• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.35-35
• /
• 2019

본 연구에서는 분포형 수문 모형 Drying Stream Assessment Tool and Water Flow Tracking (DrySAT-WTF)을 활용해 우리나라의 1976년부터 2015년까지의 유출량을 산정하고, 이를 다층퍼셉트론(Multi Layer Perceptron) 인경신경망 모형(Artificial Neural Network Model)에 적용해 미래 유출을 예측하였다. DrySAT-WFT은 전국 표준 유역을 대상으로 하천 건천화 원인 추적 및 평가를 위해 개발된 모형으로 유출모의를 위한 기상자료 외에 건천화 영향 요소를 고려하기 위한 산림 높이, 도로망, 지하수 이용량, 토지이용, 토심 변화에 대한 DB를 적용 가능한 것이 특징이다. DrySAT-WFT를 위한 기상자료로 모의 기간에 대한 일별 강우량, 상대습도, 평균풍속, 평균 및 최고, 최저 기온, 일조시간을 구축하였으며, 연대별 건천화 영향 요소 DB를 구축하여 적용하였다. 전국 다목적 댐 보 12지점의 유량을 활용해 모형의 보정(2005-2010) 및 검증(2011-2015)을 실시한 결과, 평균 결정계수(Coefficient of determination, $R^2$)는 0.76, 모형효율성계수(Nash-Sutcliffe efficiency, NSE)는 0.62, 평균제곱근오차(average root mean square error, RMSE)는 3.09로 신뢰성 있는 유출 모의 결과를 나타내었다. 미래 유출량 예측을 위한 MLP-ANN은 1976년부터 2015년까지의 유출 모의 결과를 Training Set으로 훈련하여 $R^2$가 0.5 이상이 되어 신뢰성을 확보하였고, 2016년부터 2018년까지의 기간을 1개월 단위로 실제 유출량과 예측 유출량을 비교하며 적용성을 검증 및 향상시켰다.

• Wind and Structures
• /
• v.2 no.1
• /
• pp.25-40
• /
• 1999

In this paper, artificial neural networks, a new kind of intelligent method, are employed to model and predict amplitude dependent damping in buildings based on our full-scale measurements of buildings. The modelling method and procedure using neural networks to model the damping are studied. Comparative analysis of different neural network models of damping, which includes multi-layer perception network (MLP), recurrent neural network, and general regression neural network (GRNN), is performed and discussed in detail. The performances of the models are evaluated and discussed by tests and predictions including self-test, "one-lag" prediction and "multi-lag" prediction of the damping values at high amplitude levels. The established models of damping are used to predict the damping in the following three ways : (1) the model is established by part of the data measured from one building and is used to predict the another part of damping values which are always difficult to obtain from field measurements : the values at the high amplitude level. (2) The model is established by the damping data measured from one building and is used to predict the variation curve of damping for another building. And (3) the model is established by the data measured from more than one buildings and is used to predict the variation curve of damping for another building. The prediction results are discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2168-2187
• /
• 2021

The smart grid replaces the traditional power structure with information inventiveness that contributes to a new physical structure. In such a field, malicious information injection can potentially lead to extreme results. Incorrect, FDI attacks will never be identified by typical residual techniques for false data identification. Most of the work on the detection of FDI attacks is based on the linearized power system model DC and does not detect attacks from the AC model. Also, the overwhelming majority of current FDIA recognition approaches focus on FDIA, whilst significant injection location data cannot be achieved. Building on the continuous developments in deep learning, we propose a Deep Learning based Locational Detection technique to continuously recognize the specific areas of FDIA. In the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN). The FDD is established enough to catch the fake information. As a multi-label classifier, the following CNN is utilized to evaluate the irregularity and cooccurrence dependency of power flow calculations due to the possible attacks. There are no earlier statistical assumptions in the architecture proposed, as they are "model-free." It is also "cost-accommodating" since it does not alter the current FDD framework and it is only several microseconds on a household computer during the identification procedure. We have shown that ANN-MLP, SVM-RBF, and CNN can conduct locational detection under different noise and attack circumstances through broad experience in IEEE 14, 30, 57, and 118 bus systems. Moreover, the multi-name classification method used successfully improves the precision of the present identification.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.601-612
• /
• 2022

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• Geomechanics and Engineering
• /
• v.28 no.5
• /
• pp.505-520
• /
• 2022

