Diss. (sammanfattning) Stockholm : Karolinska institutet, 2006. / Härtill 5 uppsatser.

1 Title: Mining Physiological Data for Automated Educational Feedback Author: Bc. Kateřina Bašátková Department: Department of Physics Education Supervisor: doc. RNDr. Zdena Lustigová, CSc., Department of Physics Education Abstract: This thesis deals with mining physiological data for automated educational feedback. The first part summarizes former researches of physiological data and its assertation into human behaviour. Special attention is devoted especially to eye tracking and measuring heart rate during behavioral processes. The second part is dedicated to author's own research how blink rate and heart rate are influenced by the degree of cognitive load. The research was executed on six subjects. The obtained data confirm correlation of blink rate and heart rate with the difficulty of the task. Keywords: heart rate, heart rate variability, blink rate, cognitive load

The last advancements in technology leads to an easy acquisition and spreading of multi-dimensional multimedia content, e.g. videos, which in many cases depict human faces. From such videos, valuable information describing the intrinsic characteristic of the recorded user can be retrieved: the features extracted from the facial patch are relevant descriptors that allow for the measurement of subject's emotional status or the identification of synthetic characters. One of the emerging challenges is the development of contactless approaches based on face analysis aiming at measuring the emotional status of the subject without placing sensors that limit or bias his experience. This raises even more interest in the context of Quality of Experience (QoE) measurement, or the measurement of user emotional status when subjected to a multimedia content, since it allows for retrieving the overall acceptability of the content as perceived by the end user. Measuring the impact of a given content to the user can have many implications from both the content producer and the end-user perspectives. For this reason, we pursue the QoE assessment of a user watching multimedia stimuli, i.e. 3D-movies, through the analysis of his facial features acquired by means of contactless approaches. More specifically, the user's Heart Rate (HR) was retrieved by using computer vision techniques applied to the facial recording of the subject and then analysed in order to compute the level of engagement. We show that the proposed framework is effective for long video sequences, being robust to facial movements and illumination changes. We validate it on a dataset of 64 sequences where users observe 3D movies selected to induce variations in users' emotional status. From one hand understanding the interaction between the user's perception of the content and his cognitive-emotional aspects leads to many opportunities to content producers, which may influence people's emotional statuses according to needs that can be driven by political, social, or business interests. On the other hand, the end-user must be aware of the authenticity of the content being watched: advancements in computer renderings allowed for the spreading of fake subjects in videos. Because of this, as a second challenge we target the identification of CG characters in videos by applying two different approaches. We firstly exploit the idea that fake characters do not present any pulse rate signal, while humans' pulse rate is expressed by a sinusoidal signal. The application of computer vision techniques on a facial video allows for the contactless estimation of the subject's HR, thus leading to the identification of signals that lack of a strong sinusoidality, which represent virtual humans. The proposed pipeline allows for a fully automated discrimination, validated on a dataset consisting of 104 videos. Secondly, we make use of facial spatio-temporal texture dynamics that reveal the artefacts introduced by computer renderings techniques when creating a manipulation, e.g. face swapping, on videos depicting human faces. To do so, we consider multiple temporal video segments on which we estimated multi-dimensional (spatial and temporal) texture features. A binary decision of the joint analysis of such features is applied to strengthen the classification accuracy. This is achieved through the use of Local Derivative Patterns on Three Orthogonal Planes (LDP-TOP). Experimental analyses on state-of-the-art datasets of manipulated videos show the discriminative power of such descriptors in separating real and manipulated sequences and identifying the creation method used. The main finding of this thesis is the relevance of facial features in describing intrinsic characteristics of humans. These can be used to retrieve significant information like the physiological response to multimedia stimuli or the authenticity of the human being itself. The application of the proposed approaches also on benchmark dataset returned good results, thus demonstrating real advancements in this research field. In addition to that, these methods can be extended to different practical application, from the autonomous driving safety checks to the identification of spoofing attacks, from the medical check-ups when doing sports to the users' engagement measurement when watching advertising. Because of this, we encourage further investigations in such direction, in order to improve the robustness of the methods, thus allowing for the application to increasingly challenging scenarios.

Diss. (sammanfattning) Stockholm : Karolinska institutet, 2007. / Härtill 5 uppsatser.

