Intelligent Decision Technologies

This paper focuses on the architecture of affective multimodal user interfaces that exist in e-learning applications. The OO (Object Oriented) approach has been adopted in order to combine evidence from multiple modalities of interaction and data from emotion stereotypes and classify them into well structured objects with their own properties and methods. The proposed architecture can be adopted in future multi-purpose emotion recognition systems with multiple modalities and improved emotion detection algorithms. Furthermore, the resulting emotion detection server is capable of using and handling transmitted information from different sources of data during human-computer interaction. The evaluation of the OO architecture for affective interaction by programmers and teachers revealed that there are considerable improvements in the resulting e-learning system, including easiness in adding a modality of interaction, better structure for the available multi-modal information and user friendlier environment for the human-computer interaction. The evaluation of the resulting system provided quite satisfactory results considering the proposed affective multimodal architecture.

This paper describes a comparative evaluation study carried out to assess the effect of incorporating avatars with facial expressions into interfaces of Electronic Customer Knowledge Management Systems (E-CKMS) on not only usability of E-CKMS, but also the user's trust and knowledge. Although the implementation of E-CKMS encounters several challenges, such as the lack of trust and information overload, few empirical studies were devoted to examine the role of metaphors of audio-visual nature. As a result, an empirical investigation was carried out by implementing avatars-enhanced multimodal E-CKMS (ACKMS) and comparing it with the text with graphics E-CKMS (VCKMS) and anther multimodal E-CKMS (MCKMS) that incorporated speech, earcons and auditory icons. The three experimental systems were evaluated by three independent groups of twenty users each (n=60) who performed eight common tasks of increasing complexity and design based on three different styles. The results therein revealed that the ACKMS outperform both MCKMS and VCKMS with regard to effectiveness, efficiency and the user's trust and knowledge.

Numerous researches indicate that dyslexia and dysgraphia are nowadays major problems in schools. Smart Pen is a tool for supporting the therapy of developmental dyslexia, with particular regard to dysgraphia. It comprises a display monitor equipped with a high-sensitivity touchpad and specially designed writing tool equipped with pressure sensors. The paper put emphasis on issues related to the design of the device and the development of software providing a vital part of the interface.

The software allows monitoring some interface parameters that are important from the therapy point of view, such as pen grip or time taken to complete an activity being a part of an exercise. The interface designed allows interesting (play and learn) activities to be performed with kids (i.e. learning of proper handling writing tools, basic writing etc.).

Tests have been carried out to verify usability of the Smart Pen. The test results showed that children and therapists are keen on using the new tool. Furthermore, using Smart Pen it is possible to distinguish children without writing problems from those who have some motoric disruptions. A description of the tests carried out and of their results is included in the paper.

This paper discusses the reasons why we should further adopt the use of three dimentional input devices in our common two dimensional environments. We make a case study using the Wiimote, Nintendo's main input device for the Wii console, in order to extract some useful data from user interaction.

This paper investigates a new approach to audio-visual correlation assessment based on the gaze-tracking system developed at the Multimedia Systems Department (MSD) of Gdansk University of Technology (GUT). The gaze-tracking methodology, having roots in Human-Computer Interaction borrows the relevance feedback through gaze-tracking and applies it to the new area of interests, which is Quality of Experience (QoE). Results of subjective tests carried out at the MSD showed a strong dependency between video presented in the screen and the perceived audio. It has also been shown that the application of gaze-tracking to the audio-visual correlation analysis allows for the objectivization of results obtained in subjective tests. Therefore this research study concentrates on the possibility to apply this methodology to the area of Quality of Experience.

In this paper, we present a system for musical genre classification that uses a preprocessing module to separate corresponding audio signals into three source signals. A feature extraction procedure is applied to each separated signal and the extracted features are fed into an ensemble combination of Support Vector Machine-based classifiers for genre classification. For the source separation task, we examine and compare two relevant algorithms, namely Convolutive Sparse Coding and a Wavelet Packets-based algorithm. We evaluate our system on a music database of four hundred music samples from four different music genres. Experimental results show that there is a higher classification accuracy in applying a source separation algorithm before feature extraction.