Trustworthy decentralized collaborative learning for edge intelligence: A survey

Collaborative learning in virtual classrooms has tremendous potential in institutions, as it encourages cooperative knowledge production and skill development. This study investigates how a pedagogical model for virtual learning can incorporate this methodology, emphasizing the significance of meticulous preparation, an appropriate dynamic for establishing groups, the relevance of student practices to everyday technology utilization, an evolution to educator responsibilities and learning autonomy. The research underlines the value of technology in education. This article discusses Virtual Collaborative Learning (VCL) as an effective approach to quality assurance in the age of digitization. It presents design characteristics from an academic standpoint and optimizes these approaches through a qualitative examination of written opinions by VCL participants. The research identifies and prioritizes critical criteria for collaborative learning effectiveness from the students' perspective, generating further multi-perspective design recommendations. Adaptive collaborative virtual learning is a technology-enabled technique that employs algorithms to evaluate student data and adjust to a student's learning style, pace, and accomplishments. It capitalizes on gamification to make learning more engaging and interactive, while artificial intelligence (AI), machine learning, virtual reality (VR), and augmented reality (AR) have transformed conventional education. This article explores at how cutting-edge technologies are being created and implemented into the educational system and classroom for enhancing student education and learning environments. This chapter examines the adoption of AI and machine learning in intelligent learning, emphasizing their potential for enhancing learning experiences, personalize education, and improve outcomes. It also encompasses ethical and security issues, highlighting the importance of stringent laws to protect students’ rights. By implementing these guidelines, educators and policymakers may build a more intelligent and successful classroom setting. This study visualizes AI-enabled learning systems, identifies types of interventions, and discusses popular analytical methodologies. It serves as a reference for future studies regarding the development of AI-enabled educational platforms that address specific learning challenges while enhancing user experiences, ultimately directing future research in this area of study.

Edge intelligence has received great attention for the rapid development and wild application of edge computing and artificial intelligence. As a key technology in edge intelligence for its ability of privacy protection, federated learning faces many problems when deployed in an edge environment. The staleness effect causes by device heterogeneity make the performance of synchronous federated learning limited by these slower devices. And algorithm may also obtain a worse model for statistical heterogeneity. In this paper, we develop an adaptive asynchronous federated learning for edge intelligence to solve the above problems. To improve accuracy and stability of the algorithm, we realize a balance between synchronous and asynchronous settings and implement an adaptive optimization method. At last, we verify the performance in an experiment with heterogeneous settings.

Edge intelligence (EI) has received a lot of interest because it can reduce latency, increase efficiency, and preserve privacy. More significantly, as the Internet of Things (IoT) has proliferated, billions of portable and embedded devices have been interconnected, producing zillions of gigabytes on edge networks. Thus, there is an immediate need to push AI (artificial intelligence) breakthroughs within edge networks to achieve the full promise of edge data analytics. EI solutions have supported digital technology workloads and applications from the infrastructure level to edge networks; however, there are still many challenges with the heterogeneity of computational capabilities and the spread of information sources. We propose a novel event-driven deep-learning framework, called EDL-EI (event-driven deep learning for edge intelligence), via the design of a novel event model by defining events using correlation analysis with multiple sensors in real-world settings and incorporating multi-sensor fusion techniques, a transformation method for sensor streams into images, and lightweight 2-dimensional convolutional neural network (CNN) models. To demonstrate the feasibility of the EDL-EI framework, we presented an IoT-based prototype system that we developed with multiple sensors and edge devices. To verify the proposed framework, we have a case study of air-quality scenarios based on the benchmark data provided by the USA Environmental Protection Agency for the most polluted cities in South Korea and China. We have obtained outstanding predictive accuracy (97.65% and 97.19%) from two deep-learning models on the cities’ air-quality patterns. Furthermore, the air-quality changes from 2019 to 2020 have been analyzed to check the effects of the COVID-19 pandemic lockdown.

