• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.151-152
• /
• 2019

본 논문에서는 동물 이미지 분류를위한 작은 데이터 세트를 기반으로 개선 된 심층 학습 방법을 제안한다. 첫째, CNN은 소규모 데이터 세트에 대한 교육 모델을 작성하고 데이터 세트를 사용하여 교육 세트의 데이터 세트를 확장하는 데 사용된다. 둘째, VGG16과 같은 대규모 데이터 세트에 사전 훈련 된 네트워크를 사용하여 작은 데이터 세트의 병목을 추출하여 새로운 교육 데이터 세트 및 테스트 데이터 세트로 두 개의 NumPy 파일에 저장하고, 마지막으로 완전히 연결된 네트워크를 새로운 데이터 세트로 학습한다.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2001년도 학술발표회 발표논문집
• /
• pp.59-64
• /
• 2001

The objectives of the thesis are to propose a pattern classification method for remote sensing data using artificial neural network. First, we apply the error back propagation algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. Using the training data set and the error back propagation algorithm, a layered neural network is trained such that the training pattern are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of Landsat TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method.

• Nuclear Engineering and Technology
• /
• 제39권4호
• /
• pp.337-348
• /
• 2007

A fuzzy neural network model is presented to predict residual stress for dissimilar metal welding under various welding conditions. The fuzzy neural network model, which consists of a fuzzy inference system and a neuronal training system, is optimized by a hybrid learning method that combines a genetic algorithm to optimize the membership function parameters and a least squares method to solve the consequent parameters. The data of finite element analysis are divided into four data groups, which are split according to two end-section constraints and two prediction paths. Four fuzzy neural network models were therefore applied to the numerical data obtained from the finite element analysis for the two end-section constraints and the two prediction paths. The fuzzy neural network models were trained with the aid of a data set prepared for training (training data), optimized by means of an optimization data set and verified by means of a test data set that was different (independent) from the training data and the optimization data. The accuracy of fuzzy neural network models is known to be sufficiently accurate for use in an integrity evaluation by predicting the residual stress of dissimilar metal welding zones.

• Journal of the Korean Data and Information Science Society
• /
• 제16권1호
• /
• pp.1-11
• /
• 2005

A network consisting of a set of N nodes and a set of links is considered. The nodes are assumed to be perfect and the states of links to be binary and associated to each other. After defining a network structure function, which represents the state of network as a function of the states of links, we obtain some lower and upper bounds on the network reliability by adopting minmax principle and minimal path and cut set arguments. These bounds are given as functions of the reliabilities of links. The bridge network is considered as an example.

• 한국인터넷방송통신학회논문지
• /
• 제20권6호
• /
• pp.157-165
• /
• 2020

뉴-럴 네트워크와 자동운전 데이터 셋을 개발하는 목표중의 하나가 데이터 셋을 분할함에 따라서 움직이는 물체를 검출하는 성능을 개선하는 방법이 있다. 다크넷 (DarkNet) 프레임 워크에 있어서, YOLOv4 네트워크는 Udacity 데이터 셋에서 훈련하는 셋과 검증 셋으로 사용되었다. Udacity 데이터 셋의 7개 비율에 따라서 이 데이터 셋은 훈련 셋, 검증 셋, 테스트 셋을 포함한 3개의 부분 셋으로 나누어진다. K-means++ 알고리즘은 7개 그룹에서 개체 Box 차원 군집화를 수행하기 위해 사용되었다. 훈련을 위한 YOLOv4 네트워크의 슈퍼 파라메타를 조절하여 7개 그룹들에 대하여 최적 모델 파라메타가 각각 구해졌다. 이 모델 파라메타는 각각 7 개 테스트 셋 데이터에 비교하고 검출에 사용되었다. 실험결과에서 YOLOv4 네트워크는 Udacity 데이터 셋에서 트럭, 자동차, 행인으로 표현되는 움직이는 물체에 대하여 대/중/소 물체 검출을 할수 있음을 보여 주었다. 훈련 셋과 검증 셋, 테스트 셋의 비율이 7 ; 1.5 ; 1.5 일 때 최적의 모델 파라메타로서 가장 높은 검출 성능이었다. 그 결과값은, mAP50가 80.89%, mAP75가 47.08%에 달하고, 검출 속도는 10.56 FPS에 달한다.

