• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.301-307
• /
• 2023

Deep learning requires building a deep neural network, collecting a large amount of training data, and then training the built neural network for a long time. If training does not proceed properly or overfitting occurs, training will fail. When using deep learning tools that have been developed so far, it takes a lot of time to collect training data and learn. However, due to the rapid advent of the mobile environment and the increase in sensor data, the demand for real-time deep learning technology that can dramatically reduce the time required for neural network learning is rapidly increasing. In this study, a real-time deep learning system was implemented using an Arduino system equipped with a fine dust sensor. In the implemented system, fine dust data is measured every 30 seconds, and when up to 120 are accumulated, learning is performed using the previously accumulated data and the newly accumulated data as a dataset. The neural network for learning was composed of one input layer, one hidden layer, and one output. To evaluate the performance of the implemented system, learning time and root mean square error (RMSE) were measured. As a result of the experiment, the average learning error was 0.04053796, and the average learning time of one epoch was about 3,447 seconds.

• The Korean Journal of Applied Statistics
• /
• v.33 no.4
• /
• pp.483-497
• /
• 2020

We used a deep neural network model for the prediction of the stock prices of Kia Motors and Shinsegae as listed in the KOSPI 100. We used an emotional variable derived from online news in addition to the various technical indicators most often used. The emotional variable used as a predictor variable was generated from the average of the emotional scores for companies in the industrial group after building an emotional dictionary specific to each industrial group classified in a social network analysis. The study was conducted with various combinations of predictors and confirmed that good predictive and profitable power could be expected when jointly using technical indicators and an emotional variable based on online news by industrial groups.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.11
• /
• pp.85-95
• /
• 2018

With the popularity of smartphones, most peoples have been using mobile cameras to capture photographs. However, due to insufficient amount of lights in a low lighting condition, unwanted noises can be generated during image acquisition. To remove the noise, a method of using deep convolutional neural networks is introduced. However, this method still lacks the ability to describe textures and edges, even though it has made significant progress in terms of visual quality performance. Therefore, in this paper, the HOG (Histogram of Oriented Gradients) images that contain information about edge orientations are used. More specifically, a method of learning deep convolutional neural networks is proposed by stacking noise and HOG images into an input tensor. Experiment results confirm that the proposed method not only can obtain excellent result in visual quality evaluations, compared to conventional methods, but also enable textures and edges to be improved visually.

• 재활복지
• /
• v.21 no.3
• /
• pp.129-146
• /
• 2017

In an event of an emergency, such as fire in a building, visually impaired and blind people are prone to exposed to a level of danger that is greater than that of normal people, for they cannot be aware of it quickly. Current fire detection methods such as smoke detector is very slow and unreliable because it usually uses chemical sensor based technology to detect fire particles. But by using vision sensor instead, fire can be proven to be detected much faster as we show in our experiments. Previous studies have applied various image processing and machine learning techniques to detect fire, but they usually don't work very well because these techniques require hand-crafted features that do not generalize well to various scenarios. But with the help of recent advancement in the field of deep learning, this research can be conducted to help solve this problem by using deep learning-based object detector that can detect fire using images from security camera. Deep learning based approach can learn features automatically so they can usually generalize well to various scenes. In order to ensure maximum capacity, we applied the latest technologies in the field of computer vision such as YOLO detector in order to solve this task. Considering the trade-off between recall vs. complexity, we introduced two convolutional neural networks with slightly different model's complexity to detect fire at different recall rate. Both models can detect fire at 99% average precision, but one model has 76% recall at 30 FPS while another has 61% recall at 50 FPS. We also compare our model memory consumption with each other and show our models robustness by testing on various real-world scenarios.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.867-871
• /
• 2022

Amid the recent rapid trend change, the change in design has a great impact on the sales of fashion companies, so it is inevitable to be careful in choosing new designs. With the recent development of the artificial intelligence field, various machine learning is being used a lot in the fashion market to increase consumers' preferences. To contribute to increasing reliability in the development of new products by quantifying abstract concepts such as preferences, we generate new images that do not exist through three adversarial generative neural networks (GANs) and numerically compare abstract concepts of preferences using pre-trained convolution neural networks (CNNs). Deep convolutional generative adversarial networks (DCGAN), Progressive growing adversarial networks (PGGAN), and Dual Discriminator generative adversarial networks (DANs), which were trained to produce comparative, high-level, and high-level images. The degree of similarity measured was considered as a preference, and the experimental results showed that D2GAN showed a relatively high similarity compared to DCGAN and PGGAN.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.149-156
• /
• 2020

