Collaborative Learning System Research Articles

Unveiling the nexus between quality and student engagement in web-based collaborative learning systems

Unveiling the nexus between quality and student engagement in web-based collaborative learning systems

Use of open collaborative learning system and a methodology for measuring its effectiveness

Relevance. This study is devoted to the problem of using open co-education in the training of computer science teachers in universities of the Republic of Kazakhstan. The problems covered are relevant in the context of the development of the education system, and the rethinking and updating of existing teaching methods used in education, especially in the field of training teachers in the field of information technology. Purpose. The purpose of this study is to determine the effectiveness of the use of open collaborative training of teachers in information technology to increase teachers� awareness of such teaching methods. Methodology. In the current study, an experiment based on the evaluation of three parameters was used for two groups of students � one of the groups of students was taught according to the conventional form of education, the second group of students used the form of open co-education, which is considered in this study. Results. As a result of the introduction of this technique, an increase in attendance was obtained: in the experimental group, the average number of classes attended was 42.875, compared with 39.02 in the control group (Eta-squared value 0.0093) and with 40.3 in the experimental group itself before the introduction of the technique (Eta-squared value 0.0093). Exam results: the experimental group had an average score of 4.33, compared with 3.58 in the control group (Eta-squared value 0.0035) and 3.8 in the experimental group itself, compared with the period when the group was trained in the conventional way (Eta-squared value 0.0033). Similarly, a decrease in the dropout rate was noted � from 8.33% and 5.56% to 0%, respectively. Conclusions. In other words, there is an improvement in all indicators as a result of the introduction of open collaborative learning. Thus, it is possible to recommend this methodology for educators who teach future teachers in the field of information technology. Keywords: computer science; academic achievements; learning models; trends in education; collaboration

Use of open collaborative learning system and a methodology for measuring its effectiveness

Relevance. This study is devoted to the problem of using open co-education in the training of computer science teachers in universities of the Republic of Kazakhstan. The problems covered are relevant in the context of the development of the education system, and the rethinking and updating of existing teaching methods used in education, especially in the field of training teachers in the field of information technology. Purpose. The purpose of this study is to determine the effectiveness of the use of open collaborative training of teachers in information technology to increase teachers� awareness of such teaching methods. Methodology. In the current study, an experiment based on the evaluation of three parameters was used for two groups of students � one of the groups of students was taught according to the conventional form of education, the second group of students used the form of open co-education, which is considered in this study. Results. As a result of the introduction of this technique, an increase in attendance was obtained: in the experimental group, the average number of classes attended was 42.875, compared with 39.02 in the control group (Eta-squared value 0.0093) and with 40.3 in the experimental group itself before the introduction of the technique (Eta-squared value 0.0093). Exam results: the experimental group had an average score of 4.33, compared with 3.58 in the control group (Eta-squared value 0.0035) and 3.8 in the experimental group itself, compared with the period when the group was trained in the conventional way (Eta-squared value 0.0033). Similarly, a decrease in the dropout rate was noted � from 8.33% and 5.56% to 0%, respectively. Conclusions. In other words, there is an improvement in all indicators as a result of the introduction of open collaborative learning. Thus, it is possible to recommend this methodology for educators who teach future teachers in the field of information technology. Keywords: computer science; academic achievements; learning models; trends in education; collaboration

Architecture, Design and Community in Colombia. More Urban, More Rural, More Social: The Workshop Experience

This contribution reflects on two challenges: the first focuses on analysing how architects-designers, teachers-students, should apply post-pandemic projective thinking from the academy. On the other hand, to make a critical reflection on how specifically from the PUJCali, under the methodologies of service-learning, co-design and placemaking, work has been done and can continue to be done in favor of small disadvantaged communities with the intention of producing significant changes for them. Especially after the pandemic, we wonder how it would be possible to orient these experiences towards a more collaborative, inclusive, transdisciplinary, collective and transcommunity learning system, moving away from hegemonic positions. How these workshops have a direct impact on the communities of school-age children and increase their well-being in multiple aspects, as well as improving their coexistence and behaviours. Valuing research work in conjunction with the community highlights the importance of appropriation by those directly involved when they feel part of the work process.

