• Smart Structures and Systems
• /
• 제28권6호
• /
• pp.779-789
• /
• 2021

Cracks in railway sleeper are an inevitable condition and has a significant influence on the safety of railway system. Although the technology of railway sleeper condition monitoring using machine learning (ML) models has been widely applied, the crack recognition accuracy is still in need of improvement. In this paper, a two-stage method using edge detection and convolutional neural network (CNN) is proposed to reduce the burden of computing for detecting cracks in railway sleepers with high accuracy. In the first stage, the edge detection is carried out by using the 3×3 neighborhood range algorithm to find out the possible crack areas, and a series of mathematical morphology operations are further used to eliminate the influence of noise targets to the edge detection results. In the second stage, a CNN model is employed to classify the results of edge detection. Through the analysis of abundant images of sleepers with cracks, it is proved that the cracks detected by the neighborhood range algorithm are superior to those detected by Sobel and Canny algorithms, which can be classified by proposed CNN model with high accuracy.

• 전자공학회논문지S
• /
• 제34S권2호
• /
• pp.52-62
• /
• 1997

To reconstruct the complete 3-D shape of an object, seveal range images form different viewpoints should be merged into a single model. The process of extraction of the transformation parameters between multiple range views is calle dregistration. In this paper, we propose a new algorithm to find the transformation parameters between multiple range views. Th eproposed algorithm consists of two step: initial estimation and iteratively update the transformation. To guess the initial transformation, we modify the principal axes by considering the projection effect, due to the difference fo viewpoints. Then, the following process is iterated: in order to extract the exact transformation parameters between the range views: For every point of the common region, find the nearest point among the neighborhood of the current corresponding point whose correspondency is defined by the reverse calibration of the range finder. Then, update the transformation to satisfy the new correspondencies. In order to evaluate the performance the proposed registration algorithm, some experiments are performed on real range data, acquired by space encoding range finder. The experimental results show that the proposed initial estimation accelerate the following iterative registration step.

• Journal of International Society for Simulation Surgery
• /
• 제4권1호
• /
• pp.21-23
• /
• 2017

Purpose In this paper, we proposed alternate neighborhood system and reverse spread-direction approach for accurate and fast cellular automata-based image segmentation method. Materials and Methods On the basis of a simple but effective interactive image segmentation technique based on a cellular automaton, we propose an efficient algorithm by using Moore and designed neighborhood system alternately and reversing the direction of the reference pixels for spreading out to the surrounding pixels. Results In our experiments, the GrabCut database were used for evaluation. According to our experimental results, the proposed method allows cellular automata-based image segmentation method to faster while maintaining the segmentation quality. Conclusion Our results proved that proposed method improved accuracy and reduced computation time, and also could be applied to a large range of applications.

• 방송공학회논문지
• /
• 제21권2호
• /
• pp.180-191
• /
• 2016

일반 가시광선 영상의 확대를 위한 알고리즘을 선명도가 떨어지는 적외선 영상에 적용시켰을 때 개선효과가 미흡한 문제점을 해결하기 위해 본 논문은 적외선 영상을 위한 영상 확대 알고리즘을 제안한다. 제안 알고리즘은 적외선 영상이 가시광선 영상에 비해 디테일이 적다는 특성과 에지 영역에 대해 사람이 시각적으로 민감하다는 특성을 고려하여 ADRC(Adaptive Dynamic Range Coding)와 같은 단순한 분류기법을 적용시켰으며, 에지 영역에 대해서만 알고리즘을 적용시켜 연산량을 절약한다. 또한 확대 영상의 선명도 개선을 위해 합성과정에서 전처리나 후처리를 추가시키는 방법 대신 학습과정에서 전처리를 추가하여 합성과정에서 연산량 증가 없이 확대 영상의 선명도를 개선하였다. 제안 알고리즘은 크게 학습과정과 합성과정으로 나뉜다. 이와 같은 방법으로 영상 확대 알고리즘을 수행하였을 때 최신의 영상확대 기법인 A+ (Anchored neighborhood regression)기법 대비 JNB(Just Noticeable Blur)수치가 평균 0.0201만큼 높은 결과를 확인할 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.151.5-151
• /
• 2001

Sliding mode control is investigated for a discrete-time system with uncertainties. The narrowest neighborhood of the sliding surface is shown in which the state can remain. The range is determined by the upper bound of the absolute value of the uncertainty and the equation of the sliding surface. A sliding mode control algorithm is proposed to keep the state there without requiring an enormous input. Under the presence of the system parameter variations, the origin is not always stable although the sliding surface represents the stable dynamics and the state is kept in this neighborhood. The condition for the origin to be stable is investigated. Furthermore, the problems occurring when a continuous-time sliding mode control being ...