Collaborative learning is a specific approach within the broader context of pedagogy. Collaborative learning encourages student participation via peer interaction in the learning process. It encompasses a set of approaches to education, sometimes also called cooperative learning or small-group learning (NISE, 1997; Collis, 1994). Collaborative learning creates an environment “that involves students in doing things and thinking about the things they are doing” (Bonwell & Eison, 1991, p.2). Collaborative learning involves communication. From the early availability of computer-mediated communication (CMC), questions of appropriate and adequate pedagogies using such technologies were put forward; in particular, when students are working together in collaborative learning (Kaye, 1992; Turoff, 1991). Collaborative learning can also be connected with other computer technologies, such as educational software (Wegerif, 1996) and intelligent collaboration learning systems (McManus & Aiken, 1996), or serve as a mechanism to integrate; for instance, computer conferencing with live lectures on the Internet (Eisenstadt, Brayshaw, Hasemer, & Issroff, 1996). Olson and Olson (1996) are among those who study the use of collaborative technologies to facilitate the work of groups. Referring to the widespread tools based on network or Internet technologies (World Wide Web, computer conferencing, groupware or tools for computer-supported collaborative work – CSCW), Dillenbourg and Schneider (1995) emphasize that often the appearance of new technologies “reactivates the belief that technology per se enhances education, which repeatedly has shown to be wrong in the history of educational technology”. In this context, Romiszowski and Ravitz (1997) state that, “one of the most important areas for tactical research at the moment is to investigate the potential applications and specific methodologies for collaborative learning” (p. 758). Therefore, the question about how to use computer and network technologies in education, and in particular in the context of collaborative learning, is still very relevant. In this chapter, the authors respond by suggesting a specific approach making use of Web-based tools and collaborative learning within a contribution-oriented pedagogy.

We present a collaborative learning environment called iCycle (Intelligent Computer-supported hybrid Collaborative Learning Environment) along with enabling Artificial Intelligence (AI) applications. The research is derived from a collaboration of four universities offering six cyber-learning courses in Computational Data-enabled Science and Engineering (CDSE) emphasising collaborative Project-Based Learning (PBL) and data-driven learning assessment to promote deep-learning. Relevant data sets for evidence-based learning assessment and iterative course improvement may grow in size to terabytes of information in the near future. We developed AI applications for collecting teamwork data, automating data analysis, and for formative learning assessment.

Based on the features of modern distance education, this paper puts forward a network based teaching platform which integrates network technology, intelligence technology, multimedia technology and supports computer-supported collaborative learning (CSCL). The paper also discusses in detail the design of an intelligent teaching model and collaborative learning mechanism based on this network teaching platform.

The current pandemic has significantly impacted educational practices, modifying many aspects of how and when we learn. In particular, remote learning and the use of digital platforms have greatly increased in importance. Online teaching and e-learning provide many benefits for information retention and schedule flexibility in our on-demand world while breaking down barriers caused by geographic location, physical facilities, transportation issues, or physical impediments. However, educators and researchers have noticed that students face a learning and performance decline as a result of this sudden shift to online teaching and e-learning from classrooms around the world. In this paper, we focus on reviewing eye-tracking techniques and systems, data collection and management methods, datasets, and multi-modal learning data analytics for promoting pervasive and proactive learning in educational environments. We then describe and discuss the crucial challenges and open issues of current learning environments and data learning methods. The review and discussion show the potential of transforming traditional ways of teaching and learning in the classroom, and the feasibility of adaptively driving learning processes using eye-tracking, data science, multimodal learning analytics, and artificial intelligence. These findings call for further attention and research on collaborative and intelligent learning systems, plug-and-play devices and software modules, data science, and learning analytics methods for promoting the evolution of face-to-face learning and e-learning environments and enhancing student collaboration, engagement, and success.

In today’s globally competitive environment, effective intelligent and intelligent computing technologies allow new opportunities for users and learners to be intensely connected. Advanced learning theories advocate many social aspects of learning such as collaborative learning, communities of practice, internalization of social process, participation in joint activity, and situated learning. International Symposium on Intelligent and Ubiquitous Computing in Education (IUCE 2007) brings together researchers, academics and industry practitioners who are involved or interested in the design and development of intelligent learning computing technologies. Understanding of the challenges faced in providing technology tools to support the learning process and ease the creation of instruction material using intelligent and intelligent technologies will help building a direction for further research and implementation work in the ubiquitous and intelligent learning society. Much work went into preparing a program of high quality. We received 65 submissions. Every paper was reviewed by 3 program committee members, and 28 were selected as regular papers, representing a 40% acceptance rate for regular papers. All of this work would not have been possible without the dedication and professional work of many colleagues. We would like to express our sincere appreciation to all contributors to the symposium for submitting papers. Special thanks go to our symposium chairs, Qi Luo from the Wuhan Institute of Technology, China and Yanwen Wu from the Central China Normal University, china, for their leadership and advice on planning this conference. We are also deeply grateful to Weitao Zheng, Wuhan Institute of Physical Education China, and Zhenghong Wu, East China Normal University, China. Finally, we hope you all had a very pleasant stay at IUCE 2007 in Jeju Island, Korea, and we wish you great success in your endeavors.

