• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.103-116
• /
• 2021

Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN's structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2334-2340
• /
• 2021

Radioactive particle tracking (RPT) is a minimally invasive nuclear technique that tracks a radioactive particle inside a volume of interest by means of a mathematical location algorithm. During the past decades, many algorithms have been developed including ones based on artificial intelligence techniques. In this study, RPT technique is applied in a simulated test section that employs a simplified mixer filled with concrete, six scintillator detectors and a¹³⁷Cs radioactive particle emitting gamma rays of 662 keV. The test section was developed using MCNPX code, which is a mathematical code based on Monte Carlo simulation, and 3516 different radioactive particle positions (x,y,z) were simulated. Novelty of this paper is the use of a location algorithm based on a deep learning model, more specifically a 6-layers deep rectifier neural network (DRNN), in which hyperparameters were defined using a Bayesian optimization method. DRNN is a type of deep feedforward neural network that substitutes the usual sigmoid based activation functions, traditionally used in vanilla Multilayer Perceptron Networks, for rectified activation functions. Results show the great accuracy of the DRNN in a RPT tracking system. Root mean squared error for x, y and coordinates of the radioactive particle is, respectively, 0.03064, 0.02523 and 0.07653.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.293-296
• /
• 2021

K-water에서는 다목적댐의 관리를 위해 실시간으로 댐수위, 하천 수위 및 강우량 등을 계측하고 있으며, 계측된 값들은 댐을 효과적으로 운영하는데 필요한 데이터로 활용되고 있다. 특히 댐수위 이상 데이터를 탐지하지 못한 채 그대로 사용할 경우 댐의 방류 시기와 방류량 등을 결정하는 중요한 의사결정을 그르칠 수 있으므로 이를 신속히 탐지하는 것이 매우 중요하다. 현재의 자동화된 이상 데이터 탐지방법 중 하나는 현재 데이터가 최댓값과 최솟값을 초과할 때, 다른 하나는 현재 데이터와 일정 시간 동안의 평균값 간의 차이가 관리자가 정한 특정 값을 벗어났을 때를 기준으로 삼고 있다. 전자는 상한과 하한의 초과 여부만 판단하므로 탐지가 쉬우나 정상범위 내에서 발생한 이상 데이터는 탐지가 불가하다. 후자는 관리자의 경험을 통해 판단 조건을 정하기 때문에 객관성이 결여되는 문제가 있다. 특히 방류와 강우가 복합적으로 댐수위에 영향을 미치는 홍수기에 관리자의 경험에 기초한 이상 데이터 판별은 신뢰성의 문제가 있을 수 있다. 따라서 본 연구에서는 기계학습을 최초로 적용하여 이상 데이터를 탐지하고자 하였다. 댐수위, 누적강우량 및 누적방류량 데이터와 댐수위데이터를 가공하여 생성한 댐수위차, 댐수위차평균, 댐수위평균 등 자질들의 다양한 조합을 만든 후 이를 Random Forest, SVM, AdaptiveBoost 및 다층퍼셉트론(MLP) 등과 같은 여러 가지 기계학습모델 등을 통해 이상 데이터를 판별하는 실험(분류)을 하였다. 실험결과 댐수위, 댐수위차, 댐수위-댐수위평균, 누적강우량, 누적방류량 및 댐수위차평균을 사용하였을 때 MLP에서 가장 우수한 성능을 보였다. 이 연구를 통해서 댐수위 이상 데이터를 기계학습의 분류기능을 통해 효과적으로 탐지할 수 있다는 것과 모델의 성능은 실험에 사용한 자질의 수뿐 아니라 자질의 종류에도 큰 영향을 받는다는 것을 알 수 있었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.317-317
• /
• 2021

효율적인 물관리를 위한 댐 유입량 대한 연구는 필수적이다. 본 연구에서는 다양한 머신러닝 알고리즘을 통해 40년동안의 기상 및 댐 유입량 데이터를 이용하여 소양강댐 유입량을 예측하였으며, 그 중 고유량과 저유량예측에 적합한 알고리즘을 각각 선정하여 머신러닝 알고리즘을 결합한 CombML을 개발하였다. 의사 결정 트리 (DT), 멀티 레이어 퍼셉트론 (MLP), 랜덤 포레스트(RF), 그래디언트 부스팅 (GB), RNN-LSTM 및 CNN-LSTM 알고리즘이 사용되었으며, 그 중 가장 정확도가 높은 모형과 고유량이 아닌 경우에서 특별히 예측 정확도가 높은 모형을 결합하여 결합 머신러닝 알고리즘 (CombML)을 개발 및 평가하였다. 사용된 알고리즘 중 MLP가 NSE 0.812, RMSE 77.218 m3/s, MAE 29.034 m3/s, R 0.924, R2 0.817로 댐 유입량 예측에서 최상의 결과를 보여주었으며, 댐 유입량이 100 m3/s 이하인 경우 앙상블 모델 (RF, GB) 이 댐 유입 예측에서 MLP보다 더 나은 성능을 보였다. 따라서, 유입량이 100 m3/s 이상 시의 평균 일일 강수량인 16 mm를 기준으로 강수가 16mm 이하인 경우 앙상블 방법 (RF 및 GB)을 사용하고 강수가 16 mm 이상인 경우 MLP를 사용하여 댐 유입을 예측하기 위해 두 가지 복합 머신러닝(CombML) 모델 (RF_MLP 및 GB_MLP)을 개발하였다. 그 결과 RF_MLP에서 NSE 0.857, RMSE 68.417 m3/s, MAE 18.063 m3/s, R 0.927, R2 0.859, GB_MLP의 경우 NSE 0.829, RMSE 73.918 m3/s, MAE 18.093 m3/s, R 0.912, R2 0.831로 CombML이 댐 유입을 가장 정확하게 예측하는 것으로 평가되었다. 본 연구를 통해 하천 유황을 고려한 여러 머신러닝 알고리즘의 결합을 통한 유입량 예측 결과, 알고리즘 결합 시 예측 모형의 정확도가 개선되는 것이 확인되었으며, 이는 추후 효율적인 물관리에 이용될 수 있을 것으로 판단된다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.5
• /
• pp.761-773
• /
• 2023

