Detecting High-Functioning Autism in Adults Using Eye Tracking and Machine Learning.

The purpose of this study is to test whether visual processing differences between adults with and without high-functioning autism captured through eye tracking can be used to detect autism. We record the eye movements of adult participants with and without autism while they look for information within web pages. We then use the recorded eye-tracking data to train machine learning classifiers to detect the condition. The data was collected as part of two separate studies involving a total of 71 unique participants (31 with autism and 40 control), which enabled the evaluation of the approach on two separate groups of participants, using different stimuli and tasks. We explore the effects of a number of gaze-based and other variables, showing that autism can be detected automatically with around 74% accuracy. These results confirm that eye-tracking data can be used for the automatic detection of high-functioning autism in adults and that visual processing differences between the two groups exist when processing web pages.

Less Users More Confidence: How AOIs Don't Affect Scanpath Trend Analysis.

User studies are typically difficult, recruiting enough users is often problematic and each experiment takes a considerable amount of time to be completed. In these studies, eye tracking is increasingly used which often increases time, therefore, the lower the number of users required for these studies the better for making these kinds of studies more practical in terms of economics and time expended. The possibility of achieving almost the same results with fewer users has already been raised. Specifically, the possibility of achieving 75% similarity to the results of 65 users with 27 users for searching tasks and 34 users for browsing tasks has been observed in scanpath trend analysis which discovers the most commonly followed path on a particular web page in terms of its visual elements or areas of interest (AOIs). Different approaches are available to segment or divide web pages into their visual elements or AOIs. In this paper, we investigate whether the possibility raised by the previous work is restricted to a particular page segmentation approach by replicating the experiments with two other segmentation approaches. The results are consistent with ~5% difference for the searching tasks and ~10% difference for the browsing tasks.

Emerging technologies and web accessibility: research challenges and opportunities focussing on vision issues.

This is a technological review paper focussed on identifying both the research challenges and opportunities for further investigation arising from emerging technologies, and it does not aim to propose any recommendation or standard. It is focussed on blind and partially sighted World Wide Web (Web) users along with others who use assistive technologies. The Web is a fast moving interdisciplinary domain in which new technologies, techniques and research is in perpetual development. It is often difficult to maintain a holistic view of new developments within the multiple domains which together make up the Web. This suggests that knowledge of the current developments and predictions of future developments are additionally important for the accessibility community. Web accessibility has previously been characterised by the correction of our past mistakes to make the current Web fulfil the original vision of access for all. New technologies were not designed with accessibility in mind and technologies that could be useful for addressing accessibility issues were not identified or adopted by the accessibility community. We wish to enable the research community to undertake preventative measures and proactively address challenges, while recognising opportunities, before they become unpreventable or require retrospective technological enhancement. This article then reviews emerging trends within the Web and Web Accessibility domains.