A multi-agent approach to adaptive learning using a structured ontology classification system

Abstract

Diagnostic assessment is an important part of human learning. Tutors in face-to-face classroom environment evaluate students' prior knowledge before the start of a relatively new learning. In that perspective, this thesis investigates the development of an-agent based Pre-assessment System in the identification of knowledge gaps in students' learning between a student's desired concept and some prerequisites concepts. The aim is to test a student's prior skill before the start of the student's higher and desired concept of learning. This thesis thus presents the use of Prometheus agent based software engineering methodology for the Pre-assessment System requirement specification and design. Knowledge representation using a description logic TBox and ABox for defining a domain of learning. As well as the formal modelling of classification rules using rule-based approach as a reasoning process for accurate categorisation of students' skills and appropriate recommendation of learning materials. On implementation, an agent oriented programming language whose facts and rule structure are prolog-like was employed in the development of agents' actions and behaviour. Evaluation results showed that students have skill gaps in their learning while they desire to study a higher-level concept at a given time.

Design and analysis of a multi-agent e-learning system using prometheus design tool

“…But with no prior access to the questions attempted at their pre-skills evaluation. From the results obtained in this paper, changes in the approach of pre-testing has slightly improved results, as shown in Tables 3-4 on student pre-skills exercise in contrast previous surveys in [32,39,40]. As students used the system, the system stored all pre-assessment activities and also timestamped every entry made by students into the system.…”

“…Previous reports on the pre-assessment system presented a pre-assessment mechanism [31,29] and the formalized logic model [32] for pre-skills testing, decision making, selection and recommendation of learning materials. In general, on any given knowledge graph or ontology, the following symbolic algorithm presents the underlying reasoning [29]:…”

An SQL Domain Ontology Learning for Analyzing Hierarchies of Structures in Pre-Learning Assessment Agents

“…But suppose it does, from our observation, this would lead to the creation of inconsistent predicate ground facts assertions in the respective agent beliefs from inter-agent communication; and in-turn leads to inaccurate and inconsistent recommendation of learning material. To prevent this type of multi-agent behaviour, Figures 6 and 7 are therefore the optimal model-approach for the pre-assessment system [20].…”

“…7) showed possible navigation paths through which nodes are linked for pre-assessments. This can be established either on the strategy of: Pre-Assessment By Immediate Prerequisite Class or Pre-Assessment By Multiple Prerequisite Classes [20,23]. The directed edges in the visualized models are the navigational paths from one node to another namely, class-to-class, class-to-subclass, class-to-leafnode, and subclass-to-leafnode.…”

“…The quizInsertSelect and answerInsertSelect literals are beliefs that were initialized in the BB of the agent agSupport: the agent that i) pre-assesses students using SQL query based quizzes, ii) take decisions on students' answer responses to quizzes, and iii) communicate the passed(X) or failed(X) predicate decision statement to the agent agModelling (the classifier agent) for SQL query skills classification. The classification process which is the categorization of student skill sets and recommendation for appropriate learning material(s) is a high-level reasoning procedure and has been presented using first-order logic syntax; see [20,23].…”