• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.778-789
• /
• 2021

Recently, various lightweight methods for using Convolutional Neural Network(CNN) models in mobile devices have emerged. Weight quantization, which lowers bit precision of weights, is a lightweight method that enables a model to be used through integer calculation in a mobile environment where GPU acceleration is unable. Weight quantization has already been used in various models as a lightweight method to reduce computational complexity and model size with a small loss of accuracy. Considering the size of memory and computing speed as well as the storage size of the device and the limited network environment, this paper proposes a method of compressing integer weights after quantization using a video codec as a method. To verify the performance of the proposed method, experiments were conducted on VGG16, Resnet50, and Resnet18 models trained with ImageNet and Places365 datasets. As a result, loss of accuracy less than 2% and high compression efficiency were achieved in various models. In addition, as a result of comparison with similar compression methods, it was verified that the compression efficiency was more than doubled.

• Advances in nano research
• /
• v.12 no.1
• /
• pp.81-99
• /
• 2022

The aim of current work is to evaluate thermo-electrical characteristics of graphene nanoplatelets Reinforced Composite (GNPRC) coupled with magneto-electro-elastic (MEE) face sheet. In this regard, a cylindrical smart nanocomposite made of GNPRC with an external MEE layer is considered. The bonding between the layers are assumed to be perfect. Because of the layer nature of the structure, the material characteristics of the whole structure is regarded as graded. Both mechanical and thermal boundary conditions are applied to this structure. The main objective of this work is to determine critical temperature and critical voltage as a function of thermal condition, support type, GNP weight fraction, and MEE thickness. The governing equation of the multilayer nanocomposites cylindrical shell is derived. The generalized differential quadrature method (GDQM) is employed to numerically solve the differential equations. This method is integrated with Deep Learning Network (DNN) with ADADELTA optimizer to determine the critical conditions of the current sandwich structure. This the first time that effects of several conditions including surrounding temperature, MEE layer thickness, and pattern of the layers of the GNPRC is investigated on two main parameters critical temperature and critical voltage of the nanostructure. Furthermore, Maxwell equation is derived for modeling of the MEE. The outcome reveals that MEE layer, temperature change, GNP weight function, and GNP distribution patterns GNP weight function have significant influence on the critical temperature and voltage of cylindrical shell made from GNP nanocomposites core with MEE face sheet on outer of the shell.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.46.3-47
• /
• 2021

Recently a multilayer spectral inversion (MLSI) model has been proposed to infer the physical parameters of plasmas in the solar chromosphere. The inversion solves a three-layer radiative transfer model using the strong absorption line profiles, H alpha and Ca II 8542 Å, taken by the Fast Imaging Solar Spectrograph (FISS). The model successfully provides the physical plasma parameters, such as source functions, Doppler velocities, and Doppler widths in the layers of the photosphere to the chromosphere. However, it is quite expensive to apply the MLSI to a huge number of line profiles. For example, the calculating time is an hour to several hours depending on the size of the scan raster. We apply deep neural network (DNN) to the inversion code to reduce the cost of calculating the physical parameters. We train the models using pairs of absorption line profiles from FISS and their 13 physical parameters (source functions, Doppler velocities, Doppler widths in the chromosphere, and the pre-determined parameters for the photosphere) calculated from the spectral inversion code for 49 scan rasters (~2,000,000 dataset) including quiet and active regions. We use fully connected dense layers for training the model. In addition, we utilize a skip connection to avoid a problem of vanishing gradients. We evaluate the model by comparing the pairs of absorption line profiles and their inverted physical parameters from other quiet and active regions. Our result shows that the deep learning model successfully reproduces physical parameter maps of a scan raster observation per second within 15% of mean absolute percentage error and the mean squared error of 0.3 to 0.003 depending on the parameters. Taking this advantage of high performance of the deep learning model, we plan to provide the physical parameter maps from the FISS observations to understand the chromospheric plasma conditions in various solar features.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.697-703
• /
• 2022

