• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.591-596
• /
• 2019

In this paper, we implemented a deep learning operation structure with less influence of local PC performance. In general, the deep learning model has a large amount of computation and is heavily influenced by the performance of the processing PC. In this paper, we implemented deep learning operation using AWS and streaming server to reduce this limitation. First, deep learning operations were performed on AWS so that deep learning operation would work even if the performance of the local PC decreased. However, with AWS, the output is less real-time relative to the input when computed. Second, we use streaming server to increase the real-time of deep learning model. If the streaming server is not used, the real-time performance is poor because the images must be processed one by one or by stacking the images. We used the YOLO v3 model as a deep learning model for performance comparison experiments, and compared the performance of local PCs with instances of AWS and GTX1080, a high-performance GPU. The simulation results show that the test time per image is 0.023444 seconds when using the p3 instance of AWS, which is similar to the test time per image of 0.027099 seconds on a local PC with the high-performance GPU GTX1080.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.2
• /
• pp.205-213
• /
• 2018

Development and validation of crop models often require measurements of biomass for the crop of interest. Considerable efforts would be needed to obtain a reasonable amount of biomass data because the destructive sampling of a given crop is usually used. The Kinect sensor, which has a combination of image and depth sensors, can be used for estimating crop biomass without using destructive sampling approach. This approach could provide more data sets for model development and validation. The objective of this study was to examine the applicability of the Kinect sensor for estimation of chinese cabbage fresh weight. The fresh weight of five chinese cabbage was measured and compared with estimates using the Kinect sensor. The estimates were obtained by scanning individual chinese cabbage to create point cloud, removing noise, and building a three dimensional model with a set of free software. It was found that the 3D model created using the Kinect sensor explained about 98.7% of variation in fresh weight of chinese cabbage. Furthermore, the correlation coefficient between estimates and measurements were highly significant, which suggested that the Kinect sensor would be applicable to estimation of fresh weight for chinese cabbage. Our results demonstrated that a depth sensor allows for a non-destructive sampling approach, which enables to collect observation data for crop fresh weight over time. This would help development and validation of a crop model using a large number of reliable data sets, which merits further studies on application of various depth sensors to crop dry weight measurements.

• Journal of Korean Society for Atmospheric Environment
• /
• v.22 no.5
• /
• pp.642-652
• /
• 2006

In order to understand the characteristics of surface ozone concentration and high $O_3$ concentration days, regional data from seven air quality monitoring stations which were operated by local governments were analyzed Regional characteristics of $O_3$ concentration were analyzed with the data of $O_3$ concentration and the characteristics of $O_3$ generation and weather conditions by the selection of the days in which the concentration was higher than 80 ppb. In the case of daily variation, the lowest $O_3$ concentration was shown in all regions from 7am to 8am and the highest around at 4 pm. The monthly variation of mean $O_3$ concentration and ${\Delta}O_3$ values revealed a reducing pattern in July and August following the peak in June, and again a gradual increasing trend in September and October. The result shows that the amount of ozone is dependent on photochemical reaction. The days of $O_3$ generated more than 80 ppb in the region of Gwangyang-bay were 544 days(1,760 hrs). The frequency of occurrence in the region revealed a strong pattern with the order of Samil-dong, Jinsang, and Gwangmu-dong stations in the Gwangyang region. However, Tein-dong, which is the nearest station to air pollution material generation source, showed the lowest frequency in the study area. Consequently, the meteorological parameters which can easily generate the high concentration of $O_3$ in the region of Gwangyang-bay are characterized as follows; atmospheric temperature which is higher than $19^{\circ}C$, relative humidity with the range of $60{\sim}85%$, the less average wind velocity than 5 m/s, cloud cover which is less than 5/10, and the more duration of sunshine than 8 hours.

• The Korean Journal of Applied Statistics
• /
• v.30 no.4
• /
• pp.603-613
• /
• 2017

Many people have recently posted about personal interests on social media. The development of the Internet and computer technology has enabled the storage of digital forms of documents that has resulted in an explosion of the amount of textual data generated; subsequently there is an increased demand for technology to create valuable information from a large number of documents. A text mining technique is often used since text-based data is mostly composed of unstructured forms that are not suitable for the application of statistical analysis or data mining techniques. This study analyzed the Meteorological Yearbook data of the Korea Meteorological Administration (KMA) with a text mining technique. First, a term dictionary was constructed through preprocessing and a term-document matrix was generated. This term dictionary was then used to calculate the annual frequency of term, and observe the change in relative frequency for frequently appearing words. We also used regression analysis to identify terms with increasing and decreasing trends. We analyzed the trends in the Meteorological Yearbook of the KMA and analyzed trends of weather related news, weather status, and status of work trends that the KMA focused on. This study is to provide useful information that can help analyze and improve the meteorological services and reflect meteorological policy.

• Clean Technology
• /
• v.18 no.1
• /
• pp.69-75
• /
• 2012

In this study, we executed an environmental impact assessment about recycling of ITO (Indium Tin Oxide), used for touch panel. ITO is mainly used to make transparent conductive coatings for touch and flat screen LCD (Liquid Crystal Display), ELD (Emitting Light Device), PDP (Plasma Display Panel). This demand is increasing little by little. but form current status, ITO is discarded than recycling. It is important to recycling ITO for national strategies about resource conservation, and reduce environmental burden. Also Landfill or incineration of ITO cloud be harmful to the human health in the long-term. Material Life Cycle Assessment method (MLCA) was conducted for comparison landfill and recycling of ITO. MLCA would provide more information for environmental issues and potential environmental impacts of ITO. The study includes two scenarios, the basic scenario is recycling of ITO (10, 20, 30%) and the other scenario is landfill of ITO. In addition, amount of carbon dioxide and energy were calculated.

