• 한국정보처리학회논문지
• /
• 제6권6호
• /
• pp.1686-1692
• /
• 1999

본 논문은 특징 영역 기반의 자동차 번호판 인식 시스템(VPRS : Vehicle Plate Recognition System)에 대한 연구이다. 자동차영상에서 번호판을 추출하기 위해 명암도 변화를 이용하였고, 추출된 번호판에서 문자를 포함하는 특징 영역을 추출하기 위해 히스토그램 기법과 번호판 문자의 상대적인 위치 정보를 이용하였다. 이렇게 추출된 특징 영역을 ART2 신경회로망의 입력 벡터로 사용하여 인식하였다. 제안한 방법은 기존의 문자 인식을 위한 전처리 과정을 간소화 할 수 있었고, 이치화 과정에서의 원 화상의 왜곡과 노이즈 발생 문제를 해결할 수 있었으며, 또한 기존의 이치화 방법으로 문자 추출이 어려운 번호판에 대해서도 효과적으로 문자영역을 추출하여 인식할 수 있었다.

• 한국생산제조학회지
• /
• 제21권1호
• /
• pp.33-39
• /
• 2012

The tool wear and failure in automatic production system directly influences the quality and productivity of a product, thus it is essential to monitor the tool state in real time. For such purpose, an ART2-based remote monitoring system has been developed to predict the appropriate tool change time in accordance with the tool wear, and this study aims to experimently find the relationship between the tool wear and the monitoring signals in cutting processes. Also, the roughness of workpiece according to the wool wear is examined. Here, the tool wear is indirectly monitored by signals from a vibration senor attached to a machining center. and the wear dimension is measured by a microscope at the start, midways and the end of a cutting process. A series of experiments are carried out with various feedrates and spindle speeds, and the results show that the sensor signal properly represents the degree of wear of a tool being used, and the roughnesses measured has direct relation with the tool wear dimension. Thus, it is concluded that the monitoring signals from the vibration sensor can be used as a useful measure for the tool wear monitoring.

• 한국컴퓨터그래픽스학회논문지
• /
• 제29권4호
• /
• pp.1-6
• /
• 2023

메타버스 환경에서의 배경음악은 사용자의 몰입감을 증진시키기 위해 사용된다. 하지만 현재 대부분의 메타버스 환경에서는 사전에 매칭시킨 음원을 반복 재생하며, 이는 빠르게 변화하는 사용자의 상호작용 맥락에 어울리지 못해 사용자의 몰입감을 저해시키는 경향이 있다. 본 논문에서는 보다 몰입감 있는 메타버스 대화 경험을 구현하기 위해 1) 한국어 멀티모달 감정 데이터셋인 KEMDy20을 이용하여 발화로부터 감정을 추출하는 회귀 신경망을 구현하고 2) 음원에 arousal-valence 레벨이 태깅되어 있는 DEAM 데이터셋을 이용하여 발화 감정에 대응되는 음원을 선택하여 재생한 후 3) 아바타를 이용한 실시간 대화가 가능한 가상공간과 결합하여 몰입형 메타버스 환경에서 발화의 감정에 어울리는 배경음악을 실시간으로 재생하는 시스템을 구현하였다.

• Steel and Composite Structures
• /
• 제46권2호
• /
• pp.153-173
• /
• 2023

Rectangular concrete-filled steel tubular (RCFST) column, a type of concrete-filled steel tubular (CFST), is widely used in compression members of structures because of its advantages. This paper proposes a robust machine learning-based framework for predicting the ultimate compressive strength of RCFST columns under both concentric and eccentric loading. The gradient boosting neural network (GBNN), an efficient and up-to-date ML algorithm, is utilized for developing a predictive model in the proposed framework. A total of 890 experimental data of RCFST columns, which is categorized into two datasets of concentric and eccentric compression, is carefully collected to serve as training and testing purposes. The accuracy of the proposed model is demonstrated by comparing its performance with seven state-of-the-art machine learning methods including decision tree (DT), random forest (RF), support vector machines (SVM), deep learning (DL), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and categorical gradient boosting (CatBoost). Four available design codes, including the European (EC4), American concrete institute (ACI), American institute of steel construction (AISC), and Australian/New Zealand (AS/NZS) are refereed in another comparison. The results demonstrate that the proposed GBNN method is a robust and powerful approach to obtain the ultimate strength of RCFST columns.

