Multi-intelligence critical rating assessment of fusion techniques (MiCRAFT) method

Abstract

Assessment of multi-intelligence fusion techniques includes algorithm performance credibility, mission needs quality assessment, and work-domain usability. Situation awareness (SAW) bridges low-level information fusion (tracking and identification), with high-level information fusion (threat and scenario-based assessment), against user refinement (physical, cognitive, and information tasks). To measure SAW, common techniques include the NASA TLX (Task Load Index), SAGAT (Situational Awareness Global Assessment Technique) probes, SART (Situational Awareness Rating Technique) questionnaires, and CDM (Critical Decision Method) decision points. These SAW tools are combined for a MultiIntelligence Critical Rating Assessment of Fusion Techniques (MiCRAFT). The focus is to measure user refinement of a situation over the information fusion quality of service (QoS) metrics: timeliness, accuracy, confidence, workload (cost), and attention (throughput). A key component of any user analysis includes correlation, association, and summarization of data; so we also seek measure SAW in the QuEST of information.

Value-based sensor and information fusion

“…Evaluation thus includes the situation awareness [91,92], user ratings [93], mission safety [94], and formal verification [95]. Among the many choices, Fig.…”

Multisource AI scorecard table analysis of AMIGO

“…For many decades, there has been a discussion on trust in human-machine interaction [17]. Multiple constructs have been put forward towards the dimensions of trust, with efforts towards human-machine evaluation of situation awareness [20,21,22]. For example, Schaefer et al [23] looked at a comprehensive analysis of trust constructs for human-automation interaction (HAI) of a robotics experiment that recognized the importance of system reliability and transparency towards increasing HAI trust.…”