• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.61-68
• /
• 2022

In this paper, we propose a system to predict the GPS trajectory of a pedestrian based on a deep learning model. Pedestrian trajectory prediction is a study that can prevent pedestrian danger and collision situations through notifications, and has an impact on business such as various marketing. In addition, it can be used not only for pedestrians but also for path prediction of unmanned transportation, which is receiving a lot of spotlight. Among various trajectory prediction methods, this paper is a study of trajectory prediction using GPS data. It is a deep learning model-based study that predicts the next route by learning the GPS trajectory of pedestrians, which is time series data. In this paper, we presented a data set construction method that allows the deep learning model to learn the GPS route of pedestrians, and proposes a trajectory prediction deep learning model that does not have large restrictions on the prediction range. The parameters suitable for the trajectory prediction deep learning model of this study are presented, and the model's test performance are presented.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.69-76
• /
• 2022

This paper proposes a method of refining and processing time-series data using Medical Information Mart for Intensive Care (MIMIC-IV) v2.0 data. In addition, the significance of the processing method was validated through a machine learning-based pressure ulcer early warning system using a dataset processed based on the proposed method. The implemented system alerts medical staff in advance 12 and 24 hours before a lesion occurs. In conjunction with the Electronic Medical Record (EMR) system, it informs the medical staff of the risk of a patient's pressure ulcer development in real-time to support a clinical decision, and further, it enables the efficient allocation of medical resources. Among several machine learning models, the GRU model showed the best performance with AUROC of 0.831 for 12 hours and 0.822 for 24 hours.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.97-105
• /
• 2022

This paper explains trends in security technologies for ICS. Since ICS is usually applied to large-scale national main infrastructures and industry fields, minor errors caused by cyberattack could generate enormous economic cost. ICS has different characteristic with commonly used IT systems, so considering security threats of ICS separately with IT is needed for developing modern security technology. This paper introduce framework for ICS that analyzes recent cyberattack tactics & techniques and find out trends in Intrusion Detection System (IDS) which is representative technology for ICS security, and analyzes AI technologies used for IDS. Specifically, this paper explains data collection and analysis for applying AI techniques, AI models, techniques for evaluating AI Model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.88-88
• /
• 2023

지난 100년 동안 전 지구의 기상 이변이 꾸준히 증가하고 있다. 기후 변화는 도시 홍수 피해에 큰 영향을 끼치는데 급속한 도시화와 이상 기후로 인한 돌발 강우 패턴의 증가는 도시 침수의 취약성을 가중시킨다. 또한 급격한 도시 발전으로 인한 도심지의 불투수율 또한 꾸준히 증가하였다. 특히 2022년 8월 8일에 강남역과 도림천 일대에 내린 기록적인 강우는 기후 변화를 실감하게 하는 사회적 이슈가 되었으며 도심지 미래 수방 대책 변화를 상기시키는 계기가 되었다. 이로 인한 재해 피해에 최소화하기 위해 미래 기후 변화를 고려한 도심지의 새로운 방재 목표강우량 설정이 필요하다. 하지만 전 지구 모형(GCM)의 기후 변화 시나리오는 일 단위(Daily) 상세화 자료를 보편적으로 사용하고 있다. 하지만 이는 단기 강우 자료를 필요로 하는 도시 홍수 모의에서 제대로 활용할 수 없는 한계를 가지고 있다. 따라서 본 연구는 2019년에 발간된 IPCC 6차 평가 보고서(AR6)가 제안하는 SSP(Shared Socioeconomic Pathways, 공통사회경제경로) 시나리오를 기반하여 상세화된 일 단위(Daily) 강우 데이터를 비모수적 통계 기법을 사용하여 시간 단위(Hourly)로 상세화하였다. 또한 지속 시간별 연 최대치 강우를 추출하여 빈도 해석을 통해 도시 유역의 미래 확률 강우량을 제시하였으며, 서울시 상습적인 침수 취약 지역인 도림천 유역에 강우-유출 모형(XP-SWMM)을 사용하여 미래전망 기후 자료인 SSP2-4.5와 SSP5-8.5에 따른 미래 확률 강우 침수 모의를 실시하였다. 본 연구의 결과는 최신 기후 변화 시나리오를 고려한 서울시 방재 성능 목표 강우량 산정에 활용 가능할 것으로 사료되며 미래 강우량 침수 모의를 통해 침수 취약 구역인 도림천 일대 홍수피해의 근거 자료가 되는 것에 의의를 둔다. 또한 치수 분야에서 기후 변화를 고려하기 위해서는 기후 변화 시나리오에 따른 시간 단위 자료의 상세화가 필요함을 시사한다.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.99-109
• /
• 2010

