People in this country spend increasing amounts of their work and leisure time in front of computers. The term "human computer interaction" suggests a two-way exchange, with each participant aware of the other and responding appropriately. In reality, computers may appear frequently rude, frustrating, indifferent, and generally unpleasant. Much of this can be attributed to the fact that current computers are almost completely unaware of the actual state of the human user. The research community has proposed methods for computers to understand and respond to the user's feelings with mixed results. Emphasis has been placed on stress and frustration, feelings often generated by the use of the computer itself. There is no previous work, however, with regard to monitoring the actual health of the user during computer use. In this project, the PIs will incorporate physiologic monitoring in the human-computer interface, with the help of a thermal imaging camera employed as a computer peripheral. Through bio-heat modeling of facial imagery, they will monitor a range of vital signs including blood flow and cardiac pulse. This physiological information will then be used to draw inferences about a variety of health symptoms, possibly including stress, headaches, and heartbeat irregularities. Outcomes of the project will include novel/improved facial tracking and bio-heat modeling algorithms that: will allow contact-free and accurate measurement of vital signs without restricting the user; will enable the study of ubiquitous ailments like stress, heartbeat irregularities, and headaches on an unprecedented continuous basis; and will serve as a catalyst for the creation of new HCI paradigms that incorporate the computer as an aware and responsive partner with the user (e.g., in which the computer can react in real time to physiologic data for the benefit of the user).
Broader Impacts: In the short term, the results of this project will provide less cumbersome tools for those attempting to conduct research in the areas of usability and of emotional and affective interfaces. In the longer term, they will support a fundamental change in the way that we interact with machines. Today, software designers create systems that they hope will not frustrate the users. In the future, software designers will create truly collaborative interactions in which human and machines are both observing and responding. This has the potential to greatly improve the usability of systems for the elderly, minorities, the economically disadvantaged, and other populations impacted by the "digital divide." On the clinical front, developing systems that can monitor the health status of an individual will revolutionize remote monitoring and the care of chronic conditions such as anxiety, heartbeat irregularities, and headaches.
