• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (B)
• /
• pp.748-750
• /
• 2005

Isomap [1] is a manifold learning algorithm, which extends classical multidimensional scaling (MDS) by considering approximate geodesic distance instead of Euclidean distance. The approximate geodesic distance matrix can be interpreted as a kernel matrix, which implies that Isomap can be solved by a kernel eigenvalue problem. However, the geodesic distance kernel matrix is not guaranteed to be positive semidefinite. In this paper we employ a constant-adding method, which leads to the Mercer kernel-based Isomap algorithm. Numerical experimental results with noisy 'Swiss roll' data, confirm the validity and high performance of our kernel Isomap algorithm.

• 대한조선학회논문집
• /
• 제59권6호
• /
• pp.385-392
• /
• 2022

Naval ship could face a variety of threats in isolated seas. In particular, fires and flooding are defined as disasters that are very likely to cause irreparable damage to ships. These disasters have a very high risk of personal injury as well. Therefore, when a disaster occurs, it must be quickly suppressed, but if there are people in the disaster area, the protection of life must be given priority. In order to quickly evacuate the ship crew in case of a disaster, we would like to propose a plan to quickly explore the evacuation route even in urgent situations. Using commercial escape simulation software, we obtain the data for deep neural network learning with simulations according to aisle characteristics and the properties and number of evacuation person. Using the obtained data, the passage prediction model is trained with a deep learning, and the passage time is predicted through the learned model. Construct a numerical map of a naval ship and construct a distance matrix of the vessel using predicted passage time data. The distance matrix configured in one of the path search algorithms, the Dijkstra algorithm, is applied to explore the evacuation path of naval ship.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.388-390
• /
• 2021

본 논문은 키패드, 도트매트릭스, 라이다센서, NFC 리더기를 부착한 임베디드 보드와 공공데이터포털 Open API 시스템과 딥러닝 알고리즘(YOLOv5)를 사용하여 시각장애인의 버스 탑승에 도움을 줄 수 있는 시스템을 소개한다. 이용자는 NFC 리더기 및 키패드를 통해 희망하는 버스번호를 입력한 뒤, Open API 실시간 데이터를 통해 해당 버스의 위치 및 도착예정시간 정보를 시스템에 입력해놓은 음성 출력을 통해 얻는다. 또한 도트매트릭스로 버스번호를 출력하여 기사와의 상호작용을 대기함과 동시에 딥러닝 알고리즘(YOLOv5)은 정차하는 버스 번호를 실시간 인식하고 거리센서로 버스와의 거리를 감지하여 정차유무정보를 확인, 전달하는 시스템을 제안한다.

• International Journal of Control, Automation, and Systems
• /
• 제6권2호
• /
• pp.269-277
• /
• 2008

This paper proposes a necessary and sufficient condition of convergence in the $L_2$-norm sense for a feedback-based iterative learning control (ILC) system including a multi-input multi-output (MIMO) linear time-invariant (LTI) plant. It is shown that the convergence conditions for a nominal plant and an uncertain plant are equal to the nominal performance condition and the robust performance condition in the feedback control theory, respectively. Moreover, no additional effort is required to design an iterative learning controller because the performance weighting matrix is used as an iterative learning controller. By proving that the least upper bound of the $L_2$-norm of the remaining tracking error is less than that of the initial tracking error, this paper shows that the iterative learning controller combined with the feedback controller is more effective to reduce the tracking error than only the feedback controller. The validity of the proposed method is verified through computer simulations.

• 대한임베디드공학회논문지
• /
• 제17권1호
• /
• pp.41-49
• /
• 2022

This paper proposes a novel lane detection algorithm based on inverse perspective transformation and machine learning in lightweight embedded system. The inverse perspective transformation method is presented for obtaining a bird's-eye view of the scene from a perspective image to remove perspective effects. This method requires only the internal and external parameters of the camera without a homography matrix with 8 degrees of freedom (DoF) that maps the points in one image to the corresponding points in the other image. To improve the accuracy and speed of lane detection in complex road environments, machine learning algorithm that has passed the first classifier is used. Before using machine learning, we apply a meaningful first classifier to the lane detection to improve the detection speed. The first classifier is applied in the bird's-eye view image to determine lane regions. A lane region passed the first classifier is detected more accurately through machine learning. The system has been tested through the driving video of the vehicle in embedded system. The experimental results show that the proposed method works well in various road environments and meet the real-time requirements. As a result, its lane detection speed is about 3.85 times faster than edge-based lane detection, and its detection accuracy is better than edge-based lane detection.

• Investigative Magnetic Resonance Imaging
• /
• 제25권4호
• /
• pp.293-299
• /
• 2021

Purpose: To accelerate magnetic resonance fingerprinting (MRF) by developing a flexible deep learning reconstruction method. Materials and Methods: Synthetic data were used to train a deep learning model. The trained model was then applied to MRF for different organs and diseases. Iterative reconstruction was performed outside the deep learning model, allowing a changeable encoding matrix, i.e., with flexibility of choice for image resolution, radiofrequency coil, k-space trajectory, and undersampling mask. In vivo experiments were performed on normal brain and prostate cancer volunteers to demonstrate the model performance and generalizability. Results: In 400-dynamics brain MRF, direct nonuniform Fourier transform caused a slight increase of random fluctuations on the T2 map. These fluctuations were reduced with the proposed method. In prostate MRF, the proposed method suppressed fluctuations on both T1 and T2 maps. Conclusion: The deep learning and iterative MRF reconstruction method described in this study was flexible with different acquisition settings such as radiofrequency coils. It is generalizable for different in vivo applications.

