Charalampos Karagiannidis

Layered Evaluation of Adaptive Applications and Services

In this paper we address the evaluation of adaptive applications and services. We propose a layered evaluation approach, where the success of adaptation - the major factor affecting the acceptability of adaptive applications - is addressed at two separate layers: (i) interaction assessment and (ii) adaptation decision making. We argue that the proposed framework constitutes an effective means for the evaluation of adaptive applications and services, providing useful information for their improvement, and facilitating generalisation of evaluation results and re-use of successful design practices.

Can a Virtual Reality Cognitive Training Application Fulfill a Dual Role? Using the Virtual Supermarket Cognitive Training Application as a Screening Tool for Mild Cognitive Impairment

BACKGROUND Recent research advocates the potential of virtual reality (VR) applications in assessing cognitive functions highlighting the possibility of using a VR application for mild cognitive impairment (MCI) screening. OBJECTIVE The aim of this study is to investigate whether a VR cognitive training application, the virtual supermarket (VSM), can be used as a screening tool for MCI. METHODS Two groups, one of healthy older adults (n = 21) and one of MCI patients (n = 34), were recruited from day centers for cognitive disorders and administered the VSM and a neuropsychological test battery. The performance of the two groups in the VSM was compared and correlated with performance in established neuropsychological tests. At the same time, the effectiveness of a combination of traditional neuropsychological tests and the VSM was examined. RESULTS VSM displayed a correct classification rate (CCR) of 87.30% when differentiating between MCI patients and healthy older adults, while it was unable to differentiate between MCI subtypes. At the same time, the VSM correlates with various established neuropsychological tests. A limited number of tests were able to improve the CCR of the VSM when combined with the VSM for screening purposes. DISCUSSION VSM appears to be a valid method of screening for MCI in an older adult population though it cannot be used for MCI subtype assessment. VSMs concurrent validity is supported by the large number of correlations between the VSM and established tests. It is considered a robust test on its own as the inclusion of other tests failed to improve its CCR significantly.

From to educational meta-data authoring to educational meta-data management

Educational meta-data can significantly assist the effective and efficient retrieval of educational resources. Currently, there are a number of tools for educational meta-data authoring, facilitating the creation and modification of educational meta-data files. The paper outlines the requirements, and proposes an architecture for the development of a complete EMD management toolkit which go beyond meta-data authoring, supporting the educational community in the full management of educational meta-data.

Layered Evaluation in Recommender Systems: A Retrospective Assessment

valuation of recommender systems has only lately started to become more systematic, since the emphasis has long been on the experimental evaluation of algorithmic performance. Recent studies have proposed adopting a layered evaluation approach, according to which recommender systems may be decomposed into several components, evaluating each of them separately. Nevertheless, there are still no evaluation studies of recommender systems that apply a layered evaluation framework to explore how all the different components or layers of such a system may be assessed. This paper introduces layered evaluation and examines how a previously proposed layered evaluation framework for adaptive systems can be applied in the case of recommender systems. It presents the possible adaptation of this out a retrospective analysis of its past evaluation results under the new prism that the layered evaluation approach brings. Our analysis indicates that implementing a layered- based evaluation of recommender systems has the potential to facilitate a more detailed and informed evaluation of such systems, allowing researchers and developers to better understand how to improve them.

Students Attitude and Learning Effectiveness of Emotional Agents

This paper describes the development of an emotional agent who affects the attitude of students towards learning and helps them overcome learning obstacles. Face to face communication is simulated through synthetic characters that have the potential to portray emotions by recording user’s emotions and reacting accordingly. This form of communication might offer new approaches in the educational process that could enhance and improve e-learning. A study involving 52 higher education students who used an e –learning application with emotional agents is presented.

A Preliminary Study on the Feasibility of Using a Virtual Reality Cognitive Training Application for Remote Detection of Mild Cognitive Impairment

BACKGROUND It has been demonstrated that virtual reality (VR) applications can be used for the detection of mild cognitive impairment (MCI). OBJECTIVE The aim of this study is to provide a preliminary investigation on whether a VR cognitive training application can be used to detect MCI in persons using the application at home without the help of an examiner. METHODS Two groups, one of healthy older adults (n = 6) and one of MCI patients (n = 6) were recruited from Thessaloniki day centers for cognitive disorders and provided with a tablet PC with custom software enabling the self-administration of the Virtual Super Market (VSM) cognitive training exercise. The average performance (from 20 administrations of the exercise) of the two groups was compared and was also correlated with performance in established neuropsychological tests. RESULTS Average performance in terms of duration to complete the given exercise differed significantly between healthy(μ  = 247.41 s/ sd = 89.006) and MCI (μ= 454.52 s/ sd = 177.604) groups, yielding a correct classification rate of 91.8% with a sensitivity and specificity of 94% and 89% respectively for MCI detection. Average performance also correlated significantly with performance in Functional Cognitive Assessment Scale (FUCAS), Test of Everyday Attention (TEA), and Rey Osterrieth Complex Figure test (ROCFT). DISCUSSION The VR application exhibited very high accuracy in detecting MCI while all participants were able to operate the tablet and application on their own. Diagnostic accuracy was improved compared to a previous study using data from only one administration of the exercise. The results of the present study suggest that remote MCI detection through VR applications can be feasible.

Layered Evaluation for Data Discovery and Recommendation Systems: An Initial Set of Principles

This paper examines how a layered evaluation framework proposed for adaptive systems (AS) can be applied in the case of recommender systems (RecSys). Our analysis indicates that implementing a layered-based evaluation has the potential to facilitate a more detailed and informed evaluation of RecSys, allowing researchers and developers to better understand how to improve them.

An Intelligent Emotional Agent for Students with Attention Deficit Disorder

We propose the use of an intelligent emotional pedagogical agent to improve the communication channel between the user and the machine for e-learning systems for students with attention deficit disorder. We argue that the emotional communication between users and e-learning systems could serve for better interaction and could create a social environment for learners from different backgrounds. In this paper we present a short review of related work, describe special learning needs for attention deficit disorder (ADD), correlate the emotional process with ADD, declare the learning and adaptation factors that determine agent’s behavior, present the model’s architecture and a small scale experiment between students from higher education including students with ADD. The application is evaluated. Data analysis and statistics is presented.

Adaptations of the text media type: addressing the user's perspective

Multimedia user interfaces provide augmented interaction opportunities for the population at large to access and utilise interactive applications effectively and efficiently. Many efforts towards the development of multimedia user interfaces, however, can be characterised as technology-driven, thus not adequately supporting the exploitation of this technology by a wide range of users. In this paper, we address the development of multimedia user interfaces from a user perspective. In particular, we consider the use of the text media type and present possible adaptations of it, with respect to the particular needs, abilities and preferences of diverse user categories, including disabled people.

Gender-based behavioral analysis for end-user development and the ‘RULES’ attributes

This paper addresses the role of gender in End-User Development (EUD) environments and examines whether there are gender differences in performance and in correlations between performance and a set of behavioral attributes. Based on a review of the most prominent EUD-related behavioral Human Computer Interaction (HCI) theories, and the influence of gender on them, it attempts to classify all the gender related behavioral attributes influencing the end-users’ performance. Then, it theoretically selects a subset of these attributes, namely Risk-Perception, Usefulness-Perception,Learning Willingness, Ease-of-Use-Perception, and Self-Efficacy, presents an example application and conducts a basic evaluation testing. The proposed attributes (their initials form the word RULES) can form the basis for the design of EUD-oriented user modeling techniques for gender-neutral self-adaptive software EUD environments.