• 전기학회논문지P
• /
• 제67권1호
• /
• pp.42-46
• /
• 2018

In this paper, we propose fast object detection method of the cars by applying YOLOv2(You Only Look Once version 2) and UAVs (Unmanned Aerial Vehicles) while on the highway. We operated Darknet, OpenCV, CUDA and Deep Learning Server(SDX-4185) for our simulation environment. YOLOv2 is recently developed fast object detection algorithm that can detect various scale objects as fast speed. YOLOv2 convolution network algorithm allows to calculate probability by one pass evaluation and predicts location of each cars, because object detection process has simple single network. In our result, we could find cars on the highway area as fast speed and we could apply to the real time.

• 대한원격탐사학회지
• /
• 제34권5호
• /
• pp.811-827
• /
• 2018

본 연구의 목적은 다중시기 원격탐사 자료를 이용한 작물분류에서 기계학습 알고리즘과 딥러닝 알고리즘의 비교에 있다. 이를 위해 전라남도 해남군과 미국 Illinois 주의 작물 재배지를 대상으로 기계학습 알고리즘과 딥러닝 알고리즘에 대해 (1) 하이퍼파라미터와 (2) 훈련자료의 크기에 따른 영향을 비교 분석하였다. 비교 실험에는 기계학습 알고리즘으로 support vector machine(SVM)을 적용하고 딥러닝 알고리즘으로 convolutional neural network(CNN)를 적용하였다. 특히 CNN에서 2차원의 공간정보를 고려하는 2D-CNN과 시간차원을 확장한 구조의 3D-CNN을 적용하였다. 비교 실험 결과, 다양한 하이퍼파라미터를 고려해야 하는 CNN의 경우 SVM과 다르게 두 지역에서 정의된 하이퍼파라미터 값이 유사한 것으로 나타났다. 이러한 결과를 바탕으로 모델 최적화에 많은 시간이 소요되지만 최적화된 CNN 모델을 다른 지역으로 확장할 수 있는 전이학습의 적용 가능성이 높을 것으로 판단된다. 다음 훈련자료 크기에 따른 비교 실험 결과, SVM 보다 CNN에서 훈련자료 크기의 영향이 큰 것으로 나타났는데 특히 다양한 공간특성을 갖는 Illinois 주에서 이러한 경향이 두드러지게 나타났다. 또한 Illinois 주에서 3D-CNN의 분류 성능이 저하되는 것으로 나타났는데, 이는 모델 복잡도가 증가하면서 과적합의 영향이 발생한 것으로 판단된다. 즉 모델의 훈련 정확도는 높지만 다양한 공간특성이나 입력 자료의 잡음 효과 등으로 오히려 분류 성능이 저하된 것으로 나타났다. 이러한 결과는 대상 지역의 공간특성을 고려해 적절한 분류 알고리즘을 선택해야 하는 것을 의미한다. 또한 CNN에서 특히, 3D-CNN에서 일정 수준의 분류 성능을 담보하기 위해 다량의 훈련자료 수집이 필요하다는 것을 의미한다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제2권6호
• /
• pp.323-331
• /
• 2013

An extreme learning machine (ELM) is an efficient learning algorithm that is based on the generalized single, hidden-layer feed-forward networks (SLFNs), which perform well in classification applications. Many studies have demonstrated its superiority over the existing classical algorithms: support vector machine (SVM) and BP neural network. This paper presents a novel face recognition approach based on a multi-class project extreme learning machine (MPELM) classifier and 2D Gabor transform. First, all face image features were extracted using 2D Gabor filters, and the MPELM classifier was used to determine the final face classification. Two well-known face databases (CMU-PIE and ORL) were used to evaluate the performance. The experimental results showed that the MPELM-based method outperformed the ELM-based method as well as other methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1033-1036
• /
• 2004

The study on speech recognition and understanding has been done for many years. In this paper, we propose a new type of recurrent neural network architecture for speech recognition, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units [1]. Besides that, we also proposed the new architecture and the learning algorithm of recurrent neural network such as Backpropagation Through Time (BPTT, which well-suited. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Recurrent Neural Network (RNN) and Backpropagation Through Time (BPTT) learning algorithm. 4 speakers (a mixture of male and female) are trained in quiet environment. Neural network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [2] such as Arabic. The Arabic language offers a number of challenges for speech recognition [3]. Even through positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".

• 대한통합의학회지
• /
• 제12권2호
• /
• pp.155-166
• /
• 2024

Purpose : This study aims to identify key factors for predicting dropout risk at the university level and to provide a foundation for policy development aimed at dropout prevention. This study explores the optimal machine learning algorithm by comparing the performance of various algorithms using data on college students' dropout risks. Methods : We collected data on factors influencing dropout risk and propensity were collected from N University. The collected data were applied to several machine learning algorithms, including random forest, decision tree, artificial neural network, logistic regression, support vector machine (SVM), k-nearest neighbor (k-NN) classification, and Naive Bayes. The performance of these models was compared and evaluated, with a focus on predictive validity and the identification of significant dropout factors through the information gain index of machine learning. Results : The binary logistic regression analysis showed that the year of the program, department, grades, and year of entry had a statistically significant effect on the dropout risk. The performance of each machine learning algorithm showed that random forest performed the best. The results showed that the relative importance of the predictor variables was highest for department, age, grade, and residence, in the order of whether or not they matched the school location. Conclusion : Machine learning-based prediction of dropout risk focuses on the early identification of students at risk. The types and causes of dropout crises vary significantly among students. It is important to identify the types and causes of dropout crises so that appropriate actions and support can be taken to remove risk factors and increase protective factors. The relative importance of the factors affecting dropout risk found in this study will help guide educational prescriptions for preventing college student dropout.

