• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.143-147
• /
• 2024

Image noise classification is a classical problem in the field of image processing, machine learning, deep learning and computer vision. In this paper, image noise classification is performed using deep learning. Keras deep learning library of TensorFlow is used for this purpose. 6900 images images are selected from the Kaggle database for the classification purpose. Dataset for labeled noisy images of multiple type was generated with the help of Matlab from a dataset of non-noisy images. Labeled dataset comprised of Salt & Pepper, Gaussian and Sinusoidal noise. Different training and tests sets were partitioned to train and test the model for image classification. In deep neural networks CNN (Convolutional Neural Network) is used due to its in-depth and hidden patterns and features learning in the images to be classified. This deep learning of features and patterns in images make CNN outperform the other classical methods in many classification problems.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1061-1080
• /
• 2023

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

• Journal of the Korea society of information convergence
• /
• v.5 no.2
• /
• pp.59-65
• /
• 2012

This study analyzed the websites of domestic college's Teaching and Learning Center of Quality. The title of "Teaching and Learning Center of Quality" was given to 9 colleges selected for 3 years since 2010 by Korean Council for College Education. The websites mostly consist of introduction, teaching support, learning support, e-learning support, service, media support, resources, community, and so on. This study also analyzes the similarities and differences of the websites by the degree of the webpage menu activation. This study suggests the direction of the websites functions which college's Teaching and Learning Center should have.

• Journal of Environmental Science International
• /
• v.19 no.8
• /
• pp.1057-1066
• /
• 2010

An ecological learning center is defined as a place which can establish the correct relationship between human and environment. Human can learn ecosystem and importance of environment throughout observation of nature and participation in program of ecological learning center. The most important aspects of ecological learning center planning are to reflect on user's demand and preservation of ecosystem. The prime goals of this study is to analyze user's characteristics in the Young Wheol Mulmurigol Ecological Learning Center. The second goal of this study is to find out the satisfaction model based on user's perceived performance of each program and facility in the center. For this study, questionnaire survey with 204 individuals was completed. The data from the questionnaire were analyzed statistical method by SPSS. There are several significant results from the study as following First, this ecological learning center as a newly operating facility is used not for educational purpose but for resting and relaxation purpose. It is due to that the most of users in this center are package tourists with historic scenes. Second, user's perceived performance evaluated by 23 attributions of programs and facilities, and these attributions could be classified by 5 factors such as environment friendly design, educational function, preservation of environment, provision of various bio-top and provision of resting area. Third, the user satisfaction model indicates that user satisfaction is depended on various factors such as preservation of environment, provision of various bio-top, provision of resting area. Among these factor affecting the satisfaction, provision of various bio-top is the most influence on user satisfaction.

• Journal of Korean Neurosurgical Society
• /
• v.66 no.1
• /
• pp.53-62
• /
• 2023

Objective : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance. Results : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anterior-posterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

• Journal of Practical Engineering Education
• /
• v.15 no.1
• /
• pp.199-208
• /
• 2023

Performance analysis for work-learning dual system has been mainly conducted from the perspective of diagnosing the effectiveness of policies at the macro level. This study aims to analyze issues in organizational management of the work-learning dual system training center by conducting an analysis focusing on the organizational performance of the work-learning dual system training center's employees. As a result of the analysis, it was confirmed that the perception and attitude of employees toward the work-learning dual training center differed depending on the type of work-learning dual system and the type of employment contract. Among the types of work-learning dual system, overall, in the case of IPP, the organizational performance of employees was low, while the apprenticeship was relatively high. As for the type of employment contract, the need for institutional improvement has been derived, especially for the project contract workers.

• 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.

• The Journal of Information Systems
• /
• v.14 no.2
• /
• pp.75-99
• /
• 2005

Today, many universities are confronted with the changing education paradigm such as e-learning, Distance Education, Virtual University, This IT-based teaming paradigm shift is certainly a new opportunity or a threat to our universities. To overcome this problem the universities should think e-Learning as strategic weapon, such as many firms created competitive weapons from the information systems at the 1980s. So, e-Learning system can be a SIS(Strategic Information System) which supports university's future education strategies. To build a e-Learning system, not only many H/W and S/W resources but also expert personnels are required. An organization such as local university who is week at financial status can't himself plan the system. The Local University Community e-Learning Centers that support the demand of e-learning for their community are recommended. In order to operate these centers efficiently, the strategic roles of the e-Learning center should first be defined. To define the strategic roles, We classified the strategic roles of the e-Learning center into four dimensions, (1) to improve management efficiency, (2) to enhance educational service, (3) to acquire competitive advantages, (4) to build new education infrastructure, and each dimension has 5 or 6 measurement items. As result, to enhance the educational service was considered as the most significant factor among the four dimensions of strategic roles, and the infrastructure building was the next. We also tried to find the difference for each factor by the characteristics of responsor. The data showed that there was litter difference between the groups in evaluating the significance of strategic roles of e-learning centers. Through the strategic roles definition and analysis of expected role ratings, we could have recommended the direction and operation policies of the e-Loaming centers.

• Journal of Korean Elementary Science Education
• /
• v.38 no.1
• /
• pp.43-54
• /
• 2019

In order to organize various places for science experience study, this study gathered and analyzed prior research on science experience study and various science experience perated in school. To that end, a total of 162 relevant prior studies of literature published from 2000 to 2016 were collected and 2,201 cases of science experience study conducted in 2015 were collected and analyzed. The place where the science experiential learning was done is divided into three areas of natural ecology, cultural history, facility experiential learning study, and the characteristics of participating subjects are examined. In terms of the number of articles published in the field of science-related experiential learning areas, 83 ecological experience study sites (51.2%), facilities institution experience study sites 56 (34.6%), and cultural history experience study books 23 (14.2%). Through this study, it was found out that research tendency to analyze science - related attitudes became prominent by setting study subjects using natural objects around and learning to play while playing and playing in nature. There was also an analysis by subjects of participation in science related experience learning centers. Cultural history experiential learning field was significantly lower than previous studies. In the lower grades, nature ecological experience learning was mainly performed. Combining the above findings, it can provide implications for the development of science-related experience activities. First, it is necessary to develop a technology-related experience learning center using local community resources. Second, it is necessary to expand the culture and history experience learning center related to science. Third, we need an education support center to support the expansion and operation of such a technology-related cultural history learning center.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.11
• /
• pp.95-103
• /
• 1997

A robust center estimation tecnique of n-fold engineering parts is presented, which use self-organizing neural networks with generating and merging learning for training neural units. To estimate the center of the n-fold engineering parts using neural networks, the segmented boundaries of the interested part are approximated to strainght lines, and the temporal estimated centers by thecosine theorem which formed between the approximaged straight line and the reference point, , are indexed as (.sigma.-.theta.) parameteric vecstors. Then the entries of parametric vectors are fed into self-organizing nerual network. Finally, the center of the n-fold part is extracted by mean of generating and merging learning of the neurons. To accelerate the learning process, neural network uses an adaptive learning rate function to the merging process and a self-adjusting activation to generating process. Simulation results show that the centers of n-fold engineering parts are effectively estimated by proposed technique, though not knowing the error distribution of estimated centers and having less information of boundaries.