Skip to main content

Table 6 Smart education system descriptions

From: Smart education framework

References Implementation/prototype/architectural design/framework System/architecture name System implementation/prototype/architectural design/architectural framework description
Leonidis et al. (2010) Architectural design ClassMATE The ClassMATE design builds upon the Ambient Intelligence (AmI) paradigm. Its major components are ClassMATE core and API library. The core incorporates five major components: Security service, User Profile, Device Manager, Data Space, and Context Manager. The API library provides the educational application library infrastructure. ClassMATE relies on a generic services interoperability platform, named FAMINE (FORTH’s AMI Network Environment). This platform provides the necessary intercommunication between services. The context manager and the data space components provide the necessary context-aware educational activity management and content provision. The ClassMATE core provides Learning Management System related functionalities among others. The design is based on the AmI classroom concept that is realized with a device manager service. Context Manager and Data Space provide learning analytics services and interactive educational content management. The FAMINE platform provides the necessary infrastructure for ubiquitous cloud services
Obasa et al. (2011) Architectural design Integrated virtual classroom system The proposed system architecture builds upon the notion of collaborative learning via incorporating asynchronous and synchronous learning platforms. The system architecture consists of four interrelated modules, namely, Application tiers, Application objects, Data Processing module, and Course module in a multi-tier network infrastructure. The application tier provides the network infrastructure. The application objects provide the software application infrastructure. The data processing module provides the data flow infrastructure. The course module provides the learning content-related management. The application functional modules include the user registration module, course registration module, assignment module, chat module, glossary module, Elluminate module, lessons module, wiki, and workshop module. The proposed system has learning management system functionalities, a networked virtual classroom environment, educational resources via application modules, interactive web services modules (such as a forum, wiki, etc.) using Web 2.0+ technologies
Hirsch et al. (2012) Design Next generation learning environment (NGLE) The goal of the Next Generation Learning Environment (NGLE) is to provide a learning platform that allows the integration of heterogeneous systems. The learning platform provides data management, student profile management, learning and academic analytics, the grouping of users for educational purposes. The design is envisioned to incorporate more services as they are available. The learning platform is envisioned to acquire content or services from Banner or Moodle. In addition, the platform integrates with various systems such as social network for learning (ELSE), collaborative learning environment (CLE), student grouping system to support collaborative learning, document classification for recommendation to support smart content provision, student care management (SCM) to support a number of learning analytics functionalities. With a focus on collaborative learning, NGLE provides learning management, social networking, and learning analytics functionalities
Jo et al., (2012, 2014, 2016) Prototype and partial system implementation Structured plug-in integrated teaching and learning (ITLA) system The system consists of a Smart Content Service System and School and Home Learning System. The system is designed to provide services that enable smart learning, smart teaching, smart creating, and smart assessing. The Smart Content Service System is composed of tools and services that are connected to a content management system (CMS). It includes a smart contents creation tool, content auto-translation service, content auto-transfer tool. The smart school and home learning system include a learning management system connected with a smart learning tool, smart class, and personalized learning assistance tool. The smart learning tools in couple with other tools provide learning and academic analytics functionalities. The smart class is supported with smart devices, desktops, and smartboards. The CMS and LMS are supported with a contents repository system. As a whole, based on personalized learning, this smart education system offers LMS, a smart classroom environment, learning analytics functionalities, educational resources built upon mobile and cloud computing technology
Jeong et al. (2013) Architectural design Content oriented smart education system The proposed system is a cloud-based system in which the educational resources content is stored on the cloud. The system utilizes an authoring tool for creating smart media content including texts, images, videos, 3D, AR, VR objects. Cloud-based smart media services, content viewer for displaying smart media content, inference engine for providing customized learning content, security system are applications that support the systems The content provider (instructor) creates educational content, and consumers (learners) consumes content that is stored on the cloud and accessible via devices including mobiles. The system supports both open and private educational content. The inference engine provides students with personalized content by analyzing preferences, learning styles, content usage, and interaction patterns. The platform for cloud-based educational smart media services with support from other tools provides LMS functionality, educational resources, and ubiquitous access via any device. The inference engine provides learning analytics functionality
Hwang (2014) Framework Context-aware ubiquitous learning environment The framework of a smart learning environment consists of the following modules: learning status detecting, learning performance evaluation, adaptive learning task, adaptive learning content, personal learning support, databases for learner profiles, inference engine, and knowledge base. The system based on this framework is envisioned to work on a wireless communication network and to provide a user interface to students for smart learning. Mobile technology supported with a wireless network will enable ubiquitous access to users. This framework benefits from learning analytics functionalities via its modules. To realize this framework a learning management system will be required
