Collaborative Learning Method Research Articles

Implementation of a Team Game Tournament a Collaborative Learning Method and Study of its Impact on Learners' Development

The paper showcases the encouraging results of the cooperative learning (CL) method Team Game Tournament (TGT). TGT helps students to improve and accelerate their learning. In TGT success of the team is dependent on the success of the individual [5]. A tournament is played between small academically balanced teams. Facilitators form such teams and note the performance of each team by visual monitoring, data from student questionnaires, and exam results. Exam results of Third Year Automobile course Machine Design (AE301) with and without TGT are compared. Students' performance in exams is improved, they show to be focused and participative, to develop their critical thinking. Because of TGT, deep discussions happened on topics by students in a group. They enjoy the new learning format. Social skills like teamwork and managing conflict are developed in students. Students' feedback and improvement of their performance in exams confirm the above perceptions. Keywords— Cooperative learning, Team Game, Tournament (TGT), Student attitude.

A blockchain-based decentralized collaborative learning model for reliable energy digital twins

This paper proposes a blockchain-based decentralized collaborative learning method for the Industrial Internet environment to solve the trust and security issues in Federated Learning. Deploy a decentralized network for collaborative learning based on the alliance chain, design a block data structure suitable for asynchronous learning, and model three stages of computing event triggering, computing task distribution, and computing result integration for cross-domain device collaborative learning. List the critical steps for network deployment, including inspection, tearing down old networks, creating organizational encryption material, creating channels, and deploying chaincode. It also introduces the development of crucial chaincode such as initialization, creation, query, and modification. Finally, the correlation between the number of data pieces of the network, the number of communications, and the time of communications are analyzed through experiments. This paper also proposes a decentralized asynchronous collaborative learning algorithm, develops chaincode middleware between the blockchain network and Artificial Intelligence training, and conducts experimental analysis on the industrial steam volume prediction data set in thermal power generation. The performance on the data set, and the experimental results prove that the asynchronous collaborative learning algorithm proposed in this paper can achieve a good convergence effect. It is also compared with the single-machine single-card regression prediction algorithm, proving that the proposed model has better generalization.

Collaborative Learning based Recommendation System for Content Streaming Platform using Non-Negative Matrix Factorization Clustering

The Recommender System helps users find relevant content by leveraging their interest models. This paper focuses on content-based recommender systems, which determine recommendations based on previously selected products without needing user evaluations. These systems can now use machine learning to profile both consumers and items. We introduce a collaborative learning method for content streaming platforms using Non-Negative Matrix Factorization Clustering (NNMFC). The research employs a sliding window technique for clustering, implemented with gradient descent and further optimized using Particle Swarm Optimization (PSO). The model's performance was examined through its Root Mean Square Error (RMSE) across three techniques: gradient descent, sliding window gradient descent, and sliding window PSO. The result analysis of the proposed work achieved the lowest RMSE of 0.90, outperforming existing state-of-the-art approaches such as Collaborative Filtering, K-Mean, and UPCSim. The Sliding Window PSO emerged as the most proficient, presenting a notable 9% enhancement over existing methods.

Complex matrix and multi-feature collaborative learning for polarimetric SAR image classification

Nearest-regularized subspace (NRS) algorithm is an effective tool to obtain both accuracy and speed for PolSAR image classification. However, existing NRS-based methods can only learn the polarimetric feature vector well, but ignore the PolSAR complex matrix structure and channel correlation. So, how to collaboratively learn the original complex matrix and multiple features to improve the classification accuracy is a key problem. Besides, speckle noises are also the main factor of causing misclassification. To address these limitations, two novel methods are proposed. Firstly, a superpixel-based Riemannian NRS(SRNRS) method is proposed, which can not only learn complex matrix structure by Riemannian metric, but also reduce the speckle noises and computing time by superpixels. Then, a superpixel-based collaborative learning method(CM_SJNRS) is proposed, which integrates the complex matrix and multiple features into the NRS classification framework for the first time. Coupled dictionaries and different metrics are designed for two kinds of feature spaces respectively, and then a collaborative learning model is developed to fuse them. Experimental results demonstrate the proposed SRNRS method can reduce both the speckle and computing time, and the proposed CM_SJNRS method can improve classification performance by fusing two types of features.

