Nadine Vigouroux

Genetic algorithm to generate optimized soft keyboard

In this paper, we propose a genetic algorithm formal framework to optimize character location on a soft keyboard. This method is described regardless of the language and layout used and can then easily be adapted to any language and layout. In this scope, we present a measure, based on Mackenzies model, to estimate the performances of the best characters in a given layout. We apply our method to common English language and two different layouts (hexagonal and rectangular layout) in order to compare with FITALY, OPTI or Metropolis keyboards. In all configurations, our method has the best performance.

Studying Point-Select-Drag Interaction Techniques for Older People with Cognitive Impairment

Graphical user interfaces and interactions that involve pointing to items and dragging them are becoming more common in rehabilitation and assistive technologies. We are currently investigating interaction techniques to understand point-select-drag interactions for older people with cognitive impairment. In particular, this study reports how older perform such tasks. Significant differences in behavior between all of the interaction techniques are observed and the reasons for these differences are discussed according the cognitive impairment.

Touch Screen User Interfaces for Older Subjects

This study investigated the optimal numbers of blocks and tactile targets for touch screen user interfaces intended for use by all (reference and older population). Three independent variables (number of targets, number of interaction blocks on the touch screen and number of hands used) were studied in our experiment. Huge amount of data were stored. In this paper, we will only report statistical analyses on two variables: Time needed to Realize the Test and Error Rate. Each variable will be analyzed in two times: for the whole population (reference and older) and for the comparison between these two populations.

Comparison between single-touch and multi-touch interaction for older people

This paper describes a study exploring the multi-touch interaction for older adults. The aim of this experiment was to check the relevance of this interaction versus single-touch interaction to realize object manipulation tasks: move, rotate and zoom. For each task, the user had to manipulate a rectangle and superimpose it to a picture frame. Our study shows that adults and principally older adults had more difficulties to realize these tasks for multi-touch interaction than for single-touch interaction.

Accessibility for the blind: An automated audio/tactile description of pictures in digital documents

In this paper we present our work in the field of accessibility to visual information in digital documents for the blind people. Our method consists in detecting the significant visual information in a picture/document, extracting their properties and rearrange them for the specified accessible output. Our approach relies on the efforts made in the field of digital documents accessibility along with image processing and content-based image retrieval. Our system provides then two possibilities of outputs: tactile/oral or a combination of the two.

Structuration des informations acoustiques dans le projet A.R.I.A.L.

Abstract The A.R.I.A.L. (Analyse et Reconnaissance des Informations Acoustiques et Linguistiques = Analysis and recognition of acoustic and linguistic data.) project uses acoustic and phonetic data coming from an ear model and structured in an ascending manner. The data are sometimes organized as features and sometimes as patterns and take into account context effects coded in the same way as instantaneous parameters. Our discussion will concern neither the features nor the pattern concepts, nor indeed their efficiency for recognition. What we shall do is to describe the A.R.I.A.L. project data basis. 1. 1. The acoustic data are organized hierarchically: on level 1: spectral data, intensity and pitch, on level 2: acoustic cues, on level 3: discrete cues (pseudo-features). 2. 2. Segmentation produces short, homogeneous segments (infra-phonemes) in whose all the cues take part in the implementation. A phonetic unit (phoneme, syllable, etc.) is described as a series of segments labelled Si. 3. 3. The knowledge basis is built up automatically without the help of an expert except for the initial manual segmentation of the sentences analysed. All the segments encountered make up an alphabet (Si). 3.1. Reduction of the alphabet by means of a metric routine. 3.2. Setting up of the base: Uk/ClSaSb—, Unit Uk in context Cl is a series of (Si) segments. It is then possible to define the classes of equivalence between series of segments, and this makes it possible (a) to give a single rewrite rule for Uk/Cl, (b) to study the oppositions between units. 3.3. Reduction of the data basis using a metric routine and dynamic programming.

Investigating drag and drop techniques for older people with cognitive impairment

Graphical user interfaces and interactions that involve pointing to items and dragging them are becoming more common in rehabilitation and assistive technologies. We are currently investigating interaction techniques to understand point-select-drag interactions for older people with cognitive impairment. In particular, this study reports how older perform such tasks. Significant differences in behavior between all of the interaction techniques are observed and the reasons for these differences are discussed according the Mini Mental Score.

The virtual paddle: an universal interaction for accessible video games

The video games are often inaccessible to disabled motor people of the upper limbs. The specialized games are limited choice of the set of accessible games. We present a new accessible technique of interaction: the Virtual Paddle. We designed it with a user-centered method. It is composed of three steps: questionnaire, brainstorming and paper prototypes. Next, we present the experiment to choose the optimized paddle. Finally we discuss the results and our perspective.

GrooveWrite: A Multi-purpose Stylus-Based Text Entry Method

With the emergence of mobile computing devices such as Personal Digital Assistants (PDAs), a new challenge to design methods of interacting with them for people with disabilities has been created. In this paper, we propose GrooveWrite as a novel text entry system for handheld devices equipped with touch screen and stylus, targeted at people with situational and motor impairments. Based on traditional seven-segment layout, GrooveWrite interface is designed and implemented. The characters are entered by moving the stylus inside physical side-grooves, which are used as a stabilizer for stylus motion, and crossing the subset of segments that forms intended character. Character recognition neither considers the path of movement, nor recognition pattern, but only the subset of seven segments that is crossed. We examine our system theoretically using CLC model. This study shows that GrooveWrite text entry speed will be 24.78 words per minute.

Design and evaluation of Multi-function Scanning System : a case study

We present in this paper an assistive technology of communication and command for quadriplegics. To carry out this assistive technology, a user centered design approach with the patient, his occupational therapists and his family was conducted. Various iterative versions of the prototype have been defined by means of the SOKEYTO platform to meet the needs and the abilities of the quadriplegic person. Options carried out and consecutive choice will be reported as well the difficulties to implement. The assistive technology was used by one quadriplegic person. A qualitative evaluation is also reported.