Emotions are an integral part of the human experience and their interpretation can provide valuable but also misleading clues about oneself and other people’s state of mind. Negative emotional states can be perceived as uncomfortable and – when experienced chronically – can develop into anxiety and mood disorders. The more pervasive these disorders the more severely they affect and disable a person’s everyday functioning and often their sleep as well. According to Lang and colleagues (1998), emotions may be expressed verbally, behaviorally, and physiologically, i.e., emotions can be reported, observed, and objectively measured. Each measurement approach provides important, unique, and often conflicting information that can be used in the assessment and treatment evaluation of psychological disorders affecting the emotions. Autonomic measures have been used to indicate the physiological components of emotions, such as those along the worry-anxiety-fear-panic spectrum. Worry has been shown to suppress cardiac responses to imaginal feared material (see Borkovec, Alcaine, & Behar, 2004) and reduce autonomic variability (Hoehn-Saric, McLeod, Funderburk, & Kowalski, 2004; Hoehn-Saric, McLeod, & Zimmerli, 1989). Results for panic and anticipatory anxiety are less conclusive but theoretically these states should go along with increased autonomic arousal. Abnormal autonomic arousal might also be present during sleep as both panic disorder and worrying have been associated with sleeping difficulties. However, most empirical research has been confined to the laboratory where high internal validity is achieved at the cost of poor ecological validity. Thus, the purpose of this doctoral dissertation is to extend and validate laboratory findings on worry, anticipatory anxiety, and panic using ambulatory monitoring. Twenty-four hour monitoring not only can give valuable insights into a person’s daytime emotional experience but also allows observing how these emotions might affect their sleep in their natural environment. In the following chapter, the reader will be introduced to a conceptual framework that ties together worry, anxiety, fear, and panic, and related anxiety disorders (section 2.1), to autonomic arousal and electrodermal and cardiac arousal in particular (section 2.2), to sleep and its relation to autonomic arousal and anxiety disorders (section 2.3), and to ambulatory monitoring (section 2.4). After illustrating the aims of this thesis (chapter 3), chapters 4 to 6 present the results of three empirical studies conducted as part of this doctoral research. The first study deals solely with electrodermal monitoring and how it is affected by confounding variables in an ambulatory context (chapter 4). The next study then seeks to investigate the relationship between electrodermal arousal and anticipatory anxiety and panic in a sample of panic disorder patients and healthy controls. The last study focuses primarily on the effect of trait and state worry on subjective and objective sleep and electrodermal and cardiac arousal in a group of high and low worriers. Chapters 7 to 9 summarize and integrate the findings from these three empirical studies, discuss methodological limitations, and provide an outlook into future research.

Made available in DSpace on 2014-12-17T14:44:16Z (GMT). No. of bitstreams: 1 AndreIF_DISSERT.pdf: 2389986 bytes, checksum: 01d8b844d40c7ba89fb858795c736fe4 (MD5) Previous issue date: 2013-02-28 / Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico / Os testes de caminhada de 6 minutos (TC6MIN) e 400 metros (TC400M) s?o utilizados como uma alternativa pr?tica e de baixo custo para avaliar a aptid?o aer?bia e o desempenho obtido nesses testes est? relacionado com n?veis de sa?de, capacidade funcional e risco de mortalidade. Al?m do desempenho nos testes, a avalia??o cardiovascular por meio da frequ?ncia card?aca (FC) de recupera??o (FCR) e da variabilidade da frequ?ncia card?aca (VFC) p?s-exerc?cio t?m sido utilizados como informa??o de n?veis de sa?de e risco de mortalidade. O Tai Chi Chuan (TCC) pode aumentar a capacidade aer?bia, al?m de modificar o controle auton?mico. Objetivos: O objetivo foi analisar o desempenho e marcadores auton?micos entre idosas praticantes de TCC e sedent?rias em testes de caminhada indiretos. M?todos: Foram avaliadas 36 idosas, sendo 18 praticantes de TCC, com tempo de pr?tica de pelo menos 6 meses e n?o mais de 1 ano e que realizassem apenas o TCC, e 18 idosas sedent?rias. Para o TC6MIN, os sujeitos seguiram as recomenda??es do protocolo sugerido pela American Thoracic Society (ATS, 2002), e para o TC400M foi utilizado o protocolo do estudo de Simonsick et al.2001. A FCR foi considerada como a diferen?a absoluta entre a FC obtida ao final dos testes, e as FCs medidas no primeiro (FCR60 ) e segundo minuto (FCR120 ). O protocolo de coleta da VFC utilizado foi o recomendado pela Task Force (1996). Ap?s a constata??o da normalidade de distribui??o dos dados mediante teste de Shapiro Wilk, empregou-se o teste t de Student para amostra independentes ou Mann- Whitney caso n?o apresentasse normalidade, coeficiente de correla??o intraclasse (CCI; com 95% de intervalo de confian?a) e Bland- Altman (com 95% dos limites de concord?ncia). Resultados: O desempenho em ambos os grupos apresentou uma boa confiabilidade. As idosas do TCC obtiveram um melhor desempenho nos testes em compara??o com as sedent?rias. Al?m do mais, a FCR apresentou boa confiabilidade na em ambos os grupos, e a FCR das idosas do TCC apresentaram uma melhor reativa??o parassimp?tica quando comparadas com as idosas sedent?rias. Considerando a reprodutibilidade da VFC na an?lise linear e simb?lica, tanto nas idosas praticantes de TCC como nas idosas sedent?rias apresentaram boa confiabilidade. O comportamento da VFC n?o foi significante entre os grupos. Conclus?es: Foi encontrada uma boa confiabilidade no desempenho dos grupos avaliados, e nas vari?veis auton?micas podendo estar associados a intensidade subm?xima atingida em todos os testes. Al?m do mais, o desempenho obtido nos testes podem ser usados na obten??o de medidas confi?veis na avalia??o cardiorrespirat?ria, bem como a utiliza??o da FCR e da VFC parece garantir a confiabilidade dos dados utilizados para para medida do controle auton?mico card?aco. O TCC parece que favorece a um melhor desempenho em testes indiretos, al?m de uma melhor reativa??o parassimpatica considerando a FCR, mas, considerando a VFC n?o foi encontrada diferen?a significante entre as idosas