learning can be greatly enhanced by effective feedback. Traditional assessment approaches in higher education often result in feedback being used to justify marks awarded, which is often disregarded once the assessmen...
详细信息
ISBN:
(纸本)9798350322590
learning can be greatly enhanced by effective feedback. Traditional assessment approaches in higher education often result in feedback being used to justify marks awarded, which is often disregarded once the assessment is complete. In this paper, we explore the idea of incorporating a focus mechanism to connect feedback between assessment tasks and units, discuss how this can be applied to enhance software engineering education, and present results from several staff focus groups exploring the idea. The focus groups discussed the model, its application within software engineering units, and its limitations, with staff helping co-create the enhancements to the model through discussing experiences/sharing opinions/providing insights on assessment within their units. Results indicate that staff believe that the changes will benefit their teaching and highlighted several opportunities for this initiative to encourage students to have a more holistic view of their studies. The main challenges identified were staff workload and complexity for students which must be addressed in implementing this idea.
With the integration of renewable energy sources and new power electronic devices, power grid complexity has increased, leading to frequent power quality disturbances. Existing classification models often require retr...
详细信息
With the improvement of network environment quality and the enrichment of teaching content, video learning has become a powerful supplement to the normal teaching process. It is necessary to perceive the emotional sta...
详细信息
The evolution that has been observed in the dynamic field of object identification in the past few years is remarkable, because of the integration of sophisticated learning techniques. The review presented in this pap...
详细信息
In recent years, the development of AI technology has driven the development of network edge applications such as smart manufacturing, smart factories, and smart cities. Deep neural networks are increasingly being dep...
详细信息
Use-inspired artificial intelligence (AI) tailors deep-learning models for image processing tasks in targeted scientific domains. These use-inspired models meet domain requirements for accuracy while parsimoniously us...
详细信息
ISBN:
(纸本)9798331528690;9798331528706
Use-inspired artificial intelligence (AI) tailors deep-learning models for image processing tasks in targeted scientific domains. These use-inspired models meet domain requirements for accuracy while parsimoniously using compact and efficient model architectures needed for inference in the field. However, before settling upon a model, domain experts repeatedly train and test models over a wide range of hyperparameters, contextual settings, and data configurations, making model training bespoke, time-consuming, and costly. Model-training-as-a-Service (MTaaS), i.e., cloud services designed for generic training workloads, can reduce training costs, but domain-aware designs and runtime adaptations could yield further reductions. This paper characterizes the potential for domain-aware design and runtime adaptation for MTaaS in digital agriculture. First, we studied the time to train models for 10 use-inspired agricultural datasets using pre-trained model weights derived from other agricultural datasets versus pre-trained weights derived from ImageNet, a widely used benchmark. Using agricultural datasets sped training time by up to 2X for some datasets, but provided modest speedups (< 1.07) in the common case;Choosing the right dataset is critical. Next, we present an approach to predict training time given domain-aware pre-trained weights. Our predictions are strongly correlated with training time (r = 0.93). Finally, we studied the use of domain-aware pre-trained weights in a MTaaS under Poisson and bursty arrival patterns for training tasks. Under bursty arrivals and tight memory constraints, domain-aware MTaaS reduced training time by 2.8X and 12.2X compared to model training using pre-trained ImageNet weights and from scratch, respectively.
With the advancement of online learning technologies, translation learning, teaching, and learning motivation have been influenced and even reshaped. So, there is a need for empirical investigations on the motivation ...
详细信息
ISBN:
(纸本)9783031330223;9783031330230
With the advancement of online learning technologies, translation learning, teaching, and learning motivation have been influenced and even reshaped. So, there is a need for empirical investigations on the motivation in learning translation online. Under the framework of the L2 Motivation Self System, this study uses exploratory factor analysis and structural equation model to analyze 150 college students' motivation for online translation learning and identifies six motivation factors: IL2S Factor, Escape/Stimulation Factor, Social Contact Factor, Social Service Factor, L2LE Factor, and OL2S Factor. The research findings show that motivation in online translation learning is not instrumental, and the Ideal L2 Self is the most significant and dominant motivation in online translation learning.
Traffic data analysis and forecasting is a multidimensional challenge that extracts details from sources such as social media and vehicle sensor data. This study proposes a three-stage framework using Deep learning (D...
详细信息
The use of extended time series to gather and store huge datasets has been made simpler by information science and data capture technologies. In many fields, such as astronomy, the environment, economics, business, me...
详细信息
The slow real-time and historical data processing speed and insufficient data storage capacity of power grid equipment operation have led to an increase in risk detection time and a decrease in accuracy., A risk detec...
详细信息
暂无评论