• Korean Journal of Remote Sensing
• /
• v.37 no.6_2
• /
• pp.1881-1890
• /
• 2021

Particulate matter (PM) affects the human, ecosystems, and weather. Motorized vehicles and combustion generate fine particulate matter (PM_2.5), which can contain toxic substances and, therefore, requires systematic management. Consequently, it is important to monitor and predict PM_2.5 concentrations, especially in large cities with dense populations and infrastructures. This study aimed to predict PM_2.5 concentrations in large cities using meteorological and chemical variables as well as satellite-based aerosol optical depth. For PM_2.5 concentrations prediction, a random forest (RF) model showing excellent performance in PM concentrations prediction among machine learning models was selected. Based on the performance indicators R², RMSE, MAE, and MAPE with training accuracies of 0.97, 3.09, 2.18, and 13.31 and testing accuracies of 0.82, 6.03, 4.36, and 25.79 for R², RMSE, MAE, and MAPE, respectively. The variables used in this study showed high correlation to PM_2.5 concentrations. Therefore, we conclude that these variables can be used in a random forest model to generate reliable PM_2.5 concentrations predictions, which can then be used to assess the vulnerability of schools to PM_2.5.

• Journal of the Society of Disaster Information
• /
• v.15 no.3
• /
• pp.418-426
• /
• 2019

Purpose: After analyzing the seismic capability of low-rise RC grid structures with insufficient seismic performance, the purpose of the project is to install steel slab hysteretic dampers (SSHD) to improve the seismic performance of beams and columns, and to suggest measures to minimize damage to the structure and human damage when an earthquake occurs. Method: The evaluation of the seismic performance of a structure is reviewed based on the assumption that the seismic performance is identified for the grid-type subway systems that are not designed to be seismic resistant and the installation of an SSHD system, a method that minimizes construction period, if insufficient, is required. Result: After the application and reinforce of structure with SSHD, and the results of eigenvalue analysis are as follows. The natural periodicity of longitudinal direction was 0.55s and that of vertical direction was 0.58s. Conclusion: As results of cyclic load test of structure with SSHD, the shear rigidity of damper is 101%, the energy dissipation rate is 108% and, plastic rotation angle of all column and beam is satisfied for $I_o$ level and therefore it is judged that the reinforce effect is sufficient.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.4
• /
• pp.1-7
• /
• 2019

As a unify operational processes of the safety inspection for major national facilities, it is expected that the efficiency and professionalism of the project will be enhanced. Also it is being emphasized that the importance of visual inspection that initially find physical and functional defects in facilities. In this study, we developed an E-PAD-based condition evaluation system to check the safety of the facility to overcome the problems and limitations of the existing inspection method. This system consists of introduction, work list, visual inspection, defect table and so on. It is possible to download the inspection drawings at the site and input the damage information to the drawings and check the evaluation grade. In order to verify the E-PAD based condition evaluation system, the inspection data of 10 sample bridges were inputted into the system and the evaluation results were compared. As a result, it was confirmed that the safety grade calculated from the system and the existing safety grade are the same. The feasibility analysis of the AHP method also showed that the function increased by 10%, cost by 36%, and value by 30% compared to the existing method. Therefore, it is expected to contribute to systematic data and information analysis system for improvement of facility management.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.4
• /
• pp.359-365
• /
• 2019

This paper is a basic study for the performance evaluation, durability improvement and optimal design of tractor transmission. The engine torque of the 78 kW agricultural tractor during rotary tillage was measured using CAN communication. It was calculated with equivalent torque and then analyzed. In order to develop a reliable tractor, it is important to convert measured torque in various agricultural operations into equivalent torque and analyze it. The equivalent torque was calculated using Palmgren-Miner's rule, which is a representative cumulative damage law. The equivalent torque of rotary tillage period and steering period are 229.2 and 136.7 Nm, respectively. The maximum and average torque during rotary tillage period are 336.0 and 234.4 Nm, respectively. The maximum and average torque of the steering period are 288.0 and 134.6 Nm, respectively. The engine torque in rotary tillage period is higher than in the steering period because of cultivation of soil through PTO. The maximum and rated torque of engine are 387.0 and 323.0 Nm, respectively, which are 183% and 136% higher than the equivalent torque during rotary tillage and of steering section. Because transmission of agricultural tractor in Korea companies is generally designed by the rated torque of engine, there is a difference from measured torque during agricultural operations. Therefore, it is necessary to consider it for optimal design.

• Journal of the Society of Disaster Information
• /
• v.14 no.4
• /
• pp.450-457
• /
• 2018

Purpose: The evaluation of seismic performance of critical structures has been emerging a key issue in Korea, since a magnitude 5.8 earthquake, the worst in Koran history, struck Gyeongju, southern area in Korea on september 12th, 2016. In particular, the catastrophic failure of nonstructural components such as sprinkler piping systems can cause significant economic loss or loss of life during and after an earthquake. The nonstructural components can be more fragile than structural components in seismic behavior. Method: This study presents the seismic performance evaluation of fire protection piping system, using coupled building-piping system installed with Triple Friction Pendulum Bearings (TPBs). Kobe (Japan), Kocaeli (Turkey), and GyeongJu (Korea) were selected to consider the uncertainty of ground motions in this study. Result: In the simulation results, it was observed that the reduction of maximum displacements of the piping system with the TPBs' system was significant: Kobe, Kocaeli, and Gyeongju cases were 49%, 14.4% and 21.5%, respectively. Conclusion: Therefore, using seismically isolated system in a building-piping system can be more effective to reduce the seismic risk than a normally installed building-piping systems without TPBs in strong earthquakes.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.1-6
• /
• 2021

