Identification of Potential Task Shedding Events Using Brain Activity Data
- PDF / 1,404,089 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 96 Downloads / 167 Views
(0123456789().,-volV) (0123456789().,-volV)
ORIGINAL PAPER
Identification of Potential Task Shedding Events Using Brain Activity Data Danushka Bandara1
•
Trevor Grant2 • Leanne Hirshfield2 • Senem Velipasalar1
Received: 12 November 2019 / Revised: 10 March 2020 / Accepted: 12 March 2020 Springer Nature Singapore Pte Ltd. 2020
Abstract In Human–Machine Teaming environments, it is important to identify potential performance drops due to cognitive overload. If identified correctly, they can help improve the performance of the human–machine system by offloading some tasks to less cognitively overloaded users. This can help prevent user error that can result in critical failures. Also, it can improve productivity by keeping the human operators at an optimal performance state. This paper explores a new method for identifying user cognitive load by a three-class classification using brain activity data and by applying a convolutional neural network and long short-term memory model. The data collected from a set of cognitive benchmark experiments were used to train the model, which was then tested on two separate datasets consisting of more ecologically valid task environments. We experimented with various models built with different benchmark tasks to explore which benchmark tasks were better suited for the prediction of task shedding events in these compound tasks that are more representative of real-world scenarios. We also show that this method can be extended across-tasks and across-subject pools. Keywords Human–Machine Teaming fNIRS Brain data Task shedding Convolutional neural networks LSTM Classification
Introduction As computing devices become more ubiquitous, the need for greater human–machine symbiosis becomes an important factor. This concept, of human and computer agents working together to accomplish a goal, or a set of goals, is referred to as Human–Machine Teaming (HMT). In any teaming environment, whether it is a team of all human agents, a team of all machines, or a combination of the two, it is important that resources within the team are allocated & Danushka Bandara [email protected] Trevor Grant [email protected] Leanne Hirshfield [email protected] Senem Velipasalar [email protected] 1
Syracuse University, Syracuse, USA
2
Institute of Cognitive Science, University of Colorado Boulder, Boulder, USA
as efficiently as possible such that the team may achieve its goal while simultaneously putting the least amount of strain possible on any of the team members. The finite resources of an HMT, such as the processing power of a machine, or the limited cognitive capacity of a human agent, could be viewed as potential bottlenecks within an HMT system, where the team’s ability to accomplish a task may falter. Although the processing power of a machine may have been the primary factor that stopped HMTs from achieving optimal performance in the past, processing power is now an easily obtainable resource. As such, recent efforts to improve the performance of HMTs have shifte
Data Loading...