• 전자공학회논문지S
• /
• 제35S권1호
• /
• pp.68-79
• /
• 1998

In this paper, we propose a model-based FDI(fault detetion and isolation) algorithm to detect and isolate fault in a linear system. The proposed algorithm is gased on an HFC(hydrid fault classifier) which consists of an FCART2(fault classifier by ART2 neural network) and an FCFM(fault classifier by fault models) which operate in parallel to isolate faults. The proposed algorithm is functionally composed of three main parts-parameter estimation, fault detection, and isolation. When a change in the system occurs, the estimated parameters go through a transition zone in which errors between the system output and the stimated output and the estimated output cross a predetermined thrseshold, and in this zone the estimated parameters are tranferred to the FCART2 for fault isolation. On the other hand, once a fault in the system is detected, the FCFM statistically isolates the fault by using the error between ach fault model out put and the system output. From the computer simulation resutls, it is verified that the proposed model-based FDI algorithm can be performed successfully to detect and isolate faults in a position control system of a DC motor.

• 지식경영연구
• /
• 제22권4호
• /
• pp.27-40
• /
• 2021

Click-Through Rate(CTR) 예측은 추천시스템에서 후보 항목의 순위를 결정하고 높은 순위의 항목들을 추천하여 고객의 정보 과부하를 줄임과 동시에 판매 촉진을 통한 수익 극대화를 달성할 수 있는 핵심 기능이다. 자연어 처리와 이미지 분류 분야는 심층신경망(deep neural network)의 활용을 통한 괄목한 성장을 하고 있다. 최근 이 분야의 주류를 이루던 모델과 차별화된 어텐션(attention) 메커니즘 기반의 트랜스포머(transformer) 모델이 제안되어 state-of-the-art를 달성하였다. 본 연구에서는 CTR 예측을 위한 트랜스포머 기반 모델의 성능 향상 방안을 제시한다. 자연어와 이미지 데이터와는 다른 이산적(discrete)이며 범주적(categorical)인 CTR 데이터 특성이 모델 성능에 미치는 영향력을 분석하기 위해 임베딩의 일반화(regularization)와 트랜스포머의 정규화(normalization)에 관한 실험을 수행한다. 실험 결과에 따르면, CTR 데이터 입력 처리를 위한 임베딩 과정에서 L2 일반화의 적용과 트랜스포머 모델의 기본 정규화 방법인 레이어 정규화 대신 배치 정규화를 적용할 때 예측 성능이 크게 향상됨을 확인하였다.

• 경영과학
• /
• 제16권1호
• /
• pp.157-171
• /
• 1999

In a increasingly competitive marketplace, the manufacturing companies have no choice but looking for ways to improve productivity to sustain their competitiveness and survive in the industry. Recently cellular manufacturing has been under discussion as an option to be easily implemented without burdensome capital investment. The objective of cellular manufacturing is to realize many aspects of efficiencies associated with mass production in the less repetitive job-shop production systems. The very first step for cellular manufacturing is to group the sets of parts having similar processing requirements into part families, and the equipment needed to process a particular part family into machine cells. The underlying problem to determine the part and machine assignments to each manufacturing cell is called the cell formation. The purpose of this study is to develop a clustering algorithm based on the neural network approach which overcomes the drawbacks of ART1 algorithm for cell formation problems. In this paper, a generalized learning vector quantization(GLVQ) algorithm was devised in order to transform a 0/1 part-machine assignment matrix into the matrix with diagonal blocks in such a way to increase clustering performance. Furthermore, an assignment problem model and a rearrangement procedure has been embedded to increase efficiency. The performance of the proposed algorithm has been evaluated using data sets adopted by prior studies on cell formation. The proposed algorithm dominates almost all the cell formation reported so far, based on the grouping index($\alpha$ = 0.2). Among 27 cell formation problems investigated, the result by the proposed algorithm was superior in 11, equal 15, and inferior only in 1.

