These findings increase the confidence with which these measures may be applied to assess relative differences in mental workload when developing and optimizing human machine interface (HMI) designs and in exploring their potential role in advanced workload detection and augmented cognition systems.

Cognitive distractions have been shown to affect drivers adversely and are a leading cause of accidents. Research indicates that drivers alter how they allocate their visual attention while engaging in secondary cognitive tasks. To evaluate the potential impact of secondary cognitive tasks on the allocation of drivers’ visual attention and on vehicle control, drivers were presented with increasingly complex forms of an auditory cognitive task while driving an instrumented vehicle. Measures of vehicle performance and eye gaze were assessed. Consistent with theories of visual tunneling, gaze distributions were significantly smaller while drivers performed certain levels of the secondary task; peripheral vision was thereby reduced. During the most difficult level of the secondary task, gaze dispersion was smaller than during any other level of the task. Changes in visual attention may provide earlier indications of cognitive distraction than changes in vehicle control, the latter of which were observed only during the most difficult level of the secondary task. Observed changes in vertical eye position suggest that drivers compensate for moderate cognitive demands by increasing their sight distance before further incremental increases in workload exceeded their abilities. In summary, the workload of a secondary cognitive task affected drivers’ visual attention. A low to moderate increase in workload was detectable as a change in gaze before vehicle control suffered. Gaze restriction appears related to the degree of cognitive workload. This work shows that visual attention is a potential method of detecting changes in driver state associated with cognitive workload.

Understanding the driver's cognitive load is important for evaluating in-vehicle user interfaces. This paper describes experiments to assess machine learning classification algorithms on their ability to automatically identify elevated cognitive workload levels in drivers, leading towards the development of robust tools for automobile user interface evaluation. We look at using both driver performance as well as physiological data. These measures can be collected in real-time and do not interfere with the primary task of driving the vehicle. We report classification accuracies of up to 90% for detecting elevated levels of cognitive load, and show that the inclusion of physiological data leads to higher classification accuracy than vehicle sensor data evaluated alone. Finally, we show results suggesting that models can be built to classify cognitive load across individuals, instead of building individual models for each person. By collecting data from drivers in two large field studies on the highway (20 drivers and 99 drivers), this work extends prior work and demonstrates feasibility and potential of such measures for HCI research in vehicles.

Advances in information communications technology and related computational power are providing a wide array of systems and related services that form the basis of smart home technologies to support the health, safety and independence of older adults. While these technologies offer significant benefits to older people and their families, they are also transforming older adults into lead adopters of a new 24/7 lifestyle of being monitored, managed, and, at times, motivated, to maintain their health and wellness. To better understand older adult perceptions of smart home technologies and to inform future research a workshop and focus group was conducted with 30 leaders in aging advocacy and aging services from 10 northeastern states. Participants expressed support of technological advance along with a variety of concerns that included usability, reliability, trust, privacy, stigma, accessibility and affordability. Participants also observed that there is a virtual absence of a comprehensive market and policy environment to support either the consumer or the diffusion of these technologies. Implications for research, policy and market innovation are discussed.