In the field of speech recognition, as the DNN is applied, the use of speech recognition is increasing, but the amount of calculation for parallel training needs to be larger than that of the conventional GMM, and if the amount of data is small, overfitting occurs. To solve this problem, we propose an efficient method for robust voice feature extraction and voice signal noise removal even when the amount of data is small. Speech feature extraction efficiently extracts speech energy by applying the difference in frame energy for speech and the zero-crossing ratio and level-crossing ratio that are affected by the speech signal. In addition, in order to remove noise, the noise of the speech signal is removed by removing the noise of the speech signal with an average predictive improved LMS filter with little loss of speech information while maintaining the intrinsic characteristics of speech in detection of the speech signal. The improved LMS filter uses a method of processing noise on the input speech signal by adjusting the active parameter threshold for the input signal. As a result of comparing the method proposed in this paper with the conventional frame energy method, it was confirmed that the error rate at the start point of speech is 7% and the error rate at the end point is improved by 11%.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.119-126
• /
• 2021

The modern pentathlon is an exercise in which people and people compete, as well as exercise without equipment, exercise using equipment, and exercise with animals, and it is an exercise that includes static and dynamic exercise. The ethical issues of modern pentathlon athletes are also related to the poor environment and economic reasons, and the athlete's ethical awareness, attitude, and spirit have a great influence on the athlete's mental environment. In this study, the direction of improvement of ethical problems, which are different as important issues in modern sports, was examined, and qualitative research methods were applied to explore the sports spirit and ethics of the modern pentathlon. Correct sports should not deviate from the intended purpose of the exercise or cause or force the athlete to suffer physical or mental pain. In sports, compensatoryism can be a direct cause of improved performance or record-breaking, but sometimes it can also cause distorted athletes. Air doping has ethical issues that can cause controversy over the health or fairness of athletes, mental and physical damage to athletes, and harm. Responsibilities and ethical issues of athletes who take prohibited substances or leaders or supervisors who neglect or encourage them should be treated as very important matters. In the sports field, the reward system that is subordinate to the athlete's or leader's performance is related to the athlete's or leader's livelihood. For a fair and just game progression, it is necessary to break away from the development of athletes who are only focused on performance. The problem of Unethical issues must be overcome by emphasizing the restoration of ethics that are reasonably recognized in ideology and logic.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.134-145
• /
• 2021

It is common to optimize the propulsion control system through a so-called tuning process that modifies the parameter values of the propulsion control software during a ship commissioning. However, during this process, if the error of the initial setting value is large, the tuning time may take too long, or the propulsion equipment can be seriously damaged. Therefore, we conducted research on the design of a propulsion controller that applied a Processor lever controller even for inexperienced people with relatively little experience in tuning propulsion control software to be able to reduce the tuning time while protecting the propulsion system. Through simulation, by comparing the execution result of propulsion control lever commands through the PI controller without applying the Processor lever controller. We analyzed the improvement of the Overshoot and propulsion performance. The simulation results showed that the safety of the propulsion system increased because Overshoot of approximately 9.74%, which occurred when the Processor lever function was not applied.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_3
• /
• pp.1711-1720
• /
• 2020

Particulate matter (PM) that has been artificially generated during the recent of rapid industrialization and urbanization moves and disperses according to weather conditions, and adversely affects the human skin and respiratory systems. The purpose of this study is to predict the PM10 concentration in Seoul using meteorological factors as input dataset for multiple linear regression (MLR), support vector machine (SVM), and random forest (RF) models, and compared and evaluated the performance of the models. First, the PM10 concentration data obtained at 39 air quality monitoring sites (AQMS) in Seoul were divided into training and validation dataset (8:2 ratio). The nine meteorological factors (mean, maximum, and minimum temperature, precipitation, average and maximum wind speed, wind direction, yellow dust, and relative humidity), obtained by the automatic weather system (AWS), were composed to input dataset of models. The coefficients of determination (R2) between the observed PM10 concentration and that predicted by the MLR, SVM, and RF models was 0.260, 0.772, and 0.793, respectively, and the RF model best predicted the PM10 concentration. Among the AQMS used for model validation, Gwanak-gu and Gangnam-daero AQMS are relatively close to AWS, and the SVM and RF models were highly accurate according to the model validations. The Jongno-gu AQMS is relatively far from the AWS, but since PM10 concentration for the two adjacent AQMS were used for model training, both models presented high accuracy. By contrast, Yongsan-gu AQMS was relatively far from AQMS and AWS, both models performed poorly.

• Therapeutic Science for Rehabilitation
• /
• v.10 no.3
• /
• pp.7-22
• /
• 2021

Objective : The purpose of this study was to verify the effect of virtual reality interventions (VRIs) on cognitive function in individuals with stroke through a systematic literature review and meta-analysis. Methods : We reviewed randomized controlled trials (RCTs) the last 10 years using academic databases. PubMed, MEDLINE, and CINAHL were used for international studies, and DBpia, KISS, Kyoboscholar, and e-article were used for Korean studies. For the quantitative meta-analysis, subgroups of outcomes were classified into general cognitive function (G-CF), attention and memory (A&M), and executive function (EF). Results : Nine RCTs were analyzed. The total number of participants was 271 (140 in the experimental group). The effect size (Cohen's d) was estimated using a random effects model. The effect sizes of the outcome subgroups of were as follows: small to medium for G-CF (d=0.422; 95% CI: 0.101~0.742; p=0.010), small for A&M (d=0.249; 95% CI: -0.107~0.605; p=0.170), and medium for EF (d=0.666; 95% CI: 0.136~1.195; p=0.014). Conclusion : Considering the various stimuli provided by the virtual environment and the results from available research, virtual reality should be applied to interventions for integrated cognitive functions. In addition, it would be appropriate to be used as an additional intervention to traditional cognitive rehabilitation for stroke.