• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.3
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• Communications for Statistical Applications and Methods
• /
• v.27 no.3
• /
• pp.313-326
• /
• 2020

Deep Learning is the most important key to the development of Artificial Intelligence (AI). There are several distinguishable architectures of neural networks such as MLP, CNN, and RNN. Among them, we try to understand one of the main architectures called Recurrent Neural Network (RNN) that differs from other networks in handling sequential data, including time series and texts. As one of the main tasks recently in Natural Language Processing (NLP), we consider Neural Machine Translation (NMT) using RNNs. We also summarize fundamental structures of the recurrent networks, and some topics of representing natural words to reasonable numeric vectors. We organize topics to understand estimation procedures from representing input source sequences to predict target translated sequences. In addition, we apply multiple translation models with Gated Recurrent Unites (GRUs) in Keras on English-Korean sentences that contain about 26,000 pairwise sequences in total from two different corpora, colloquialism and news. We verified some crucial factors that influence the quality of training. We found that loss decreases with more recurrent dimensions and using bidirectional RNN in the encoder when dealing with short sequences. We also computed BLEU scores which are the main measures of the translation performance, and compared them with the score from Google Translate using the same test sentences. We sum up some difficulties when training a proper translation model as well as dealing with Korean language. The use of Keras in Python for overall tasks from processing raw texts to evaluating the translation model also allows us to include some useful functions and vocabulary libraries as well.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.11a
• /
• pp.445-453
• /
• 2002

Past and current customer behavior is the best predicator of future customer behavior. This paper introduces a procedure on personalized defection detection and prevention for an online game site. The basic idea for our defection detection and prevention is adopted from the observation that potential defectors have a tendency to take a couple of months or weeks to gradually change their behavior (i.e. trim-out their usage volume) before their eventual withdrawal. For this purpose, we suggest a SOM (Self-Organizing Map) based procedure to determine the possible states of customer behavior from past behavior data. Based on this representation of the state of behavior, potential defectors are detected by comparing their monitored trajectories of behavior states with frequent and confident trajectories of past defectors. The key feature of this study includes a defection prevention procedure which recommends the desirable behavior state for the ext period so as to lower the likelihood of defection. The defection prevention procedure can be used to design a marketing campaign on an individual basis because it provides desirable behavior patterns for the next period. The experiments demonstrate that our approach is effective for defection prevention and efficient for defection detection because it predicts potential defectors without deterioration of prediction accuracy compared to that of the MLP (Multi-Layer Perceptron) neural network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4214-4230
• /
• 2020

This paper introduces a pilot allocation scheme for massive MIMO systems based on deep convolutional neural network (CNN) learning. This work is an extension of a prior work on the basic deep learning framework of the pilot assignment problem, the application of which to a high-user density nature is difficult owing to the factorial increase in both input features and output layers. To solve this problem, by adopting the advantages of CNN in learning image data, we design input features that represent users' locations in all the cells as image data with a two-dimensional fixed-size matrix. Furthermore, using a sorting mechanism for applying proper rule, we construct output layers with a linear space complexity according to the number of users. We also develop a theoretical framework for the network capacity model of the massive MIMO systems and apply it to the training process. Finally, we implement the proposed deep CNN-based pilot assignment scheme using a commercial vanilla CNN, which takes into account shift invariant characteristics. Through extensive simulation, we demonstrate that the proposed work realizes about a 98% theoretical upper-bound performance and an elapsed time of 0.842 ms with low complexity in the case of a high-user-density condition.

• Journal of the Korea Safety Management & Science
• /
• v.14 no.3
• /
• pp.269-276
• /
• 2012

플라스틱 사출 제품은 다양한 가전제품과 하이테크 제품에 널리 사용되고 있다. 그러나 현재의 치열한 경쟁적 비즈니스 환경에서 플라스틱 사출 제품 제조업자들은 고객을 만족시키면서 경쟁력을 얻기 위하여 다른 경쟁자들보다 먼저 새로운 제품을 시장에 출시하고 신제품의 개발기간을 줄이기 위한 노력을 할 여유가 부족하다. 따라서 무한경쟁의 시장에서 살아남기 위해서는 제조업자들은 시장 마켓 점유를 빠르게 올리는 것과 동시에 제품의 가격 경쟁력을 가져야 한다. 특징기반 모델의 구조는 현재 연구에서 3D 제작 도구로서 일반적으로 적용되고 있으며 신제품 개발 엔지니어들이 새로운 제품의 개념을 개발하는 데에도 널리 사용되고 있다. 본 연구에서는 특징기반 플라스틱 사출제품을 위한 유전자 알고리즘과 Support Vector Regression (SVR) 기반의 새로운 하이브리드 비용 평가 모델을 제안한다. 제안하는 하이브리드 모델은 기존의 플라스틱 사출제품의 비용평가절차와 계산을 위해 필요로 하는 변수들을 극적으로 간단하게 하고 줄일 수 있다. 사례연구에서는 제안하는 하이브리드 모델과 기존의 multilayer perceptron networks (MLP) 및 pure SVR과의 비교분석을 통하여 제안모델이 플라스틱 사출 제품의 개발단계에서의 비용평가문제를 해결하는데 효율성과 효과성이 있음을 입증한다.

• Journal of Electrical Engineering and information Science
• /
• v.3 no.3
• /
• pp.355-365
• /
• 1998

The purposes of this study are to propose a network for the characterizing of the input data and to show how to design predictive neural net재가 expert system which doesn't need previous knowledge base. We derived this network from the radial basis function networks(RBFN), and named it as a statistical EBFN. The proposed network can replace the statistical methods for analyzing dynamic relations between target disease and other parameters in medical studies. We compared statistical RBFN with the probabilistic neural network(PNN) and fuzzy logic(FL). And we testified our method in the diabetes prediction and compared our method with the well-known multilayer perceptron(MLP) neural network one, and showed good performance of our network. At last, we developed the diabetes prediction expert system based on the proposed statistical RBFN without previous knowledge base. Not only the applicability of the characterizing of parameters related to diabetes and construction of the diabetes prediction expert system but also wide applicabilities has the proposed statistical RBFN to other similar problems.