The genesis of ore bodies is a very diverse and complex process, and the target depth of mineral exploration increases. These create a need for predictive mineral exploration, which may be facilitated by the advancement of machine learning and geological database. In this study, we confirm that the faults and igneous rocks distributions and magnetic data can be used as input data for potential mapping using deep neural networks. When the input data are constructed with faults, igneous rocks, and magnetic data, we can build a potential mapping model of the metal deposit that has a predictive accuracy greater than 0.9. If detailed geological and geophysical data are obtained, this approach can be applied to the potential mapping on a mine scale. In addition, we confirm that the magnetic data, which provide the distribution of the underground igneous rock, can supplement the limited information from the surface igneous rock distribution. Therefore, rather than simply integrating various data sets, it will be more important to integrate information considering the geological correlation to genesis of minerals.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.326-332
• /
• 2019

Recently, the deep learning technology has gained lots of attention which leads to its application to various fields. Especially, there are recent attempts to overcome the limit of wireless communications systems through the use of the deep learning. In this paper, we have verified the performance of deep learning based transmit power control scheme. Unlike previous transmit power control schemes where the optimal transmit power is derived by solving the optimization problem explicitly, in the deep learning based transmit power control, the general solver for the optimization problem is derived through the deep neural network (DNN). Especially, by using the spectral efficiency as the loss function of DNN, the training can be performed without needing labels. Through simulation based on Tensorflow, we confirm that the transmit power control based on deep learning can achieve the optimal performance while reducing the computational complexity by 1/200.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.117-130
• /
• 2020

Noises can distort acquired geophysical data, leading to their misinterpretation. Potential noises sources include anthropogenic activity, natural phenomena, and instrument noises. Conventional denoising methods such as wavelet transform and filtering techniques, are based on subjective human investigation, which is computationally inefficient and time-consuming. Recently, many researchers attempted to implement neural networks to efficiently remove noise from geophysical data. This study aims to review and analyze different types of neural networks, such as artificial neural networks, convolutional neural networks, autoencoders, residual networks, and wavelet neural networks, which are implemented to remove different types of noises including seismic, transient electromagnetic, ground-penetrating radar, and magnetotelluric surveys. The review analyzes and summarizes the key challenges in the removal of noise from geophysical data using neural network, while proposes and explains solutions to the challenges. The analysis support that the advancement in neural networks can be powerful denoising tools for geophysical data.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.5-8
• /
• 2019

단일 영상 초해상도 (Single Image Super-Resolution - SISR)기법은 카메라로 획득된 저해상도 영상에 필터 기반의 연산을 적용하여 좋은 화질의 고해상도 영상을 복원하는 과정이다. 최근에 심층 합성곱 신경망 학습의 발전에 따라 단일 영상 초해상도에 적용되는 심층 학습 기법들은 좋은 성과를 보여 주고 있다. 본 논문은 단일 영상 초해상도 성능을 개선하기 위해 웨이블릿 예측 네트워크를 효율적으로 적용하는 방법에 대해 연구하였으며, 저해상도 입력 영상의 특징을 잘 추출해내기 위해 네트워크 내부에 RDB를 적용하여 기존 방식보다 효율적으로 고해상도 영상 복원하는 기법을 제안한다. 모의실험을 통해 제안하는 방법이 기존 방법보다 화질은 약 PSNR 0.18dB만큼 우수하며 속도는 1.17배 빠른 것을 확인하였다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.234-240
• /
• 2022

This paper proposes a customized AI exercise recommendation service for balancing the relative amount of exercise according to the working environment by each occupation. WISDM database is collected by using acceleration and gyro sensors, and is a dataset that classifies physical activities into 18 categories. Our system recommends a adaptive exercise using the analyzed activity type after classifying 18 physical activities into 3 physical activities types such as whole body, upper body and lower body. 1 Dimensional convolutional neural network is used for classifying a physical activity in this paper. Proposed model is composed of a convolution blocks in which 1D convolution layers with a various sized kernel are connected in parallel. Convolution blocks can extract a detailed local features of input pattern effectively that can be extracted from deep neural network models, as applying multi 1D convolution layers to input pattern. To evaluate performance of the proposed neural network model, as a result of comparing the previous recurrent neural network, our method showed a remarkable 98.4% accuracy.