• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2509-2528
• /
• 2019

There are various styles of license plates for different countries and use cases that require style-specific methods. In this paper, we propose and illustrate a multi-style license plate recognition system. The proposed system performs a series of processes for license plate candidates detection, structure classification, character segmentation and character recognition, respectively. Specifically, we introduce a license plate structure classification process to identify its style that precedes character segmentation and recognition processes. We use a K-Nearest Neighbors algorithm with pre-training steps to recognize numbers and characters on multi-style license plates. To show feasibility of our multi-style license plate recognition system, we evaluate our system for multi-style license plates covering single line, double line, different backgrounds and character colors on Korean and the U.S. license plates. For the evaluation of Korean license plate recognition, we used a 50 minutes long input video that contains 138 vehicles of 6 different license plate styles, where each frame of the video is processed through a series of license plate recognition processes. From two experiments results, we show that various LP styles can be recognized under 50 ms processing time and with over 99% accuracy, and can be extended through additional learning and training steps.

• 한국멀티미디어학회논문지
• /
• 제23권9호
• /
• pp.1129-1138
• /
• 2020

The performance of convolutional deep learning networks is generally determined according to parameters of target dataset, structure of network, convolution kernel, activation function, and optimization algorithm. In this paper, a genetic algorithm is used to select the appropriate deep learning model and parameters for Alzheimer's classification and to compare the learning results with preliminary experiment. We compare and analyze the Alzheimer's disease classification performance of VGG-16, GoogLeNet, and ResNet to select an effective network for detecting AD and MCI. The simulation results show that the network structure is ResNet, the activation function is ReLU, the optimization algorithm is Adam, and the convolution kernel has a 3-dilated convolution filter for the accuracy of dementia medical images.

• Journal of Ship and Ocean Technology
• /
• 제8권2호
• /
• pp.41-60
• /
• 2004

Ship design process requires lots of complicated analyses for determining a large number of design variables. Due to its complexity, the process is divided into several tractable designs or analysis problems. The interdependent relationship requires repetitive works. This paper employs collaborative optimization (CO), one of the multidisciplinary design optimization (MDO) techniques, for treating such complex relationship. CO guarantees disciplinary autonomy while maintaining interdisciplinary compatibility due to its bi-level optimization structure. However, the considerably increased computational time and the slow convergence have been reported as its drawbacks. This paper proposes the use of an approximation model in place of the disciplinary optimization in the system-level optimization. Neural network classification is employed as a classifier to determine whether a design point is feasible or not. Kriging is also combined with the classification to make up for the weakness that the classification cannot estimate the degree of infeasibility. For the purpose of enhancing the accuracy of a predicted optimum and reducing the required number of disciplinary optimizations, an approximation management framework is also employed in the system-level optimization.

• 로봇학회논문지
• /
• 제11권3호
• /
• pp.115-126
• /
• 2016

This paper suggests the method of the spherical signature description of 3D point clouds taken from the laser range scanner on the ground vehicle. Based on the spherical signature description of each point, the extractor of significant environmental features is learned by the Deep Belief Nets for the urban structure classification. Arbitrary point among the 3D point cloud can represents its signature in its sky surface by using several neighborhood points. The unit spherical surface centered on that point can be considered to accumulate the evidence of each angular tessellation. According to a kind of point area such as wall, ground, tree, car, and so on, the results of spherical signature description look so different each other. These data can be applied into the Deep Belief Nets, which is one of the Deep Neural Networks, for learning the environmental feature extractor. With this learned feature extractor, 3D points can be classified due to its urban structures well. Experimental results prove that the proposed method based on the spherical signature description and the Deep Belief Nets is suitable for the mobile robots in terms of the classification accuracy.

• 한국측량학회지
• /
• 제25권6_1호
• /
• pp.499-505
• /
• 2007

A method of improving the correctness and confidence in land use classification as well as urban spatial structure analysis of local governments using GIS and satellite imagery is suggested. This study also compares and analyzes LSAS (Land Suitability Assessment System) results using two approaches-LSAS with priority classification, and LSAS using standard estimation factors without priority classification. The conclusions that can be drawn from this study are as follows. First, a method of maintaining up-to-date local government data by updating the LSAS database using high-resolution satellite imagery is suggested. Second, to formulate a scientific and reasonable land use plan from the viewpoint of territory development and urban management, a method of simultaneously processing the two described approaches is suggested. Finally, LSAS was constructed by using varieties of land information such as the cadastral map, the digital topographic map, varieties of thematic maps, and official land price data, and expects to utilize urban management plan establishment widely and effectively through regular data updating and problem resolution of data accuracy.

