• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.159-159
• /
• 2016

북한 지역에서 시작되어 한반도의 금문댐까지 연결되는 임진강은 북한지역의 유출량 미계측으로 인해 유출량 산출에 많은 어려움이 있어왔다. 본 연구에서는 위성 데이터를 활용하여 미계측 유역의 유출량을 추정 할 수 있는 기법을 제시하였다. Satellite-derived Flow Signal (SDF)는 위성 기반 특정 지역의 유출 정보를 제공하며, JAXA의 GCOM-W1 위성에 탑재된 Advanced Microwave Scanning Radiometer 2(AMSR2) 센서에서 산출된다. 본 연구에서는 SDS 뿐 아니라 유출에 크게 관련이 있는 지표 토양수분 데이터와 식생인자를 임진강 유출 값을 예측하기 위한 입력 값으로 활용하였다. 토양수분 데이터는 Metop-A 위성에 탑재된 Advanced Scatterometer(ASCAT) 센서에서 산출되는 데이터를 활용하였으며, 식생데이터는 Aqua 위성에 탑재된 Moderate Resolution Imaging Spectroradiometer(MODIS) 센서에서 측정되는 Normalized Difference Vegetation Index(NDVI) 데이터를 활용하였다. 추가적으로 SDS, 토양수분, NDVI 데이터는 다양한 lag time으로 약 150여개의 입력데이터로 세분화되었다. 150개의 방대한 입력인자는 Partial Mutual Information(PMI) 방법을 통해 소수 중요 인자들로 간추려져 기계 학습 입력인자로 활용되었다. 기계학습에 있어서는 Support Vector Machine(SVM), Artificial Neural Network (ANN) 기법을 활용하였다. SVM, ANN을 통해 모델화된 유출데이터는 금문댐 유출데이터와 비교/분석되었다. SVM 기법 기반의 유출량은 실제 유출량과 0.73의 상관계수를 보여주었고, ANN 기법 기반의 유출량은 0.66의 상관계수를 결과를 나타내었다. 하지만 SVM 기반 유출데이터는 과소 산정 되는 경향을 보였으며, ANN 기법 기반의 유출량은 과대산정되는 결과가 산출되는 한계점이 있음을 파악할 수 있었다.

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.5
• /
• pp.247-255
• /
• 2018

In this research, the effect of normal load, sliding velocity, and texture density on thefriction coefficient of surfaces micro-textured on AISI 4140 under paraffin oil lubrication were investigated. The predicted tribological behavior by numerical calculation can be serves as guidance for the designer during the machine development stage. Therefore, in this research friction coefficient prediction model based on response surface methodology (RSM), support vector machine (SVM), and artificial neural network (ANN) were developed. The experimental result shows that the variation of load, speed and texture density were influence the friction coefficient. The RSM, ANN and SVM model was successfully developed based on the experimental data. The ANN model can effectively predict the tribological characteristics of micro-textured AISI 4140 in paraffin oil lubrication condition compare to RSM and SVM.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.33 no.4
• /
• pp.122-129
• /
• 2010

High-performance concrete (HPC) is a new terminology used in concrete construction industry. Several studies have shown that concrete strength development is determined not only by the water-to-cement ratio but also influenced by the content of other concrete ingredients. HPC is a highly complex material, which makes modeling its behavior a very difficult task. This paper aimed at demonstrating the possibilities of adapting artificial neural network (ANN) to predict the comprresive strength of HPC. Mahalanobis Distance (MD) outlier detection method used for the purpose increase prediction ability of ANN. The detailed procedure of calculating Mahalanobis Distance (MD) is described. The effects of outlier compared with before and after artificial neural network training. MD outlier detection method successfully removed existence of outlier and improved the neural network training and prediction performance.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.6
• /
• pp.15-26
• /
• 2006

Although numerous investigations have been performed over the years to predict the behavior and bearing capacity of piles, the mechanisms are not yet entirely understood. The prediction of bearing capacity is a difficult task, because large numbers of factors affect the capacity and also have complex relationship one another. Therefore, it is extremely difficult to search the essential factors among many factors, which are related with ground condition, pile type, driving condition and others, and then appropriately consider complicated relationship among the searched factors. The present paper describes the application of Artificial Neural Network (ANN) in predicting the capacity including its components at the tip and along the shaft from dynamic load test of the driven piles. Firstly, the effect of each factor on the value of bearing capacity is investigated on the basis of sensitivity analysis using ANN modeling. Secondly, the authors use the design methodology composed of ANN and genetic algorithm (GA) to find optimal neural network model to predict the bearing capacity. The authors allow this methodology to find the appropriate combination of input parameters, the number of hidden units and the transfer structure among the input, the hidden and the out layers. The results of this study indicate that the neural network model serves as a reliable and simple predictive tool for the bearing capacity of driven piles.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.469-484
• /
• 2021

