• 대한산업공학회지
• /
• 제21권4호
• /
• pp.609-628
• /
• 1995

This paper presents a reliability model and a data-analytic procedure for a repairable unit subject to failures due to multiple non-identifiable causes. We regard a failure cause as a state and assume the life distribution for each cause to be exponential. Then we represent the dependency among the causes by a Markov switching model(MSM) and estimate the transition probabilities and failure rates by maximum likelihood(ML) method. The failure data are incomplete due to masked causes of failures. We propose a specific version of EM(expectation and maximization) algorithm for finding maximum likelihood estimator(MLE) under this situation. We also develop statistical procedures for determining the number of significant states and for testing independency between state transitions. Our model requires only the successive failure times of a unit to perform the statistical analysis. It works well even when the causes of failures are fully masked, which overcomes the major deficiency of competing risk models. It does not require the assumption of stationarity or independency which is essential in mixture models. The stationary probabilities of states can be easily calculated from the transition probabilities estimated in our model, so it covers mixture models in general. The results of simulations show the consistency of estimation and accuracy gradually increasing according to the difference of failure rates and the frequency of transitions among the states.

• 한국도로학회논문집
• /
• 제15권1호
• /
• pp.155-161
• /
• 2013

PURPOSES: This study is to develop a road traffic sign recognition and automatic positioning for road facility management. METHODS: In this study, we installed the GPS, IMU, DMI, camera, laser sensor on the van and surveyed the car position, fore-sight image, point cloud of traffic signs. To insert automatic position of traffic sign, the automatic traffic sign recognition S/W developed and it can log the traffic sign type and approximate position, this study suggests a methodology to transform the laser point-cloud to the map coordinate system with the 3D axis rotation algorithm. RESULTS: Result show that on a clear day, traffic sign recognition ratio is 92.98%, and on cloudy day recognition ratio is 80.58%. To insert exact traffic sign position. This study examined the point difference with the road surveying results. The result RMSE is 0.227m and average is 1.51m which is the GPS positioning error. Including these error we can insert the traffic sign position within 1.51m CONCLUSIONS: As a result of this study, we can automatically survey the traffic sign type, position data of the traffic sign position error and analysis the road safety, speed limit consistency, which can be used in traffic sign DB.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.912-928
• /
• 2019

Crowd behavior analysis research has revealed a central role in helping people to find safety hazards or crime optimistic forecast. Thus, it is significant in the future video surveillance systems. Recently, the growing demand for safety monitoring has changed the awareness of video surveillance studies from analysis of individuals behavior to group behavior. Group detection is the process before crowd behavior analysis, which separates scene of individuals in a crowd into respective groups by understanding their complex relations. Most existing studies on group detection are scene-specific. Crowds with various densities, structures, and occlusion of each other are the challenges for group detection in diverse crowded scenes. Therefore, we propose a group detection approach called Collective Interaction Filtering to discover people motion interaction from trajectories. This approach is able to deduce people interaction with the Expectation-Maximization algorithm. The Collective Interaction Filtering approach accurately identifies groups by clustering trajectories in crowds with various densities, structures and occlusion of each other. It also tackles grouping consistency between frames. Experiments on the CUHK Crowd Dataset demonstrate that approach used in this study achieves better than previous methods which leads to latest results.

• 한국군사과학기술학회지
• /
• 제24권2호
• /
• pp.245-254
• /
• 2021

The intelligent control algorithm based on the real-time biological monitoring system has been emphasized to enhance the survivability of the combat warrior in the future combat fields. In this study, AHP(Analytic Hierarchy Process) method was deployed to categorize the factors related to the improvement of survivability, then to determine the relative importances between them. As the details of the research process, the historical survivability determinants were firstly categorized, which was nextly judged their relative importance by the experts in the actual fileds through the survey of AHP. In this process, the consistency of the survey was investigated to filter out the error. As a result, the global priority of factors can be acquired to establish the optimized operational concepts in the intelligent warrior platform.

