In light of the COVID-19 epidemic, many educational institutions throughout the globe now need online instruction. Using digital tools and platforms, include teaching, testing, and encouraging student participation. T...
详细信息
ISBN:
(纸本)9798350391558;9798350379990
In light of the COVID-19 epidemic, many educational institutions throughout the globe now need online instruction. Using digital tools and platforms, include teaching, testing, and encouraging student participation. These are some of the main features and difficulties of teaching remotely during the epidemic. To hold lessons and communicate with students, teachers use a variety of online platforms including Zoom, Google Meet, Microsoft Teams, or specialised learning Management Systems (LMS) like Canvas or Moodle. To effectively engage students and transmit concepts, teachers modify their teaching strategies to fit the needs of online settings. This includes adding multimedia materials, interactive exercises, and virtual simulations. It might be difficult to evaluate pupils' learning progress from a distance. Instructors can measure their student's comprehension through online tests, projects, assignments, and peer evaluations. For students to progress, timely feedback via digital channels is crucial. The inequitable availability of technology and dependable internet connections among students may impede their engagement in remote learning environments (RLE). It could be necessary for educators to come up with other strategies to guarantee that every student has access to learning resources and can engage in class activities. The use of Online Education Technology (OET) has been expedited by the epidemic. Online instruction will probably continue to be a crucial component of education even after the epidemic passes, necessitating continuous funding for curriculum creation, infrastructure, and training. A statistical analysis of how the student communities were impacted by internet-based education during the COVID-19 pandemic using Machine learning (ML).
Course evaluation plays a crucial role in analysing the effectiveness of a course. Despite the emerging trend of applying learning analytics approaches to course evaluation, only limited research has been conducted on...
详细信息
ISBN:
(纸本)9789819744411;9789819744428
Course evaluation plays a crucial role in analysing the effectiveness of a course. Despite the emerging trend of applying learning analytics approaches to course evaluation, only limited research has been conducted on reviewing and examining the features of relevant practices. This study analysed the learning analytics approaches used for supporting course evaluation. It covered 27 empirical studies collected from Scopus that were published between 2013 and 2022. The results show the purposes of course evaluation based on learning analytics, including the enhancement of learning experience, effectiveness in learning and teaching, and learning performance and engagement. They also highlight the popular types of data for the learning analytics approaches, such as student performance, feedback, and online learning behaviours, as well as the analytical methods frequently applied, such as statistical tests, content analysis, and descriptive statistics. Additionally, the data visualisation methods most frequently used are also identified, such as tables, bar charts, and line charts. These findings inform the use of learning analytics in course evaluation and provide practical references for its implementation.
In this paper, we present AnaVu, a light weight visualization system for teaching 3D anatomy at classroom scale. We propose a stereoscopic system along with an easy to use interface as a scalable 3D visual aid as oppo...
详细信息
ISBN:
(纸本)9781665453318
In this paper, we present AnaVu, a light weight visualization system for teaching 3D anatomy at classroom scale. We propose a stereoscopic system along with an easy to use interface as a scalable 3D visual aid as opposed to learning from traditional 2D images. This is an alternative to VR/XR devices that can only serve a handful of students and are heavy on computational resources. For large scale classes (similar to 50-150 students) 3D visualization provides good feedback of spatial relations, with stereoscopic projection further providing depth cues to distinguish fine structures. The visualization is controllable by the lecturer with the ability to control interactive operators along with labels, animations and multimedia capabilities. Lessons can be premeditated and loaded quickly in class to integrate with the ongoing lecture. A quantitative evaluation on 43 students yielded results which show the proposed solution to be viable and effective for learning.
Machine learning education related applications have increased with the appearance of large language models. While automatic essay grading (AEG) has been studied extensively in the past, most of these studies have foc...
详细信息
ISBN:
(纸本)9781665453318
Machine learning education related applications have increased with the appearance of large language models. While automatic essay grading (AEG) has been studied extensively in the past, most of these studies have focused on evaluating English competence instead of assessing knowledge competence in an engineering field. This study aimed to develop an AEG model to evaluate student's mechanical engineering Constructive Response Test (CRT) question responses which were instructor graded. Because of the small number of student responses (45), a synthesized set of responses was also generated by using text-to-text paraphrasing models. A neural network grading engine was built and trained to assess comprehension utilizing the Bidirectional Encoder Representation Transformer (BERT) and related models on student and synthesized responses. This study showed that the AEG based Natural Language Processing (NLP) model showed high accuracy and a higher degree of consistency in grading student responses compared to instructor-graded responses.
Time series forecasting is a valuable tool for many applications, such as stock price predictions, demand forecasting or logistical optimization. There are many well-established statistical and machine learning models...
