a first part, we present the implementation of logic environment. We present statistics on this environment, with data collected during an experimental study. Three types of data: engagement, workload and distraction, these measures were effective and can predict and classify learner’s performance. In a second part, we describe the LewiSpace game, aimed at teaching Lewis diagrams. We conducted an experimental study and collected data from electroencephalograms, emotions and eye-tracking software. Combined with machine learning algorithms, it is possible to anticipate a learner’s need for help using these data. In a third part, we finish by presenting some assistance strategies in a virtual reality game called Inertia (to teach Physics). The latter adapts according to two measures extracted from electroencephalograms (frustration and engagement). Based on our study, we were able to enhance the learner’s success rate on game missions, by improving its cognitive state.
54

Využití kvalitativního a kvantitativního výzkumu pro tvorbu následné marketingové strategie u tištěných medií / Aplication of quality and quantity data outputs of research to be used for follow up marketing strategy in print medias

Hofmannová, Vlasta January 2008 (has links)
Diploma thesis entitled "Application of Qualitative and Quantitative Research Methods into Marketing Strategy of Print Medias" discusses employment of output research data accumulated on eye-tracking, in-depth interviewing and CAWI method of research. These research outcomes are further analyzed and implemented in the development process of the EURO Business Weekly strategy in the Czech publishing market. The final evaluation is based on a mutual comparison of results which were recorded by the EURO Business Weekly in the years 2005 and 2006.

Page generated in 0.049 seconds