A domain-specific visual language for modeling metacognition in intelligent systems

作者：Caro Manuel F^*; Josyula Darsana P; Jimenez Jovani A; Kennedy Catriona M; Cox Michael T

来源：Biologically Inspired Cognitive Architectures, 2015, 13: 75-90.

DOI：10.1016/j.bica.2015.06.004

• Metacognition
• Domain-specific visual language
• Intelligent system
• Modeling tool
• MOF

Metacognition has been used in artificial intelligence to increase the level of autonomy of intelligent systems. However the design of systems with metacognitive capabilities is a difficult task due to the number and complexity of processes involved. This paper presents a domain-specific visual language specifically developed for modeling metacognition in intelligent systems called M++. In M++ the specifications of the cognitive level (object-level) and metacognitive level (meta-level) are supported in a metamodel configured according to the standard Meta-Object Facility (MOF) of Model-Driven Architecture (MDA) methodology. M++ allows the generation of metacognitive diagrams in a visual editor named Meta Think. A validation process was conducted to ensure the reliability of M++ in terms of quality of the notation and consistency of generated models. The validation was performed using two techniques: (i) empirical study and (ii) model tracing. The results given in the experimental study demonstrate that M++ is a useful notation for the process of modeling metacognitive components in intelligent systems. Metacognitive models generated from the validation process using the Tracing technique were consistent with the MOF-based metannodel. M++ contribute to cognitive architecture research adding precision to metacognitive concepts and enabling cognitive architecture researchers to do fast and exploratory prototyping of nnetacognitive systems using Meta Think tool.

• 出版日期2015-7