Due to the recent economic downturn caused by Covid-19 and the unstable international situation, many investors are choosing the derivatives market as a means of investment. However, the derivatives market has a greater risk than the stock market, and research on the market of market participants is insufficient. Recently, with the development of artificial intelligence, machine learning has been widely used in the derivatives market. In this paper, reinforcement learning, one of the machine learning techniques, is applied to analyze the scalping technique that trades futures in minutes. The data set consists of 21 attributes using the closing price, moving average line, and Bollinger band indicators of 1 minute and 3 minute data for 6 months by selecting 4 products among futures products traded at trading firm. In the experiment, DNN artificial neural network model and three reinforcement learning algorithms, namely, DQN (Deep Q-Network), A2C (Advantage Actor Critic), and A3C (Asynchronous A2C) were used, and they were trained and verified through learning data set and test data set. For scalping, the agent chooses one of the actions of buying and selling, and the ratio of the portfolio value according to the action result is rewarded. Experiment results show that the energy sector products such as Heating Oil and Crude Oil yield relatively high cumulative returns compared to the index sector products such as Mini Russell 2000 and Hang Seng Index.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• pp.48-55
• /
• 2022

The color image of the brand comes first and is an important visual element that leads consumers to the consumption of the product. To express more effectively what the brand wants to convey through design, the printing market is striving to print accurate colors that match the intention. In 'offset printing' mainly used in printing, colors are often printed in CMYK (Cyan, Magenta, Yellow, Key) colors. However, it is possible to print more accurate colors by making ink of the desired color instead of dotting CMYK colors. The resulting ink is called 'spot color' ink. Spot color ink is manufactured by repeating the process of mixing the existing inks. In this repetition of trial and error, the manufacturing cost of ink increases, resulting in economic loss, and environmental pollution is caused by wasted inks. In this study, a deep learning algorithm to predict printed spot colors was designed to solve this problem. The algorithm uses a single DNN (Deep Neural Network) model to predict printed spot colors based on the information of the paper and the proportions of inks to mix. More than 8,000 spot color ink data were used for learning, and all color was quantified by dividing the visible light wavelength range into 31 sections and the reflectance for each section. The proposed algorithm predicted more than 80% of spot color inks as very similar colors. The average value of the calculated difference between the actual color and the predicted color through 'Delta E' provided by CIE is 5.29. It is known that when Delta E is less than 10, it is difficult to distinguish the difference in printed color with the naked eye. The algorithm of this study has a more accurate prediction ability than previous studies, and it can be added flexibly even when new inks are added. This can be usefully used in real industrial sites, and it will reduce the attempts of the operator by checking the color of ink in a virtual environment. This will reduce the manufacturing cost of spot color inks and lead to improved working conditions for workers. In addition, it is expected to contribute to solving the environmental pollution problem by reducing unnecessarily wasted ink.

• Journal of Advanced Navigation Technology
• /
• v.21 no.6
• /
• pp.643-650
• /
• 2017

Photovoltaic generation which has unlimited energy sources are very intermittent because they depend on the weather. Therefore, it is necessary to get accurate generation prediction with reducing the uncertainty of photovoltaic generation and improvement of the economics. The Meteorological Agency predicts weather factors for three days, but doesn't predict the sunshine and solar radiation that are most correlated with the prediction of photovoltaic generation. In this study, we predict sunshine and solar radiation using weather, precipitation, wind direction, wind speed, humidity, and cloudiness which is forecasted for three days at Meteorological Agency. The photovoltaic generation forecasting model is proposed by using predicted solar radiation and sunshine. As a result, the proposed model showed better results in the error rate indexes such as MAE, RMSE, and MAPE than the model that predicts photovoltaic generation without radiation and sunshine. In addition, DNN showed a lower error rate index than using SVM, which is a type of machine learning.