• Korean Journal of Remote Sensing
• /
• v.17 no.1
• /
• pp.15-31
• /
• 2001

The relationship between GMS-5 IR1 brightness temperature (CTT:cloud top temperature) and AWS (automatic weather station) rainfall is investigated on a heavy rain event over the mid-western part of Korea for August 5-6, 1998. It is found that a temporal variability of the heavy rain can be described in detail y the time series of rain area and rain rates over the study area that are calculated from AWS accumulated rainfalls for 15 minutes. A time period of 0030-0430 LST 6 August 1998 is chosen in the time series as a heavy rain period which has relatively small rain area (20~25%) and very strong rain rates(6~9 mm/15 min.) with a good time continuity. In the heavy rain period, CTT of a point and AWS 15-minute rainfall beneath that point are compared. From the comparison, AWS rainfalls are shown to be not closely correlated with CTT. In the range of CTT lower than -5$0^{\circ}C$ where most AWS with rain are distributed, the probability of rain is at most about 30%. However, when the satellite images are shifted by 2~3 pixels southward and 3 pixels westward for the geometric correction of images, AWS rainfalls are shown to be statistically correlated with CTT (correlation coefficient:-0.46). Most AWS with rain are distributed in the much lower CTT range(lower than -58$^{\circ}C$), but there is still not much change in the rain probability. Even though a temporal change of CTT is taken into account, the rain probability amount to at most 50~55% in the same range.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.368-376
• /
• 2021

Artificial intelligence clouds help to efficiently develop the autonomous things integrating artificial intelligence technologies and control technologies by sharing the learned models and providing the execution environments. The existing autonomous things development technologies only take into account for the accuracy of artificial intelligence models at the cost of the increment of the complexity of the models including the raise up of the number of the hidden layers and the kernels, and they consequently require a large amount of computation. Since resource-constrained computing environments, could not provide sufficient computing resources for the complex models, they make the autonomous things violate time criticality. In this paper, we propose a digital twin software development framework that selects artificial intelligence models optimized for the computing environments. The proposed framework uses a load estimation DNN model to select the optimal model for the specific computing environments by predicting the load of the artificial intelligence models with digital twin data so that the proposed framework develops the control software. The proposed load estimation DNN model shows up to 20% of error rate compared to the formula-based load estimation scheme by means of the representative CNN models based experiments.

• Convergence Security Journal
• /
• v.18 no.1
• /
• pp.19-31
• /
• 2018

As the ICT technologies advance, the unprecedently large amount of digital data is created, transferred, stored, and utilized in every industry. With the data scale extension and the applying technologies advancement, the new services emerging from the use of large scale data make our living more convenient and useful. But the cybercrimes such as data forgery and/or change of data generation time are also increasing. For the data security against the cybercrimes, the technology for data integrity and the time verification are necessary. Today, public key based signature technology is the most commonly used. But a lot of costly system resources and the additional infra to manage the certificates and keys for using it make it impractical to use in the large-scale data environment. In this research, a new and far less system resources consuming signature technology for large scale data, based on the Hash Function and Merkle tree, is introduced. An improved method for processing the distributed hash trees is also suggested to mitigate the disruptions by server failures. The prototype system was implemented, and its performance was evaluated. The results show that the technology can be effectively used in a variety of areas like cloud computing, IoT, big data, fin-tech, etc., which produce a large-scale data.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.7
• /
• pp.445-454
• /
• 2022

Ice accretion on the aircraft components, such as wings, fuselage, and empennage, can occur when the aircraft encounters a cloud zone with high humidity and low temperature. The prevention of ice accretion is important because it causes a decrease in the aerodynamic performance and flight stability, thus leading to fatal safety problems. In this study, a shape design optimization of a multi-element airfoil is performed to minimize the amount of ice accretion on the high-lift device including leading-edge slat, main element, and trailing-edge flap. The design optimization framework proposed in this paper consists of four major parts: air flow, droplet impingement and ice accretion simulations and gradient-free optimization algorithm. Reynolds-averaged Navier-Stokes (RANS) simulation is used to predict the aerodynamic performance and flow field around the multi-element airfoil at the angle of attack 8°. Droplet impingement and ice accretion simulations are conducted using the multi-physics computational analysis tool. The objective function is to minimize the total mass of ice accretion and the design variables are the deflection angle, gap, and overhang of the flap and slat. Kriging surrogate model is used to construct the response surface, providing rapid approximations of time-consuming function evaluation, and genetic algorithm is employed to find the optimal solution. As a result of optimization, the total mass of ice accretion on the optimized multielement airfoil is reduced by about 8% compared to the baseline configuration.

• Journal of Industrial Convergence
• /
• v.20 no.6
• /
• pp.27-35
• /
• 2022

The purpose of this study is to analyze the metaverse-related issues in the news big data from an educational perspective, explore their characteristics, and provide implications for the educational applicability of the metaverse and future education. To this end, 41,366 cases of metaverse-related data searched on portal sites were collected, and weight values of all extracted keywords were calculated and ranked using TF-IDF, a representative term weight model, and then word cloud visualization analysis was performed. In addition, major topics were analyzed using topic modeling(LDA), a sophisticated probability-based text mining technique. As a result of the study, topics such as platform industry, future talent, and extension in technology were derived as core issues of the metaverse from an educational perspective. In addition, as a result of performing secondary data analysis under three key themes of technology, job, and education, it was found that metaverse has issues related to education platform innovation, future job innovation, and future competency innovation in future education. This study is meaningful in that it analyzes a vast amount of news big data in stages to draw issues from an education perspective and provide implications for future education.