• 한국정보전자통신기술학회논문지
• /
• 제16권1호
• /
• pp.41-49
• /
• 2023

CNN(Convolutional Neural Network) 알고리즘은 인공신경망 구현에 활용되는 대표적인 알고리즘으로 기존 FNN(Fully connected multi layered Neural Network)의 문제점인 연산의 급격한 증가와 낮은 객체 인식률을 개선하였다. 그러나 IT 기기들의 급격한 발달로 최근 출시된 스마트폰 및 태블릿의 카메라에 촬영되는 이미지들의 최대 해상도는 108MP로 약 1억 8백만 화소이다. 특히 CNN 알고리즘은 고해상도의 단순 이미지를 학습 및 처리에 많은 비용과 시간이 요구된다. 이에 본 논문에서는 고해상도 단순 이미지의 객체 분류 학습모델 구현을 위한 개선된 CNN 알고리즘을 제안한다. 제안하는 알고리즘은 고해상도의 이미지들의 학습모델 생성 시간을 감소하기 위해 CNN 알고리즘의 풀링계층의 Max Pooling 알고리즘 연산을 위한 인접 행렬 값을 변경한다. 변경한 행렬 값마다 4MP, 8MP, 12MP의 고해상도 이미지들의 처리할 수 있는 학습 모델들을 구현한다. 성능평가 결과, 제안하는 알고리즘의 학습 모델의 생성 시간은 12MP 기준 약 36.26%의 감소하고, 학습 모델의 객체 분류 정확도와 손실률은 기존 모델 대비 약 1% 이내로 오차 범위 안에 포함되어 크게 문제가 되지 않는다. 향후 본 연구에서 사용된 학습 데이터보다 다양한 이미지 종류 및 실제 사진으로 학습 모델을 구현한 실질적인 검증이 필요하다.

• 문화기술의 융합
• /
• 제10권1호
• /
• pp.471-476
• /
• 2024

다양한 스마트 기기 및 컴퓨팅 디바이스의 보급에 따라 빅데이터 생성이 광범위하게 일어나고 있다. 기계학습은 데이터의 패턴을 학습하여 추론을 수행하는 알고리즘이다. 다양한 기계학습 알고리즘 중에서 주목을 받는 알고리즘은 신경망 기반의 딥러닝 학습이다. 딥러닝은 다양한 응용이 발표되면서 빠른 성능 향상을 달성하고 있다. 최근 딥러닝 알고리즘 중에서 그래프 구조를 활용하여 데이터를 분석하려는 시도가 증가하고 있다. 본 연구에서는 그래프 구조를 활용하여 딥러닝 네트워크에 전달하기 위한 그래프 생성 방법을 제시한다. 본 논문은 그래프 생성 과정에서 노드의 속성과 간선의 가중치를 일반화하고 행렬화 과정을 제시하여 딥러닝 입력에 필요한 구조로 전환하는 방법을 제시한다. 그래프 생성 과정에서 속성과 가중치 정보를 보전할 수 있는 선형변환 매트릭스 적용 방법을 제시한다. 마지막으로 일반 그래프의 딥러닝 입력 구조를 제시하고 성능 분석을 위한 접근법을 제시한다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.784-791
• /
• 2022

Tack coat is a thin layer of asphalt between the existing pavement and asphalt overlay. During construction, insufficient tack coat layering can later cause surface defects such as slippage, shoving, and rutting. This paper proposed a method for tack coat inspection improvement using an unmanned aerial vehicle (UAV) and deep learning neural network for automatic non-uniform assessment of the applied tack coat area. In this method, the drone-captured images are exploited for assessment using a combination of Mask R-CNN and Grey Level Co-occurrence Matrix (GLCM). Mask R-CNN is utilized to detect the tack coat region and segment the region of interest from the surroundings. GLCM is used to analyze the texture of the segmented region and measure the uniformity and non-uniformity of the tack coat on the existing pavements. The results of the field experiment showed both the intersection over union of Mask R-CNN and the non-uniformity measured by GLCM were promising with respect to their accuracy. The proposed method is automatic and cost-efficient, which would be of value to state Departments of Transportation for better management of their work in pavement construction and rehabilitation.

• 전기학회논문지
• /
• 제57권1호
• /
• pp.117-120
• /
• 2008

This paper investigates the convergence condition of ADILC(iterative learning control with advanced output data) for nonminimum phase systems. ADILC has simple learning structure including both minimum phase and nonminimum phase systems. However, for nonminimum phase systems, the overall time horizon must be considered in input update law. This makes the dimension of convergence condition matrix large. In this paper, a new sufficient condition is proposed to satisfy the convergence condition. Also, it has been shown that this sufficient condition can be satisfied although it is not full impulse response.