Cognitive and Behavioural Simulations

View at publisher Summarise with VIRAT
Authors: Kuldeep Singh Kaswan, Jagjit Singh Dhatterwal, Anand Nayyar
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

By using behavioural and cognitive models, we can simulate how humans would realistically make decisions, particularly those influenced by emotions, through techniques such as simulation. Given that emotion plays a key role in human decision making, mathematical models for decisions based on emotion have also been proposed within the context of cognitive architectures, probabilistic reasoning, and computational neuroscience, using aspects of human behaviour as a benchmark for agent performance. These models use affective computing, reinforcement learning, and Bayesian networks to measure emotions and forecast their influence on decisions. There exist advanced frameworks, for example, the OCC model and appraisal theories, that allow for a systemic way of defining emotional influences in decision-making processes. Autoencoders/Similar Neural Network Techniques: These techniques significantly improve the fidelity of emotion-driven simulations by allowing them to accurately reflect complex features of human psyches. By integrating these models into artificial intelligence systems, it is possible to create interactions that more closely resemble human communication, enhancing applications such as robotics, virtual assistants, and adaptive learning systems. By combining emotioninformed choice frameworks with cognitive structures, such as ACT-R and SOAR, the accuracy of predictions is enhanced, enabling artificial systems to reproduce human actions more closely. This chapter outlines the architecture and design of either category of models, which entailed their computational efficiency, the ability to adapt to real-time data and their scalability. Through a Mathematical Framework, Intermediary (speculative) foundations of real-world ramifications, this study exemplifies the necessity of fluid thought (emotions) not only for the making of sound decisions but for the evolutionary generation of intelligent AI.

Fields of Study & Subjects

Psychiatry Mental Health Neuroscience Emotion and Mood Recognition Cognitive Science and Education Research

Publication details

Journal / source
CRC Press eBooks
Pages
146–169
Publication date
26 March 2026
Language
EN
Document type
Book chapter