• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1250-1256
• /
• 2019

Although one can easily generate real-world 3D mesh data using a 3D printer or a depth camera, the generated data inevitably includes unnecessary noise. Therefore, mesh denoising is essential to obtain intact 3D mesh data. However, conventional mathematical denoising methods require preprocessing and often eliminate some important features of the 3D mesh. To address this problem, this paper proposes a deep learning based 3D mesh denoising method. Specifically, we propose a convolution-based autoencoder model consisting of an encoder and a decoder. The convolution operation applied to the mesh data performs denoising considering the relationship between each vertex constituting the mesh data and the surrounding vertices. When the convolution is completed, a sampling operation is performed to improve the learning speed. Experimental results show that the proposed autoencoder model produces faster and higher quality denoised data than the conventional methods.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.63-71
• /
• 2020

Speech recognition is one of the areas actively commercialized using deep learning and machine learning techniques. However, the majority of speech recognition systems on the market are developed on data with limited diversity of speakers and tend to perform well on typical adult speakers only. This is because most of the speech recognition models are generally learned using a speech database obtained from adult males and females. This tends to cause problems in recognizing the speech of the elderly, children and people with dialects well. To solve these problems, it may be necessary to retain big database or to collect a data for applying a speaker adaptation. However, this paper proposes that a new end-to-end speech recognition method consists of an acoustic augmented recurrent encoder and a transformer decoder with linguistic prediction. The proposed method can bring about the reliable performance of acoustic and language models in limited data conditions. The proposed method was evaluated to recognize Korean elderly and children speech with limited amount of training data and showed the better performance compared of a conventional method.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.967-973
• /
• 2020

As the implementation of export controls is spreading, the importance of classifying strategic items is increasing, but Korean export companies that are new to export controls are not able to understand the concept of strategic items, and it is difficult to classifying strategic items due to various criteria for controlling strategic items. In this paper, we propose a method that can easily approach the process of classification by lowering the barrier to entry for users who are new to export controls or users who are using classification of strategic items. If the user can confirm the decision result by providing a manual or a catalog for the procedure of classifying strategic items, it will be more convenient and easy to approach the method and procedure for classfying strategic items. In order to achieve the purpose of this study, it utilizes deep learning, which are being studied in image recognition and classification, and OCR(optical character reader) technology. And through the research and development of the support tool, we provide information that is helpful for the classification of strategic items to our companies.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.23-30
• /
• 2022

The failure of the reefer container causes a great loss of cost, but the current reefer container alarm system is inefficient. Existing studies using simulation data of refrigeration systems exist, but studies using actual operation data of refrigeration containers are lacking. Therefore, this study classified the causes of failure using actual refrigerated container operation data. Data imbalance occurred in the actual data, and the data imbalance problem was solved by comparing the logistic regression analysis with ENN-SMOTE and class weight with the 2-stage algorithm developed in this study. The 2-stage algorithm uses XGboost, LGBoost, and DNN to classify faults and normalities in the first step, and to classify the causes of faults in the second step. The model using LGBoost in the 2-stage algorithm was the best with 99.16% accuracy. This study proposes a final model using a two-stage algorithm to solve data imbalance, which is thought to be applicable to other industries.

• Journal of Positioning, Navigation, and Timing
• /
• v.13 no.1
• /
• pp.111-115
• /
• 2024

This study builds a machine learning model optimized for clocks among various techniques in the field of artificial intelligence and applies it to clock stabilization or synchronization technology based on atomic clock noise characteristics. In addition, the possibility of providing stable source clock data is confirmed through the characteristics of machine learning predicted values during holdover of atomic clocks. The proposed machine learning model is evaluated by comparing its performance with the AutoRegressive Integrated Moving Average (ARIMA) model, an existing statistical clock prediction model. From the results of the analysis, the prediction model proposed in this study (MSE: 9.47476) has a lower MSE value than the ARIMA model (MSE: 221.2622), which means that it provides more accurate predictions. The prediction accuracy is based on understanding the complex nature of data that changes over time and how well the model reflects this. The application of a machine learning prediction model can be seen as a way to overcome the limitations of the statistical-based ARIMA model in time series prediction and achieve improved prediction performance.