In recent years, geotextile-encased gravel columns (usually called stone columns) have become a popular method to increasing soil shear strength, decreasing the settlement, acceleration of the rate of consolidation, reducing the liquefaction potential and increasing the bearing capacity of foundations. The behavior of improved loose base-soil with gravel columns under shear loading and the shear stress-horizontal displacement curves got from large scale direct shear test are of great importance in understanding the performance of this method. In the present study, by performing 36 large-scale direct shear tests on sandy base-soil with different fine-content of zero to 30% in both not improved and improved with gravel columns, the effect of the presence of gravel columns in the loose soils were investigated. The results were used to predict the shear stress-horizontal displacement curve of these samples using support vector machines (SVM). Variables such as the non-plastic fine content of base-soil (FC), the area replacement ratio of the gravel column (Arr), the geotextile encasement and the normal stress on the sample were effective factors in the shear stress-horizontal displacement curve of the samples. The training and testing data of the model showed higher power of SVM compared to multilayer perceptron (MLP) neural network in predicting shear stress-horizontal displacement curve. After ensuring the accuracy of the model evaluation, by introducing different samples to the model, the effect of different variables on the maximum shear stress of the samples was investigated. The results showed that by adding a gravel column and increasing the Arr, the friction angle (ϕ) and cohesion (c) of the samples increase. This increase is less in base-soil with more FC, and in a proportion of the same Arr, with increasing FC, internal friction angle and cohesion decreases.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.855-867
• /
• 2022

As the need for a deep learning accelerator increases with the development of IoT equipment, research on the implementation and safety verification of the deep learning accelerator is actively. In this paper, we propose a new side channel analysis methodology for secret information that overcomes the limitations of the previous study in Usenix 2019. We overcome the disadvantage of limiting the range of weights and restoring only a portion of the weights in the previous work, and restore the IEEE754 32bit single-precision with 99% accuracy with a new method using CPA. In addition, it overcomes the limitations of existing studies that can reverse activation functions only for specific inputs. Using deep learning, we reverse activation functions with 99% accuracy without conditions for input values with a new method. This paper not only overcomes the limitations of previous studies, but also proves that the proposed new methodology is effective.

• Computers and Concrete
• /
• v.32 no.3
• /
• pp.327-337
• /
• 2023

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1611-1633
• /
• 2022

At EUROCRYPT 2019, a new block cipher algorithm called BISON was proposed by Canteaut et al. which uses a novel structure named as Whitened Swap-Or-Not (WSN). Unlike the traditional wide trail strategy, the differential and linear properties of this algorithm can be easily determined. However, the encryption speed of the BISON algorithm is quite low due to a large number of iterative rounds needed to ensure certain security margins. Commonly, denoting by n is the data block length, this design requires 3n encryption rounds. Moreover, the block size n of BISON is always odd, which is not convenient for operations performed on a byte level. In order to overcome these issues, we propose a new block cipher, named DBISON, which more efficiently employs the ideas of double layers typical to the BISON-like construction. More precisely, DBISON divides the input into two parts of size n/2 bits and performs the round computations in parallel, which leads to an increased encryption speed. In particular, the data block length n of DBISON can be even, which gives certain additional implementation benefits over BISON. Furthermore, the resistance of DBISON against differential and linear attacks is also investigated. It is shown the maximal differential probability (MDP) is 1/2^n-1 for n encryption rounds and that the maximal linear probability (MLP) is strictly less than 1/2^n-1 when (n/2+3) iterative encryption rounds are used. These estimates are very close to the ideal values when n is close to 256.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.179-186
• /
• 2023

For the future prosperity of any society, the sound growth of children is essential. Autism Spectrum Disorder (ASD) is a neurobehavioral disorder which has an impact on social interaction of autistic child and has an undesirable effect on his learning, speaking, and responding skills. These children have over or under sensitivity issues of touching, smelling, and hearing. Its symptoms usually appear in the child of 4- to 11-year-old but parents did not pay attention to it and could not detect it at early stages. The process to diagnose in recent time is clinical sessions that are very time consuming and expensive. To complement the conventional method, machine learning techniques are being used. In this way, it improves the required time and precision for diagnosis. We have applied TFLite model on image based dataset to predict the autism based on facial features of child. Afterwards, various machine learning techniques were trained that includes Logistic Regression, KNN, Gaussian Naïve Bayes, Random Forest and Multi-Layer Perceptron using Autism Spectrum Quotient (AQ) dataset to improve the accuracy of the ASD detection. On image based dataset, TFLite model shows 80% accuracy and based on AQ dataset, we have achieved 100% accuracy from Logistic Regression and MLP models.