• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.8
• /
• pp.3452-3457
• /
• 2011

This paper introduces a case study on the development of the evaluation system for capstone design course which is usually provided at engineering education program. A capstone design is an engineering education course which aims to improve the students' ability on analysis and design of practical industrial problems by use of overall engineering knowledge which has been learned in undergraduate program. Firstly, this paper provides a literature review on evaluation indices and methods related with a capstone design course. Secondly, the evaluation system for learning outcomes of capstone design course is described. The evaluation system for learning outcomes of capstone design course provided in this paper could be referred by other universities opening a capstone design course, and used to design an evaluation system for internship program or education course which is provided as an industry-academic connection program.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.57-66
• /
• 1994

In this paper, we present an iterative learning method of compensating for position sensor error. The previously known compensation algorithms need a special perfect position sensor or a priori information about error sources, while ours does not. to our best knowledge, any iterative learning approach has not been taken for sensor error compensation. Furthermore, our iterativelearning algorithm does not have the drawbacks of the existing interativelearning control theories. To be more specivic, our algorithm learns an uncertain function itself rather than its special time-trajectory and does not reuquest the derivatives of measurement signals. Moreover, it does not require the learning system to start with the same initial condition for all iterations. To illuminate the generality and practical use of our algorithm, we give the rigorous proof for its convergence and some experimental results.

• Journal of the Korean Institute of Educational Facilities
• /
• v.10 no.3
• /
• pp.27-36
• /
• 2003

This paper aims to analyse facilities and characteristics of management for 21 model schools' open education system. So, we analyzed the class management and the methods of open education, teacher's mind, the shape and form of study group and we investigated teachers' satisfaction rate about the physical space. As a result, it is considered that the change for structure of learning space unit is needed because of the limitation in standard class size by the rule for construction. Considering the decrease of real using space by the space of learning materials or learning furniture, it should enlarge the structure of learning space unit or decrease the number of students. And to use multipurpose space practically as a place of study, it need that the multiple support of study program for teachers by government, support in course of study, giving training opportunity to teachers, distribution of personal management.

• Journal of KIBIM
• /
• v.9 no.1
• /
• pp.42-51
• /
• 2019

Maintenance of aging structures has attracted societal attention. Maintenance of the aging structure can be efficiently performed with a digital twin. In order to maintain the structure based on the digital twin, it is required to accurately detect the damage of the structure. Meanwhile, deep learning-based damage detection approaches have shown good performance for detecting damage of structures. However, in order to develop such deep learning-based damage detection approaches, it is necessary to use a large number of data before and after damage, but there is a problem that the amount of data before and after the damage is unbalanced in reality. In order to solve this problem, this study proposed a method based on Generative adversarial network, one of Generative Model, for generating acceleration data usually used for damage detection approaches. As results, it is confirmed that the acceleration data generated by the GAN has a very similar pattern to the acceleration generated by the simulation with structural analysis software. These results show that not only the pattern of the macroscopic data but also the frequency domain of the acceleration data can be reproduced. Therefore, these findings show that the GAN model can analyze complex acceleration data on its own, and it is thought that this data can help training of the deep learning-based damage detection approaches.

• Psychiatry investigation
• /
• v.15 no.11
• /
• pp.1030-1036
• /
• 2018

Objective In this study, we aimed to develop a model predicting individuals with suicide ideation within a general population using a machine learning algorithm. Methods Among 35,116 individuals aged over 19 years from the Korea National Health & Nutrition Examination Survey, we selected 11,628 individuals via random down-sampling. This included 5,814 suicide ideators and the same number of non-suicide ideators. We randomly assigned the subjects to a training set (n=10,466) and a test set (n=1,162). In the training set, a random forest model was trained with 15 features selected with recursive feature elimination via 10-fold cross validation. Subsequently, the fitted model was used to predict suicide ideators in the test set and among the total of 35,116 subjects. All analyses were conducted in R. Results The prediction model achieved a good performance [area under receiver operating characteristic curve (AUC)=0.85] in the test set and predicted suicide ideators among the total samples with an accuracy of 0.821, sensitivity of 0.836, and specificity of 0.807. Conclusion This study shows the possibility that a machine learning approach can enable screening for suicide risk in the general population. Further work is warranted to increase the accuracy of prediction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.911-931
• /
• 2021