This paper proposes a method to increase the power-analysis resistance of the neural network model's feedforward process by replacing the exponential-based activation function, used in the deep-learning field, with an approximated function especially at the multi-layer perceptron model. Due to its nature, the feedforward process of neural networks calculates secret weight and bias, which already trained, so it has risk of exposure of internal information by side-channel attacks. However, various functions are used as the activation function in neural network, so it's difficult to apply conventional side-channel countermeasure techniques, such as masking, to activation function(especially, to exponential-based activation functions). Therefore, this paper shows that even if an exponential-based activation function is replaced with approximated function of simple form, there is no fatal performance degradation of the model, and than suggests a power-analysis resistant feedforward neural network with exponential-based activation function, by masking approximated function and whole network.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.2 no.2
• /
• pp.69-78
• /
• 1999

In this paper, a neural network approach to forecast Korean regional precipitation is presented. We first analyze the characteristics of the conventional models for time series prediction, and then propose a new model and its learning method for the precipitation forecast. The proposed model is a layered network in which the outputs of a layer are buffered within a given period time and then fed fully connected to the upper layer. This study adopted the dual connections between two layers for the model. The network behavior and learning algorithm for the model are also described. The dual connection structure plays the role of the bias of the ordinary Multi-Layer Perceptron(MLP), and reflects the relationships among the features effectively. From these advantageous features, the model provides the learning efficiency in comparison with the FIR network, which is the most popular model for time series prediction. We have applied the model to the monthly and seasonal forecast of precipitation. The precipitation data and SST(Sea Surface Temperature) data for several decades are used as the learning pattern for the neural network predictor. The experimental results have shown the validity of the proposed model.

• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.2
• /
• pp.311-316
• /
• 2016

Network intrusion detection system based on machine learning method such as artificial neural network is quite dependent on the selected features in terms of accuracy and efficiency. Nevertheless, choosing the optimal combination of features, which guarantees accuracy and efficienty, from generally used many features to detect network intrusion requires extensive computing resources. In this paper, we deal with a optimal feature selection problem to determine 6 denial service attacks and normal usage provided by NSL-KDD data. We propose a optimal feature selection algorithm. Proposed algorithm is based on the multi-start local search algorithm, one of representative meta-heuristic algorithm for solving optimization problem. In order to evaluate the performance of our proposed algorithm, comparison with a case of all 41 features used against NSL-KDD data is conducted. In addtion, comparisons between 3 well-known machine learning methods (multi-layer perceptron., Bayes classifier, and Support vector machine) are performed to find a machine learning method which shows the best performance combined with the proposed feature selection method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.236-244
• /
• 2005

In this study, we introduce a new topology of Fuzzy Polynomial Neural Networks(FPNN) that is based on fuzzy relation and evolutionally optimized Multi-Layer Perceptron, discuss a comprehensive design methodology and carry out a series of numeric experiments. The construction of the evolutionally optimized FPNN(EFPNN) exploits fundamental technologies of Computational Intelligence. The architecture of the resulting EFPNN results from a synergistic usage of the genetic optimization-driven hybrid system generated by combining rule-based Fuzzy Neural Networks(FNN) with polynomial neural networks(PNN). FNN contributes to the formation of the premise part of the overall rule-based structure of the EFPNN. The consequence part of the EFPNN is designed using PNN. As the consequence part of the EFPNN, the development of the genetically optimized PNN(gPNN) dwells on two general optimization mechanism: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the EFPNN, the models are experimented with the use of several representative numerical examples. A comparative analysis shows that the proposed EFPNN are models with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1307-1315
• /
• 2021

The Changjiang Diluted Water (CDW) spreads over the East China Sea every summer and significantly affects the sea surface salinity changes in the seas around Jeju Island and the southern coast of Korea peninsula. Sometimes its effect extends to the eastern coast of Korea peninsula through the Korea Strait. Specifically, the CDW has a significant impact on marine physics and ecology and causes damage to fisheries and aquaculture. However, due to the limited field surveys, continuous observation of the CDW in the East China Sea is practically difficult. Many studies have been conducted using satellite measurements to monitor CDW distribution in near-real time. In this study, an algorithm for estimating Sea Surface Salinity (SSS) in the East China Sea was developed using the Geostationary Ocean Color Imager (GOCI). The Multilayer Perceptron Neural Network (MPNN) method was employed for developing an algorithm, and Soil Moisture Active Passive (SMAP) SSS data was selected for the output. In the previous study, an algorithm for estimating SSS using GOCI was trained by 2016 observation data. By comparison, the train data period was extended from 2015 to 2020 to improve the algorithm performance. The validation results with the National Institute of Fisheries Science (NIFS) serial oceanographic observation data from 2011 to 2019 show 0.61 of coefficient of determination (R²) and 1.08 psu of Root Mean Square Errors (RMSE). This study was carried out to develop an algorithm for monitoring the surface salinity of the East China Sea using GOCI and is expected to contribute to the development of the algorithm for estimating SSS by using GOCI-II.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.