• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.1-18
• /
• 2023

With the recent developments in big data and deep learning, a variety of traffic information is collected widely and used for traffic operations. In particular, long short-term memory (LSTM) is used in the field of traffic information prediction with time series characteristics. Since trends, seasons, and cycles differ due to the nature of time series data input for an LSTM, a trial-and-error method based on characteristics of the data is essential for prediction models based on time series data in order to find hyperparameters. If a methodology is established to find suitable hyperparameters, it is possible to reduce the time spent in constructing high-accuracy models. Therefore, in this study, a traffic information prediction model is developed based on highway vehicle detection system (VDS) data and LSTM, and an impact assessment is conducted through changes in the LSTM evaluation indicators for each hyperparameter. In addition, a methodology for finding hyperparameters suitable for predicting highway traffic information in the transportation field is presented.

• Journal of Korea Water Resources Association
• /
• v.56 no.10
• /
• pp.641-653
• /
• 2023

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.1-14
• /
• 2023

Soybeans are one of the world's top five staple crops and a major source of plant-based protein. Due to their susceptibility to climate change, which can significantly impact grain production, the National Agricultural Science Institute is conducting research on crop phenotypes through growth analysis of various soybean varieties. While the process of capturing growth progression photos of soybeans is automated, the verification, recording, and analysis of growth stages are currently done manually. In this paper, we designed and trained a YOLOv5s model to detect soybean leaf objects from image data of soybean plants and a Convolution Neural Network (CNN) model to judgement the unfolding status of the detected soybean leaves. We combined these two models and implemented an algorithm that distinguishes layers based on the coordinates of detected soybean leaves. As a result, we developed a program that takes time-series data of soybeans as input and performs growth analysis. The program can accurately determine the growth stages of soybeans up to the second or third compound leaves.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.751-759
• /
• 2023

Breast ultrasonography is difficult to image in fatty breasts and to find micro-calcification, but the discovery of micro-calcification is very important for breast cancer screening. Among the color Doppler artifact of ultrasound, twinkle artifact mainly occur on strong reflectors such as stones or calcification in images, and evaluation methods using them are clinically being used. In this study, we are conducting experiments on the color Doppler settings of ultrasound equipment, such as repetition frequency, ensemble, persist, wall filtering, smoothing, linear density, and dissociation value, by producing a breast simulation phantom using the largest amount of calcium phosphate among breast implants. The purpose of this study was to improve the contrast of twinkle artifact in breast ultrasound examinations and to maximize their use in clinical practice. As a result, the pulse repetition frequency occurred in the range of 3.6 kHz to 7.2 kHz, and did not occur above 10.5 kHz. For ensembles, twinkle artifact occurred in all sizes of calcification under low conditions, and in threshold settings, the twinkle artifact increased slightly only under 80 to 100 conditions, and did not occur in 1 mm size calcification. Persist, wall filter, smoothing, and line density settings did not have much meaning in the setting variable because conditions did not increase by condition, and pulse repetition frequency, ensemble, and thresholds had the greatest impact on the twinkling artifact image. This study is expected to help examiners select optimal conditions to effectively increase twinkle artifact by adjusting color Doppler settings.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.159-167
• /
• 2023

Due to the convergence of digital technology and the rapidly changing characteristics of the digital industry, the development projects in each technology field that have been carried out so far have blurred the boundaries of the business, dispersed business effects, and reached the limit in fostering a flexible industry that accommodates technological development. It appears that Therefore, the goal is to support the policy of the digital content development project by suggesting a plan to reorganize the structure and improve the management system of the digital content industry development project to effectively respond to the changing direction of the future digital content industry. Through structural analysis and diagnosis of government supported projects, it was proposed to reorganize the existing 19 key projects and 49 detailed projects into 7 key projects projects and 17 detailed projects. As a plan to improve the project management system, there are too many project implementation agencies and the absence of a general agency for detailed project support management, which limits the promotion of large-scale projects for organic linkage between projects and market creation. To improve this, a general agency that oversees the project management function was selected, and it was suggested that there was a need to unify project management into a general organization to manage the project efficiently.

• Journal of the Korean Dietetic Association
• /
• v.29 no.4
• /
• pp.211-229
• /
• 2023

