• 한국멀티미디어학회논문지
• /
• 제13권4호
• /
• pp.504-511
• /
• 2010

본 논문에서는 인간 뇌의 내부에 존재하는 해마를 모델링한 해마 신경망을 사용하여 도시방범용 CCTV를 위한 얼굴영역 인식 시스템을 제안한다. 이 시스템은 특징추출 부분과 학습 및 인식 부분으로 구성되어 있으며, 특징 추출 부분은 PCA(Principal Component Analysis)와 LDA(Linear Discriminant Analysis) 사용하여 구성한다. 학습부분에서는 해마의 구조의 순서에 따라 입력되는 영상 데이터들의 특징을 치아 이랑 영역에서 호감도 조정에 의해 반응 패턴을 이진화 하고, 다음으로 CA3 영역에서의 자기 연상을 통해 영상에 포함되어 있는 노이즈를 제거하게 된다. 노이즈가 제거된 데이터는 CA1 영역에서 신경망을 통해 장기기억이 이루어진다. 제안한 시스템의 성능을 평가하기 위해 형태변화와 조명변화에 따른 인식률 실험을 실시하였다. 실험 결과, 본 논문에서 제안한 특징 추출 및 학습 방법을 다른 학습 방법들과 비교하였을 때, 우수한 인식률을 가짐을 확인하였다.

• Journal of Multimedia Information System
• /
• 제7권1호
• /
• pp.41-44
• /
• 2020

In autonomous driving, object recognition based on machine learning is one of the core software technologies. In particular, the object recognition using deep learning becomes an essential element for autonomous driving software to operate. In this paper, we introduce a drivable area detection method based on Region-based CNN model to support autonomous driving. To effectively detect the drivable area, we used the BDD dataset for model training and demonstrated its effectiveness. As a result, our R-CNN model using BDD datasets showed interesting results in training and testing for detection of drivable areas.

• International Journal of Advanced Culture Technology
• /
• 제10권1호
• /
• pp.160-169
• /
• 2022

This qualitative study aimed to investigate ways to improve effective cooperative learning from students' perspective by understanding and analyzing the learning experiences of nursing students who participated in a collaborative problem-solving learning model. Data were collected through focus group interviews and reflection journals of six second-year nursing students from G-university in J-city who participated in a collaborative problem-solving learning model course. The interview data were analyzed and divided into 3 categories and 10 subcategories according to the six-step thematic analysis method proposed by Braun and Clarke. The results of analyzing the interviews were considered based on three areas: preparation before learning, the process of collaborating as a cooperative learning experience, and solutions and expectations after learning. The participants felt frustrated because collaborative problem-solving took more time for individual learning than traditional methods did and would not allow them to check the correct answers immediately. However, they gained new experiences by solving problems and engaging in discussions within their learning community. The participants' expectations included material that could help their learning, measures to prevent free-riders, and consideration of the learning process in evaluation factors. Although this study has sample limitations by targeting nursing students in only one region, it can be used to help operate collaborative problem-solving classes, as it reflects the real experiences and opinions of students.

• Structural Engineering and Mechanics
• /
• 제82권3호
• /
• pp.271-282
• /
• 2022

The active learning surrogate model based on adaptive sampling strategy is increasingly popular in reliability analysis. However, most of the existing sampling strategies adopt the trial and error method to determine the size of the Monte Carlo (MC) candidate sample pool which satisfies the requirement of variation coefficient of failure probability. It will lead to a reduction in the calculation efficiency of reliability analysis. To avoid this defect, a new method for determining the optimal size of the MC candidate sample pool is proposed, and a new structural reliability analysis method combining polynomial chaos-based Kriging model (PC-Kriging) with adaptive sampling region is also proposed (PCK-ASR). Firstly, based on the lower limit of the confidence interval, a new method for estimating the optimal size of the MC candidate sample pool is proposed. Secondly, based on the upper limit of the confidence interval, an adaptive sampling region strategy similar to the radial centralized sampling method is developed. Then, the k-means++ clustering technique and the learning function LIF are used to complete the adaptive design of experiments (DoE). Finally, the effectiveness and accuracy of the PCK-ASR method are verified by three numerical examples and one practical engineering example.

• 한국산학기술학회논문지
• /
• 제19권3호
• /
• pp.693-698
• /
• 2018

본 논문은 최근 물체탐지 분야에서 실시간 물체 탐지 알고리즘으로 주목을 받고 있는 YOLOv2(You Only Look Once) 알고리즘을 이용하여 밀집 영역에 주차되어 있는 자동차 탐지 방법을 제안한다. YOLO의 컨볼루션 네트워크는 전체 이미지에서 한 번의 평가를 통해서 직접적으로 경계박스들을 예측하고 각 클래스의 확률을 계산하고 물체 탐지 과정이 단일 네트워크이기 때문에 탐지 성능이 최적화 되며 빠르다는 장점을 가지고 있다. 기존의 슬라이딩 윈도우 접근법과 R-CNN 계열의 탐지 방법은 region proposal 방법을 사용하여 이미지 안에 가능성이 많은 경계박스를 생성하고 각 요소들을 따로 학습하기 때문에 최적화 및 실시간 적용에 어려움을 가지고 있다. 제안하는 연구는 YOLOv2 알고리즘을 적용하여 기존의 알고리즘이 가지고 있는 물체 탐지의 실시간 처리 문제점을 해결하여 실시간으로 지상에 있는 자동차를 탐지하는 방법을 제안한다. 제안하는 연구 방법의 실험을 위하여 오픈소스로 제공되는 Darknet을 사용하였으며 GTX-1080ti 4개를 탑재한 Deep learning 서버를 이용하여 실험하였다. 실험결과 YOLO를 활용한 자동차 탐지 방법은 기존의 알고리즘 보다 물체탐지에 대한 오버헤드를 감소 할 수 있었으며 실시간으로 지상에 존재하는 자동차를 탐지할 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.969-981
• /
• 2018

