Nestor Garay

The use of guidelines to automatically verify Web accessibility

Accessibility is one of the key challenges that the Internet must currently face to guarantee universal inclusion. Accessible Web design requires knowledge and experience from the designer, who can be assisted by the use of broadly accepted guidelines. Nevertheless, guideline application may not be obvious, and many designers may lack experience to use them. The difficulty increases because, as the research on accessibility is progressing, existing sets of guidelines are updated and new sets are proposed by diverse institutions. Therefore, the availability of tools to evaluate accessibility, and eventually repair the detected bugs, is crucial. This paper presents a tool, EvalIris, developed to automatically check the accessibility of Websites using sets of guidelines that, by means of a well-defined XML structure, can be easily replaced or updated.

Towards an Ontology for Describing Emotions

The study of emotion in human beings has traditionally been a research interest area in disciplines such as psychology and sociology. The appearance of affective computing paradigm has made it possible to include findings from these disciplines in the development of affective interfaces. Still, there is a lack of applications that take emotion related aspects into account. This situation is mainly due to the great amount of proposed theoretical models and the complexity of human emotions. Besides, the importance that mobile computing area is acquiring has made necessary to bear context related aspects in mind. The proposal presented in this paper is based on a generic ontology for describing emotions and their detection and expression systems taking contextual and multimodal elements into account. The ontology is proposed as a way to develop a formal model that can be easily computerized. Moreover, it is based on a standard, the Web Ontology Language (OWL), which also makes ontologies easily shareable and extensible. Once formalized as an ontology, the knowledge about emotions is used in order to make computers more accessible, personalised and adapted to user needs.

An ontology for description of emotional cues

There is a great variety of theoretical models of emotions and implementation technologies which can be used in the design of affective computers. Consequently, designers and researchers usually made practical choices of models and develop ad-hoc solutions that sometimes lack flexibility. In this paper we introduce a generic approach to modeling emotional cues. The main component of our approach is the ontology of emotional cues. The concepts in the ontology are grouped into three global modules representing three layers of emotions’ detection or production: the emotion module, the emotional cue module, and the media module. The emotion module defines emotions as represented with emotional cues. The emotional cue module describes external emotional representations in terms of media properties. The media module describes basic media properties important for emotional cues. Proposed ontology enables flexible description of emotional cues at different levels of abstraction. This approach could serve as a guide for the flexible design of affective devices independently of the starting model and the final way of implementation.

Optimisation of the Selection Set Features for Scanning Text Input

Scanning is one of the most popular text input methods for people with severe movement restrictions due to diverse kinds of disabilities. It is frequently used to input messages into communication systems, such as text-to-voice translators in order to maintain conversations. Nevertheless, the rate of text production usually obtained is very slow. For this reason, every effort to save time and optimize communication speed is welcome. In this way, this paper presents a study on the influence on the character input rate of diverse parameters related to the matrix that contains the selection set, such as shape, size, number of dimensions and layout of the selectable items. Its purpose is to extract a set of guidelines to design efficient input systems well adapted to the user, based on the scanning of items and its selection by means of one switch or push-button.

An Expert-Based Usability Evaluation of the EvalAccess Web Service

The activities developed by means of Internet have rapidly increased in the last years. Most of the Internet success is due to the proliferation and popularization of the information and services provided through web sites. However, many web pages have been designed without having in mind that there may be people, devices and even browsers that can not access them. A number of initiatives have been developed to prevent web accessibility barriers, including the accessibility laws promulgated by diverse countries-such as the Section 508 in the USA-. There are also independent institutions that have compiled accessible design guidelines, some of them with great influence in the design of accessible web pages. In particular, the best known ones are the guidelines compiled by the Web Accessibility Initiative (WAI), which is part of the Web Worldwide Consortium (W3C) [1]. All these initiatives specify and regulate the characteristics that universal accessible web sites must have. However, these efforts are not enough if the developers are not provided with tools that support universal design. EvalAccess1 is a tool that automatically evaluates the accessibility of web pages. It is an evolution of the EvalIRIS tool that was developed within IRIS European project [2]. EvalAccess allows verifying whether a web page -or a web sitesatisfies a particular set of guidelines in order to determine its accessibility. WAI accessibility guidelines are habitually used, but EvalAccess can evaluate the compliance with any other set of guidelines if they are specified using a specifically designed XML-schema.

Validating a multilingual and multimodal affective database

This paper summarizes the process of validating RekEmozio, a multilingual (Spanish and Basque) and multimodal (audio and video) affective database. Fifty-seven participants validated a sample of 2,618 videos of facial expressions and 102 utterances in the database. The results replicated previous findings of no significant differences in recognition rates among emotions. This validation has allowed having the audio and video material in the database classified in terms of the emotional category expressed. This normative data has proven to be useful for both training affective recognizers and synthesizers and carrying out empirical studies on emotions by psychologists.

Emotion Elicitation Oriented to the Development of a Human Emotion Management System for People with Intellectual Disabilities

The integration of people with intellectual disabilities into working and social environments is one of the main issues in applying Information and Communication Technology (ICT) into Assistive Technology field. In order to solve this problem, the use of Intelligent Tutoring Systems (ITSs) is a fact among the attendance community. Human Emotion Management System (HEMS) enhances the performance of ITSs. In this work a HEMS is included in a new ITS system (LAGUNTXO) which adds user affective information. People with intellectual disabilities and elderly need physical and intellectual support. This may be achieved by a HEMS which attempts to solve critical situations, like those presented in blockage stages. In this paper, new methods and material to analyze and classify human emotions and corresponding elicited emotions have been tested. This study has provided finding emotional changes which give the opportunity of detecting blockage situations in people with disabilities. The evaluation results of the created elicitation material and methods indicate a high level of accuracy with respect to others classically presented in the literature.

Interfacing users with very severe mobility restrictions with a semi-automatically guided wheelchair

TetraNauta is an on-going R&D project aimed to develop a controller for standard electric-powered wheelchairs that permits users with very severe mobility restrictions (such as people with tetraplegy) to easily navigate in closed environments (home, hospital, school, etc.). This project intends to design a non-expensive guidance system to help this kind of users to drive the wheelchair with the minimum effort, but maintaining the user as active as possible. For this reason the design of the user interface is a key factor. Some characteristic of this interface can be taken as a workbench for the design of more complex and security critical mobile systems.

A comparison using different speech parameters in the automatic emotion recognition using feature subset selection based on evolutionary algorithms

Study of emotions in human-computer interaction is a growing research area. Focusing on automatic emotion recognition, work is being performed in order to achieve good results particularly in speech and facial gesture recognition. This paper presents a study where, using a wide range of speech parameters, improvement in emotion recognition rates is analyzed. Using an emotional multimodal bilingual database for Spanish and Basque, emotion recognition rates in speech have significantly improved for both languages comparing with previous studies. In this particular case, as in previous studies, machine learning techniques based on evolutive algorithms (EDA) have proven to be the best emotion recognition rate optimizers.

Application of feature subset selection based on evolutionary algorithms for automatic emotion recognition in speech

The study of emotions in human-computer interaction is a growing research area. Focusing on automatic emotion recognition, work is being performed in order to achieve good results particularly in speech and facial gesture recognition. In this paper we present a study performed to analyze different machine learning techniques validity in automatic speech emotion recognition area. Using a bilingual affective database, different speech parameters have been calculated for each audio recording. Then, several machine learning techniques have been applied to evaluate their usefulness in speech emotion recognition, including techniques based on evolutive algorithms (EDA) to select speech feature subsets that optimize automatic emotion recognition success rate. Achieved experimental results show a representative increase in the success rate.