• 대기
• /
• 제30권4호
• /
• pp.319-333
• /
• 2020

Aircraft observations constitute one of the major sources of temperature observations which provide three-dimensional information. But it is well known that the aircraft temperature data have warm bias against sonde observation data, and therefore, the correction of aircraft temperature bias is important to improve the model performance. In this study, the algorithm of the bias correction modified from operational KMA (Korea Meteorological Administration) global model is adopted in the preprocessing of aircraft observations, and the effect of the bias correction of aircraft temperature is investigated by conducting the two experiments. The assimilation with the bias correction showed better consistency in the analysis-forecast cycle in terms of the differences between observations (radiosonde and GPSRO (Global Positioning System Radio Occultation)) and 6h forecast. This resulted in an improved forecasting skill level of the mid-level temperature and geopotential height in terms of the root-mean-square error. It was noted that the benefits of the correction of aircraft temperature bias was the upper-level temperature in the midlatitudes, and this affected various parameters (winds, geopotential height) via the model dynamics.

• Steel and Composite Structures
• /
• 제44권1호
• /
• pp.119-139
• /
• 2022

This paper aims to use the artificial intelligence approach to develop a new model for predicting the ultimate axial strength of the circular concrete-filled steel tubular (CFST) stub columns. For this, the results of 314 experimentally tested circular CFST stub columns were employed in the generation of the design model. Since the influence of the column diameter, steel tube thickness, concrete compressive strength, steel tube yield strength, and column length on the ultimate axial strengths of columns were investigated in these experimental studies, here, in the development of the design model, these variables were taken into account as input parameters. The model was developed using the backpropagation algorithm named Bayesian Regularization. The accuracy, reliability, and consistency of the developed model were evaluated statistically, and also the design formulae given in the codes (EC4, ACI, AS, AIJ, and AISC) and the previous empirical formulations proposed by other researchers were used for the validation and comparison purposes. Based on this evaluation, it can be expressed that the developed design model has a strong and reliable prediction performance with a considerably high coefficient of determination (R-squared) value of 0.9994 and a low average percent error of 4.61. Besides, the sensitivity of the developed model was also monitored in terms of dimensional properties of columns and mechanical characteristics of materials. As a consequence, it can be stated that for the design of the ultimate axial capacity of the circular CFST stub columns, a novel artificial intelligence-based design model with a good and robust prediction performance was proposed herein.

• International Journal of Advanced Culture Technology
• /
• 제11권3호
• /
• pp.302-309
• /
• 2023

This study aimed to develop a VR-based digital therapeutic intervention for the diagnosis and treatment of ADHD. The research combined medical data with virtual reality technology to develop an algorithm for ADHD diagnostic scales and implemented a VR-based digital therapeutic platform using a head-mounted display (HMD). This platform can be used for the diagnosis and treatment of ADHD in children and adolescents. Additionally, we four VR games were developed, including archery timing, Antarctic exploration, grocery shopping, and rhythm-based drumming(RBD), incorporating various psychiatric treatment techniques based on cognitive-behavioral therapy(CBT). To evaluate the usability of this digital therapeutic intervention, a group of experts specialized in counseling psychology participated in the study. The evaluations received highly positive feedback regarding the ability to access the system menu while wearing the HMD, the consistency of terminology used in menus and icons, the usage of actual size for 3D graphic elements, and the support for shortcut key functionality. The assessments also indicated that the games could improve attention, working memory, and impulse control, suggesting potential therapeutic effects for ADHD. This intervention could provide a daily treatment method for families experiencing financial constraints that limit hospital-based therapies, thereby reducing the burden.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2020년도 추계학술대회
• /
• pp.113-117
• /
• 2020

Images were taken under various weather such as rain, haze, snow often show low visibility, which can dramatically decrease accuracy of some tasks in computer vision: object detection, segmentation. Besides, previous work to enhance image usually downsample the image to receive consistency features but have not yet good upsample algorithm to recover original size. So, in this research, we jointly implement removal streak in heavy rain image and super resolution using a deep network. We put forth a 2-stage network: a multi-model network followed by a refinement network. The first stage using rain formula in the single image and two operation layers (addition, multiplication) removes rain streak and noise to get clean image in low resolution. The second stage uses refinement network to recover damaged background information as well as upsample, and receive high resolution image. Our method improves visual quality image, gains accuracy in human action recognition task in datasets. Extensive experiments show that our network outperforms the state of the art (SoTA) methods.