• 한국음향학회지
• /
• 제40권2호
• /
• pp.130-138
• /
• 2021

본 논문에서는 지진 이벤트 분류를 위한 다양한 정규화 기법 분석 및 효과적인 합성곱 신경망(Convolutional Neural Network, CNN)기반의 네트워크 구조를 제안하였다. 정규화 기법은 신경망의 학습 속도를 개선할 뿐만 아니라 잡음에 강인한 모습을 보여 준다. 본 논문에서는 지진 이벤트 분류를 위한 딥러닝 모델에서 입력 정규화 및 은닉 레이어 정규화가 모델에 미치는 영향을 분석하였다. 또한, 적용 은닉 레이어의 구조에 따른 다양한 실험을 통해 효과적인 모델을 도출하였다. 다양한 모의실험 결과 입력 데이터 정규화 및 제1 은닉 레이어에 가중치 정규화를 적용한 모델이 가장 안정적인 성능 향상을 보여 주었다.

• 인터넷정보학회논문지
• /
• 제4권5호
• /
• pp.69-76
• /
• 2003

본 논문에서는 패턴 분류를 위한 새로운 학습 알고리즘을 소개한다. 이 알고리즘은 학습 데이터 집합에 포함된 오류 때문에 네트워크 구조가 너무 복잡하게 되는 점증적 학습 알고리즘의 문제를 해결하기 위해 고안되었다. 이 문제를 위한 접근 방법으로 미리 정의된 판단기준을 가지고 학습 과정을 중단하는 전지 방법을 사용한다. 이 과정에서 적절한 처리과정에 의해 3층 전향구조를 가지는 반복적 모델이 점증적 모델로부터 유도된다 여기서 이 네트워크 구조가 위층과 아래층 사이에 완전연결이 아니라는 점을 주목한다. 전지 방법의 효율성을 확인하기 위해 이 네트워크는 EBP로 다시 학습한다. 이 결과로부터 제안된 알고리즘이 시스템 성능과 네트워크 구조를 이루는 노드의 수 면에서 효과적임을 발견할 수 있다.

• 한국조경학회지
• /
• 제25권1호
• /
• pp.82-99
• /
• 1997

The purpose of this study is to establish work classification system of landscape construction in order to offer the basis of new estimation system of public landscape construction. New estimation system is based on historical construction data. For application of this system, the standard work classification system is necessary. Because extensive cost data should be accumulated under an unified construction work classification system. In the study of new estimation system carried by KICT(Korea Institute of Construction Technology), landscaping works belong to earth work of civil engineering. It looks very unreasonable work classification, because landscape archtecture has its own specialties and professional domain. In this study, information classification systems in the construction industry and various landscaping works of housing developments are analysed. As a result. a standard work classification system of housing landscape construction is proposed in section VI-3. This standard work classification structure consists of three levels divisions (i.e large work division, middle work division, small work division) . Now in this study, housing landscape construction works are divided into four large works and twenty six middle works. According to work attributes, middle and small work division is possible to subdivide into details.

• 건축역사연구
• /
• 제25권5호
• /
• pp.51-62
• /
• 2016

Since the recent Hanok boom in Korea, Contemporary Hanok has been evolving in terms of structure, space, form, etc. To get a comprehensive understanding of the diversified Contemporary Hanok, this paper aims at its type classification by analyzing architects' designs since 2000. The criteria for the classification are two: (1) renovation [Re] or new construction [New]; and (2) degree of Contemporary Hanok's deviation from the traditional Hanok's standard - maintaining the traditional form [Main]; changing space within the traditional form [Space]; changing the traditional frame [Frame]; and juxtaposing the traditional and the modern [Combi]. From the two criteria, this paper deduced eight types of Contemporary Hanok, named respectively: Re-Main, New-Main, Re-Space, New-Space, Re-Frame, New-Frame, Re-Combi, and New-Combi, and studied their cases. It can be argued that various aspects of Contemporary Hanok and their critical meanings were well-investigated through this type classification and case-studies.

• 한국비블리아학회지
• /
• 제11권2호
• /
• pp.5-23
• /
• 2000

본 연구는 지식과 분류 사이의 연관성을 고찰하였다. 분류표는 분류 대상의 지식을 표현하는 구조로 그 안의 포함되는 내용과 다양한 관계를 표현해 주는데 대표적인 4가지 분류학적 접근방식인 계층 구조, 나무 구조, 패러다임. 패싯 분석을 새로운 지식의 창조와 발견의 측면에서 장단점을 기술하였다. 이를 바탕으로 지식과 분류 과정이 서로 영향을 주고받는 방식을 확인하고, 미래의 보다나은 새로운 분류 방식의 필요성과 그 가능성을 제시하였다.