A decision model for cognitive task allocation
Abstract
Cognitive task allocation is an important phase in the design of advanced computer-driven automation. In its most broadly practiced methodology today, cognitive task allocation employs task analysis to identify the performance requirements of each function; and demand/resource matching to evaluate the match between the identified requirements and human and computer performance of the function. The current methodologies of cognitive task allocation are either too aggregate to provide adequate resolution of performance requirements or empirical and domain-specific and thus of limited applicability. The presented research introduced a formal, quantitative, and domain-independent model of cognitive task allocation aimed at eliminating or reducing the limitations inherent in the currently practiced methodologies. In the newly developed model of cognitive task allocation, demand/resource matching is modeled as an Analytic Hierarchy Process. The Analytic Hierarchy Process of Demand/Resource Matching is defined as a mapping process along a four 4-level Analytic Hierarchy. By means of the Analytic Hierarchy Process task functions (Level 1 of the Analytic Hierarchy) are analyzed into the cognitive processes required for their performance (Level 2); performance criteria, e.g. validity, scope, speed of performance, etc., are set for each cognitive process (Level 3), by means of which the capacities of the human and computer controller (Level 4) are evaluated and compared. The Analytic Hierarchy Process then integrates partial judgements of relative human and computer capacity into a global weighted average indicating the relative capacity of human and computer to perform the overall function. This assessment of relative merit of performance can hence be applied, along with criteria for allocation pertaining to dynamic allocation, work design, or non-cognitive psychological factors, towards the final allocation design. The Analytic Hierarchy Process was applied and evaluated in the design of task allocation in production scheduling of a flexible manufacturing system by comparing the allocation designs of two groups of subjects. One group was supported by the decision model, the other received no decision support. The observed differences between the two sets of designs of demand/resource matching indicated that decision support by means of the Analytic Hierarchy Process results in: (i) better identification of performance requirements, (ii) better identification of design tradeoffs, and (iii) reduced decision bias.
Degree
Ph.D.
Advisors
Salvendy, Purdue University.
Subject Area
Industrial engineering|Occupational psychology
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.