• 한국수자원학회논문집
• /
• 제33권4호
• /
• pp.505-515
• /
• 2000

본 연구는 하천에서 호우의 발생에 따라 하천 유출수문곡선을 예측코자 블랙박스모형의 신경망이론을 적용하여 수문학적인 문제를 규명하고자 하였다. 이를 위해 신경망 이론 중 Levenverg-Marquardt 방법에 의한 오차역전파 알고리즘과 Radial Basis Function Network(RBFN)를 이용하여 IHP 대표유역인 보청청유역에 수문곡선을 적용하여 선행유출량 예측과 미학습 유역의 적용성을 검토하였다. 그 결과 복잡하고 비선형적인 수문계의 강우-유출 과정의 학습에 있어 RBFN은 은닉층에서 자율학습, 출력층에서 지도학습의 두 단계로 나누어 학습을 함으로서 BP 알고리즘보다 학습시간이 빠르게 나타났고, 선행유출량의 예측결과 여러 통계적 지표에서 RBFN이 BP 알고리즘보다 좋은 결과를 얻을 수 있었다. 미학습 유역의 적용성 검토에서도 BP알고리즘과 RBFN 모두 첨두치가 비교적 실측자료의 경향과 비슷한 경향으로 나타났다.

• 산업경영시스템학회지
• /
• 제38권3호
• /
• pp.169-180
• /
• 2015

Recently, scheduling problems with position-dependent processing times have received considerable attention in the literature, where the processing times of jobs are dependent on the processing sequences. However, they did not consider cases in which each processed job has different learning or aging ratios. This means that the actual processing time for a job can be determined not only by the processing sequence, but also by the learning/aging ratio, which can reflect the degree of processing difficulties in subsequent jobs. Motivated by these remarks, in this paper, we consider a two-agent single-machine scheduling problem with linear job-dependent position-based learning effects, where two agents compete to use a common single machine and each job has a different learning ratio. Specifically, we take into account two different objective functions for two agents: one agent minimizes the total weighted completion time, and the other restricts the makespan to less than an upper bound. After formally defining the problem by developing a mixed integer non-linear programming formulation, we devise a branch-and-bound (B&B) algorithm to give optimal solutions by developing four dominance properties based on a pairwise interchange comparison and four properties regarding the feasibility of a considered sequence. We suggest a lower bound to speed up the search procedure in the B&B algorithm by fathoming any non-prominent nodes. As this problem is at least NP-hard, we suggest efficient genetic algorithms using different methods to generate the initial population and two crossover operations. Computational results show that the proposed algorithms are efficient to obtain near-optimal solutions.

• 한국산업융합학회 논문집
• /
• 제2권1호
• /
• pp.61-67
• /
• 1999

An active control for the swing of crane systems is very important for increasing the productivity. This article introduces the control for the position and the swing of a crane using the fuzzy learning method. Because the crane is a multi-variable system, learning is done to control both position and swing of the crane. Also the fuzzy control rules are separately acquired with the loading and unloading situation of the crane for more accurate control. And We designed controller by fuzzy learning method, and then compare fuzzy learning method with LQR. The result of simulations shows that the crane is controlled better than LQR for a very large swing angle of 1 radian within nearly one cycle.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 추계학술대회
• /
• pp.995-998
• /
• 2013

본 논문에서는 자기 조직화 기능을 갖는 Kohonen의 SOM(Self Organization Map) 신경회로망에 2단계의 학습과정을 활용하여 항공영상에서 물체를 인근의 물체와 효과적으로 구별하기 위한 접근방법을 제안하고 실제의 항공영상에 적용하여 기존의 고전적인 K-means 알고리즘 및 원래의 SOM 알고리즘보다 우수함을 보인다.

• KEPCO Journal on Electric Power and Energy
• /
• 제2권2호
• /
• pp.311-316
• /
• 2016

인공신경망과 같은 기계학습에 기반한 네트워크 침입탐지/방지시스템은 특징 조합에 따라 탐지의 정확성과 효율성 측면에서 크게 영향을 받는다. 하지만 침입탐지에 사용 가능한 여러개의 특징들 중 정확성과 효율성 측면에서 최적의 특징 조합을 추출하는 특징 선택 문제는 많은 계산량을 요구한다. 본 논문에서는 NSL-KDD 데이터 집합에서 제공하는 6가지 서비스 거부 공격과 정상 트래픽을 구분해 내기 위한 최적 특징 조합 선택 문제를 다룬다. 최적 특징 조합 선택 문제를 해결하기 위해 대표적인 메타 휴리스틱 알고리즘 중 하나인 다중 시작 지역탐색 알고리즘에 기반한 최적 특징 선택 알고리즘을 제시한다. 제안한 특징 선택 알고리즘의 성능 평가를 위해 NSL-KDD 데이터를 상대로 41개의 특징 모두를 사용한 경우와 비교한다. 그리고 선택된 특징 조합을 사용했을 때 가장 높은 성능을 보여주는 기계학습 방법을 찾기위해 3가지 잘 알려진 기계학습 방법들 (베이즈 분류기와 인공신경망, 서포트 벡터 머신)을 사용해 성능을 비교한다.