Recent advances in machine learning approaches such as deep neural network and reinforcement learning offer significant performance improvements in generating detailed and varied motions in physically simulated virtual environments. The optimization methods are highly attractive because it allows for less understanding of underlying physics or mechanisms even for high-dimensional subtle control problems. In this paper, we propose an efficient learning method for stochastic policy represented as deep neural networks so that agent can generate various energetic motions adaptively to the changes of tasks and states without losing interactivity and robustness. This strategy could be realized by our novel trajectory search method motivated by the trust region policy optimization method. Our value-based trajectory smoothing technique finds stably learnable trajectories without consulting neural network responses directly. This policy is set as a trust region of the artificial neural network, so that it can learn the desired motion quickly.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.748-757
• /
• 2017

In order to recognize the facial expressions, good features that can express the facial expressions are essential. It is also essential to find the characteristic areas where facial expressions appear discriminatively. In this study, we propose a directional LBP feature for facial expression recognition and a method of finding directional LBP operation and feature region for facial expression classification. The proposed directional LBP features to characterize facial fine micro-patterns are defined by LBP operation factors (direction and size of operation mask) and feature regions through AdaBoost learning. The facial expression classifier is implemented as a SVM classifier based on learned discriminant region and directional LBP operation factors. In order to verify the validity of the proposed method, facial expression recognition performance was measured in terms of accuracy, sensitivity, and specificity. Experimental results show that the proposed directional LBP and its learning method are useful for facial expression recognition.

• International Journal of Quality Innovation
• /
• 제8권2호
• /
• pp.57-68
• /
• 2007

Benchmarking is more than just a comparison of measures about different company's performance in a wider sense. It is a methodology of learning-comparing-learning, at least within small and medium sized enterprises. This learning is not just limited to learn by copying successful concepts from other enterprises or competitors. It starts in learning more about the own company, about its structure and processes causing its own success or its failure. This kind of learning is necessary before the enterprise starts watching for a suitable Benchmarking partner. Learning from each other's strengths and weaknesses is the main goal of the European research project Quality beyond Borders! By using the Benchmarking methodology, small and medium sized enterprises get the opportunity to take part in a Benchmarking study and can learn more about the different strengths and weaknesses of other enterprises on both sides of the border. The results of such a Benchmarking can help to identify potentials for future cooperations among German and Polish enterprises in the same market or business. These potentials can lie in different ways of realising the same success or top-position. The Benchmarking study is not focused on an special business or region. That helps to find out trends for different kinds of top-positions, which can be claimed in all markets within a country. Every trend is characterised by different success factors which are responsible for the success in this top-position. In a first overview, the results of the Benchmarking study show 5 different groups of top-positions within a market which all have different profiles regarding to the importance of their success factors. By the end of the Benchmarking study it will be possible, to give answer about the special reasons for different kind of successes of these groups. These answers can be related to a special region within a country, a special business or of course related to possible differences in the expression of the group success factors in comparison of both countries.

• ETRI Journal
• /
• 제29권5호
• /
• pp.700-702
• /
• 2007

We present a relevance feedback approach based on multi-class support vector machine (SVM) learning and cluster-merging which can significantly improve the retrieval performance in region-based image retrieval. Semantically relevant images may exhibit various visual characteristics and may be scattered in several classes in the feature space due to the semantic gap between low-level features and high-level semantics in the user's mind. To find the semantic classes through relevance feedback, the proposed method reduces the burden of completely re-clustering the classes at iterations and classifies multiple classes. Experimental results show that the proposed method is more effective and efficient than the two-class SVM and multi-class relevance feedback methods.

• 한국지역지리학회지
• /
• 제11권4호
• /
• pp.536-545
• /
• 2005

본 논문은 제7차 교육과정의 고등학교 사회과와 관련하여 Landsat ETM 및 IKONOS 위성영상을 이용한 지역학습방안을 제시한 것이다. 현재 10학년 사회과에서는 원격탐사 등과 관련하여 교육내용이 개념학습의 수준으로 진행되고 있으며, 실제 응용사례 및 학생들의 활동은 포함되어 있지 않은 실정이다. 주변 지역이해와 정체성 확립을 주요 목적으로 하는 지역학습은 학생들의 야외답사 및 조사에 있어 중요한 부분이지만, 현(現) 교육과정 내에서 실천이 어려운 부분이 많으므로 이를 대체할 수 있는 위성영상을 이용하는 학습방안을 제안해 보았다. 본 논문에서는 위성영상을 이용하여 해상도 즉 스케일에 따른 지역이해를 위한 지역학습방안을 제시하고자 하였다. GIS, RS 관련 기술을 일부 활용함으로서 학생들의 지리에 대한 관심과 학습효과를 향상시킬 것으로 기대된다.