A decision making human-computer interface

Abstract

A decision-making human-computer interface capable of adapting to the human's changing performance with time is presented. The interface's components are identified, and a suitable theoretical framework for each component is discussed. The interface's algorithm is based on the following interaction of the components. As the human performs tasks, his or her performance is measured and this knowledge is integrated with the estimated task arrival and service rates. An optimal task allocation that determines which tasks are allocated to the human and to the computer is then chosen on the basis of the current human and system performance. The algorithm was tested in a human-controlled surveillance system. Results showed that the use of the interface enhanced the human's performance during periods of high mental workload