Water is one of the most essential natural resources for the sustenance of humankind. Despite its renewable nature, water faces considerable challenges arising from urban growth, climate change, and deforestation. Eff...
详细信息
ISBN:
(纸本)9798350370058;9798350370164
Water is one of the most essential natural resources for the sustenance of humankind. Despite its renewable nature, water faces considerable challenges arising from urban growth, climate change, and deforestation. Effectively managing water to meet the demands of agricultural activities remains a formidable task due to the inherent difficulty in predicting water quantities. This study addresses these concerns by tapping into the rapid advancement of computing power on edge devices and employing federated learning techniques. Deploying and training prediction models on resource-limited devices allows for rapid prediction and response to water levels, outpacing conventional deployment and training on centralized servers. However, the distribution of water level stations in Thailand presents a problem in transferring prediction models from edge devices for aggregation on a central server due to communication cost constraints. Consequently, this paper applied hierarchical federated learning to predict water levels in Thailand. This approach aims to reduce communication overhead and enhance scalability. The study examined the clustering of water level stations in Thailand based on Harversine distance, aiming to balance between reducing communication costs and minimizing accuracy loss. As a result, the proposed approach clusters the water level stations into ten clusters. This clustering yields a reduction in distance from local water level stations of 78.02%.
The incorporation of technology and teaching-learning techniques evolves over time. However, the methodological aspects seem to remain fairly invariant as well as the teaching strategies. These continuous incorporatio...
详细信息
Training science and engineering students to become responsible citizens and professionals requires novel and creative pedagogical approaches, such as design thinking. This concept relies on processes and tools to dev...
详细信息
ISBN:
(纸本)9781665453318
Training science and engineering students to become responsible citizens and professionals requires novel and creative pedagogical approaches, such as design thinking. This concept relies on processes and tools to develop creativity and problem-solving skills with a human-centered mindset in learning scenarios. This article presents the implementation of a digital intervention designed to support collaboration in design thinking activities. These activities are built around the Sustainability Value Proposition Canvas. This canvas was developed to structure the collaborative design of a human-centered value proposition. Our results indicate that the students adopted a human-centered approach. We observed that contributions to the value proposition were evenly distributed within the groups. Our observations suggest that collaboration was not impaired by the usage of digital tools. They revealed that the students worked in parallel but did not build on each other's contributions most of the time. Finally, our data shed light on a difference between the usage of two types of collaborative digital tools, a virtual canvas and a text editor. In addition to these results, we demonstrate how learning analytics can be harnessed to reconstruct and analyze design processes. This paper contributes to science and engineering education by providing new insights on teamwork activities supported by digital tools in design-based learning scenarios.
This papermainly explores how to improve the performance of knowledge graph reasoning in natural language processing, especially in few-shot learning scenarios, by utilizing Graph Convolutional Networks (GCN), the met...
详细信息
ISBN:
(纸本)9789819756711;9789819756728
This papermainly explores how to improve the performance of knowledge graph reasoning in natural language processing, especially in few-shot learning scenarios, by utilizing Graph Convolutional Networks (GCN), the meta-learning algorithm Reptile, and Reinforcement learning. In this work, the study proposed a novel model, REGCKG, which combines the advantages of GCN, meta-learning, and reinforcement learning to effectively handle relationships with a small number of samples in knowledge graphs. REGCKG uses GCN to encode path information and utilizes Reptile to learn meta-parameters from high-frequency relationships, and then uses the meta-parameters to adapt to few-shot tasks, improving the model's generalization ability on few-shot data.
Artificial Intelligence (AI) is at the cusp of disruptive force across sectors, and the application in higher education stands to deeply transform it. This paper, therefore, wrestles in great depth with the many-facet...
详细信息
Microelectronics is an important field that has the potential to revolutionize many industries, offering numerous c areer opportunities, including research and development, desig n, manufacturing, and testing. The cur...
详细信息
ISBN:
(纸本)9781665453318
Microelectronics is an important field that has the potential to revolutionize many industries, offering numerous c areer opportunities, including research and development, desig n, manufacturing, and testing. The current state of undergradu ate education in this field is outdated and inadequate to meet th e demands of the modern industry. Despite the importance of t his field, there are several challenges facing undergraduate cou rses in this area. In this part, we will discuss the current state a nd urgent necessity of reformation in microelectrics undergrad uate education. We will also discuss the advantages and disadv antages of incorporating Chat-Bots into microectronics educati on.
This study explores the effect of mobile-based peer feedback on enhancing ESL learners' language proficiency, engagement, and collaboration. By leveraging mobile technology to facilitate peer assessments, the rese...
详细信息
The computing sector has undergone radical changes in the last few decades. Conventional computers use binary (1s and 0s) numbers to perform tasks that are specified by the user. Using the concepts of quantum physics,...
详细信息
University of Nottingham Ningbo China (UNNC) has been investigating the use of an augmented-reality (AR) educational game to aid in the teaching of Design for Manufacturing and Assembly (DfMA) theories in design and e...
详细信息
ISBN:
(纸本)9781665453318
University of Nottingham Ningbo China (UNNC) has been investigating the use of an augmented-reality (AR) educational game to aid in the teaching of Design for Manufacturing and Assembly (DfMA) theories in design and engineering education (DEE). DfMA mastery is critical, as it allows students to create products that are feasible for mass production;it increases material optimization, shortens manufacturing times, and elevates overall quality. However, feedback from students and published research indicates that the topic is complex and underappreciated. Utilizing AR and gamification (GF) is relatively novel in this context, but it has the potential to redefine the topic by giving each student an enhanced learning experience that is fun, engaging, visually appealing, and cognitively stimulating. Our game was developed by a Students-as-Partners (SaP) team at UNNC and combines a tangible puzzle with an AR interface, encouraging collaboration, cooperation, and reflective practices. This research focuses on undergraduate DDE students and aims to understand students' perceptions of AR educational games and their influence on students' intrinsic motivation and performance. The results of this study inform the deployment of AR technology in classroom settings, as well as the instructional design of AR and GF learning experiences.
The advent of Artificial Intelligence (AI) in this fast-changing education landscape promises to be one of the transformative forces, altering the mode of curation and delivery of educational content. This paper, henc...
详细信息
暂无评论