Modelling human cognition of abnormal machine behaviour

Abstract

Despite the advances in intelligent systems, there is no guarantee that those systems will always behave normally. Machine abnormalities, unusual responses to controls or false alarms, are still common; therefore, a better understanding of how humans learn and respond to abnormal machine behaviour is essential. Human cognition has been researched in many domains. Numerous theories such as utility theory, three-level situation awareness and theory of dual cognition suggest how human cognition behaves. These theories present the varieties of human cognition including deliberate and naturalistic thinking. However, studies have not taken into consideration varieties of human cognition employed when responding to abnormal machine behaviour. This study reviews theories of cognition, along with empirical work on the significance of human cognition, including several case studies. The different propositions of human cognition concerning abnormal machine behaviour are compared to dual cognition theories. Our results show that situation awareness is a suitable framework to model human cognition of abnormal machine behaviour. We also propose a continuum which represents varieties of cognition, lying between explicit and implicit cognition. Finally, we suggest a theoretical approach to learn how the human cognition functions when responding to abnormal machine behaviour during a specific event. In conclusion, we posit that the model has implications for emerging waves of human-intelligent system collaboration.

Collaborating AI and human experts in the maintenance domain

“…2. DCAM also supports the opportunities identified in a previous study (Illankoon et al 2019c) to model the cognition of abnormal machine behavior using a combined approach along two dimensions: broad types of knowledge (i.e., explicit-implicit) and broad levels of agents (i.e., human-intelligent systems). In the next sections, we discuss how the DCAM can overcome the two major limitations of the present models: limited focus on dynamics, and limited focus on perceptual-cognitive tasks.…”

“…MDS model should consider both the different levels of automation (Parasuraman et al 2000) offered by a decision support system and the wide modes of human cognition involved in gaining situation awareness of machine behaviors (Illankoon et al 2019c). Accordingly, in the DCAM, the internal problem representation is identified as a continuum between two poles: explicit and implicit knowledge.…”

From human resource management to intelligent human resource management: a conceptual perspective

“…Computer systems and any device that operates on software and has access to a network are on target, vulnerable, and thereby open to exploit, misuse, and manipulation. Abnormal behaviors (Illankoon et al 2019), data access interruptions, delays, data modifications, fabrications, losses, leakages, or other problems in these systems and devices emanate from both human and nonhuman motives and causes. Such motives and causes, in general terms, consist of user error, defects in code, malicious acts, hardware failure, and acts of nature (Strebe 2002).…”

Judgemental errors in aviation maintenance

“…Previous studies have shown SA applicability in maintenance (e.g. Illankoon et al 2019c). In this paper, using case studies, we tested the hypothesis "SA intervention can rectify the judgemental errors in maintenance".…”