Privacy-Preserving Deep Learning Framework Based on Restricted Boltzmann Machines and Instance Reduction Algorithms

The combination of collaborative deep learning and Cyber-Physical Systems (CPSs) has the potential to improve decision-making, adaptability, and efficiency in dynamic and distributed environments. However, it brings privacy, communication, and resource restrictions concerns that must be properly addressed for successful implementation in real-world CPS systems. Various privacy-preserving techniques have been proposed, but they often add complexity and decrease accuracy and utility. In this paper, we propose a privacy-preserving deep learning framework that combines Instance Reduction Techniques (IR) and the Restricted Boltzmann Machine (RBM) to preserve privacy while overcoming the limitations of other frameworks. The RBM encodes training data to retain relevant features, and IR selects the relevant encoded instances to send to the server for training. Privacy is preserved because only a small subset of the training data is sent to the server. Moreover, it is sent after encoding it using RBM. Experiments show that our framework preserves privacy with little loss of accuracy and a substantial reduction in training time. For example, using our framework, a CNN model for the MNIST dataset achieves 96% accuracy compared to 99% in a standard collaborative framework (with no privacy measures taken), with training time reduced from 133.259 s to 99.391 s. Our MLP model for MNIST achieves 97% accuracy compared to 98% in the standard collaborative framework, with training time reduced from 118.146 s to 87.873 s. Compared to other studies, our method is a simple approach that protects privacy, maintains the utility of deep learning models, and reduces training time and communication costs.

Detecting non-verbal speech and gaze behaviours with multimodal data and computer vision to interpret effective collaborative learning interactions

AbstractCollaboration is argued to be an important skill, not only in schools and higher education contexts but also in the workspace and other aspects of life. However, simply asking students to work together as a group on a task does not guarantee success in collaboration. Effective collaborative learning requires meaningful interactions among individuals in a group. Recent advances in multimodal data collection tools and AI provide unique opportunities to analyze, model and support these interactions. This study proposes an original method to identify group interactions in real-world collaborative learning activities and investigates the variations in interactions of groups with different collaborative learning outcomes. The study was conducted in a 10-week long post-graduate course involving 34 students with data collected from groups’ weekly collaborative learning interactions lasting ~ 60 min per session. The results showed that groups with different levels of shared understanding exhibit significant differences in time spent and maximum duration of referring and following behaviours. Further analysis using process mining techniques revealed that groups with different outcomes exhibit different patterns of group interactions. A loop between students’ referring and following behaviours and resource management behaviours was identified in groups with better collaborative learning outcomes. The study indicates that the nonverbal behaviours studied here, which can be auto-detected with advanced computer vision techniques and multimodal data, have the potential to distinguish groups with different collaborative learning outcomes. Insights generated can also support the practice of collaborative learning for learners and educators. Further research should explore the cross-context validity of the proposed distinctions and explore the approach’s potential to be developed as a real-world, real-time support system for collaborative learning.

Impacts of online-community-based collaborative learning on project scope appropriateness and stakeholder management

ABSTRACT Most corporate projects suffer from the problem of scope creep, despite of the methodologies available to cope with this issue. Organisations have utilised computer-supported collaborative learning (CSCL) approaches to enhance employees’ project management (PM) training. Most prior studies on CSCL and PM focus on the application of CSCL for PM training in the contexts of educational institutions. It is thus uncertain that their findings are applicable to the real-world PM situations. Additionally, those studies did not specifically investigate the effects of key PM-related CSCL features on PM learning. Therefore, this study identifies and empirically investigate the effects of the key CSCL features, namely goal orientation, individual accountability, and structured interaction, on the level of scope completeness and the effectiveness of stakeholder management (SHM) in a context in which an online case-based collaborative learning system was implemented for PM learning purposes. Data collected from 264 PM professionals were analyzed using the method of partial least squares to examine the proposed research model. The results show that all the three key CSCL features have a significant direct/indirect influence on the level of scope completeness and the SHM effectiveness. Implications for theory and practice, research limitations, and future research directions are discussed correspondingly.

