Curtis S. Ikehara

Assessing Cognitive Load with Physiological Sensors

Assessing the cognitive load of a subject performing a computer task using task performance data is normally available at the end of the task. For assessing cognitive load, physiological data has the advantage of being available in real-time and the potential of assessing the affective components of cognitive load. Described are two new methods of assessing cognitive load from eye tracking and the pressures a subject applies to a computer mouse when subjects perform a math task that involves moving targets. Physiological measures that significantly discriminated task difficulty included eye movement, skin conductivity and one of the pressure signals from the computer mouse. Also, in some cases, these physiological measures can be more sensitive than task performance measures of cognitive load (i.e., incorrect actions) to detect interaction effects with task difficulty. The suite of physiological sensors is shown to be a viable alternative or supplement to task performance measures.

A model for integrating an adaptive information filter utilizing biosensor data to assess cognitive load

Information filtering is an effective tool for improving performance but requires real-time information about the users changing cognitive states to determine the optimal amount of filtering for each individual at any given time. Current research at the Adaptive Multimodal Interactive Laboratory assesses the users cognitive ability and cognitive load from physiological measures including: eye tracking, heart rate, skin temperature, electrodermal activity, and the pressures applied to a computer mouse during task performance. A model of adaptive information filtering is proposed that would improve learning and task performance by optimizing the human-computer interface based on real-time information of the users cognitive state obtained from these passive physiological measures.

Methodological issues of real time data acquisition from multiple sources of physiological data

Safe and effective use of monitoring, scheduling, and action-guidance technologies is often dependent upon human operator agency. The cognitive ability of the human operator to control the environment varies depending on the individuals affective and physiological state as well as on situation-dependent temporal and contextual factors. Clearly, there is a need for real-time assessment of cognitive load in order to increase operator effectiveness through adaptive filtering of information. In order to begin assessment of how to flexibly augment human operator capabilities in real time, a study to determine the best practices for intercepting and synchronizing biosensor information from operators engaged in visual search tasks was performed.

User identification based on the analysis of the forces applied by a user to a computer mouse

This paper describes the framework for a branch of augmented cognition research performed at the Adaptive Multimodal Laboratory at the University of Hawaii and a spec application involving the identification of a computer user based on the forces applied to a computer mouse (i.e., click signature) during a task. Data was collected from six people during a pilot study. Two methods used to identify users were a back propagation neural network and discriminant analysis. Results indicate that the discriminant analysis was slightly better at identifying users than the neural network, but its primary advantage was that it required less data preparation. Continuous identification of the user is possible with either method. Successful, identification of the user is a useful first step to proceed to the next stage of the research framework, which is to identify the users cognitive state for implementation in an augmented cognition system.

Modeling and implementing an adaptive human-computer interface using passive biosensors

Modeling of the human-computer interaction as a partnership between two systems provides a flexible method of modeling both the quantitative and qualitative requirements of a human-computer interface. A discussion of the components of a system, system structures and system issues are reviewed along with a description of the research model used at the adaptive multimodal interactive laboratory.

Plan Recognition of Movement

Plan recognition of movement by car or foot is generally intractable because of the huge number of potential destinations and routes. However in restricted areas with limited ingress/egress and few places to go such as a military base, plan recognition of movement can be done. The ABM system uses RFID and Lidar to track the movement of vehicles and people, infer their plans/goals, and distinguish threat from normal behavior. ABM represents plans as a series of polygons that abstract important road/terrain features such as intersections and driveways. ABMs keyhole plan recognition algorithm handles unobserved steps caused by insufficient data rates or deficient sensor coverage and handles position inaccuracies due to limited sensor precision or multi-path reflections from buildings. ABM guards privacy by storing only a persons role (e.g., visitor, office worker, grounds keeper) on the military base.

Predicting remote view performance for tasks with different visual information content

Predictions of task performance based on the information required by the task, visual information acquired from the source, information transmission channel characteristics, and human information processing limitations are compared to actual performance on tasks viewed directly or remotely either monoscopically or stereoscopically, under different motion conditions. The tasks require varying amounts of information and channel capacity for proficient task completion and are based on the rapid sequential positioning task. The rapid sequential positioning task measures the time a subject takes to locate and tap an illuminated point source light target with a probe. Performance was measured using the task in a 3D and 3D plus motion configurations. The 3D plus motion configurations were given to subjects at four different movement speeds under different viewing conditions to test the effects of changing viewing bandwidth requirements. Subjects performed all tasks in a single session with data collected by computer. Data analysis involved the comparison of actual results with predictions derived from the Model Human Processor model and information theory. Results indicate that the requirements, availability, transmission, and human processing limitations of information are key components to task performance.