Hackathon as an Effective Learning and Assessment Tool: An Analysis of Student Proficiency against Bloom's Taxonomy

In recent years, several learning strategies have been adopted to boost students’ learning and performance. Hackathon as a collaborative learning method, gives students the opportunity to investigate the practical usage of concepts by solving a real-world project in a limited time. Many researchers have investigated the effect of hackathons on students’ engagement, team work and learning motivation. In this paper, we integrate a hackathon component in a software development and architecture course curriculum to evaluate the effect of working on a real-world web development project in a hackathon setting on deepening the theoretical concepts learnt in lectures. The data is collected through two surveys which were accessible to students before and after the hackathon and students code commits on GitHub. By comparing the students’ code quality as well as their answers to survey questions before and after the hackathon against the Bloom’s taxonomy, we understand their knowledge state in each step and possible improvements in each one of the areas. The research findings show the importance of hackathon participation on students’ performance and state of knowledge.

Learning on the job through collaborative learning: analysing the appropriation of BIM knowledge in micro-enterprise architectural design companies

The lack of Building Information Modelling (BIM) knowledge appropriation by Architectural, Engineering, Construction and Operation (AECO) professionals is often considered one of the main obstacles to successful BIM implementation. Although barriers to implementation have been substantially investigated, a literature review on knowledge appropriation revealed that this area is poorly investigated and biased towards small and medium construction companies. The review also shows that no published research has addressed micro-enterprise design firms, despite these representing approximately 90% of the firms in the AECO sector. In this context, this research investigates whether collaborative learning can be a teaching and learning strategy for appropriating BIM knowledge in architectural design micro-enterprises. The Zone of Proximal Development concept and the Collaborative Learning method were the theoretical lenses to study BIM knowledge appropriation. The research method involved documental analysis of four years of data from a micro-enterprise. The data was classified into vertical collaboration, diagonal collaboration; horizontal collaboration; and individual action. Results show a progressive development of the professionals’ (BIM knowledge) autonomy, as they gradually moved from individual action and vertical collaboration relationships to diagonal and horizontal collaboration actions. The evidence indicates that teaching and learning strategies can contribute to the appropriation of BIM knowledge in the context of micro and small companies.

PervasiveFL: Pervasive Federated Learning for Heterogeneous IoT Systems

Federated learning (FL) has been recognized as a promising collaborative on-device machine learning method in the design of Internet of Things (IoT) systems. However, most existing FL methods fail to deal with IoT applications that contain a variety of IoT devices equipped with different types of neural network (NN) models. This is because traditional FL methods assume that local models on devices should have the same architecture as the global model on cloud. To address this problem, we propose a novel framework named PervasiveFL that enables efficient and effective FL among heterogeneous IoT devices. Without modifying original local models, PervasiveFL installs one lightweight NN model named modellet on each device. By using the deep mutual learning (DML) and our entropy-based decision gating (EDG) method, modellets and local models can selectively learn from each other through soft labels using locally captured data. Meanwhile, since modellets are of the same architecture, the learned knowledge by modellets can be shared among devices in a traditional FL manner. In this way, PervasiveFL can be pervasively applied to any heterogeneous IoT system. Comprehensive experimental results on four well-known datasets show that PervasiveFL can not only pervasively enable FL among heterogeneous devices within a large-scale IoT system, but also significantly enhance the inference accuracy of heterogeneous IoT devices with low communication overhead.