• Imaging Science in Dentistry
• /
• 제50권2호
• /
• pp.169-174
• /
• 2020

Purpose: Periodontal disease causes tooth loss and is associated with cardiovascular diseases, diabetes, and rheumatoid arthritis. The present study proposes using a deep learning-based object detection method to identify periodontally compromised teeth on digital panoramic radiographs. A faster regional convolutional neural network (faster R-CNN) which is a state-of-the-art deep detection network, was adapted from the natural image domain using a small annotated clinical data- set. Materials and Methods: In total, 100 digital panoramic radiographs of periodontally compromised patients were retrospectively collected from our hospital's information system and augmented. The periodontally compromised teeth found in each image were annotated by experts in periodontology to obtain the ground truth. The Keras library, which is written in Python, was used to train and test the model on a single NVidia 1080Ti GPU. The faster R-CNN model used a pretrained ResNet architecture. Results: The average precision rate of 0.81 demonstrated that there was a significant region of overlap between the predicted regions and the ground truth. The average recall rate of 0.80 showed that the periodontally compromised teeth regions generated by the detection method excluded healthiest teeth areas. In addition, the model achieved a sensitivity of 0.84, a specificity of 0.88 and an F-measure of 0.81. Conclusion: The faster R-CNN trained on a limited amount of labeled imaging data performed satisfactorily in detecting periodontally compromised teeth. The application of a faster R-CNN to assist in the detection of periodontally compromised teeth may reduce diagnostic effort by saving assessment time and allowing automated screening documentation.

• 스마트미디어저널
• /
• 제9권2호
• /
• pp.22-32
• /
• 2020

The hippocampal volume atrophy is known to be linked with neuro-degenerative disorders and it is also one of the most important early biomarkers for Alzheimer's disease detection. The measurements of hippocampal pure volumes from Magnetic Resonance Imaging (MRI) is a crucial task and state-of-the-art methods require a large amount of time. In addition, the structural brain development is investigated using MRI data, where brain morphometry (e.g. cortical thickness, volume, surface area etc.) study is one of the significant parts of the analysis. In this study, we have proposed a patch-based ensemble model of 3-D convolutional neural network (CNN) to measure the hippocampal pure volume from MRI data. The 3-D patches were extracted from the volumetric MRI scans to train the proposed 3-D CNN models. The trained models are used to construct the ensemble 3-D CNN model and the aggregated model predicts the pure volume in one-step in the test phase. Our approach takes only 5 seconds to estimate the volumes from an MRI scan. The average errors for the proposed ensemble 3-D CNN model are 11.7±8.8 (error%±STD) and 12.5±12.8 (error%±STD) for the left and right hippocampi of 65 test MRI scans, respectively. The quantitative study on the predicted volumes over the ground truth volumes shows that the proposed approach can be used as a proxy.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제9권6호
• /
• pp.757-772
• /
• 2019

본 논문에서는 아시아 38개 컨테이너항만 들을 대상으로 10년(2007년-2016년)동안의 4개의 투입요소(선석길이, 수심, 총면적, 크레인 수)와 1개의 산출요소(컨테이너화물 처리량)를 이용하여 인공신경망모형(다층퍼셉트론, 방사형기저함수)으로 클러스터링에 영향을 미친 요소들을 파악하였으며, 1단계 교차효율성 메트릭스를 이용한 군집 수를 사회연결망모형과 타부서치모형에 적용하여 클러스터링을 파악하고 효율성을 측정하였다. 또한 2단계효율성 메트릭스모형을 이용한 클러스터링을 파악하고 효율성을 측정하여 1단계 교차효율성 메트릭스에 의한 측정결과와 비교하였다. 주요한 실증분석 결과는 다음과 같다. 첫째, 인공신경망모형에 의해서 측정해 보았을 때, 군집에 영향을 많이 미친 요소별로 제시해 보면 컨테이너화물 처리량, 선석길이와 수심, 총면적, 크레인 수의 순서로 나타났다. 둘째, 사회연결망분석에서는 2단계 교차효율성(Type IV)메트릭스에 의한 군집은 benevolent 와 aggressive 모형에서 매년 동일한 결과를 보였다. 셋째, 클러스터링 후에 1단계 교차효율성 모형에 비해서 사회연결망 모형 분석과 타부서치 모형 분석에서 국내항만들의 효율성이 거의(사회연결망 모형에서 인천항의 경우 제외) 악화되는 것으로 나타났다. 다섯째, 일반적인 투입지향, 규모수확불변하의 CCR모형의 효율성 측정결과와 비교했을 때는 클러스터링이 모든 항만들에 대해서 약 37%이상의 효율성을 증대시켰다. 여섯째, 사회연결망모형과 타부서치모형에 의해서 클러스터링 되는 항만들은 부산항(고베, 오사카, 포트클랑, 탄중 펠파스, 마닐라항), 인천항(사히드 라자히, 광양), 광양항(아카바, 포트 슐탄 카바스, 담만, 크호르 파칸, 인천)으로 나타났다. 한국항만당국은 본 연구에서 이용된 방법을 도입하여 항만개선방안을 마련해야만 한다.