Dimitris Giakoumis

Using activity-related behavioural features towards more effective automatic stress detection

This paper introduces activity-related behavioural features that can be automatically extracted from a computer system, with the aim to increase the effectiveness of automatic stress detection. The proposed features are based on processing of appropriate video and accelerometer recordings taken from the monitored subjects. For the purposes of the present study, an experiment was conducted that utilized a stress-induction protocol based on the stroop colour word test. Video, accelerometer and biosignal (Electrocardiogram and Galvanic Skin Response) recordings were collected from nineteen participants. Then, an explorative study was conducted by following a methodology mainly based on spatiotemporal descriptors (Motion History Images) that are extracted from video sequences. A large set of activity-related behavioural features, potentially useful for automatic stress detection, were proposed and examined. Experimental evaluation showed that several of these behavioural features significantly correlate to self-reported stress. Moreover, it was found that the use of the proposed features can significantly enhance the performance of typical automatic stress detection systems, commonly based on biosignal processing.

Advances in Computational Psychometrics.

Advances in computational psychometrics and mathematical methods have been gaining a significant role in both medicine and psychology over these past years. The mainstream in psychometrics is moving towards ever greater use of computational and mathematical modeling techniques. Such techniques are critical in the emerging fields of affective and wearable computing, where new biomedical instruments available both in the laboratory and in the field are allowing for deeper understanding of human psychology. These experimental methods offer new opportunities but also new challenges in data interpretation and analysis. This special issue has two foci, namely, to feature works that (a) advance scientific knowledge in the area of computational psychometrics and (b) explore deep investigated methods, techniques, and instruments for the assessment of cognitive, emotional, and medical (e.g., diagnostic) as well as mental health at the cutting edge of current technology. There have recently been an increasing number of research initiatives that utilize computational technologies in order to support patients in maintaining or regaining a healthy mental state. Computational psychometrics and related tools have been exploited for assessing, measuring, and defining new methods for an effective and focused psychological intervention. It is of utmost importance to provide people with higher quality of life and also to shift a part of monitoring tasks from therapists and caregivers to unobtrusive technological systems. Efforts have started with Internet-based self-help therapies, but recently systems make an increasing use of computational psychometrics, including ambient intelligence, pervasive computing, smart phones, and sensor systems. Their common goal is to provide effective solutions for maintaining and improving mental health and related assessment. This special issue received many articles, accepting for publication five exciting contributions to the field. P. Cipresso et al. describe a promising approach for managing data from the interaction of two communicating individuals by collecting multiple electrophysiological signals and eye movements with computational methods. D. Cardone et al. introduced a promising thermal infrared imaging-based tool for the computational assessment of human autonomic nervous activity and psychophysiological states in a contactless and noninvasive way. I. A. C. Giglioli et al. presented a systematic review in the novel field of augmented reality for the assessment and treatment of psychological disorders, highlighting 13 selected articles after an initial screening of 784 articles emerging from the scientific databases. Last but not least, two articles in the exciting field of virtual reality are published: C. Wilson and A. Soranzo review some current uses for VR environments when examining visual perception and discuss limitations or questions that can arise; and S. Segkouli et al. define a more robust cognitive prediction model, accurately fitted to human data to be used for more reliable interface evaluation through simulation on the basis of virtual models of users with mild cognitive impairment (MCI). We hope that this special issue will foster wider discussion for these exciting themes in computational psychometrics. Pietro Cipresso Aleksandar Matic Dimitris Giakoumis Yuri Ostrovsky

A decision support system for real-time stress detection during virtual reality exposure

Virtual Reality (VR) is increasingly being used in combination with psycho-physiological measures to improve assessment of distress in mental health research and therapy. However, the analysis and interpretation of multiple physiological measures is time consuming and requires specific skills, which are not available to most clinicians. To address this issue, we designed and developed a Decision Support System (DSS) for automatic classification of stress levels during exposure to VR environments. The DSS integrates different biosensor data (ECG, breathing rate, EEG) and behavioral data (body gestures correlated with stress), following a training process in which self-rated and clinical-rated stress levels are used as ground truth. Detected stress events for each VR session are reported to the therapist as an aggregated value (ranging from 0 to 1) and graphically displayed on a diagram accessible by the therapist through a web-based interface.

A Semantic Framework to Support the Management of Cloud-Based Service Provision Within a Global Public Inclusive Infrastructure

ABSTRACT Cloud computing has opened a new era in e-commerce. As the growth and complexity of public and private clouds increases, novel solutions are needed, enabling vendors to effectively manage the cloud-based distribution of their services. To this end, this paper presents a novel semantic framework with the main aim to support providers in the overall cloud-based service provision process, in terms of service ownership, licensing, and usage monitoring. The base of our framework is an ontological schema that models service business rules definition and license agreements registration, as well as service usage monitoring, with a special focus on web service and software applications cloud-based distribution. Our proposed ontology supports complex distribution schemas, related to multiple vendor-based service distribution, as well as personalized discount schemas, facilitating the deployment of marketing strategies during cloud-based service provision. On top of this ontological schema, we have further developed service and provider reputation and trust inference mechanisms, which operate on the basis of both service usage statistics and subjective end user feedback. Taking a step forward from the state of the art, our mechanisms also provide personalized discount suggestions, further facilitating providers in defining marketing strategies. Apart from supporting providers, our mechanisms also facilitate users in service and provider selection. In order to examine the application of our framework in practice, we have developed a user interface that provides basic features of our framework, within the context of a real cloud, oriented toward personalized cloud service provision; our framework has been integrated in the “Cloud4All” Global Public Inclusive Infrastructure (GPII).