Multidimensional Science Education on Performance Assessment Comprehensively with Collaborative Project Learning Based Model: Philosophy Perspective

Competency-based learning requires an assessment instrument capable of comprehensively measuring learning objectives in the cognitive, psychomotor and affective domains. Therefore, an alternative assessment model based on performance is needed. The purpose of writing this article was to find out whether it is possible to comprehensively assess performance based on collaborative project learning in multidimensional science education from a philosophical perspective through literature study. Performance appraisal is a continuous assessment process through the process of collecting various activity-based information as an object of assessment in various ways and tools. Based on the results and discussion of the literature review, performance assessment is a continuous assessment process using various strategies and methods (multi-methods) where in this article the author combined collaborative project-based learning methods. Project based learning provides opportunities for students to explore content and learning experiences using various ways that are meaningful to themselves and to conduct experiments collaboratively by combining various interrelated subjects. Exploration of authentic and complex problems based on tasks that have been designed to produce joint work for reporting project results. Collaborative project learning between subjects is essentially a learning system that allows students to actively seek, explore, and discover concepts and principles authentically by involving various groups as assessors through self-assessment and Peer Assessment. The comprehensive performance appraisal process is a multidimensional process and information is obtained from the assessment process on aspects of cognitive skills, attitudes, critical thinking, process skills and products as an integral part of the learning process by empowering students and educators.

Student engagement in health professions education: AMEE Guide No. 152

This guide aims to support our colleagues to have comprehensive understanding of student engagement in health professions education. Despite the universal agreement about the significance of student engagement, there is lack of uniformity in conceptualizing and operationalizing this emerging construct. We review the theoretical basis explaining student engagement from three main perspectives: behavioral, psychological, and socio-cultural. In addition, we propose a contemporary and comprehensive framework for the student engagement in higher education, which is applicable to health professions education contexts. Drawing from this framework, we explain the conceptualization of the construct and its preceding factors, mediators, dimensions, spheres, and outcomes of student engagement. The proposed framework introduces student ‘engagement through partnerships’ as a novel component compared with the existing models of student engagement in higher education. This way, we are proposing a mixed model that not only considers the student as a ‘customer’ but also as a ‘partner’ in education. Engagement of students through partnerships include four areas: (1) provision of the education program, (2) scholarly research, (3) governance and quality assurance, and (4) community activities. This guide will provide practical applications on how to improve student engagement in health professions education. Finally, we highlight the current gaps in areas of research in the student engagement literature and suggested plans for future directions. Practice points Student engagement is student investment of time and energy in academic and non-academic experiences that include learning, teaching, research, governance, and community activities. Students are involved in these aspects at the cognitive, affective, behavioral, agentic, and socio-cultural dimensions. Student engagement could be explained by three theoretical perspectives: behavioral, psychological, and socio-cultural. The theoretical framework for student engagement in health professions education consists of five components: (1) antecedents of engagement, which refer to institutional and student factors as well as the interactions (student-student and student-staff), (2) mediators of engagement, which include self-efficacy, motivation, belonging, and reflectivity, (3) engagement dimensions, which refer to the five dimensions of engagement: cognitive, behavioral, emotional, agentic, and socio-cultural, (4) Spheres of engagement, which refer to engagement in own learning and engagement through partnerships, and (5) outcomes of engagement, which are short-term and long-term. Engagement through partnerships includes four main areas: (1) provision of the education program, (2) scholarly research, (3) governance and quality assurance, and (4) community activities. The following measures are necessary to promote student engagement in HPE: (1) promote a culture of community and psychological safety, (2) create a culture of ‘students as partners’, (3) promote the use of active, collaborative learning methods with relevance to future career, and (4) promote the use of technology-enhanced learning.

INTEGRASI NILAI-NILAI MULTIKULTURAL DALAM KURIKULUM PENDIDIKAN AGAMA ISLAM UNTUK MEMBANGUN TOLERANSI DI SEKOLAH

This study aims to examine the integration of multicultural values into the Islamic Religious Education (PAI) curriculum as a means of fostering tolerance in schools. The research employs a qualitative method with a library research approach, focusing on several schools in Indonesia that have implemented a multicultural-based PAI curriculum. The findings indicate that integrating multicultural values into PAI enhances students' understanding and tolerance toward religious and cultural diversity. The appropriate implementation of the curriculum, including the use of collaborative learning methods and relevant teaching materials, has proven effective in shaping students' inclusive character and appreciation for differences. However, the study also identifies several challenges, such as the lack of teacher training in delivering multicultural values and resistance to curriculum changes. Despite these challenges, the research highlights that integrating multicultural values into the PAI curriculum has significant potential to create a harmonious school environment and promote the development of a more tolerant society.

