Automatic evaluation of assistive interfaces

Abstract

Computers offer valuable assistance to people with physical disabilities. However designing human-computer interfaces for these users is complicated. The range of abilities is more diverse than for able-bodied users, which makes analytical modelling harder. Practical user trials are also difficult and time consuming. We are developing a simulator to help with the evaluation of assistive interfaces. It can predict the likely interaction patterns when undertaking a task using a variety of input devices, and estimate the time to complete the task in the presence of different disabilities and for different levels of skill. In this paper we describe the different components of the simulator in detail and present a prototype of its implementation.

Evaluating the Cluster Scanning System

“…Our study also confirms the value of automatically evaluating assistive interfaces using a simulator [1,2]. Before running a formal user trial, a system designer may tune interface parameters or select the best design alternative using our simulator.…”

“…We recorded sample interactions by two able-bodied users to generate a list of tasks, which were fed to the simulator [2]. The model for the cluster scanning system takes the scan delay, the number of clusters, the intended target and the total number and positions of targets in a screen as input and gives the target acquisition time as output by running the cluster scanning algorithm on the input.…”

The potential of adaptive interfaces as an accessibility aid for older web users

“…There are also standard models of human capabilities [11], including some data on how these capabilities are affected by disabilities [4]. However there is currently a dearth of detailed and long-term studies covering the needs of people who may experience minor to moderate impairments (sometimes many simultaneously), and the effects of dynamic diversity on assistive technology effectiveness.…”

Perception Model for People with Visual Impairments

“…The model is part of a larger system that is used to evaluate interfaces with respect to a wide range of skills and physical abilities [2,3]. Our perception model takes a list of mouse events, a sequence of bitmap images of an interface and locations of different objects in the interface as input, and produces a sequence of eye-movements as output.…”

“…The motor-behaviour model predicts the completion time and possible interaction patterns for performing an action. The details of the simulator and the cognitive and motor-behaviour models can be found in two separate papers [2,3]. In the following sections we present the perception model in detail.…”