• International Journal of Naval Architecture and Ocean Engineering
• /
• 제12권1호
• /
• pp.314-324
• /
• 2020

Due to the nonlinearity and environmental uncertainties, the design of the ship's steering controller is a long-term challenge. The purpose of this study is to design an intelligent autopilot based on Extended Kalman Filter (EKF) trained Radial Basis Function Neural Network (RBFNN) control algorithm. The newly developed free running model scaled surface vessel was employed to execute the motion control experiments. After describing the design of the EKF trained RBFNN autopilot, the performances of the proposed control system were investigated by conducting experiments using the physical model on lake and simulations using the corresponding mathematical model. The results demonstrate that the developed control system is feasible to be used for the ship's motion control in the presences of environmental disturbances. Moreover, in comparison with the Back-Propagation (BP) neural networks and Proportional-Derivative (PD) based control methods, the EKF RBFNN based control method shows better performance regarding course keeping and trajectory tracking.

• Smart Structures and Systems
• /
• 제28권6호
• /
• pp.811-825
• /
• 2021

High-voltage isolating switches play a paramount role in ensuring the safety of power supply systems. However, their exposure to outdoor environmental conditions may cause serious physical defects, which may result in great risk to power supply systems and society. Image processing-based methods have been used for anomaly detection. However, their accuracy is affected by numerous uncertainties due to manually extracted features, which makes the anomaly detection of isolating switches still challenging. In this paper, a vision-based anomaly detection method for isolating switches, which uses the rotational angle of the switch system for more accurate and direct anomaly detection with the help of deep learning (DL) and image processing methods (Single Shot Multibox Detector (SSD), improved frame differencing method, and Hough transform), is proposed. The SSD is a deep learning method for object classification and localization. In addition, an improved frame differencing method is introduced for better feature extraction and a hough transform method is adopted for rotational angle calculation. A number of experiments are conducted for anomaly detection of single and multiple switches using video frames. The results of the experiments demonstrate that the SSD outperforms the You-Only-Look-Once network. The effectiveness and robustness of the proposed method have been proven under various conditions, such as different illumination and camera locations using 96 videos from the experiments.

• 반도체디스플레이기술학회지
• /
• 제22권2호
• /
• pp.112-119
• /
• 2023

In urban environments, signals of Global Positioning System (GPS) can be blocked and reflected by tall buildings, large vehicles, and complex components of road network. Therefore, the performance of the positioning system using the GPS module in urban areas can be degraded due to the loss of GPS signals necessary for the position estimation. To deal with this issue, various localization schemes using inertial measurement unit (IMU) sensors, such as gyroscope and accelerometer, and Bayesian filters, such as Kalman filter (KF) and particle filter (PF), have been designed to enhance the performance of the GPS-based positioning system. Among Bayesian filters, the PF has been widely used for the target tracking and vehicle navigation, since it can provide superior performance in estimating the state of a dynamic system under nonlinear/non-Gaussian circumstance. This paper presents a positioning system that uses the double-stacked particle filter (DSPF) as well as the accelerometer, gyroscope, and GPS receiver on the smartphone to provide higher pedestrian positioning accuracy in urban environments. The DSPF employs a nonparametric technique (Parzen-window) to create the multimodal target distribution that approximates the posterior distribution. Experimental results show that the DSPF-based positioning system can provide the significant improvement of the pedestrian position estimation in urban environments.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.975-983
• /
• 2022

This paper presents an innovative way of integrating scheduling and project controls with the environmental impact of a construction project to track, monitor, and manage environmental emissions at the activity level. As a starting point, scheduling and project controls help monitor the status of a project to provide an assessment of the duration and sequence of activities. Additionally, project schedules can also reflect resource allocation and costs associated with various phases of a construction project. Owners, contractors and construction managers closely monitor tasks or activities on the critical path(s) and/or longest path(s) calculated through network based scheduling techniques. However, existing industry practices do not take into account environmental impact associated with each activity during the life cycle of a project. Although the environmental impact of a project may be tracked in various ways, that tracking is not tied to the project schedule and, as such, generally is not updated when schedules are revised. In this research, a Cradle to Gate approach is used to estimate environmental emissions associated with each activity of a sample project schedule. The research group has also investigated the potential determination of scenarios of lowest environmental emissions, just as project managers currently determine scenarios with lowest cost or time. This methodology can be scaled up for future work to develop a library of unit emissions associated with commonly used construction materials and equipment. This will be helpful for project owners, contractors, and construction managers to monitor, manage, and reduce the carbon footprint associated with various projects.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.140-142
• /
• 2023