New members entering productive organizations require considerable training. Computer tools can support such training by providing an opportunity to learn while engaging in authentic activities and receiving appropriate coaching. We describe two tools that incorporate this approach. Sherlock, an existing computer coach, is an effective environment for learning how to troubleshoot complex electronic devices. A newer research effort focuses on tools for supporting knowledge-building argumentation and scientific theory evaluation in post-elementary school science education. Both tools offer users opportunities for reflecting on their own performance and support individual as well as collaborative learning.

In mobile and edge intelligence systems, federated learning (FL) enables local data training and learning model sharing without obtaining actual data from mobile and edge users, which are data owners. Data training processes are performed at the user side with only trained gradients passed to an aggregator, i.e., learning server. The learning server continually trains and updates corresponding learning models by collecting gradients. The updated learning models are delivered back to the mobile and edge users for improved data training results. Despite the advantages of federated learning in preserving privacy, the local data training process will consume an adequate amount of energy from the perspective of mobile and edge users. In mobile and edge intelligence systems, mobile users may not always prefer to apply federated learning to reduce energy consumption. There is a trade-off between applying federated learning to reserve data privacy and updating actual data for learning servers to train. In this work, a Markov decision process (MDP) based system model is proposed for mobile and edge users to make federated learning decisions to optimize long-term performance in terms of utility function consists of data training reward and data processing delay. A deep reinforcement learning approach is proposed to solve the MDP problem in highly dynamic systems with a large state space.

Along with continuous evolution, the future 6G network will become a converged “Cloud-Edge-Terminal” ecosystem which can carry various crucial AI applications on edge computing units, formulating an ubiquitous “Edge Intelligence” paradigm to enable differentiated service innovations and empower intelligent transformation of vertical industries. However, due to issues of data security, user privacy, wireless network transmission capability and etc., it is not feasible for conventional machine learning methods to build AI models by directly collecting massive distributed edge data together, and hence resulting a large number of “isolated data islands” in the edge units. In order to break the data sharing barrier and drive cross-edge data cooperation, this paper studies a federated learning based AI model training method by which sensitive raw data can be maintained and protected in its original edge units. Based on the general scheme, some challenging problems are discussed to implement this new paradigm in practical scenarios, and the corresponding promising solutions and key techniques are proposed to inspire further researches.Keywords6GFederated learningEdge intelligence

The fusion of Federated Learning and Edge Computing has opened up new horizons for intelligent, secure, and efficient data processing. This chapter provides an in-depth exploration of “Federated Learning for Edge Intelligence.” It explores into the fusion of decentralized machine learning with edge devices, highlighting the important aspects of privacy protection and real-time data analysis. The chapter examines the components, workflows, and practical applications of this transformative technology. The real-world use cases presented discuss how this technology is already revolutionizing industries like healthcare and predictive maintenance. Furthermore, the chapter also explores the challenges and considerations in deploying Federated Learning at the edge.

The existing power system cyber security protection system lacks pertinence for new services and has a low degree of automation. It is urgent to propose a security protection framework for the characteristics of new generation of power system business, especially to improve the attack prevention capability of distributed power sources, flexible and adjustable loads, etc., ensuring the stable operation of the power grid. Aiming at the lack of efficient linkage and coordination of existing cyber security protection devices in new generation of power systems, this paper proposes an interacted response technology for security protection devices based on intelligent learning. Our scheme standardizes and correlates the various threat intelligence collected by the security protection equipment, and use the multi-agent deep reinforcement learning method to realize the issuance and optimization of automated strategies in combination with the analysis results. The interacted strategy of safety protection devices is optimized through collaborative heterogeneous reinforcement learning model. And the validity of interacted configuration is verified for correctness, completeness, redundancy and consistency.

Incentive mechanism for collaborative distributed learning in Artificial Intelligence of Things

On the basis of concept, characteristics and related work of collaborative learning, this paper proposes an intelligent web collaborative learning system prototype based on multi-agent technology. At first, the paper introduces a collaborative learning framework which supporting group learning and illustrates the whole learning process. Secondly, the paper presents some key issues to implementation of the virtual learning environment, such as intelligent grouping, automatic question answering, knowledge management, and opinion mining. Preliminary learning practice shows that it is a practical and efficient way.