Collaborative Fuzzy Linguistic Learning to Low-Resource and Robust Decision System Based on Bounded Rationality

Low-resource languages are challenging to process intelligent decision systems due to limited data and resources. As an effective way of processing low-resource languages in intelligent decision systems, fuzzy linguistic approaches excel in transforming original uncertain linguistic information into highly structured data and learning valid decision rules between complex data structures. However, existing fuzzy linguistic methods may not fully capture realistic features of multi-attribute group decision-making (MAGDM), such as incomplete and hesitant linguistic expressions, stable information fusion, and bounded rationality of decision-makers (DMs). Therefore, it is necessary to develop a collaborative fuzzy language learning system based on bounded rationality, low-resource and robust decision-making. Specifically, we present a new multi-granularity (MG) group decision-making (GDM) scheme by using MULTIMOORA (Multi-Objective Optimization by Ratio Analysis plus the full MULTIplicative form) and PT (Prospect Theory) for incomplete hesitant fuzzy linguistic information systems (I-HFL-ISs), where MG GDM aims to discover knowledge from complex MAGDM problems with MG features. To achieve the above goal, we first introduce the concept of MG-I-HFL-ISs to represent incomplete, hesitant and imprecise linguistic evaluation information offered by multiple decision-makers (DMs). Then, we apply a valid transformation scheme to convert MG-I-HFL-ISs into MG-HFL-ISs, and use the MG probability rough set (PRS) to develop a series of MG-HFL-PRSs with the support of MULTIMOORA. Afterwards, an HFL MG GDM method is designed by integrating MULTIMOORA and PT for solving MAGDM problems with MG-I-HFL-ISs. The proposed method can effectively synthesize low-resource languages and mine useful decision-making knowledge. At last, a drug selection case and a simulated case are performed for showing the rationality of the designed HFL MG GDM scheme.

An Evaluation of Redefining Education with Industry 4.0

In recent years, a new industrial paradigm known as Industry 4.0 has begun to trend in emerging technologies in the world, helping to bridge the gap between humans and machines in ways that can only be imagined in science fiction books. This technology is rapidly gaining traction in different parts of the world as a potential tool that can maximize corporate productivity, contribute to scientific growth, enrich a country's economy, and improve people's quality of life. This paper describes the concepts of the implementation of Industry 4.0 to redefine education in India. This study aims to identify the possible uses of Industry 4.0 technologies in the area of education and how they can be utilized to facilitate learning. The question is raised on why the Indian education system needs to implement Industry 4.0. A literature study method and a SWOT analysis were used in this study. The results show that it can help to achieve personalized learning, smart classrooms, Data analytics, collaborative learning, and learning management systems. Industry 4.0 has the potential to transform education in India by providing new tools and methods for teaching and learning that can enhance the quality and effectiveness of education.

A First Application of Collaborative Learning In Particle Physics

Over the last ten years, the popularity of Machine Learning (ML) has grown exponentially in all scientific fields, including particle physics. The industry has also developed new powerful tools that, imported into academia, could revolutionise research. One recent industry development that has not yet come to the attention of the particle physics community is Collaborative Learning (CL), a framework that allows training the same ML model with different datasets. This work explores the potential of CL, testing the library Colearn with neutrino physics simulation. Colearn, developed by the British Cambridge-based firm Fetch.AI, enables decentralised machine learning tasks. Being a blockchain-mediated CL system, it allows multiple stakeholders to build a shared ML model without needing to rely on a central authority. A generic Liquid Argon Time-Projection Chamber (LArTPC) has been simulated and images produced by fictitious neutrino interactions have been used to produce several datasets. These datasets, called learners, participated successfully in training a Deep Learning (DL) Keras model using blockchain technologies in a decentralised way. This test explores the feasibility of training a single ML model using different simulation datasets coming from different research groups. In this work, we also discuss a framework that instead makes different ML models compete against each other on the same dataset. The final goal is then to train the most performant ML model across the entire scientific community for a given experiment, either using all of the datasets available or selecting the model which performs best among every model developed in the community.

