• 한국도로학회논문집
• /
• 제20권2호
• /
• pp.57-65
• /
• 2018

PURPOSES : The study aims to predict the service life of national highway asphalt pavements through deep learning methods by using maintenance history data of the National Highway Pavement Management System. METHODS : For the configuration of a deep learning network, this study used Tensorflow 1.5, an open source program which has excellent usability among deep learning frameworks. For the analysis, nine variables of cumulative annual average daily traffic, cumulative equivalent single axle loads, maintenance layer, surface, base, subbase, anti-frost layer, structural number of pavement, and region were selected as input data, while service life was chosen to construct the input layer and output layers as output data. Additionally, for scenario analysis, in this study, a model was formed with four different numbers of 1, 2, 4, and 8 hidden layers and a simulation analysis was performed according to the applicability of the over fitting resolution algorithm. RESULTS : The results of the analysis have shown that regardless of the number of hidden layers, when an over fitting resolution algorithm, such as dropout, is applied, the prediction capability is improved as the coefficient of determination ($R^2$) of the test data increases. Furthermore, the result of the sensitivity analysis of the applicability of region variables demonstrates that estimating service life requires sufficient consideration of regional characteristics as $R^2$ had a maximum of between 0.73 and 0.84, when regional variables where taken into consideration. CONCLUSIONS : As a result, this study proposes that it is possible to precisely predict the service life of national highway pavement sections with the consideration of traffic, pavement thickness, and regional factors and concludes that the use of the prediction of service life is fundamental data in decision making within pavement management systems.

• 전기전자학회논문지
• /
• 제11권1호통권20호
• /
• pp.1-14
• /
• 2007

In this paper, a design of an integral augmented nonlinear optimal variable structure system(INOVSS) is presented for the prescribed output control of uncertain MIMO systems under persistent disturbances. This algorithm basically concerns removing the problems of the reaching phase and combining with the nonlinear optimal control theory. By means of an integral nonlinear sliding surface, the reaching phase is completely removed. The ideal sliding dynamics of the integral nonlinear sliding surface is obtained in the form of the nonlinear state equation and is designed by using the nonlinear optimal control theory, which means the design of the integral nonlinear sliding surface and equivalent control input. The homogeneous $2{\upsilon}(\kappa)$ form is defined in order to easily select the $2{\upsilon}$ or even $(\kappa)-form$ higher order nonlinear terms in the suggested sliding surface. The corresponding nonlinear control input is designed in order to generate the sliding mode on the predetermined transformed new surface by means of diagonalization method. As a result, the whole sliding output from a given initial state to origin is completely guaranteed against persistent disturbances. The prediction/predetermination of output is enable. Moreover, the better performance by the nonlinear sliding surface than that of the linear sliding surface can be obtained. Through an illustrative example, the usefulness of the algorithm is shown.

• Nuclear Engineering and Technology
• /
• 제53권8호
• /
• pp.2547-2555
• /
• 2021

The frequency of reactor coolant leakage is expected to increase over the lifetime of a nuclear power plant owing to degradation mechanisms, such as flow-acceleration corrosion and stress corrosion cracking. When loss of coolant accidents (LOCAs) occur, several parameters change rapidly depending on the size and location of the cracks. In this study, leak flow during LOCAs is predicted using a deep fuzzy neural network (DFNN) model. The DFNN model is based on fuzzy neural network (FNN) modules and has a structure where the FNN modules are sequentially connected. Because the DFNN model is based on the FNN modules, the performance factors are the number of FNN modules and the parameters of the FNN module. These parameters are determined by a least-squares method combined with a genetic algorithm; the number of FNN modules is determined automatically by cross checking a fitness function using the verification dataset output to prevent an overfitting problem. To acquire the data of LOCAs, an optimized power reactor-1000 was simulated using a modular accident analysis program code. The predicted results of the DFNN model are found to be superior to those predicted in previous works. The leak flow prediction results obtained in this study will be useful to check the core integrity in nuclear power plant during LOCAs. This information is also expected to reduce the workload of the operators.

• Steel and Composite Structures
• /
• 제51권4호
• /
• pp.417-440
• /
• 2024

Artificial neural networks (ANN) have been the focus of several studies when it comes to evaluating the pile's bearing capacity. Nonetheless, the principal drawbacks of employing this method are the sluggish rate of convergence and the constraints of ANN in locating global minima. The current work aimed to build four ANN-based prediction models enhanced with methods from the black hole algorithm (BHA), league championship algorithm (LCA), shuffled complex evolution (SCE), and symbiotic organisms search (SOS) to estimate the carrying capacity of piles in cold climates. To provide the crucial dataset required to build the model, fifty-eight concrete pile experiments were conducted. The pile geometrical properties, internal friction angle 𝛗 shaft, internal friction angle 𝛗 tip, pile length, pile area, and vertical effective stress were established as the network inputs, and the BHA, LCA, SCE, and SOS-based ANN models were set up to provide the pile bearing capacity as the output. Following a sensitivity analysis to determine the optimal BHA, LCA, SCE, and SOS parameters and a train and test procedure to determine the optimal network architecture or the number of hidden nodes, the best prediction approach was selected. The outcomes show a good agreement between the measured bearing capabilities and the pile bearing capacities forecasted by SCE-MLP. The testing dataset's respective mean square error and coefficient of determination, which are 0.91846 and 391.1539, indicate that using the SCE-MLP approach as a practical, efficient, and highly reliable technique to forecast the pile's bearing capacity is advantageous.