• The Journal of the Korea Contents Association
• /
• v.20 no.11
• /
• pp.216-227
• /
• 2020

In science and technology diplomacy, major countries actively utilize their capabilities in science and technology for public diplomacy, especially for promoting diplomatic relations with politically sensitive regions and countries. Recently, with an increase in the influence of science and technology on national development, interest in science and technology diplomacy has increased. So far, science and technology diplomacy has relied on experts to find research topics that are of common interest to both the countries. However, this method has various problems such as the bias arising from the subjective judgment of experts, the attribution of the halo effect to famous researchers, and the use of different criteria for different experts. This paper presents an objective data-based approach to identify and recommend research topics to support science and technology diplomacy without relying on the expert-based approach. The proposed approach is based on big data analysis that uses deep-learning techniques and bibliometric methods. The Scopus database is used to find proper topics for collaborative research between two countries. This approach has been used to support science and technology diplomacy between Korea and Hungary and has raised expectations of policy makers. This paper finally discusses aspects that should be focused on to improve the system in the future.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.200-207
• /
• 2020

Recently, deep neural networks such as CNN are showing excellent performance in various fields such as image classification, object recognition, visual quality enhancement, etc. However, as the model size and computational complexity of deep learning models for most applications increases, it is hard to apply neural networks to IoT and mobile environments. Therefore, neural network compression algorithms for reducing the model size while keeping the performance have been being studied. In this paper, we apply few compression methods to CNN models and evaluate their performances in the embedded environment. For evaluate the performance, the classification performance and inference time of the original CNN models and the compressed CNN models on the image inputted by the camera are evaluated in the embedded board equipped with QCS605, which is a customized AI chip. In this paper, a few CNN models of MobileNetV2, ResNet50, and VGG-16 are compressed by applying the methods of pruning and matrix decomposition. The experimental results show that the compressed models give not only the model size reduction of 1.3~11.2 times at a classification performance loss of less than 2% compared to the original model, but also the inference time reduction of 1.2~2.21 times, and the memory reduction of 1.2~3.8 times in the embedded board.

• Korean Journal of Remote Sensing
• /
• v.33 no.6_2
• /
• pp.1061-1073
• /
• 2017

In this study, images were classified using convolutional neural network (CNN) - a deep learning technique - to investigate the feasibility of information production through a combination of artificial intelligence and spatial data. CNN determines kernel attributes based on a classification criterion and extracts information from feature maps to classify each pixel. In this study, a CNN network was constructed to classify materials with similar spectral characteristics and attribute information; this is difficult to achieve by conventional image processing techniques. A Compact Airborne Spectrographic Imager(CASI) and an Airborne Imaging Spectrometer for Application (AISA) were used on the following three study sites to test this method: Site 1, Site 2, and Site 3. Site 1 and Site 2 were agricultural lands covered in various crops,such as potato, onion, and rice. Site 3 included different buildings,such as single and joint residential facilities. Results indicated that the classification of crop species at Site 1 and Site 2 using this method yielded accuracies of 96% and 99%, respectively. At Site 3, the designation of buildings according to their purpose yielded an accuracy of 96%. Using a combination of existing land cover maps and spatial data, we propose a thematic environmental map that provides seasonal crop types and facilitates the creation of a land cover map.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1077-1093
• /
• 2020

Sea Surface Temperature (SST) is an important environmental indicator that affects climate coupling systems around the world. In particular, coastal regions suffer from abnormal SST resulting in huge socio-economic damage. This study used Long Short Term Memory (LSTM) and Convolutional Long Short Term Memory (ConvLSTM) to predict SST up to 7 days in the south sea region in South Korea. The results showed that the ConvLSTM model outperformed the LSTM model, resulting in a root mean square error (RMSE) of 0.33℃ and a mean difference of -0.0098℃. Seasonal comparison also showed the superiority of ConvLSTM to LSTM for all seasons. However, in summer, the prediction accuracy for both models with all lead times dramatically decreased, resulting in RMSEs of 0.48℃ and 0.27℃ for LSTM and ConvLSTM, respectively. This study also examined the prediction of abnormally high SST based on three ocean heatwave categories (i.e., warning, caution, and attention) with the lead time from one to seven days for an ocean heatwave case in summer 2017. ConvLSTM was able to successfully predict ocean heatwave five days in advance.