Federated learning (FL) is a new paradigm in machine learning (ML) that enables multiple devices to collaboratively train a shared ML model without sharing their local data. FL is well-suited for applications where data is sensitive or difficult to transmit in large volumes, or where collaborative learning is required. The Internet of Underwater Things (IoUT) is a network of underwater devices that collect and exchange data. This data can be used for a variety of applications, such as monitoring water quality, detecting marine life, and tracking underwater vehicles. However, the harsh underwater environment makes it difficult to collect and transmit data in large volumes. FL can address these challenges by enabling devices to train a shared ML model without having to transmit their data to a central server. This can help to protect the privacy of the data and improve the efficiency of training. In this view, this paper provides a brief overview of Fed-IoUT, highlighting its various applications, challenges, and opportunities.

• Journal of Astronomy and Space Sciences
• /
• 제40권3호
• /
• pp.123-129
• /
• 2023

This paper presents an analysis of the trans-lunar trajectory insertion performance of the Korea Pathfinder Lunar Orbiter (KPLO), the first lunar exploration spacecraft of the Republic of Korea. The successful launch conducted on August 4, 2022 (UTC), utilized the SpaceX Falcon 9 rocket from Cape Canaveral Space Force Station. The trans-lunar trajectory insertion performance plays a crucial role in ensuring the overall mission success by directly influencing the spacecraft's onboard fuel consumption. Following separation from the launch vehicle (LV), a comprehensive analysis of the trajectory insertion performance was performed by the KPLO flight dynamics (FD) team. Both orbit parameter message (OPM) and orbit determination (OD) solutions were employed using deep space network (DSN) tracking measurements. As a result, the KPLO was accurately inserted into the ballistic lunar transfer (BLT) trajectory, satisfying all separation requirements at the target interface point (TIP), including launch injection energy per unit mass (C3), right ascension of the injection orbit apoapsis vector (RAV), and declination of the injection orbit apoapsis vector (DAV). The precise BLT trajectory insertion facilitated the smoother operation of the KPLO's remainder mission phase and enabled the utilization of reserved fuel, consequently significantly enhancing the possibilities of an extended mission.

• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• pp.126-134
• /
• 2023

Drones are emerging as a new security threat, and the world is working to reduce them. Detection and identification are the most difficult and important parts of the anti-drone systems. Existing detection and identification methods each have their strengths and weaknesses, so complementary operations are required. Detection and identification performance in anti-drone systems can be improved through the use of artificial intelligence. This is because artificial intelligence can quickly analyze differences smaller than humans. There are three ways to utilize artificial intelligence. Through reinforcement learning-based physical control, noise and blur generated when the optical camera tracks the drone may be reduced, and tracking stability may be improved. The latest NeRF algorithm can be used to solve the problem of lack of enemy drone data. It is necessary to build a data network to utilize artificial intelligence. Through this, data can be efficiently collected and managed. In addition, model performance can be improved by regularly generating artificial intelligence learning data.

• 한국의학물리학회지:의학물리
• /
• 제20권3호
• /
• pp.132-138
• /
• 2009

호흡으로 인한 방사선 치료 표적의 움직임을 고려함으로써 치료 성적 향상과 동시에 주변 장기 보호를 지향하는 4차원 방사선 치료의 구현, 성능 개선의 연구가 활발히 진행되고 있다. 환자가 자연스럽게 호흡하도록 하는 장점이 있는 호흡 동기방식이나 종양추적방식을 사용하는 경우, 방사선조사 표적의 움직임을 예측, 방사선조사 시 이를 보정하여 줌으로써 방사선치료 효과를 극대화할 수 있다. 신경회로망은 통계 수식에 의존하지 않고 주어진 자료를 표현하는 일종의 규칙을 찾아내므로, 방사선 치료 표적의 실시간 움직임과 같은 비선형성을 가진 시계열(Time Series)을 표현하는 데에 유리하다. 본 연구에서는 신경회로망 예측 알고리즘의 4차원 방사선치료에 적용 가능성을 평가하였다. Multi-layer Perceptron으로 신경회로망을 구성하였고 Scaled Conjugate Gradient 알고리즘을 신경회로망 학습 알고리즘으로 사용하였다. RPM 시스템을 이용하여 획득한 실제 임상 현장의 환자에 대한 호흡 자료를 기반으로 학습한 신경회로망 예측 결과를 RPM 시스템의 측정치와 상호 비교하였다. 10명의 환자에의 적용 결과, 신경회로망 학습에 사용된 자료가 환자의 호흡 범위 전체를 포함하지 않는 경우를 제외하고는, 최대절대오차 3 mm 미만의 우수한 예측 성능을 보였다. 학습 영역 이외의 호흡 자료 예측 시 발생하는 상당한 오차는 신경회로망의 외삽에 대한 학습능력 부족을 보이는 것으로, 오차의 원인을 제거하기 위한 일환으로, 호흡자료를 측정할 때 최대 호흡을 하도록 하여 충분한 학습 자료를 확보하는 방안을 고려해 볼 수있겠다. 4차원 방사선치료 시스템 성능 개선에의 직접 활용을 위하여, 다양한 시스템 대기시간에 따른 예측 성능 평가와 방사선 조사 장치와 연동, 실용 타당성 검증의 추가 연구가 진행될 것이다.