• 한국정보시스템학회지:정보시스템연구
• /
• 제25권1호
• /
• pp.159-182
• /
• 2016

Purpose This paper aims to develop a novel tabu search algorithm for solving the sequencing problems with precedence constraints. Due to constraints, the traditional meta heuristic methods can generate infeasible solutions during search procedure, which must be carefully dealt with. On the contrary, the candidate order based tabu search (COTS) is based on a novel neighborhood structure that guarantees the feasibility of solutions, and can dealt with a wide range of sequencing problems in flexible manner. Design/methodology/approach Candidate order scheme is a strategy for constructing a feasible sequence by iteratively appending an item at a time, and it has been successfully applied to genetic algorithm. The primary benefit of the candidate order scheme is that it can effectively deal with the additional constraints of sequencing problems and always generates the feasible solutions. In this paper, the candidate order scheme is used to design the neighborhood structure, tabu list and diversification operation of tabu search. Findings The COTS has been applied to the single machine job sequencing problems, and we can see that COTS can find the good solutions whether additional constraints exist or not. Especially, the experiment results reveal that the COTS is a promising approach for solving the sequencing problems with precedence constraints. In addition, the operations of COTS are intuitive and easy to understand, and it is expected that this paper will provide useful insights into the sequencing problems to the practitioners.

• Journal of Advanced Marine Engineering and Technology
• /
• 제40권2호
• /
• pp.138-145
• /
• 2016

This paper proposes an improved tabu search method for subset selection in multiple linear regression models. Variable selection is a vital combinatorial optimization problem in multivariate statistics. The selection of the optimal subset of variables is necessary in order to reliably construct a multiple linear regression model. Its applications widely range from machine learning, timeseries prediction, and multi-class classification to noise detection. Since this problem has NP-complete nature, it becomes more difficult to find the optimal solution as the number of variables increases. Two typical metaheuristic methods have been developed to tackle the problem: the tabu search algorithm and hybrid genetic and simulated annealing algorithm. However, these two methods have shortcomings. The tabu search method requires a large amount of computing time, and the hybrid algorithm produces a less accurate solution. To overcome the shortcomings of these methods, we propose an improved tabu search algorithm to reduce moves of the neighborhood and to adopt an effective move search strategy. To evaluate the performance of the proposed method, comparative studies are performed on small literature data sets and on large simulation data sets. Computational results show that the proposed method outperforms two metaheuristic methods in terms of the computing time and solution quality.

• 제어로봇시스템학회논문지
• /
• 제17권12호
• /
• pp.1234-1239
• /
• 2011

The scan matching is widely used in localization and mapping of mobile robots. This paper presents a probabilistic scan matching method. To improve the performance of the scan matching, a direction of data point is incorporated into the scan matching. The direction of data point is calculated using the line fitted by the neighborhood data. Owing to the incorporation, the performance of the matching was improved. The number of iterations in the scan matching decreased, and the tolerance against a high rotation between scans increased. Based on real data of a laser range finder, experiments verified the performance of the proposed direction augmented probabilistic scan matching algorithm.

• 한국정보통신학회논문지
• /
• 제21권5호
• /
• pp.921-928
• /
• 2017

유선 네트워크와 달리 무선 네트워크 환경에서의 브로드캐스팅은 단일 전송으로 다수의 노드로 데이터를 한 번에 송신할 수 있다. 무선 네트워크에서 노드의 전방향 브로드캐스팅은 인접한 모든 노드에게 동시에 도달한다. 본 논문에서는 무선 네트워크에서 브로드캐스팅 시 전체 송신 전력을 최소화하는 최소 전력 브로드캐스팅 문제를 해결하기 위한 탐욕 알고리즘을 제안한다. 제안된 알고리즘은 각 노드의 최대 전송 범위 내에서 메시지를 전송할 수 있는 노드의 집합인 이웃 노드 리스트를 이용하여 데이터를 수신한 송신 노드 중 이웃 노드를 가장 많이 가지고 있는 노드가 우선적으로 이웃 노드로 데이터를 전송한다. 제안된 알고리즘은 컴퓨터 시뮬레이션을 이용하여 성능평가가 이루어졌으며, 네트워크상의 모든 노드로 브로드캐스팅 시 소요되는 송신 전력과 브로드캐스팅 횟수의 관점에서 기존의 알고리즘과 비교하였다. 실험 결과에서 제안된 알고리즘은 기존의 알고리즘보다 성능이 우수함을 보인다.

• 지적과 국토정보
• /
• 제48권2호
• /
• pp.185-195
• /
• 2018

서울시에서 시민들이 사용하는 미세먼지 앱은 위치기반으로 자신의 위치에서 가장 가까운 측정소의 미세먼지 농도를 제공받는다. 현재 환경부에서 고려하는 미세먼지 측정망 선정 방법은 측정소의 분포 및 인구밀도를 고려한 방식과 지도상의 표현방식이 주 결정방법이나 인위적인 변수 및 다른 환경요인을 고려하지 않는다. 본 연구에서는 미세먼지 측정소와 행정동의 대표성을 보여주는 행정동 중심점을 활용하여 측정소와 동중심의 거리에 대해 분석하였으며, 측정값을 제공하는 측정소의 개수를 확인하였다. 또한 보로노이 알고리즘과 헥사곤 격자를 활용하여 각 측정소의 제공범위를 면적으로 나타내며 현 측정소의 공간적인 위치의 문제점을 지적하였다. 공간분석을 위한 환경변수는 단독주택, 공동주택, 제1종 근린생활권, 제2종 근린생활권, 쓰레기처리장, 위험물처리시설, 공장이며 분석결과로 만들어진 신규 측정소 위치는 기존의 환경부에서 제공하는 선정기준이 아닌 추가적인 변수를 고려한 선정기준을 제시하였다.