Rock mass classification results have a great influence on construction schedule and budget as well as tunnel stability in tunnel design. A total of 3,526 tunnels have been constructed in Korea and the associated techniques in tunnel design and construction have been continuously developed, however, not many studies have been performed on how to assess rock mass quality and grade more accurately. Thus, numerous cases show big differences in the results according to inspectors' experience and judgement. Hence, this study aims to suggest a more reliable rock mass classification (RMR) model using machine learning algorithms, which is surging in availability, through the analyses based on various rock and rock mass information collected from boring investigations. For this, 11 learning parameters (depth, rock type, RQD, electrical resistivity, UCS, V_p, V_s, Young's modulus, unit weight, Poisson's ratio, RMR) from 13 local tunnel cases were selected, 337 learning data sets as well as 60 test data sets were prepared, and 6 machine learning algorithms (DT, SVM, ANN, PCA & ANN, RF, XGBoost) were tested for various hyperparameters for each algorithm. The results show that the mean absolute errors in RMR value from five algorithms except Decision Tree were less than 8 and a Support Vector Machine model is the best model. The applicability of the model, established through this study, was confirmed and this prediction model can be applied for more reliable rock mass classification when additional various data is continuously cumulated.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.597-600
• /
• 2007

신경망은 복잡한 데이터에서 일정한 패턴을 찾아 이를 분류하는 능력이 뛰어난 모델이다. 그러나 다량의 데이터가 입력으로 들어오면 연산에 오랜 시간이 걸리고 패턴을 찾기가 어려워진다는 한계가 있다. 본 연구에서는 set association과 의사결정나무를 이용하여 신경망에 입력되는 데이터의 수를 줄여서 다량의 데이터에도 적용 가능하며 예측의 정확도를 높인 신경망 모델을 구성하였다. 이 모델을 천식 관련 SNP 데이터에 적용하여 천식 발병 여부를 예측한 결과, 각각의 방법을 독립적으로 사용했을 때 보다 높은 예측 정확도를 얻었다.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1E
• /
• pp.64-70
• /
• 1994

Predictive neural network models are powerful speech recognition models based on a nonlinear pattern prediction. But those models suffer from poor discrimination between acoustically similar words. In this paper we propose an discriminative training algorithm for predictive neural network models. This algorithm is derived from GPD (Generalized Probabilistic Descent) algorithm coupled with MCEF(Minimum Classification Error Formulation). It allows direct minimization of a recognition error rate. Evaluation of our training algoritym on ten Korean digits shows its effectiveness by 30% reduction of recognition error.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.773-776
• /
• 2014

최근 기업의 기술력이 기업의 경영성과에 미치는 영향이 증가함에 따라 기업이 보유한 기술적 정보가 경영성과예측에 있어 필수적 요소로 대두되었다. 본 연구에서는 기업의 기술적 정보를 담고 있는 특허정보 및 특허지표를 활용하여 기업의 경영성과를 정량적으로 예측하는 모델을 제안한다. 또 미국 정보통신기업의 재무정보와 특허정보를 활용하여 제안된 예측모델을 구축하고 그 성능을 검증 및 평가하였다. 본 연구에서 제안한 기업실적예측 모델의 구축을 위해 인간의 두뇌가 학습하는 과정을 모방한 인공신경망알고리즘을 활용하였다.

• Proceedings of the KIPE Conference
• /
• 2019.07a
• /
• pp.445-446
• /
• 2019

전기적 등가회로의 모델의 정확도 향상을 위하여 정확한 내부 저항과 OCV의 반영은 필수적이며, 이를 위한 OCV 실험에서 SOC 구간을 작게 작을수록 OCV의 정확도는 향상되지만 실험시간은 증가한다. 따라서 실험 시간을 고려한 적당한 SOC(5%, 10%) 구간으로 실험을 진행하며, 측정 되지 않은 영역의 내부 파라미터는 선형보간법으로 등가회로 모델에 반영한다. 이러한 문제로, 본 연구는 SOC 추정에의 주요 인자인 OCV의 추정 기법으로 뉴럴 네트워크(Neural Network)를 사용하였다. 추정 방법은 뉴럴 네트워크로 기존 OCV 실험 데이터를 학습하여 모델을 구축한다. 학습 모델의 입력값으로 용량 실험 데이터의 전압, 전류를 적용하였고 결과로 얻은 SOC-OCV 곡선을 비교 분석하였다.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.79-85
• /
• 2022

Anomaly detection is a method to detect and block abnormal data flows in general users' data sets. The previously known method is a method of detecting and defending an attack based on a signature using the signature of an already known attack. This has the advantage of a low false positive rate, but the problem is that it is very vulnerable to a zero-day vulnerability attack or a modified attack. However, in the case of anomaly detection, there is a disadvantage that the false positive rate is high, but it has the advantage of being able to identify, detect, and block zero-day vulnerability attacks or modified attacks, so related studies are being actively conducted. In this study, we want to deal with these anomaly detection mechanisms, and we propose a new mechanism that performs both anomaly detection and classification while supplementing the high false positive rate mentioned above. In this study, the experiment was conducted with five configurations considering the characteristics of various algorithms. As a result, the model showing the best accuracy was proposed as the result of this study. After detecting an attack by applying the Extra Tree and Three-layer ANN at the same time, the attack type is classified using the Extra Tree for the classified attack data. In this study, verification was performed on the NSL-KDD data set, and the accuracy was 99.8%, 99.1%, 98.9%, 98.7%, and 97.9% for Normal, Dos, Probe, U2R, and R2L, respectively. This configuration showed superior performance compared to other models.