Existing research about automated wafer transport management strategy for semiconductor manufacturing equipment was mainly focused on dispatching rules which is optimized to specific system layout, process environment or transfer patterns. But these methods can cause problem as like requiring additional rules or changing whole transport management strategy when applied to new type of process or system. In addition, a lack of consideration for interconnectedness of the added rules can cause unexpected deadlock. In this study, in order to improve these problems, propose dynamic priority based transfer job decision making algorithm which is applicable with regardless of system lay out and transfer patterns. Also, extra rule handling part proposed to support special transfer requirement which is available without damage to generality for maintaining a consistent scheduling policies and minimize loss of stability due to expansion and lead to improve productivity at the same time. Simulation environment of Twin-slot type semiconductor equipment was built In order to measure performance and examine validity about proposed wafer scheduling algorithm.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.4
• /
• pp.210-219
• /
• 2023

The decline in the rural populace and an aging workforce have led to fatalities due to worsening environments and hazards within vinyl greenhouses. Therefore, it is necessary to automate crop cultivation and disease detection system in greenhouses to prevent labor loss. In this paper, an object detection-based model is used to detect diseased crop in greenhouses. In addition, the system proposed configures the environment of the artificial intelligence model in the cloud to ensure stability. The system captures images taken inside the vinyl greenhouse and stores them in a database, and then downloads the images to the cloud to perform inference based on Yolo-v4 for detection, generating JSON files for the results. Analyze this file and send it to the database for storage. From the experimental results, it was confirmed that disease detection through object detection showed high performance in real environments like vinyl greenhouses. It was also verified that efficient monitoring is possible through the database

• Journal of Advanced Navigation Technology
• /
• v.27 no.4
• /
• pp.436-446
• /
• 2023

In the field of safety-critical systems, analyzing the effects of various failure factors (failure modes) is essential through Failure Mode and Effects Analysis (FMEA). However, with the increasing importance of software in systems, applying FMEA analysis to the design phase has become challenging. This paper proposes the use of Automatic FMEA, which can automatically perform FMEA using model-based design techniques, and presents a case study of FMEA for automotive engines. A comparison is made between the model-based Automatic FMEA analysis tool and existing FMEA tools. The study aims to demonstrate the performance of the Automatic FMEA analysis tool and propose future research plans.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.545-550
• /
• 2023

A pretensioner is a safety device that protects occupants by pulling the seat belt in the event of a vehicle collision. However, since the pretensioner is driven by a explosive method, it is necessary to replace not only the gas generator but also all connecting parts including the manifold after an accident. Therefore, in this paper, we propose an elastic force-based pretensioner that can be used safely and semi-permanently. After analyzing the operating mechanism of the existing pretensioner from a thermodynamic/dynamic point of view, the spring stiffness that can be deployed within an appropriate operating time was determined by converting the gas explosion energy into elastic energy. In addition, the coil spring shape that satisfies the elastic stiffness was designed in consideration of the vehicle interior installation standard. Finally, the operating performance of the pretensioner driven by elastic force was verified through fabrication.

• Journal of the Korean Geosynthetics Society
• /
• v.22 no.2
• /
• pp.13-21
• /
• 2023

Mean sea level has recently been rising due to global warming causing coastal erosion. As Korea is peninsula, the land loss due to coastal erosion is critical. An approach in this study is cementing the coastal area using bacteria, which is called microbially induced carbonate precipitation (MICP). This study tried to see how fresh water and sea water work with MICP as a solvent. Ureolytic activity during the MICP reaction was measured with deionized and sea water. A soil column was prepared to evaluate the strength of MICP-treated sand. Sands were treated by MICP with surface percolation method. As the treatmen t style was different with other conventional methods, several methods were proposed to properly evaluate the MICP-treated sand surface. A micro-scale evaluation was performed to assess the mineral structure treated by different solvents. As results, sea water rendered the ureolytic reaction slower. A needle penetrometer worked well to evaluate the MICP-treated sand surface. This study confirmed the utilization of sea water is feasible as the solvent of MICP.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.3
• /
• pp.287-295
• /
• 2023

The collapse of bridges due to earthquakes results in many casualties and property damages. Thus, accurate prediction and preparation are required for the behavior of bridges during earthquakes. In particular, columns play an important role in the seismic behavior of bridges. The risk of collapse due to an earthquake increases when there is a problem of the insufficient lap splice in the column. In this study, to analyze the characteristics of the lap splice in the column, a numerical model was defined for the insufficient lap-spliced columns and verified using experimental data. The developed column model was applied to a commonly used RC slab bridge. Nonlinear static analysis for the column was performed to evaluate the change in the performance of the column according to the lap-spliced length. In addition, this study assessed the effect of the lap-spliced length on the seismic fragility analysis.