IMPLEMENTASI PEMBELAJARAN BERBASIS CASE METHOD DALAM MENINGKATKAN KEMAMPUAN BERKOMUNIKASI DAN CRITICAL THINKING MAHASISWA

: Participatory and collaborative learning systems, including case-based learning methods, are an alternative to adapt to the developments and challenges of the 21st century, which requires students to master the skills of communication and critical thinking. The purpose of this study is whether there are differences in students' communication skills and critical thinking through the application of case-based learning methods. How is the relationship between communication skills and critical thinking. This type of research is a quasi-experimental research. 2 groups of students who took the statistics course II semester IV were the research samples. The data analysis technique used independent t-test with prerequisite tests, namely homogeneity test and data normality test. As well as a correlation test to see the relationship between students' communication skills and critical thinking with the help of SPSS version 24. The results showed that there was an increase in students' communication skills in classes using case-based learning methods. There is an increase in students' critical thinking in classes that use case-based learning methods. There is a strong relationship between communication skills and students' critical thinking.

Rancang Sistem Presensi Online dengan Metode Gamifikasi dan Online Collaborative Learning

Online lectures are still being held while Covid-19 pandemic is going to end. Suitable system is needed to ensure the quality of online learning. We must combine the teleconference with the Collaborative Learning System to maintenance the interactions between students and their lecturer. The research is to build a system that can implement the Collaborative Learning System in online lectures. The methods used are gamification and Extreme Programming. The results of the research is the Online Presence application with chat system features, real-time polling system, real-time question-answer, and real-time leaderboard. The application can be accessed athttps://ikmiapp.web.id/presline.

Using quality improvement to deliver a systematic organisational approach to enjoying work in healthcare

Staff wellbeing is increasingly linked to good outcomes for service users in healthcare. Therefore, it is important for organisations to find ways to focus on wellbeing and staff experience at work. This article shares learning from 5 years of using the Institute for Healthcare Improvement's joy in work framework, coupled with quality improvement methods to enhance staff experience and wellbeing. This demonstrates how teams were brought together in a collaborative learning system to apply quality improvement to enhance joy in work. Key steps are shared for other organisations wanting to undertake this work, including the application of improvement methods to empower teams locally to develop, design and test change ideas, and measure their impact. The design of systems and structures required to meaningfully bring teams together and the type of leadership that enhances this work are also considered. Key learning points for other organisations include the need for improvement principles to iterate the organisational approach, make measurement simple, encourage a bias to action and make the work fun.

Multi-Agent-Based Film Editing Collaboration System.

In order to realize the effective cooperation between editor agents in the film and television editing collaboration system, it is analyzed that the state change of the film and television editing and production process is affected by the cross influence of multiple factors. A single agent can no longer satisfy the current film and television production. From the point of view of system theory, this article constructs the learner agent in the film and television editing system by introducing a new cooperation mechanism—the multi-agent collaborative system model. Collaboration and cooperation between multiple agents and the reinforcement learning between multiple editor agents are realized based on the film and television editing system between multiple agents. The operation mechanism of the separate organization is organized together, cooperates with each other and works in harmony to complete the collaborative effect of the film and television editing system, and can improve the interaction efficiency between the editor agents. Agent film and television editing's cooperative learning approach allows for successful collaboration among editor agents. The Bayesian technique is utilized in this study to assess the likelihood of effective cooperation between two agents, and a trust model based on this method is presented, making up for the shortcomings of the existing collaborative learning system. The multi-agent collaboration system will be utilized for production in the film and television editing collaboration system. Many of the movie's scenes and segments are created using computer technology special effects, giving viewers a very unique experience and a feast for the eyes and ears.

The mental health safety improvement programme: a national quality improvement collaborative to reduce restrictive practice in England

In 2018, 38 mental health inpatient wards belonging to NHS trusts across England took part in the national reducing restrictive practice collaborative project, which aimed to reduce the use of rapid tranquillisation, restraint and seclusion of patients by 33%. Teams were supported to use quality improvement tools by skilled coaches as part of a national collaborative learning system. At the end of the programme, the overall use of restrictive practice had reduced by 15%. Of the teams that achieved improvements, the average reduction in restrictive practice was 61%. Across the collaborative there were improvements in the mean monthly use of restraints and rapid tranquillisation, and in the total use of all three measures of restrictive practice combined. Support from quality improvement coaches allowed ideas to be tested across the collaborative, enabling the creation of a theory of change for reducing restrictive practice based on areas with a high degree of belief to inform future improvement work in this area.