详细信息
ISBN:
(纸本)9798331541378
Time series forecasting is a valuable tool for many applications, such as stock price predictions, demand forecasting or logistical optimization. There are many well-established statistical and machine learning models that are used for this purpose. Recently in the field of quantum machine learning many candidate models for forecasting have been proposed, however in the absence of theoretical grounds for advantage thorough benchmarking is essential for scientific evaluation. To this end, we performed a benchmarking study using real data of various quantum models, both gate-based and annealing-based, comparing them to the state-of-the-art classical approaches, including extensive hyperparameter optimization. Overall we found that the best classical models outperformed the best quantum models. Most of the quantum models were able to achieve comparable results and for one data set two quantum models outperformed the classical ARIMA model. These results serve as a useful point of comparison for the field of forecasting with quantum machine learning.
Context: Recent years have witnessed a noteworthy surge in the emphasis on research and practice in Empirical Software engineering (ESE). However, teaching this discipline through traditional pedagogical methods prese...
详细信息
ISBN:
(纸本)9798400704987
Context: Recent years have witnessed a noteworthy surge in the emphasis on research and practice in Empirical Software engineering (ESE). However, teaching this discipline through traditional pedagogical methods presents a challenge. Students typically acquire theories and concepts through lectures or expository classes but have limited opportunities to apply this knowledge. Goal: This report aims to share our experiences with the instructional process, using the Active learning approach within the context of ESE education. Method: We describe an ESE course that was taught using active methodology principles. At the end of the course, we conducted a personal opinion survey to gather students' feedback. Results: The findings indicated that Active learning principles can offer several advantages in ESE education. These include improved comprehension of course material, better retention of knowledge gained during classes, and enhanced preparation for involvement in scientific research. Conclusion: This experience provides insights into incorporating active learning principles into an ESE course. We also discuss lessons learned and suggest areas for improvement in future ESE courses.
Design thinking has been gaining importance in engineering education worldwide. There is ample information available on design thinking course content, but limited information is available about details of execution o...
详细信息
ISBN:
(纸本)9781665453318
Design thinking has been gaining importance in engineering education worldwide. There is ample information available on design thinking course content, but limited information is available about details of execution of the course especially for a large group of students. At the Singapore University of Technology and Design (SUTD), all the 400 over first-year undergraduate students go through the introductory course on design thinking which has a strong focus on technology. We use this context to look at the processes involved in the effective delivery of the design thinking course. The process components discussed are - course delivery format, assignment design, diverse mentorship, access to past projects and teamwork facilitation. Through our discussion we highlight how these processes - reinforce the design thinking philosophy of balancing divergence and convergence (course delivery, assignment design), inculcate the habit of exploring beyond boundaries (assignment design), develop the capability of processing diverse input (diverse mentorship), reinforce the importance of following the design thinking process for problem solving (access to past projects), and support the pedagogical approach of project based learning (teamwork facilitation). The article intends to stimulate further exploration on course development through process perspective.
learning the problem structure at multiple levels of coarseness to inform the decomposition-based hybrid quantum-classical combinatorial optimization solvers is a promising approach to scaling up variational approache...
详细信息
ISBN:
(纸本)9798331541378
learning the problem structure at multiple levels of coarseness to inform the decomposition-based hybrid quantum-classical combinatorial optimization solvers is a promising approach to scaling up variational approaches. We introduce a multi-level algorithm reinforced with the spectral graph representation learning-based accelerator to tackle large-scale graph maximum cut instances and fused with several versions of the quantum approximate optimization algorithm (QAOA) and QAOA-inspired algorithms. The graph representation learning model utilizes the idea of QAOA variational parameters concentration and substantially improves the performance of QAOA. We demonstrate the potential of using multilevel QAOA and representation learning-based approaches on extensive graphs by achieving high-quality solutions much faster. Reproducibility: Our source code and results are available at https://***/bachbao/MLQAOA
Open digital badges (OB) and micro-accreditation (MA) linked to micro-credentials (MC) are effective means for recognizing skills and competencies, of any kind, in an open, digital, and shareable way. Latin American e...
详细信息
ISBN:
(纸本)9783031530210;9783031530227
Open digital badges (OB) and micro-accreditation (MA) linked to micro-credentials (MC) are effective means for recognizing skills and competencies, of any kind, in an open, digital, and shareable way. Latin American engineering universities are currently discussing the benefits of using these strategies as a complement to the student's final degree. In this scenario, the organizers of the internationalengineering Educator Certification Program (IEECP) decided to address the use of OB in this program through its integration into a Moodle based learning Management System (LMS). This paper describes the ongoing experience developed by the IGIP Accredited Training Center (ATC) InnovaHiEd Academy, regarding the use of OB in the IEECP, the motivation and educational decisions that led to the use of this open and universal method for the recognition of competencies, and its integration into the IEECP LMS. Moreover, this study presents evidence regarding the impact of OB and MA on the program teaching practices and participant's engagement. This paper is expected to contribute as a reference for other investigations that address these topics, for those institutions interested in considering this approach in their learning programs and for other IGIP ATCs.
Deep learning (DL) approaches are utilized across three distinct contexts to showcase their applicability in commercial environments with restricted data for training. This study showcases the application of unsupervi...
详细信息
暂无评论