CRMRL: Collaborative Relationship Meta Reinforcement Learning for Effectively Adapting to Type Changes in Multi-Robotic System

Multi-agent reinforcement learning methods have been widely used for multi-robotic systems, and meta-learning methods are also applied to help robots reuse prior experiences to guide new tasks learning. But in some multi-robotic tasks, the robot types cannot be determined in advance or may dynamically change in practical application, bringing urgent challenges. When the robot types change, the prior experiences may be outdated and useless for new robots, even leading to negative transfer. It significantly limits the performance of most existing meta reinforcement learning methods. We get inspiration from the structure of bees, ants, and neurons. These colonies can overcome the interference caused by individual replacement, and always maintain dynamic stability. We find the relationship among individuals is more important than individuals themselves in these colonies, and propose a collaborative relationship meta reinforcement learning method (CRMRL). It concentrates on the relationship among robots, and reuses the collective knowledge to alleviate the interference caused by robot changes, dealing with the challenge of different combinations and dynamic changes in multi-robotic systems. The experiments are carried out on the StarCraft II platform and Webots simulator. The extensive results indicate that our method has noticeable improvement on many indicators compared with the traditional meta reinforcement learning methods.

Audio–visual collaborative representation learning for Dynamic Saliency Prediction

The Dynamic Saliency Prediction (DSP) task simulates the human selective attention mechanism to perceive a dynamic scene, which is significant and imperative in many vision tasks. Most of existing methods only consider visual cues, while neglecting the accompanying audio information, which can provide complementary information for the scene understanding. Indeed, there exists a strong relation between auditory and visual cues, and humans generally perceive the surrounding scene by collaboratively sensing these cues. Motivated by this, an audio–visual collaborative representation learning method is proposed for the DSP task, which explores the implicit knowledge in the audio modality to better predict the dynamic saliency map by assisting the visual modality. The proposed method consists of three parts: (1) audio–visual encoding, (2) audio–visual localization, and (3) collaborative integration parts. First, a refined SoundNet architecture is adopted to encode audio modality for obtaining corresponding features, and a modified 3D ResNet-50 architecture is employed to learn visual features, containing both spatial location and temporal motion information. Secondly, an audio–visual localization part is devised to locate the sounding salient object in the visual scene by learning the correspondence between audio and visual information. Thirdly, a collaborative integration part is devised to adaptively aggregate the audio–visual information and a center-bias prior to generate the final saliency map. Extensive experiments are conducted on six challenging audiovisual eye-tracking datasets, namely DIEM, AVAD, Coutrot1, Coutrot2, SumMe, and ETMD, which shows significant superiority over state-of-the-art DSP models.

Infrared-visible cross-modal person re-identification via dual-attention collaborative learning

Person re-identification is regarded as a retrieval task for searching the same person in different cameras, within which infrared-visible cross-modal re-identification (VI-ReID) is challenging because the inter-class distance is larger than the intra-class distance. In this paper, a dual-attention collaborative(DAC) learning method is proposed, which unites channel and spatial attentive deep features to obtain supplementary information for multiple classifiers via a cross-modal consistency constraint. A channel attention and part-wise spatial pooling are adopted for discriminative feature learning. A multiple-classifier strategy with a cross-modal consistency constraints is presented for the cross-modal identification. In this way complementary information among modality-sharable classifier and modality-specific classifier can be better utilized. The experimental results show that the proposed method distinctly outperforms the baseline method by a margin of 9.83% Rank-1 and 6.84% mAP on SYSU-MM01.