Connecting digital literacy in higher education to the 21st century workforce

The remarkable advancements in technology have affected the way people engage, work, and learn. Digital literacy, also known as virtual learning, has the potential to improve lifelong learning. Workplace skills evolve at such a rapid pace that no school system can keep up with the continual need to alter how we work and live. Most crucially, our society's profound changes require young people to acquire new abilities. Malaysia has a long-term vision that calls for sustainable and productivity-driven growth that can only be accomplished with digitally literate employees. Although to some extent Malaysia education system has been initiating, there is very limited research that focuses on what drives digital literacy. There is no proper framework or guidelines that can be used as a blueprint to prepare the young graduates in the 21st-century workforce. The purpose of the study is to examine the drivers of digital literacy that can be taught in higher institutions and apply in today's digital workplace. This research focused on young adults as a unit of analysis and a quantitative method was used to collect the data. A total of 300 young individuals responded through self-administered questionnaires. The finding of the research showed that critical skills, operational skills, visual learning style, collaborative learning style and learning system enhance digital literacy. Finding further recommend that digital literacy improve both academic performance and employability. From this research, solutions can be proposed to both academicians and employers in achieving the digital literate graduates for the 21st-century workforce.

Design of a web-based learning model: Shifting the accent from knowledge transmission to knowledge construction

The aim of this work is to design a web-based learning model using learning techniques based on knowledge construction in order to increase learners’ competency in higher education.
 Since knowledge is under a change as a result of improvements in the technology, the learning approaches that levitate around students’ learning activities could be considerably improved by web-based learning environments that switched education from knowledge transmission to knowledge construction. In addition to the development of learning patterns, educational technologies are constantly expanding. Changes produced by universities, course content, quality assurance, educational leadership, cultural and ethical occurrences have to be considered in the development of web-based learning in order to meet their requirements. But even now, much of the web-based learning environments are accomplished without embedding pedagogical considerations based on learning issues and learner-centred paradigm.
 This paper analyses and states the principles that could be implemented in a web-based learning model relying on the combination of various aspects of e-learning strategies, pedagogical insights, as well managerial and technological techniques. The key point is the cognitive change that shapes learning behaviour from simple information transmission to a constructivist way. Acting as a present-day educational framework of approaches for effective web-based learning, the research presents a set of steps following the exploration of instructional context concerning learning theories and pedagogical principles of the web-based learning paradigm.
 The approaches investigated by this research are settled on the base of specific references, European recommendations, theoretical researches regarding the vision of web-based learning environments, and literature relevant case studies. The paper proposes that, as a part of the shared technology environment, more attention need to be concentrated on developing and reinforcing the collaborative and constructive web-based learning system in higher education. As well, the author brings out the lack of the researches regarding web-based learning applied in higher education of the Republic of Moldova and proposes a particular and modern web-based learning paradigm.

Mobile learning in higher education environmental science: state of the field and future possibilities