• 한국콘텐츠학회논문지
• /
• 제9권7호
• /
• pp.76-85
• /
• 2009

높은 해상도를 갖는 UWB 신호는 무선 개인영역망에서 거리추정 및 위치추정에 사용된다. 이들 노드는 국부클럭으로 동작하고, 노드간의 클럭 주파수 차이는 이동노드의 위치를 추정하는 거리추정 알고리즘에 심각한 영향을 미친다. IEEE802.15.4a의 저속 UWB에서는 추가적인 망동기의 도움 없이 수행하는 TWR 및 SDS-TWR의 비동기 양방향 거리추정 방식을 기술하고 있으나 클럭 주파수차이의 영향을 없애지는 못하고 있다. 그러므로 UWB 물리기능에 두 노드의 수정발진기 주파수 차이를 추정하는 방식이 필요하다. 고속 UWB에서는 추적회로를 사용한 수정발진기 편이 추정이 표준에 별도로 요구되지 않고 있다. 그러나 잡음이 없는 환경에서는 노드간의 수정발진기 편이 추정이 가능하다. 본 논문에서는 상대주파수 편이를 사용하여 TWR 기반의 거리추정 수식을 유도하였으며, 이상적인 수식에서의 잔여 오차를 분석하였다. 또한 시뮬레이션으로 상대주파수 편이 알고리즘의 성능을 평가하고, TWR 횟수에 따른 거리추정오차를 분석하였다. 결과적으로 클럭 해상도가 낮더라도 다수의 TWR을 사용한 상대주파수 편이 보상 방식에 의하여 거리추정오차의 성능이 개선됨을 알 수 있다.

• 대한토목학회논문집
• /
• 제43권5호
• /
• pp.667-674
• /
• 2023

건물에서 재난이 발생할경우, 건물 내 인원을 신속히 구조하여 사상자를 최소화하는 것은 단연 최우선순위가 된다. 이러한 구조활동을 위해서는 건물내 어디에 몇 명이 있는지를 알아야 하는데, 실시간으로 알기가 어렵다보니 주로 건물주나 경비원 등 관계자의 진술이나 층별 면적, 수용 인원과 같은 기초자료에 의존하는 실정이다. 따라서 빠르고 정확하게 재실인원 정보를 파악하여 현장에 대한 불확실성을 낮추고 골든타임내 효율적인 구조활동을 지원하는 것이 반드시 필요하다. 본 연구는 컴퓨터 비전 알고리즘을 활용하여 이미 건물에 설치되어 있는 여러대의 CCTV 가 촬영한 이미지 로부터 건물 위치별 재실인원을 계수하는 방법론을 제시한다. 계수 방법론은 (1)카메라별 관심선(LOI) 설정을 통한 다중카메라 네트워크 환경구축, (2)딥러닝을 활용한 모니터링 구역내 사람 탐지 및 추적, (3)다중 카메라 네트워크 환경을 고려한 인원 합산 세단계로 구성된다. 제안된 방법론은 5층 건물을 대상으로 세 개의 시간대 별로 수행된 현장 실험을 통해 검증되었다. 최종 결과는 89.9%의 정확도로 재실자를 인식하는 것으로 나타났으며, 층별, 구역별 합산결과도 93.1%, 93.3%의 정확도로 우수했다. 층별 평균MAE와 RMSE는 각각 0.178과 0.339이었다. 이 처럼 실시간으로 제공하는 건물내 재실자 정보는 초기 재난 대응단계에 신속하고 정확한 구조활동을 지원 할 수있다.