• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.57-62
• /
• 2021

As the parallel computing capability for artificial intelligence improves, the field of artificial intelligence technology is expanding in various industries. In particular, artificial intelligence is being introduced to process data generated from IoT sensors that have enoumous data. However, the limitation exists when applying the AI techniques on IoT network because IoT has time series data, where the importance of data changes over time. In this paper, we propose time-weighted and user-state based artificial intelligence processing techniques to effectively process IoT sensor data. This technique aims to effectively classify IoT sensor data through a data pre-processing process that personalizes time series data and places a weight on the time series data before artificial intelligence learning and use status of personal data. Based on the research, it is possible to propose a method of applying artificial intelligence learning in various fields.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.766-769
• /
• 2021

In order to perform tasks such as design, control, optimization, and prediction of flight vehicle trajectories based on machine learning techniques including deep learning, a certain amount of flight vehicle trajectory data is required. However, there are cases in which it is difficult to secure more than a certain amount of flight vehicle trajectory data for various reasons. In such cases, synthetic data generation could be one way to make machine learning possible. In this paper, to explore this possibility, we generated and evaluated synthetic flight vehicle trajectory data using time-series generative adversarial neural network. In addition, various ablation studies (comparative experiments) were performed to explore the possibility of using synthetic data in the aircraft trajectory prediction task. The experimental results presented in this paper are expected to be of practical help to researchers who want to conduct research on the possibility of using synthetic data in the generation of synthetic flight vehicle trajectory data and the work related to flight vehicle trajectories.

• Journal of the Korean Geosynthetics Society
• /
• v.21 no.2
• /
• pp.11-19
• /
• 2022

In this paper, we propose a GoogleNet transfer learning and CNN-LSTM combination method to improve the time-series prediction performance for crack detection using crack data captured inside the sewer pipes. LSTM can solve the long-term dependency problem of CNN, so spatial and temporal characteristics can be considered at the same time. The predictive performance of the proposed method is excellent in all test variables as a result of comparing the RMSE(Root Mean Square Error) for time series sections using the crack data inside the sewer pipe. In addition, as a result of examining the prediction performance at the time of data generation, the proposed method was verified that it is effective in predicting crack detection by comparing with the existing CNN-only model. If the proposed method and experimental results obtained through this study are utilized, it can be applied in various fields such as the environment and humanities where time series data occurs frequently as well as crack data of concrete structures.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.483-483
• /
• 2023

2020년 8월 섬진강 유역에서 100년 빈도 이상의 대홍수가 발생함에 따라 제방이 붕괴되거나 하천 범람이 발생하는 피해가 발생하였다. 8월 홍수를 대상으로 섬진강 본류 남원(신덕리) 수위국에서 기존의 수위-유량 관계 곡선식(이하 Rating curve)의 최대 적용 가능 수위는 2.53m 이지만, 해당 기간 첨두 수위는 10m 이상을 기록하였다. 이러한 대홍수의 경우 기왕의 관측데이터가 없을 뿐만 아니라 기존의 Rating curve를 외삽하여 활용하는 것에도 한계가 있어 간접적으로 유량을 산정할 수 있는 기법이 필요하다. 본 연구에서는 이와 같이 유량측정이 어려운 지점을 대상으로 주어진 유량에 대하여 수위를 재현할 수 있는 K-water에서 개발된 K-River모형(1차원 하천수리해석모형)과 Monte Carlo 시뮬레이션 기법을 활용하여 간접적으로 유량을 산정할 수 있는 기법을 개발하였다. 개발된 방법론은 고수위 구간에 대한 Rating curve의 불확실성으로 인하여 본류와 지류의 유입량 추정이 어려웠던 섬진강 요천 합류부에 적용하였다. 대상구간은 본류(섬진강) 26km 및 지류(요천) 15km로 구성되어 있으며, 본류와 지류의 상류인 수위국 남원(신덕리) 관측소와 남원(동림교) 관측소에는 각각 기존의 Rating curve가 존재한다. 불확실성이 높은 Rating curve의 고수위 구간에 대한 매개변수를 조정하여 다수의 Rating curve를 생성하고, 이를 기반으로 관측수위를 다수의 상류 시계열 유량자료(경계조건)로 환산하였다. 다음으로 이 유량자료를 기반으로 앙상블 모의를 수행 후 대상구간의 중간지점에 위치한 수위국(고달(고달교) 관측소, 송동(요천대교) 관측소, 곡성(금곡교) 관측소)에서 수위재현성(NSE, RSR등 활용)을 평가하여 최적 샘플 추출을 추출하였다. 추출된 샘플로부터 상류 경계지점의 적정 Rating curve 선정과 각 지점에서의 시계열 수위 및 유량을 역으로 추정하였다. 이를 통해 실제 유량측정결과 없이도 간접적으로 신뢰도 높은 유량 자료를 확보할 수 있음을 확인할 수 있었으며, 향후 수자원의 효율적 관리 및 홍수관리를 위하여 효율적으로 활용이 가능할 것으로 생각된다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.159-165
• /
• 2023