• 스마트미디어저널
• /
• 제9권3호
• /
• pp.31-40
• /
• 2020

현재 제조 분야 빅데이터 분석을 위하여 black-box 기반 기계 학습 알고리즘을 활용하고 있다. 해당 알고리즘은 높은 분석 정합성 가지는 장점이 있지만, 분석 결과에 대한 해석이 어렵다는 단점이 있다. 그러나 제조업에서는 분석 알고리즘은 제조 공정 원리 기반 해석을 통하여 결과의 근거 및 도출 타당성에 대한 검증이 중요하다. 이러한 기계 학습 알고리즘의 결과 설명력 한계를 극복하기 위하여 유전 프로그래밍을 활용한 제조 빅데이터 분석 방법을 제안한다. 본 알고리즘은 생물학적 진화유전 프로그래밍 알고리즘은 생물학적 진화를 모방한 진화 연산 (선택, 교배, 돌연변이) 반복하면서 최적의 해를 찾아간다. 그리고 해는 수학적 기호를 활용하여 변수 간의 관계로 나타나며, 가장 높은 설명력을 가지는 해가 최종적으로 선택된다. 이를 통하여 입력 및 출력 변수 관계 수식화를 통한 결과를 도출하므로 직관적인 제조 매카니즘에 대한 해석이 가능하며 또한 수식으로 나타낸 변수간의 관계 기반으로 기존 해석이 불가한 제조 원리 도출도 가능하다. 제안 기법은 대표적인 기계 학습 알고리즘과 성능을 비교 분석 결과 동등 또는 우수한 성능을 보였다. 향후 해당 기법을 통하여 다양한 제조 분야 활용 가능성을 검증하였다.

• 한국산학기술학회논문지
• /
• 제22권3호
• /
• pp.446-452
• /
• 2021

우리나라 생활수준의 향상과 더불어 식품소비의 양적인 요구가 충족되면서, 세분화된 식품의 기호 성향을 충족시킬 수 있는 닭고기 소비가 증가하고 있다. 2003년 3월 축산물 품질평가원에서 고시(농림부 고시 제2003-14호)한 닭 도체 품질판정세부기준은 닭 도체 부위별 이물질 부착, 피·멍의 크기 및 중량에 따라 품질 등급을 기준을 제시하였다. 그러나 현실적으로 검사관 개개인의 주관적인 평가 기준으로 적용된 고시로 수천 마리의 닭 도체 등급판정을 유지하기가 어려운 문제점을 가지고 있다. 본 논문에서는 닭 도체 품질 세부기준에 따라 닭 도체 부위 분할하기 위해 비접촉/비파괴방식인 컴퓨터 시각 기술 알고리즘을 제안한다. 제안된 알고리즘은 실시간으로 빠르게 움직이는 닭 도체를 부위 분할하기 위하여 조명 외란에 강인하도록 보정하는 과정과 닭 도체와 배경을 구분하기 위한 EM(Expectation maximization), Erosion 및 Labeling 알고리즘, 그리고 닭 도체의 기하학적 형태를 분석하여 부위별 특징점을 찾고 점들의 위치를 계산하여 부위를 분할 할 수 있는 알고리즘을 사용하였다. 총 78마리의 닭 도체 샘플에 대하여 제안한 영상처리 알고리즘을 적용한 결과 닭 도체 부위 분할 알고리즘이 효과적임을 알 수 있었다.