• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.3
• /
• pp.81-89
• /
• 2012

This paper presents a set of controlled simulated statical and engineering mechanical experiments accessible via the virtual world environment (VWE) and virtual physics lab S/W. Online courses of the university offering courses and/or programs online are growing and the number of students want education in ways which fit their personal places, e-learning is becoming more important and ubiquitous each year. In this study, first of all, question is rather 'How do we execute the learning effectiveness of e-learning courses?' than 'Why does they need e-learnig or VW-learning?'. In particular, is it possible to effectively teach mechanical engineering courses online? The answer was 'No'. So, there is little research on many of these questions. And another important question is 'Is e-learning cost effective?'. For the answer, This research provided that an instructional design model is used to 'How to think and apply the Newtonian forces' in the virtual physics lab S/W. Collected data from student are administered in the spring semester when students studied 'Introduction to Bio-resources and Systems Engineering'. Results show that a cadre of students can take highly interactively physical properties of mechanical engineering in the virtual laboratory environment. Those show that VWE is greater than that of a similar real world presentation or experimental lab, since most of students are delighted to modify and retry modeling works in the VWE.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.13-18
• /
• 2022

In this paper, we proposed VW-FedAVG(Validation based Weighted FedAVG) which updates the global model by weighting according to performance verification from the models of each device participating in the training. The first method is designed to validate each local client model through validation dataset before updating the global model with a server side validation structure. The second is a client-side validation structure, which is designed in such a way that the validation data set is evenly distributed to each client and the global model is after validation. MNIST, CIFAR-10 is used, and the IID, Non-IID distribution for image classification obtained higher accuracy than previous studies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2093-2108
• /
• 2017

In this paper, we describe a novel method for recognizing human actions from different views via view knowledge transfer. Our approach is characterized by two aspects: 1) We propose a unsupervised topic transfer model (TTM) to model two view-dependent vocabularies, where the original bag of visual words (BoVW) representation can be transferred into a bag of topics (BoT) representation. The higher-level BoT features, which can be shared across views, can connect action models for different views. 2) Our features make it possible to obtain a discriminative model of action under one view and categorize actions in another view. We tested our approach on the IXMAS data set, and the results are promising, given such a simple approach. In addition, we also demonstrate a supervised topic transfer model (STTM), which can combine transfer feature learning and discriminative classifier learning into one framework.