Introducing accessibility in the Web services domain

The ever increasing diversification of Web services and software applications poses a real challenge to developers and designers when creating software that has to cope with a myriad of interaction situations, as well as specific directives for ensuring an accessible interaction. Utilizing an advanced web services accessibility assessment tool, they can obtain a better understanding of the accessibility constraints for people with disabilities within Web services and software applications user interfaces. The proposed Web services assessment tool will assist them, with a minimal effort, to explore user-centered design and important accessibility issues for their software implementations. In an effort to solve such issues, this paper takes a step forward and introduces the notion of accessibility in the web service domain, in order to enhance web services with accessibility features capable to ensure that HCI through applications utilizing them is accessible.

Real-time monitoring of behavioural parameters related to psychological stress.

We have developed a system, allowing real-time monitoring of human gestures, which can be used for the automatic recognition of behavioural correlates of psychological stress. The system is based on a low-cost camera (Microsoft Kinect), which provides video recordings capturing the subjects upper body activity. Motion History Images (MHIs) are calculated in real-time from these recordings. Appropriate algorithms are thereafter applied over the MHIs, enabling the real-time calculation of activity-related behavioural parameters. The systems efficiency in real-time calculation of behavioural parameters has been tested in a pilot trial, involving monitoring of behavioural parameters during the induction of mental stress. Results showed that our prototype is capable to effectively calculate simultaneously eight different behavioural parameters in real-time. Statistical analysis indicated significant correlations between five of these parameters and self-reported stress. The preliminary findings suggest that our approach could potentially prove useful within systems targeting automatic stress detection, through unobtrusive monitoring of subjects.

ARE THERE DIFFERENCES IN THE OPINION OF PATIENTS WITH ALZHEIMER DISEASE AND THEIR CAREGIVERS ABOUT HAVING SUPPORT FROM A SERVICE ROBOT AT HOME

experiences. Our innovative study provided a means for individuals with dementia to express how they experienced music therapist-led group singing in a residential care home. The guiding research question was: What is the experience of music therapist-led group singing for individuals with dementia living in a residential care facility? Methods: Six male residents, diagnosed with moderate to advanced dementia and ranging in age from 78 to 92 years, participated in six 30-minute group singing sessions facilitated by a music therapist who also played the piano. Repertoire incorporated familiar folk, pop, country and hymn selections. Sources of data included observation, field notes, video recording, and individual interviews (fully recorded and transcribed), which were analyzed using an adapted observational checklist (Davidson & Fedele, 2011) and Interpretive Phenomenological Analysis (Smith & Osborn, 2003). Results: The analysis process produced six themes that described three aspects of the singers’ experience of group singing: (1) how they experienced themselves (Self as Performer, Self as Part of a Group); (2) how they experienced the music (Live Music is Special; Music is a Gift); and (3) how they experienced dementia and music (Gaps in Time, Memory and Ability; The Music Is Still There). During post-singing session interviews, participants were able to express a range of feelings (e.g., joy, pride, pleasure, relaxation), despite verbal limitations. Conclusions:Conclusions included support about the value and appropriateness of engaging individuals with dementia in research (as participants were able to contribute meaningful data) as well as, in group singing led by a music therapist. Furthermore, evidence supporting group singing as an aspect of dementia care that contributes to wellbeing (as conceptualized by the PERMA model’s five elements of positive emotions, engagement, relationships, meaning, and achievement, Seligman, 2011) was noted.

16. Human Computer Confluence in the Smart Home Paradigm: Detecting Human States and Behaviours for 24/7 Support of Mild-Cognitive Impairments

The research advances of recent years in the area of smart homes highlight the prospect of future homes equipped with sophisticated systems that monitor the resident and cater for her/his needs. A basic prerequisite for this is the development of non-obtrusive methods to detect human states and behaviours at home. Especially in the case of residents with mild cognitive impairments (MCI), such systems should be able to identify abnormal behaviours and trends, supporting independent living and well-being through appropriate interventions. The integration of monitoring and intervention mechanisms within a home needs special attention, given the fact that after a period of time, these will be perceived from the resident as inherent home features, altering the traditional way that the notion of home is perceived by the mind, transforming it into a Human Computer Confluence (HCC) paradigm. Activity detection and behaviour monitoring in smart homes is typically based on sensors (e.g. on appliances) or computer vision techniques. In this chapter, both approaches are explored and a system that integrates sensors with resident visionbased location tracking is presented. Location tracking is based herein on low-cost depth cameras (Kinect), allowing for privacy preserving, unobtrusive monitoring. The focus is on detecting the MCI resident’s Activities of Daily Living (ADLs), as well as extracting parameters, toward identifying abnormalities within her/his behaviour. Preliminary results show that the sole use of user position trajectories has potential toward effective ADL and abnormality detection, whereas the addition of sensors further enhances effectiveness, with increase however in system cost and complexity.