• 한국멀티미디어학회논문지
• /
• 제25권11호
• /
• pp.1572-1581
• /
• 2022

Energy conversion to renewable energy is being promoted to solve the recently serious environmental pollution problem. Solar energy is one of the promising natural renewable energy sources. Compared to other energy sources, it is receiving great attention because it has less ecological impact and is sustainable. It is important to predict power generation at a future time in order to maximize the output of solar energy and ensure the stability and variability of power. In this paper, solar power generation data and sensor data were used. Using the PCC(Pearson Correlation Coefficient) analysis method, factors with a large correlation with power generation were derived and applied to the GAM(Generalized Additive Model). And the prediction accuracy of the power generation prediction model was judged. It aims to derive efficient solar power generation in the future and improve power generation performance.

• Computers and Concrete
• /
• 제32권5호
• /
• pp.513-525
• /
• 2023

Recently, research on predicting the behavior of reinforced concrete (RC) columns using machine learning methods has been actively conducted. However, most studies have focused on predicting the ultimate strength of RC columns using a regression algorithm. Therefore, this study develops a successive machine learning process for predicting multiple nonlinear behaviors of rectangular RC columns. This process consists of three stages: single machine learning, bagging ensemble, and stacking ensemble. In the case of strength prediction, sufficient prediction accuracy is confirmed even in the first stage. In the case of displacement, although sufficient accuracy is not achieved in the first and second stages, the stacking ensemble model in the third stage performs better than the machine learning models in the first and second stages. In addition, the performance of the final prediction models is verified by comparing the backbone curves and hysteresis loops obtained from predicted outputs with actual experimental data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2853-2873
• /
• 2013

Over the last few years, one of the most common purposes of smart homes is to provide human centric services in the domain of u-healthcare by analyzing inhabitants' daily living. Currently, the major challenges in activity recognition include the reliability of prediction of each classifier as they differ according to smart homes characteristics. Smart homes indicate variation in terms of performed activities, deployed sensors, environment settings, and inhabitants' characteristics. It is not possible that one classifier always performs better than all the other classifiers for every possible situation. This observation has motivated towards combining multiple classifiers to take advantage of their complementary performance for high accuracy. Therefore, in this paper, a method for activity recognition is proposed by optimizing the output of multiple classifiers with Genetic Algorithm (GA). Our proposed method combines the measurement level output of different classifiers for each activity class to make up the ensemble. For the evaluation of the proposed method, experiments are performed on three real datasets from CASAS smart home. The results show that our method systematically outperforms single classifier and traditional multiclass models. The significant improvement is achieved from 0.82 to 0.90 in the F-measures of recognized activities as compare to existing methods.

• 한국정보통신학회논문지
• /
• 제2권3호
• /
• pp.335-341
• /
• 1998

본 논문에서는 CS-ACELP(Conjugate Structure Algebraic Code Excited Linear prediction) 음성부호화기의 실시간 구현에 관하여 논한다. CS-ACELP 알고리즘은 ITU-T에서 G.729로 표준화되었다. CS-ACELP 음성부호화 알고리즘의 실시간 구현은 16비트 정수형 DSP 칩을 사용하였다. 16비트 정수형 DSP 칩상에 구현하기 위하여, CS-ACELP 알고리즘의 정수형 시뮬레이션을 사용하였다. CS-ACELP 음성부호화기에 포함된 입출력기능과 통신 기능을 설명한다. DSP Evaluation board를 사용하여 CS-ACELP 음성부호화기를 개발하였고 IMT-2000 Test-bed를 사용하여 검증하였다.

• Earthquakes and Structures
• /
• 제17권3호
• /
• pp.307-315
• /
• 2019

Building prediction and control theory have been drawing the attention of many scientists over the past few years because design and control efficiency consumes the most financial and energy. In the literature, many methods have been proposed to achieve this goal by trying different control theorems, but all of these methods face some problems in correctly solving the problem. The Evolutionary Bat (EB) Algorithm is one of the recently introduced optimization methods and providing researchers to solve different types of optimization problems. This paper applies EB to the optimization of building control design. The optimized parameter is the input to the fuzzy controller, which gives the status response as an output, which in turn changes the state of the associated actuator. The novel control criterion for guarantee of the stability of the system is also derived for the demonstration in the analysis. This systematic and simplified controller design approach is the contribution for solving complex dynamic engineering system subjected to external disturbances. The experimental results show that the method achieves effective results in the design of closed-loop system. Therefore, by establishing the stability of the closed-loop system, the behavior of the closed-loop building system can be precisely predicted and stabilized.

• 터널과지하공간
• /
• 제13권6호
• /
• pp.434-443
• /
• 2003

본 연구에서는 비서형 모델에 적용 가능한 역전파 알고리즘을 이용하여 도로터널에서 발생하는 오염물질을 예측하기 위한 인공신경망을 개발하였다. 도로 터널에서 중요시되는 오염인자는 CO농도와 가시도이므로, 인공신경망의 구성을 각각의 독립적인 네트워크로서 구성하였다. 사용한 입력데이터는 영동고속도로에 위치한 종류식 환기 방식을 채택한 일방향 2차선 도로 터널 2개소에서 실측한 데이터를 사용하였다. 예측치와 실측치를 비교할 때 인공신경망의 학습도는 약 95%의 정확성을 보이는 것으로 나타났다. 분석결과 개발된 인공신경망에 의한 결과는 PIARC 방식에 의한 계산치 보다 약 5배 정도의 정확성을 보였다. 특히 주행속도가 낮을 경우 더 높은 정확도를 나타낼 것으로 기대 되었다.