Ali et al. (2017) Architectural design IoTFLiP: IoT-based flipped learning platform The proposed architecture is designed for flipped and case-based learning (CBL) for medical education. The platform architecture has business, application and service, presentation, and cloud security layers on the cloud. On the client-side, access technologies, local security, data aggregation and preprocessing, and data perception layers. The architecture proposes an interactive case-based flip learning tool (ICBFLT) that facilitates the learning activity between students and medical experts. The platform supports medical case data collection via IoT devices, data creation, case formulation, case evaluation, case feedback, and storage of medical knowledge. The business, application, and service layers in combination with the security layer provide various LMS functionalities. ICBFLT provides medical educational content with the help of a CBL Case Repository. IoT devices supported by mobile technology collect medical data for case creation
El Janati et al. (2018) Architectural design Adaptive learning system based on dynamic adaptive hypermedia system The proposed approach aims at providing adaptive educational content based on learners’ preferences and the disability of learners. The proposed approach utilizes a Dynamic Adaptive Hypermedia System (DAHS). The adaptive learning system (ALS) architecture includes a learner detector engine, learner model engine, transcoding engine, domain model, adaptation presentation engine. In this proposal, the system adapts the educational content for learners suffering from visual and auditory limitations. Various mechanisms such as text-to-speech, speech-to-text are used to adapt educational content to learners. The learner detector combined with the learner model provides learning analytics functions. The proposed architecture provides educational content (text, image, audio, and video) via adaptive web pages
Bajaj and Sharma (2018) Framework Smart education with artificial intelligence based determination of learning styles The goal of the framework is to develop a system that identifies the most suitable learning style via AI for a specific student interacting with a virtual instructor on the cloud. In this framework, the software tool utilizes artificial intelligence to analyze the students’ learning styles. Then the learning styles are used to generate personalized content and personalized learning paths. The interaction with the virtual teacher is enabled with cloud computing technology. The software tool provides LMS and learning analytics functionality
Hartono et al. (2018) Architectural design Smart hybrid learning system Smart Hybrid Learning System (SHLS) is based on Smart Hybrid Learning Method (SHLM) supporting flipped classrooms combined with Challenge Based Learning and Case-Based Learning. In SHLM, students learn in and out of class. In out-of-class learning, the students will have access to not only teachers but also industry and community partners. The educational resources are obtained from platforms providing MOOC that supports quizzes and tests. SHLS is envisioned to integrate with smart learning, social media, MOOC out-of-class technologies. Challenge-based learning system (CBLS) and case-based learning (CBL) system are in-class technologies integrated with SHLS. Furthermore, the SHLS supports interaction with industries, government, communities, and experts while creating a smart learning environment. The proposed system framework has 3 layers such as view layer, domain layer, data access layer. The view layer provides the user interface for SHLS. In the domain layer, there are smart learning system, smart conference layer, forum discussion layer, MOOC layer, Social Media Layer, CBLS layer, CBL system layer. The data access layer provides the database server acting as a content repository. The SHLS provides LMS, educational resource access, social media access, and advanced web functionalities
Kim et al. (2018) Architectural design Emotionally aware AI smart classroom The goal of the Emotionally Aware AI Smart Classroom is to create an educational environment in which the presenter is provided feedback on the emotional responses of audiences. Based on this feedback, the presenter will adapt their body language, voice intonation, and other non-verbal behavior to provide a more effective and emotionally intelligent presentation aiming for better learning. The system captures non-verbal cues including facial expressions, body movements, speech prosody, etc. Then these cues are analyzed via artificial intelligence technology Based on crowd scoring, the system analyzes listeners via AI technology. The machine intelligence component of the system sends data to the feedback decision component that provides feedback to the presenter via haptic glove or some other visual aid. The system is envisioned to work in a cloud environment as well. This system supports the notion of adaptive tutoring with help of academic analytics based on machine intelligence. Gesture-based computing in combination with ambient intelligent/smart classroom and related technologies are used to recognize and analyze the presenter’s verbal and non-verbal cues
Lisitsyna et al. (2020) Prototype Basic online course—remote laboratory control protocol (RLCP)-compatible virtual laboratory technology The goal of this approach is to increase the learning effectiveness utilizing blended learning technology with the use of a basic online course. Remote Laboratory Control Protocol (RLCP)-Compatible Virtual Laboratory Technology for a MOOC was modified and improved. The system is supported by virtual stands that allow students to solve practical exercises individually. After finishing the exercise, the student sends the results to the RLCP server to get evaluation results. Virtual laboratory uses special algorithms to construct efficient learning paths. The system provides basic LMS and learning analytics functionalities. Virtual stands and virtual laboratories are realized with web technologies