• Annual Conference of KIPS
• /
• 2017.11a
• /
• pp.1258-1261
• /
• 2017

1급 발암물질인 미세먼지 중 44.3%를 차지하고 있는 도로 비산먼지는 효과적인 미세먼지 농도 저감 대책의 방안 중 하나이다. 도로 비산먼지 제거는 일반적으로 특수 차량을 이용, 정해진 경로와 주기에 따라 운행된다. 이러한 운행방식은 도로의 오염 현황에 따른 효과적 경로 선정 및 운영이 어렵다. 본 논문에서는 도로 비산먼지 제거의 효율적인 경로 제안을 위해 대구지역에 분포된 KISTI 이동형 도시센싱 테스트베드에서 수집되는 고해상도의 실시간 지역별 오염 현황 데이터를 활용하여 실시간 오염도를 분석하고, LSTM(LONG SHORT-TERM MEMORY) 알고리즘을 활용하여 미래의 미세먼지 농도를 예측하였다. 기존 연구와 달리 지역별 상황을 고려한 데이터를 사용하여 선형 회귀 분석을 수행하였다. 실험 결과, 시간 속성을 고려한 LSTM이 MLP 보다 평균 제곱근 오차 값이 경우에 따라 최대 30% 더 작음을 확인했다. 본 연구를 기반으로 고해상도 사물 데이터 기반 예측 연구의 가능성을 보였으며, 미세먼지 예측 결과를 활용 유연하고 효과적인 도로 청소차량의 운행 경로를 설정에 활용될 수 있을 것으로 기대한다.

• Journal of Ocean Engineering and Technology
• /
• v.15 no.2
• /
• pp.46-52
• /
• 2001

In this paper, the real-time prediction of high temperature creep life was carried out for the friction welded joints of dissimilar heat resisting steels (SUH3-SUH35). various life prediction method such as LMP (Larson_miller Parameter) and ISM (initial strain method) were applied. The creep behaviors of those steels and the welds under static load were examined by ISM combined with LMP at 500, 600 and $700^{\circ}C$, and the relationship between these two methods was investigated. A real-time creep lie (tr, hr) prediction equation by initial strain (${\varepsilon}_0$, %) under any creep stress ($\sigma$, MPa) at any high temperature (T, K) was developed as follows: $t_r={\alpha}{\varepsilon}_0^{\beta}{\sigma}^{-1}$ where, ${\phi}=16: {\alpha}=10^{51.412-0.104T+5.375{\times}10^5T^2}$, $ {\beta}=-83.989+0.180T-9.957{\times}10^{-5}T^2,{\phi}=20:$ ${\alpha}=10^{69.910-0.146T+7.744{\times}10^{-5}T^2$, ${\beta}=-51.442+0.105T-5.595{\times}10^{-5}T^2$ for SUH3-SUH35 friction weld of =16mm and 20mm, respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.716-721
• /
• 2010

In this work we address the use of support vector machine (SVM) in the multi-class gas classification system. The objective is to classify single gases and their mixture with a semiconductor-type electronic nose. The SVM has some typical multi-class classification models; One vs. One (OVO) and One vs. All (OVA). However, studies on those models show weaknesses on calculation time, decision time and the reject region. We propose a hierarchical clustering method (HCM) based on the SVM for real-time gas mixture classification. Experimental results show that the proposed method has better performance than the typical multi-class systems based on the SVM, and that the proposed method can classify single gases and their mixture easily and fast in the embedded system compared with BP-MLP and Fuzzy ARTMAP.

• Proceedings of the KIEE Conference
• /
• 2006.10a
• /
• pp.145-146
• /
• 2006

본 논문은 부분방전(PD: Partial Discharge)의 패턴인식 확률 극대화를 목적으로 신경망(NN: Neural Network) 파라미터 중에서 은닉층 뉴런의 수, 모멘텀(momentum)의 Step size와 Decay rate 를 최적화하기 위하여 유전 알고리즘(GA: Genetic Algonthm)을 적응하였다. 실험적 연구의 대상으로서, GIS(Gas Insulated Switchgear)사고의 주요 원인으로 보고되어있는 결함들을 인위적으로 모의한 16개 Test cell을 이용하여 부분방전을 발생시켰다. 부분방전 신호는 본 연구팀이 개발한 센서를 이용하여 검출되어 데이터베이스가 구축되어 그로부터 추출된 학습 데이터들의 학습에 다음과 같은 5가지 신경망 모델이 적응되었다: Multilayer Perception (MLP), Jordan-Elman Network (JEN), Recurrent Network (RN), Self-Organizing Feature Map (SOFM), Time-Lag Recurrent Network (TLRN). 유전 알고리즘 적용 효율성을 분석하기 위하여 동일한 데이터를 이용하여 다음과 같은 두 가지 방법을 적용한 결과를 상호 비교하였다. 우선 상기 선택된 모델만 적용하였고 다근 하나는 상기 모델과 Genetic Algorithm이 동시에 적용되었다. 모든 모델에 대하여 학습오차와 패턴 분류 확률을 비교한 결과, 유전 알고리즘 적응 시 부분방전 패턴인식 확률이 향상되었음이 확인되어 향후 신뢰성 있는 GIS 부분방전 진단기술에 활용될 수 있을 것으로 사료된다.