Relative Effectiveness of Guided Inquiry and Collaborative Learning Instructional Strategies on Students’ Performance and Retention Ability of Physics Students’ in Akoko Southwest Local Government Area, Ondo State, Nigeria

Poor teaching methods have been single handily adduced for students’ poor performance in physics at secondary school level. In lieu of this, this study investigates the relative and comparative effectiveness of the guided inquiry, collaborative learning conventional teaching methods on students’ academic achievement and retention in physics. This study hypothesized that there is no significant difference in the academic performance and retention ability in physics by the students’ taught with these methods. Pre-test, post-test control group quasi experimental design consisting of two experimental and one control groups was the research design used. The studied population consisted of all students who are offering physics in senior secondary class two in Akoko Southwest Local Government Area of Ondo State. Three secondary schools among the seventeen senior secondary schools in the study area were randomly selected and their 113 students were purposively selected schools were randomly selected and randomly assigned to two treatment and one control groups. The physics achievement test, an instructional package on physics were administered on the sampled students. The data collected were analyzed using ANCOVA. It was revealed that students taught using the collaborative learning method academically performed better to those taught using guided enquiry and conventional teaching methods. Similarly, collaborative method (CM) group retained best the contents taught followed by the guided inquiry group and lastly the conventional teacher expository method group. This study concludes that CM method is the best method of improving learning outcomes (performance and retention ability) in physics in the study area. This study therefore recommends that physics teacher in secondary schools in the study area should be synthetized via workshops, symposia, lectures, etc. on the procedures, techniques, and applications of collaborative teaching method in physics classrooms. Similarly, active participation of students in physics classroom should be encouraged by teachers.

Feasibility of a Vertically Integrated Teaching Strategy during a Surgical Clerkship Event—Learning Methods Matter

Sound foundational knowledge improves disease conceptualization and clinical diagnosis. Vertical integration (VI) is an appealing educational strategy to refresh relevant pre-clinical information during clinical rotations. However, an optimal learning approach for this has not yet been established. We hypothesized that a small group collaborative discussion format might serve as an appealing learning method to deliver integrated material and increase retention. During AYs 2018/2019 and 2019/2020, our multidisciplinary team utilized a Colorectal Cancer workshop incorporating pre-clinical material for Y3 students on Surgical Clerkship. In search of an optimized way to deliver vertically integrated content, we alternately presented the workshop material either in a small group (SG) case-based collaborative format or as a standard-sized group (StdG) exercise. We achieved this by testing immediate and late (4-week post-event) recall and assessing student satisfaction with the VI strategy in both physical settings (StdG and SG). A total of 93% of participants considered VI-based training worthwhile, 96% reported an increased knowledge base and 93% would welcome similar VI events in the curriculum. Significantly more SG students than StdG (52% vs. 31%, p = 0.014) enthusiastically endorsed their event and would prefer to have future VI events delivered in the format they experienced (88% for SG vs. 42% for StdG) (p < 0.0001). Combined (immediate + late) recall scores were significantly better in SG versus StdG (p = 0.007), while the rate of attrition at 4 weeks did not differ significantly (p = 0.81). VI strategy successfully reactivated pre-clinical concepts, achieving both high content retention and learner satisfaction during this workshop. Students endorsed future VI events, especially when delivered in a case-based, interactive SG setting. Although resource intensive, a VI strategy employing a small-group collaborative learning method may be considered for broader curricular use in undergraduate medical education.

Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State-of-the-Art and Future Directions.

Federated learning (FL) and split learning (SL) are two emerging collaborative learning methods that may greatly facilitate ubiquitous intelligence in the Internet of Things (IoT). Federated learning enables machine learning (ML) models locally trained using private data to be aggregated into a global model. Split learning allows different portions of an ML model to be collaboratively trained on different workers in a learning framework. Federated learning and split learning, each have unique advantages and respective limitations, may complement each other toward ubiquitous intelligence in IoT. Therefore, the combination of federated learning and split learning recently became an active research area attracting extensive interest. In this article, we review the latest developments in federated learning and split learning and present a survey on the state-of-the-art technologies for combining these two learning methods in an edge computing-based IoT environment. We also identify some open problems and discuss possible directions for future research in this area with the hope of arousing the research community’s interest in this emerging field.