• Analytical Science and Technology
• /
• v.33 no.2
• /
• pp.98-107
• /
• 2020

Methamphetamine (MA) is currently the most abused illicit drug in Korea. MA is produced by chemical synthesis, and the final target drug that is produced contains small amounts of the precursor chemicals, intermediates, and by-products. To identify and quantify these trace compounds in MA seizures, a practical and feasible approach for conducting chromatographic fingerprinting with a suite of traditional chemometric methods and recently introduced machine learning approaches was examined. This was achieved using gas chromatography (GC) coupled with a flame ionization detector (FID) and mass spectrometry (MS). Following appropriate examination of all the peaks in 71 samples, 166 impurities were selected as the characteristic components. Unsupervised (principal component analysis (PCA), hierarchical cluster analysis (HCA), and K-means clustering) and supervised (partial least squares-discriminant analysis (PLS-DA), orthogonal partial least squares-discriminant analysis (OPLS-DA), support vector machines (SVM), and deep neural network (DNN) with Keras) chemometric techniques were employed for classifying the 71 MA seizures. The results of the PCA, HCA, K-means clustering, PLS-DA, OPLS-DA, SVM, and DNN methods for quality evaluation were in good agreement. However, the tested MA seizures possessed distinct features, such as chirality, cutting agents, and boiling points. The study indicated that the established qualitative and semi-quantitative methods will be practical and useful analytical tools for characterizing trace compounds in illicit MA seizures. Moreover, they will provide a statistical basis for identifying the synthesis route, sources of supply, trafficking routes, and connections between seizures, which will support drug law enforcement agencies in their effort to eliminate organized MA crime.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1202-1208
• /
• 2020

In line with the current era of the 4th Industrial Revolution, it is necessary to prepare for the future by integrating AI elements in the ship sector. In addition, it is necessary to respond to this in the field of power management for the appearance of autonomous ships. In this study, we propose a battery-linked electric propulsion system (BLEPS) algorithm using machine learning's DNN. For the experiment, we learned the pattern of ship power consumption for each operation mode based on the ship data through LabView and derived the battery status through Python to check the flexibility of the generator and battery interlocking. As a result of the experiment, the low load operation of the generator was reduced through charging and discharging of the battery, and economic efficiency and reliability were confirmed by reducing the fuel consumption of 1% of LNG.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.44-57
• /
• 2019

Various studies have been conducted to solve traffic congestions in many metropolitan cities through accurate traffic flow prediction. Most studies are based on the assumption that past traffic patterns repeat in the future. Models based on such an assumption fall short in case irregular traffic patterns abruptly occur. Instead, the approaches such as predicting traffic pattern through big data analytics and artificial intelligence have emerged. Specifically, deep learning algorithms such as RNN have been prevalent for tackling the problems of predicting temporal traffic flow as a time series. However, these algorithms do not perform well in terms of long-term prediction. In this paper, we take into account various external factors that may affect the traffic flows. We model the correlation between the multi-dimensional context information with temporal traffic speed pattern using deep neural networks. Our model trained with the traffic data from TOPIS system by Seoul, Korea can predict traffic speed on a specific date with the accuracy reaching nearly 90%. We expect that the accuracy can be improved further by taking into account additional factors such as accidents and constructions for the prediction.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1243-1249
• /
• 2019

People who gathered to enjoy a specific event or content are called audiences or spectators, and show various propensity according to the characteristics of the crowd. Although there is such a difference, in general, the number of attendance is directly related to the business aspect, which enables stable financial operation for the sale of contents through various incomes, such as the admission fee and the use of other facilities. Therefore, prediction of audience can be used as a major factor in marketing and budgeting strategies. In this study, we review several existing models for predicting the number of attendance and propose an efficient machine learning model. In addition, we studied daily attendance prediction and abnormal attendance prediction using combine DNN(Deep Neural Network) and RF(Random Forest) model.