The development of realistic 3D simulation environments is an expensive and time-consuming enterprise and requires expertise in many areas far a field from artificial intelligence. Game Engine is the core component of modern computer games. It provides fundamental functions for games. Using game engine as platform to develop simulation environment for agents can save time and money. This paper proposed an Unreal Tournament-Based Simulation Environment (UTSE) for agent simulation. The reasons for selecting Unreal Engine as the start point of developing our simulation environment are presented. The implementation details of UTSE are also expatiated. And finally, a simple case is given to demonstrate the effectiveness of UTSE to rapidly produce game engine-based high fidelity simulations.

UTSE: A Game Engine-Based Simulation Environment for Agent

Hybrid Approach to Designating Ontology Attribute Semantics

In-class group work activities are found to promote the interpersonal skills of learners. To support the teachers in facilitating such activities, we designed a learning analytics-enhanced technology framework, Group Learning Orchestration Based on Evidence (GLOBE) using data-driven approaches. In this study, we implemented the algorithmic group formation and group work evaluation systems in a Japanese junior high school context. Data from a series of 12 collaborative learning activities were used to validate the difference in the measured heterogeneity of the formed homogeneous and heterogeneous groups compared to random grouping. Further, the peer rating and self-perception of the group work were compared for comparative reading and idea exchange tasks. We found algorithmically formed groups, considering the learner model data, either heterogeneously or homogeneously performed better than random grouping. Specifically, students in groups created by the homogeneous algorithm received higher peer ratings and more positive self-perception of group work in the idea exchange group tasks. We did not find significant differences in the comparative reading tasks. Along with the empirical findings, this work presents a paradigm of continuous data-driven group learning support by incorporating the peer and teacher evaluation scores as an input to the subsequent algorithmic grouping. 

Algorithmic group formation and group work evaluation in a learning analytics-enhanced environment: implementation study in a Japanese junior high school

Building the right learning teams is a key to the success of collaborative learning in online and offline learning environments. However, existing research on learning team formation (LTF) ignores the uncertainty of learners’ abilities and lacks a common problem modeling and optimization approach. Aiming at the characteristics of two typical types of leader-centered (LC) LTF problems, a universal optimization framework of LC-LTF is proposed by introducing role-based collaboration (RBC) theory. This framework evaluates the comprehensive ability of learners via a fuzzy description mechanism; applies the environments–classes, agents, roles, groups, and objects (E-CARGO) model to formulate the LC-LTF problem; and employs an optimization platform to obtain an optimal solution. A case study demonstrates the effectiveness and feasibility of the proposed framework. 

Universal Optimization Framework: Leader-Centered Learning Team Formation Based on Fuzzy Evaluations of Learners and E-CARGO

Building the right learning teams is a key to the success of collaborative learning in online and offline learning environments. However, existing research on learning team formation (LTF) ignores the uncertainty of learners’ abilities and lacks a common problem modeling and optimization approach. Aiming at the characteristics of two typical types of leader-centered (LC) LTF problems, a universal optimization framework of LC-LTF is proposed by introducing role-based collaboration (RBC) theory. This framework evaluates the comprehensive ability of learners via a fuzzy description mechanism; applies the environments–classes, agents, roles, groups, and objects (E-CARGO) model to formulate the LC-LTF problem; and employs an optimization platform to obtain an optimal solution. A case study demonstrates the effectiveness and feasibility of the proposed framework.

The study aims to investigate the effect of homogenous and heterogeneous grouping on students’ achievement and experiences of learning in a collaborative environment. A collaborative learning environment has been used as a pedagogical tool for a long time now. However, there is no clarity on which grouping strategy to use. In this paper, we study the impact of grouping on students’ performances. We aim to examine how different grouping arrangements, leading to different learning environments, affect students’ academic achievement. Also, in most cases homogeneity or heterogeneity is decided on the basis of students’ ability. For group learning, students were grouped into two different settings on the basis of their learning perspectives derived from class notes and their personality types. In the present study, we used a novel algorithm based on k modes clustering. Grouping indeed improved students’ performance, particularly, the heterogeneous groups performed better than the homogenous groups. Students’ experience with learning in the two different environments indicates that they were more satisfied with homogeneous group settings. 

Effect of different grouping arrangements on students’ achievement and experience in collaborative learning environment

WordNet is a huge repository being used as a tool in various fields. With an increasing number of applications referring to WordNet as a dictionary, several attempts have been made to update it. The paper proposes to extend the huge repository by adding words and relationships derived from students’ class notes through wikidata. These terms can be phrases, technical terms, or any subject specific terminology appearing in students’ notes of a specific subject. Although various WordNet enriching techniques are available, it is for the first time that subject specific terminology is being added. The resulting version of WordNet has some very common phrases and technical terms along with the generic terms. Making subject specific and generic terms available in a hierarchy can improve the accuracy of various applications like text summarization and clustering for text belonging to a specific domain.

Enriching WordNet with Subject Specific Out of Vocabulary Terms Using Existing Ontology

In this study, an innovative tool for enabling contextual teaching based on visual inputs, named Visual Stimuli‐based Teaching Aid (VISTA), was developed. This system establishes the meaning and significance of concepts that are taught in the classroom within different environmental contexts. The idea of contextual teaching has been deliberated for more than a decade now. Nevertheless, using this in a classroom with limited time and resources has several challenges. VISTA leverages the ubiquitous mobile devices to boost conventional teaching methods with contextual teaching–learning. With VISTA, contextual teaching does not require any specialized device, expensive sensors, or simulated environment. To assess the applicability of VISTA in computer science education, we gathered the responses and experiences from 42 computer science teachers teaching in various universities of India. The responses garnered indicate that contextualization through VISTA is relevant as well as interesting. In total, 86.31% of the teachers found the contextual information provided by VISTA to be significantly related to both the captured images and the concepts presented in the class. These results encourage the use of VISTA as a pedagogical tool for contextual teaching.

Manan Madan

Papers

Effect of different grouping arrangements on students’ achievement and experience in collaborative learning environment

Enriching WordNet with Subject Specific Out of Vocabulary Terms Using Existing Ontology

VISTA: A teaching aid to enhance contextual teaching