Authentic, place-based learning is essential for students of ecological and environmental sciences, providing connection to the discipline and building environmental literacy (O’Neil et al. 2020). In a COVID-affected world where opportunities to provide field-based learning may be limited, evaluating how mobile technologies may be used to enhance the field-based learning experiences of students is increasingly important.
 Advances in mobile technologies have seen a surge in customised applications for species identification, data collection and collation aimed at public users and citizen scientists (e.g. iNaturalist: Unger et al. 2020; eBird: Sullivan et al. 2009; FrogID: Rowley et al. 2019). With field-based learning central to ecology and environmental science disciplines, there is a clear opportunity for the expanded use of mobile tools in higher education. We evaluated recent projects through a systematic review of the use of mobile learning technologies and approaches in field-based environmental sciences within higher education over the last decade.
 Our search criteria terms encompassed mobile learning, mobile devices, teaching methods, field-based learning, undergraduate students and science disciplines and identified 1613 initial records. After removing irrelevant and duplicate records, 130 studies were identified that implemented mobile learning within science, technology, engineering and mathematics (STEM) disciplines, with engineering (32/130 studies, 24.6%), geology and geosciences (17/130, 13.1%) and natural/environmental sciences (17/130, 13.1%) the most common. Narrowing this search again to field-based studies, we identified 18 records, most of which (12/18, 66.7%) were in geology and geosciences disciplines.
 A range of mobile learning technologies were used in the field, spanning the SAMR continuum (Laurillard 2012) from the substitution of traditional field activities with species identification apps (Pfeiffer et al. 2009; Thomas and Fellowes 2017), and augmentation of field experiences with multimedia resources such as podcasts (Jarvis and Dickie 2010) and other apps and resources viewed on mobile devices (Welsh et al. 2015; France et al. 2016; Unger et al. 2018), through to the modification and reinvention of field-based learning by incorporating multimedia displays, visualisations, games and information hotspots (Habib et al. 2012; Fitzpatrick et al. 2012; Bursztyn et al. 2015), virtual field trips and augmented reality (Stokes et al. 2010; Howard 2011; Litherland and Stott 2012; Kingston et al. 2012; Bursztyn et al. 2017; Prietnall et al. 2019), and customised apps that allow student-generated content (Chang et al. 2012) such as data collection, analysis and reflection (Chatterjea 2012; Wang et al. 2016). Studies used both enterprise and custom-built tools, with most incorporating geolocation capabilities.
 Our review criteria only identified two studies in ecology disciplines, both of which utilised an existing enterprise application for species identification (Pfeiffer et al. 2009; Thomas and Fellowes 2017). There remains ample opportunity to develop collaborative mobile learning systems that use custom-built applications for field data collection and are integrated with the learning management systems, such as those in development in collaborative international projects (Bone et al. 2020). We strongly encourage the exploration of the potential for mobile learning in these contexts, and the publication of other projects that have incorporated mobile tools in ecological and environmental sciences curricula.

Designing a Co-creation System for the Development of Work-process-related Learning Material in Manufacturing

The increasing digitalization and automatization in the manufacturing industry as well as the need to learn on the job has reinforced the need for much more granular learning, which has not yet impacted the design of learning materials. In this regard, granular learning concepts require situated learning materials to support self-directed learning in the workplace in a targeted manner. Co-creation approaches offer promising opportunities to support employees in the independent design of such situated learning materials. Using an action-design research (ADR) approach, we derived requirements from co-creation concepts and practice by conducting focus group workshops in manufacturing and vocational training schools to develop design principles for a co-creation system that supports employees through the creation process of work-process-related learning material. Consequently, we formulate four design principles for the design of a collaborative learning and qualification system for manufacturing. Using an innovative mixed methods approach, we validate these design principles and design features to demonstrate the success of the developed artifact. The results provide insights regarding the design of a co-creation system to support learners in the co-creation of learning material with the consideration of cognitive load (CL). Our study contributes to research and practice by proposing novel design principles for supporting employees in peer creation processes. Furthermore, our study reveals how co-creation systems can support the collaborative development of learning materials in the work process.

Blind Federated Learning at the Wireless Edge With Low-Resolution ADC and DAC

We study collaborative machine learning systems where a massive dataset is distributed across independent workers which compute their local gradient estimates based on their own datasets. Workers send their estimates through a multipath fading multiple access channel with orthogonal frequency division multiplexing to mitigate the frequency selectivity of the channel. We assume that there is no channel state information (CSI) at the workers, and the parameter server (PS) employs multiple antennas to align the received signals. To reduce the power consumption and the hardware costs, we employ complex-valued low-resolution digital-to-analog converters (DACs) and analog-to-digital converters (ADCs), at the transmitter and the receiver sides, respectively, and study the effects of practical low-cost DACs and ADCs on the learning performance. Our theoretical analysis shows that the impairments caused by low-resolution DACs and ADCs, including those of one-bit DACs and ADCs, do not prevent the convergence of the federated learning algorithms, and the multipath channel effects vanish when a sufficient number of antennas are used at the PS. We also validate our theoretical results via simulations, and demonstrate that using low-resolution, even one-bit, DACs and ADCs causes only a slight decrease in the learning accuracy.