The Influence of Application of Community of Inquiry (CoI) in Blend-ed Learning

The teaching and learning process must be able to foster student independence and activeness so that students do not depend on the teacher in understanding the material. The teacher center learning method is not able to foster the active role of students in learning so that the method must shift to become student-centered. The student center learning method supported by blended learning facilitates students to explore their knowledge actively and independently. Community of Inquiry (CoI) can be applied to blended learning to create more interactive and innovative learning. This study intends to ascertain the influence of implementing Community of Inquiry (CoI) on Blended Learning. This research is a literature study. Data collection was carried out by reviewing and digging up several journals, articles, data sources and also various information related to research. Data analysis was carried out by analyzing and comparing library sources to obtain theoretical data. The study's findings suggest that the application of Community of Inquiry (CoI) has an influence on: 1) increasing student motivation, 2) improving student learning outcomes, 3) problem solving ability, and 4) increasing student understanding. Therefore, it can be said that the application of Community of Inquiry (CoI) on blended learning is a framework designed to offer independent, active, and collaborative learning methods

Application of the Jigsaw Method in Qiro'ah Learning at MTs Darul Ulum Kepuhdoko Tembelang Jombang | Penerapan Metode Jigsaw dalam Pembelajaran Qiro’ah di MTs Darul Ulum Kepuhdoko Tembelang Jombang

The issue raised in this study is about learning qiro'ah using the jigsaw method as an innovative teaching method. Jigsaw is a collaborative learning method, which forms students to study in small groups consisting of 4 people by paying attention to the heterogeneity of students' ability levels, the teacher gives a jigsaw card containing material topics to be discussed by expert groups who will then be tasked with explaining the material to group members origin and each group presents the results of their discussion. The purpose of this study was to determine the application of the jigsaw method in learning qiro'ah and to identify the supporting and inhibiting factors. This research method uses case study qualitative research. The application of the jigsaw method in qiro'ah learning has supporting and inhibiting factors. The supporting factors are: 1. the expertise of the teacher who can guide students to understand the material, 2. the activeness of students in discussing and explaining to their group members. The inhibiting factors are 1) limited time in delivering material, because the application of the jigsaw method takes a long time, 2) An unsupportive environment, namely many students who live in an environment who do not have the habit of reading and writing Arabic, 3) Lack of interest in reading Arabic on students, 4). lack of mastery of Arabic vocabulary so that it is difficult to determine the meaning of sentences in the material read.

Situating critical thinking and creativity as enablers of value-based education among secondary school students in Kenya

This article aimed at reviewing the literature based on the critical thinking and creativity as enablers of value-based education education among Secondary School Students in Kenya. This paper may help highlight the need to include critical thinking and creativity in the curriculum, thus prompting the need for a curriculum review. In understanding the context of this discourse, the paper focused on two approaches: philosophical and psychological perspectives, emphasising moral philosophy for value-based education. This paper employed the collection of secondary data by using a desk research method of data collection. The data utilised two types of approaches: Internal and external desk research. The data was then subjected to content and discourse analyses to realise systematic and objective outcomes and interpretation as guided by the theoretical conceptualisation. The paper revealed that critical thinking involves inductive and deductive reasoning and problem-solving, nurturing creativity and innovativeness. Education aims at producing well-informed learners with skills and competencies that enable them to think analytically and critically, thereby applying what they have learned to enhance their own lives and sustainably contribute to society's development. This paper highlighted the need for instructors to provide explicit instructions to learners on how to transfer to new contexts and use cooperative and collaborative learning methods (constructivist approaches) that place students at the centre of the learning process.

Mutual Contrastive Learning for Visual Representation Learning

We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks. A crucial component of MCL is Interactive Contrastive Learning (ICL). Compared with vanilla contrastive learning, ICL can aggregate cross-network embedding information and maximize the lower bound to the mutual information between two networks. This enables each network to learn extra contrastive knowledge from others, leading to better feature representations for visual recognition tasks. We emphasize that the resulting MCL is conceptually simple yet empirically powerful. It is a generic framework that can be applied to both supervised and self-supervised representation learning. Experimental results on image classification and transfer learning to object detection show that MCL can lead to consistent performance gains, demonstrating that MCL can guide the network to generate better feature representations. Code is available at https://github.com/winycg/MCL.