This study analyzed the differences in the general characteristics, mental and health-related factors, eating habits, and nutrient intake of Korean male youths before and after the outbreak of the coronavirus disease 2019 (COVID-19). The data of a total of 1,231 subjects, from among the participants in the 2018 and 2020 Korea National Health and Nutrition Examination Survey (KNHANES), were analyzed. The 2020 group had fewer married members than the 2018 group. The subjects in the 2020 group weighed more (P<0.05), had a higher waist circumference (P<0.01), and showed greater weight gain (P<0.05) than the 2018 group subjects. The aerobic physical activity of the 2020 group was lower (P<0.01) compared to the 2018 group. The members of the 2020 group had higher depression scores (P<0.01), suicidal tendencies (P<0.01), and need for counseling for mental problems (P<0.05) than those of the 2018 group. The prevalence of high fasting blood sugar levels and diabetes was higher in the 2020 group compared to the 2018 group. The frequency of breakfast (P<0.01) and dining out (P<0.001) and the proportion of breakfast (P<0.01) and dinner (P<0.05) taken with the family or non-family members was lower in the 2020 group than in the 2018 group. The rate of dietary supplement intake of the 2020 group was higher than that of the 2018 group (P<0.01). There were significant differences in the protein (P<0.05), riboflavin (P<0.01), and carbohydrate (P<0.01) intakes between the two groups. These results suggest that male youths had a higher waist circumference and high levels of depression, and showed a decrease in frequency of breakfast intake and dining out after the out break COVID-19 pandemic. Therefore, nutrition and health promotion programs are urgently needed to improve mental health, other health-related factors and nutritional status of male adults that are associated with the COVID-19 pandemic.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.126-133
• /
• 2023

In this study, electromyography was obtained in the six muscle areas that move the joints of the two legs, and by analyzing it, an exercise robot system capable of gait rehabilitation was proposed in consideration of the individual's muscle state. Through this, the system was constructed to prevent the effect of exercise from decreasing because the patient's will was not reflected when walking exercise was simply provided automatically. As a result of the evaluation of the developed system, it was confirmed that the pedestrian rehabilitation robot system manufactured through this study had performance suitable for the design requirements, and it was also confirmed that the usability evaluation was comprehensively satisfactory. The results of this study are thought to be of great help to patients who are having difficulty in gait rehabilitation, and are believed to be helpful in the development of electromyography signal-based gait robot systems.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.27-33
• /
• 2023

Recently, water shortages have occurred due to climate change, and the need for water management of agricultural water has increased due to the occurrence of algal blooms in reservoirs. Existing algae prevention is operated by putting many people on site and misses the optimal spraying time due to movement through boats. In order to solve this problem, it is necessary to block contamination in advance and move within time to uniformly spray complex microorganisms uniformly. Control drones are used for pesticide spraying and can be applied to algae prevention work by utilizing control drones. In this paper, basic research for the establishment of a marine control system was conducted for application to the reservoir environment, and as one of the results, the characteristics of a drone nozzle, a core technology that can be used for control drones, were calculated. In particular, it was found that the existing agricultural control drones had a disadvantage that the concentration was non-uniform within the suggested spraying interval, and to compensate for this, nozzle positioning and nozzle spraying uniformity were calculated. Based on the experimental results, we develop a core algorithm for establishing an algal bloom monitoring system in the reservoir environment and propose a precision control technology that can be used for marine control work in the future.

• Journal of Advanced Technology Convergence
• /
• v.2 no.4
• /
• pp.13-19
• /
• 2023

Following the signing of the Paris Agreement on Climate Change (UNFCCC, 2015), the world is expanding greenhouse gas reduction activities through comprehensive participation that includes not only developed countries but also developing countries. Major countries around the world are placing high expectations on the effectiveness of total carbon emissions regulation through the carbon emissions market. However, in order to obtain carbon credits, third-party verification is required based on quantitative carbon reduction data. Accordingly, in this paper, we developed an AIoT high-efficiency street light for carbon emissions and conducted a performance analysis study to measure the luminous efficiency of the lighting fixture. To obtain carbon emissions rights, we used high-efficiency LED PKG, developed our own high-voltage PFC, and developed high-efficiency lighting fixtures capable of communication. For communication, the 2.4GHz LoRa method was adopted between the lighting fixture and the gateway. Lens design was conducted through simulation of Korea Expressway Corporation's standard streetlight types A, B, and C. The performance of the streetlight was verified as being more efficient than other existing products through the measurement of luminous efficiency by an accredited rating agency, and it is expected that carbon emissions rights will be obtained by reducing electrical energy through this.

• Journal of the Korea Society for Simulation
• /
• v.32 no.4
• /
• pp.77-84
• /
• 2023

In the agricultural sector, power sources are being developed that use alternative energy sources such as electric tractors and hydrogen tractors, away from internal combustion engine tractors. As parts such as engines and transmissions used in conventional internal combustion engine tractors are replaced with motors and batteries, the center of gravity changes, and thus the risk of rollover should be considered. The purpose of this study is to analyze the overturn angle of the main parts of the electric tractor through dynamic simulation to minimize the overturn accident and to derive the optimal arrangement of parts to improve stability. A total of nine dynamics simulations were conducted by designing three components of the PTO motor, drive motor and the battery pack, and three factors of the arrangement method. As a result of the experiment, it was confirmed that Type3 Level3, in which the drive motor and the PTO motor are located at the front and rear of the tractor, and two battery packs are located in the middle of the tractor, has a high rollover angle. As a result of this study, the stability increased as the center of gravity was placed backward and located below. Future research needs to be done to find the optimal location of parts considering their performance and placement efficiency.