This study aims to analyze the changes in the management efficiency of public institutions in time series, and to examine the relationship with financial performance based on the results of time series changes. Specifically, we classified into upper and lower groups of financial performance based on the government's management evaluation results, and analyze how the management efficiency of each group changed in the period before the evaluation year. Based on public institutions published in public business information system, DEA(Data Envelopment Analysis) was performed for estimating management efficiency. The results are summarized as follows; First, we find that DEA of the upper group changed in the direction of increasing, but DEA of the lower group changed in the direction of decreasing. Second, we find that there is a significant positive relation between DEA and financial performance. This result means that the higher financial performance, the higher management efficiency. These findings imply that management efficiency can be a factor that improve financial performance in public institutions. The results also suggest that government's innovation strategies to improve financial stability by enhancing management efficiency were effective.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.679-684
• /
• 2023

Currently, large-scale and deep-depth excavation construction is being carried out in the vicinity of structures due to overdensity in urban areas in Korea. It is very important to secure the safety of retaining structures and underground structures for adjacent excavation work in urban areas. The safety of facilities is managed by introducing an automated measurement system. However, the utilization of the results of the automated measurement system is very low. Conventional evaluation techniques rely only on the maximum value of the measured data, and can overestimate abnormal behavior. In this study, we intend to improve the analysis technique for the automation measurement results. In order to identify abnormal behavior of facilities, a time-series analysis method for automated measurement data was presented. By applying a probability statistical analysis technique to a vast amount of data, highly reliable results were derived. In this study, the analysis method and evaluation method that can process the vast amount of data of facilities have been improved.

• Korea Science and Art Forum
• /
• v.34
• /
• pp.251-262
• /
• 2018

The purpose of this study is to understand how wearable computing devices are designed and how to design them in a technology based wearable device design research. Research is premised on the consideration of producers and consumers. There is wearable computer of eyeglasses, watches, clothes, and so on. The user can always wear these products comfort and use as part of the body without any sense of discomfort, and the goal is to supplement or double the ability of the human being. It should be easy to use them convenient, wear comfortable, safe and sociable at any time. For the satisfaction these conditions, the wearable computing devices have several factors. There are technical performances, visual aesthetics, Human body system and devices communication and safety. Furthermore, these factors have to match to operating system, real-time operating system and applied software. To comprehend wearable computing devices should be offered the design of the both software and hardware designed.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.6
• /
• pp.763-774
• /
• 2023

The water availability in a river is related to the return flow of residential water. However it is still difficult to determine the exact return flow. In this study, the residential water-cycle system is defined as a process consisting of water inflow, water transfer and water outflow. The study area is Hampyeong-gun, Jeollanam-do, and is set as a single inflow to a single outflow through the water-cycle system after classification of complete and incomplete measurement points. The time-series prediction models(ARIMA model and TFM) are established with daily inflow and outflow data for 6 years. Inflow and outflow are predicted by dividing into training and test periods. As a result, both models show the feasibility of short-term prediction by deriving stable residuals and securing statistical significance, implementing the preliminary form of the water-cycle system. As a further study, it is suggested to predict the actual return flow of the target basin and efficient water operation by adding input factors and selecting the optimal model.

• Korea journal of population studies
• /
• v.29 no.2
• /
• pp.27-51
• /
• 2006

In this paper, I have tested various kinds of methods for mortality projection and chose Lee-Carter method for projection of Korean mortality by age and sex. I reviewed the trends of life tables and life expectancies by age and sex from 2005 to 2050 projected by Lee-Carter method and found that the method was very applicable for Korean mortality projection. The differences between reported and estimated data for the period of 1971-2003 were small enough for both sexes and for all of the age groups. The projected life expectancies in 2051 were 82.73 years for males and 89.41 for females, and the differences decreased from 7.06 years in 2005 to 6.68 years. Because of the limitation of Korean infant mortality rate, I adopted the Japanese estimated IMR in 2050 as Korean object level in 2051. When the time series of IMR become long enough, we can use Korean IMR directly for the mortality projection. In addition, if we can estimate the changes of the main cause of death correctly in future, the mortality projection will be more correct and reliable. This will be available when we can produce a long series of life tables by cause of deaths.

• The Journal of Engineering Geology
• /
• v.25 no.1
• /
• pp.21-33
• /
• 2015

This study tests the potential of detecting small-magnitude earthquakes (~M3.0) and their precursors using a long-term groundwater-monitoring database. In groundwater records from April to June 2012, abnormal changes in water level, temperature, and electrical conductivity were identified in the bedrock monitoring wells of the Gimcheon-Jijwa, Gangjin-Seongjeon, and Gongju-Jeongan stations. These anomalies could be attributed to the M3.1 earthquake that occurred in the Youngdeok area on May 30th, although no linear relationship was found between the scale of changes and the distance between each monitoring station and the epicenter, which is attributed in part to the wide screen design of the monitoring wells. Groundwater monitoring networks designed specifically for monitoring earthquake impacts could provide better information on the safety of underground space and on the security of emergency water-resources in earthquake disaster areas.