• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.165-171
• /
• 2017

It is difficult to recognize Human's facial expression in the real-world. For these reason, when database and test data have similar condition, we can accomplish high accuracy. Solving these problem, we need to many facial expression data. In this paper, we propose the algorithm for gathering many facial expression data within various environment and gaining high accuracy quickly. This algorithm is training initial model with the ASSL (Active Semi-Supervised Learning) using deep learning network, thereafter gathering unlabeled facial expression data and repeating this process. Through using the ASSL, we gain proper data and high accuracy with less labor force.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.3
• /
• pp.281-292
• /
• 2021

With the development of deep learning technology, researchers and technicians keep attempting to apply deep learning in various industrial and academic fields, including the defense. Most of these attempts assume that the data are balanced. In reality, since lots of the data are imbalanced, the classifier is not properly built and the model's performance can be low. Therefore, this study proposes cost-sensitive learning as a solution to the imbalance data problem of image classification in the defense field. In the proposed model, cost-sensitive learning is a method of giving a high weight on the cost function of a minority class. The results of cost-sensitive based model shows the test F1-score is higher when cost-sensitive learning is applied than general learning's through 160 experiments using submarine/non-submarine dataset and warship/non-warship dataset. Furthermore, statistical tests are conducted and the results are shown significantly.

• Journal of the Korean Society of Radiology
• /
• v.15 no.4
• /
• pp.547-554
• /
• 2021

In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

• Journal of Energy Engineering
• /
• v.27 no.2
• /
• pp.26-31
• /
• 2018

This paper introduces a study to improve the thermal efficiency of the district heating user control facility based on reinforcement learning. As an example, it is proposed a general method of constructing a deep Q learning network(DQN) using deep Q learning, which is a reinforcement learning algorithm that does not specify a model. In addition, it is also introduced the big data platform system and the integrated heat management system which are specialized in energy field applied in processing huge amount of data processing from IoT sensor installed in many thermal energy control facilities.

• Journal of Korean Society of Forest Science
• /
• v.109 no.1
• /
• pp.23-30
• /
• 2020

The use of increased computing power, machine learning, and deep learning techniques have dramatically increased in various sectors. In particular, image detection algorithms are broadly used in forestry and remote sensing areas to identify forest types and tree species. However, in South Korea, machine learning has rarely, if ever, been applied in forestry image detection, especially to classify tree species. This study integrates the application of machine learning and forest image detection; specifically, we compared the ability of two machine learning data collection methods, namely image data captured by forest experts (D1) and web-crawling (D2), to automate the classification of five trees species. In addition, two methods of characterization to train/test the system were investigated. The results indicated a significant difference in classification accuracy between D1 and D2: the classification accuracy of D1 was higher than that of D2. In order to increase the classification accuracy of D2, additional data filtering techniques were required to reduce the noise of uncensored image data.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.1-6
• /
• 2019

The proposed model is developed to minimize the loss of information in incomplete data including missing data. The first step is to transform the learning data to compensate for the loss information using the data extension technique. In this conversion process, the attribute values of the data are filled with binary or probability values in one-hot encoding. Next, this conversion data is input to the deep learning model, where the number of entries is not constant depending on the cardinality of each attribute. Then, the entry values of each attribute are assigned to the respective input nodes, and learning proceeds. This is different from existing learning models, and has an unusual structure in which arbitrary attribute values are distributedly input to multiple nodes in the input layer. In order to evaluate the learning performance of the proposed model, various experiments are performed on the missing data and it shows that it is superior in terms of performance. The proposed model will be useful as an algorithm to minimize the loss in the ubiquitous environment.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.3
• /
• pp.119-127
• /
• 2019

In this study, we investigated the application of deep learning to the manufacturing process of traffic and road signs which are constituting the road layer in map production with 1 / 1,000 digital topographic map. Automated classification of road traffic sign images was carried out through construction of training data for images acquired by using transfer learning which is used in image classification of deep learning. As a result of the analysis, the signs of attention, regulation, direction and assistance were irregular due to various factors such as the quality of the photographed images and sign shape, but in the case of the guide sign, the accuracy was higher than 97%. In the digital mapping, it is expected that the automatic image classification method using transfer learning will increase the utilization in data acquisition and classification of various layers including traffic safety signs.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.13-23
• /
• 2021

In this paper, we proposed a framework that generates the trajectory of a single rigid body based on its COM configuration and contact pose. Because we use a smaller input dimension than when we use a full body state, we can improve the learning time for reinforcement learning. Even with a 68% reduction in learning time (approximately two hours), the character trained by our network is more robust to external perturbations tolerating an external force of 1500 N which is about 7.5 times larger than the maximum magnitude from a previous approach. For this framework, we use centroidal dynamics to calculate the next configuration of the COM, and use reinforcement learning for obtaining a policy that gives us parameters for controlling the contact positions and forces.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.21-28
• /
• 2021

This study proposes a deep learning-based flat foot classification methodology using transfer learning. We used a transfer learning with VGG16 pre-trained model and a data augmentation technique to generate a model with high predictive accuracy from a total of 176 image data consisting of 88 flat feet and 88 normal feet. To evaluate the performance of the proposed model, we performed an experiment comparing the prediction accuracy of the basic CNN-based model and the prediction model derived through the proposed methodology. In the case of the basic CNN model, the training accuracy was 77.27%, the validation accuracy was 61.36%, and the test accuracy was 59.09%. Meanwhile, in the case of our proposed model, the training accuracy was 94.32%, the validation accuracy was 86.36%, and the test accuracy was 84.09%, indicating that the accuracy of our model was significantly higher than that of the basic CNN model.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.2
• /
• pp.329-335
• /
• 2023

Avocado, a superfood selected by Time magazine and one of the late ripening fruits, is one of the foods with a big difference between local prices and domestic distribution prices. If this sorting process of avocados is automated, it will be possible to lower prices by reducing labor costs in various fields. In this paper, we aim to create an optimal classification model by creating an avocado dataset through crawling and using a number of deep learning-based transfer learning models. Experiments were conducted by directly substituting a deep learning-based transfer learning model from a dataset separated from the produced dataset and fine-tuning the hyperparameters of the model. When an avocado image is input, the model classifies the ripeness of the avocado with an accuracy of over 99%, and proposes a dataset and algorithm that can reduce manpower and increase accuracy in avocado production and distribution households.