Recently, most cloud services use Docker container environment to provide their services. However, there are no researches to evaluate the performance of communication libraries for multi-GPU based distributed deep learning in a Docker container environment. In this paper, we propose an efficient communication architecture for multi-GPU based deep learning in a Docker container environment by evaluating the performances of various communication libraries. We compare the performances of the parameter server architecture and the All-reduce architecture, which are typical distributed deep learning architectures. Further, we analyze the performances of two separate multi-GPU resource allocation policies - allocating a single GPU to each Docker container and allocating multiple GPUs to each Docker container. We also experiment with the scalability of collective communication by increasing the number of GPUs from one to four. Through experiments, we compare OpenMPI and MPICH, which are representative open source MPI libraries, and NCCL, which is NVIDIA's collective communication library for the multi-GPU setting. In the parameter server architecture, we show that using CUDA-aware OpenMPI with multi-GPU per Docker container environment reduces communication latency by up to 75%. Also, we show that using NCCL in All-reduce architecture reduces communication latency by up to 93% compared to other libraries.

• Journal of Drive and Control
• /
• v.19 no.3
• /
• pp.9-15
• /
• 2022

This paper proposes a method for constructing and verifying datasets used in deep learning technology, to prevent safety accidents in automated construction machinery or autonomous vehicles. Although open datasets for developing image recognition technologies are challenging to meet requirements desired by users, this study proposes the interface of virtual simulators to facilitate the creation of training datasets desired by users. The pixel-level training image dataset was verified by creating scenarios, including various road types and objects in a virtual environment. Detecting an object from an image may interfere with the accurate path determination due to occlusion areas covered by another object. Thus, we construct a database, for developing an occlusion area detection algorithm in a virtual environment. Additionally, we present the possibility of its use as a deep learning dataset to calculate a grid map, that enables path search considering occlusion areas. Custom datasets are built using the RDBMS system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.1
• /
• pp.51-73
• /
• 2023

Social media play a significant role in communicating information across the globe, connecting with loved ones, getting the news, communicating ideas, etc. However, a group of people uses social media to spread fake information, which has a bad impact on society. Therefore, minimizing fake news and its detection are the two primary challenges that need to be addressed. This paper presents a multi-modal deep learning technique to address the above challenges. The proposed modal can use and process visual and textual features. Therefore, it has the ability to detect fake information from visual and textual data. We used EfficientNetB0 and a sentence transformer, respectively, for detecting counterfeit images and for textural learning. Feature embedding is performed at individual channels, whilst fusion is done at the last classification layer. The late fusion is applied intentionally to mitigate the noisy data that are generated by multi-modalities. Extensive experiments are conducted, and performance is evaluated against state-of-the-art methods. Three real-world benchmark datasets, such as MediaEval (Twitter), Weibo, and Fakeddit, are used for experimentation. Result reveals that the proposed modal outperformed the state-of-the-art methods and achieved an accuracy of 86.48%, 82.50%, and 88.80%, respectively, for MediaEval (Twitter), Weibo, and Fakeddit datasets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• Journal of Internet Computing and Services
• /
• v.13 no.5
• /
• pp.45-53
• /
• 2012

The appearance of Intelligent mobile and home appliance increased the using of not only various multimedia contents but also educational contents. Especially the growth of smart device such as smart phone, smart pad and smart TV, provided the environment which everyone can use educational content anytime, anywhere, any device. However many smart devices are hard to reuse the various educational contents because the devices and mobile os policies are not unify. In this paper, we suggest the design of NeS(N-Screen e-learning system) in order to solve this problem. NeS is consisted of User Management, Educational Content Management, Content Convert System and Interactive Management System. In this system, we use the HTML5 language to assure interoperability in various Smart Device Environment. Through NeS, we can achieve Content OSMU(One Source Multi Use) in various device environment and assure the continuity of the contents for using the educational contents more easily.