PACA-ITS: A Multi-Agent System for Intelligent Virtual Laboratory Courses

Saima Munawar,Saba Khalil Toor,Muhammad Aslam,Esma Aimeur

doi:10.3390/app9235084

Abstract

This paper describes an intensive design leading to the implementation of an intelligent lab companion (ILC) agent for an intelligent virtual laboratory (IVL) platform. An IVL enables virtual labs (VL) to be used as online research laboratories, thereby facilitating and improving the analytical skills of students using agent technology. A multi-agent system enhances the capability of the learning system and solves students’ problems automatically. To ensure an exhaustive Agent Unified Modeling Language (AUML) design, identification of the agents’ types and responsibilities on well-organized AUML strategies is carried out. This work also traces the design challenge of IVL modeling and the ILC agent functionality of six basic agents: the practical coaching agent (PCA), practical dispatcher agent (PDA), practical interaction and coordination agent (PICA), practical expert agent (PEA), practical knowledge management agent (PKMA), and practical inspection agent (PIA). Furthermore, this modeling technique is compatible with ontology mapping based on an enabling technology using the Java Agent Development Framework (JADE), Cognitive Tutor Authoring Tools (CTAT), and Protégé platform integration. The potential Java Expert System Shell (Jess) programming implements the cognitive model algorithm criteria that are applied to measure progress through the CTAT for C++ programming concept task on IVL and successfully deployed on the TutorShop web server for evaluation. The results are estimated through the learning curve to assess the preceding knowledge, error rate, and performance profiler to engage cognitive Jess agent efficiency as well as practicable and active decisions to improve student learning.

Highlights

The physical laboratory is used to assist students in performing practical work [1], but it requires expensive equipment and a high level of expertise
This paper presents the pedagogical agent-based cognitive architecture (PACA-ITS), which is aligned with the intelligent tutoring system (ITS) and was constructed based on the unified theory of cognition for developing intelligent virtual laboratory (IVL) courses
We present the Agent Unified Modeling Language (AUML) modeling languages, which are used to demonstrate the interactions between these intelligent lab companion (ILC) agents and specialized agents and communication with the eLearning students according to the knowledge level

Summary

Introduction

The physical laboratory is used to assist students in performing practical work [1], but it requires expensive equipment and a high level of expertise. It is a challenging task to circulate practical education online on a large scale in terms of distance and the blending of education modes [2,3]. To resolve these issues, we developed the online practical intelligent virtual laboratory. A multi-agent system is a self-organized system that performs multiple tasks through the cooperation and coordination of multiple agents. It can solve complex problems which are difficult to handle and attempt concurrently [4]. It has been mentioned that agents are active objects because they incorporate a thread of control as opposed to passive objects which are operated by other objects [7]

Objectives

Methods

Discussion

Conclusion