• Genomics & Informatics
• /
• 제5권3호
• /
• pp.133-136
• /
• 2007

The Gene Set network viewer (GSnet) visualizes the functional enrichment of a given gene set with a protein interaction network and is implemented as a plug-in for the Cytoscape platform. The functional enrichment of a given gene set is calculated using a hypergeometric test based on the Gene Ontology annotation. The protein interaction network is estimated using public data. Set operations allow a complex protein interaction network to be decomposed into a functionally-enriched module of interest. GSnet provides a new framework for gene set analysis by integrating a priori knowledge of a biological network with functional enrichment analysis.

• 지능정보연구
• /
• 제4권1호
• /
• pp.133-147
• /
• 1998

Recently, many researchers have been involved in finding deterministic equations which can accurately predict future event, based on chaotic theory, or fractal theory. The theory says that some events which seem very random but internally deterministic can be accurately predicted by fractal equations. In contrast to the conventional methods, such as AR model, MA, model, or ARIMA model, the fractal equation attempts to discover a deterministic order inherent in time series data set. In discovering deterministic order, researchers have found that neural networks are much more effective than the conventional statistical models. Even though prediction accuracy of the network can be different depending on the topological structure and modification of the algorithms, many researchers asserted that the neural network systems outperforms other systems, because of non-linear behaviour of the network models, mechanisms of massive parallel processing, generalization capability based on adaptive learning. However, recent survey shows that prediction accuracy of the forecasting models can be determined by the model structure and data structures. In the experiments based on actual economic data sets, it was found that the prediction accuracy of the neural network model is similar to the performance level of the conventional forecasting model. Especially, for the data set which is deterministically chaotic, the AR model, a conventional statistical model, was not significantly different from the MLP model, a neural network model. This result shows that the forecasting model. This result shows that the forecasting model a, pp.opriate to a prediction task should be selected based on characteristics of the time series data set. Analysis of the characteristics of the data set was performed by fractal analysis, measurement of Hurst index, and measurement of Lyapunov exponents. As a conclusion, a significant difference was not found in forecasting future events for the time series data which is deterministically chaotic, between a conventional forecasting model and a typical neural network model.

• 방송공학회논문지
• /
• 제13권1호
• /
• pp.86-91
• /
• 2008

네트워크 데이터 분석에 있어서 추정모델이 얼마나 모집단을 대표하느냐는 반드시 연구되어야 한다. 본 논문에서는 네트워크 데이터의 각 추출 가능한 표준 정보를 이용하여 현재 공개되어 사용하고 있는 MIT Lincoln Lab의 네트워크 데이터와 모델링 된 KDD CUP 99 데이터를 비교 분석한다. 비교, 분석에 있어서 두 데이터에 공통으로 포함되고 표준 정보인 프로토콜 정보를 이용하여 분석한다. 분석은 통계적 분석 방법인 대응 분석 방법을 이용하여 분석하고, SVD를 이용해 2차원 공간에 표현하며, 가중 유클리드 거리를 이용해 네트워크 데이터를 수량화하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제15권2호
• /
• pp.499-506
• /
• 2004

The Unscented Kalman Filter is known to outperform the Extended Kalman Filter for the nonlinear state estimation with a significance advantage that it does not require the computation of Jacobian but EKF has a competitive advantage to the UKF on the performance time. We compare both algorithms on training the artificial neural network. The validation data set is used to estimate parameters which are supposed to result in better fitting for the test data set. Experimental results are presented which indicate the performance of both algorithms.

• 한국시뮬레이션학회논문지
• /
• 제5권1호
• /
• pp.1-12
• /
• 1996

We propose a new approach to classifying a time series data into one of the autoregressive moving-average (ARMA) models. It is bases on two pattern recognition concepts for solving time series identification. The one is an extended sample autocorrelation function (ESACF). The other is a neural network-driven decision tree classifier(NNDTC) in which two pattern recognition techniques are tightly coupled : neural network and decision tree classfier. NNDTc consists of a set of nodes at which neural network-driven decision making is made whether the connecting subtrees should be pruned or not. Therefore, time series identification problem can be stated as solving a set of local decisions at nodes. The decision values of the nodes are provided by neural network functions attached to the corresponding nodes. Experimental results with a set of test data and real time series data show that the proposed approach can efficiently identify the time seires patterns with high precision compared to the previous approaches.