• 전기학회논문지
• /
• 제66권4호
• /
• pp.621-628
• /
• 2017

This paper presents an artificial neural network (ANN) based model with a back-propagation algorithm for short-term load forecasting in microgrid power systems. Owing to the significant weather factors for such purpose, relevant input variables were selected in order to improve the forecasting accuracy. As remarked above, forecasting is more complex in a microgrid because of the increased variability of disaggregated load curves. Accurate forecasting in a microgrid will depend on the variables employed and the way they are presented to the ANN. This study also shows numerically that there is a close relationship between forecast errors and the number of training patterns used, and so it is necessary to carefully select the training data to be employed with the system. Finally, this work demonstrates that the concept of load forecasting and the ANN tools employed are also applicable to the microgrid domain with very good results, showing that small errors of Mean Absolute Percentage Error (MAPE) around 3% are achievable.

• Structural Engineering and Mechanics
• /
• 제70권6호
• /
• pp.671-681
• /
• 2019

This paper examines the applicability of artificial neural network (ANN) and multivariate adaptive regression splines (MARS) to predict the compressive strength of bacteria incorporated geopolymer concrete (GPC). The mix is composed of new bacterial strain, manufactured sand, ground granulated blast furnace slag, silica fume, metakaolin and fly ash. The concentration of sodium hydroxide (NaOH) is maintained at 8 Molar, sodium silicate ($Na_2SiO_3$) to NaOH weight ratio is 2.33 and the alkaline liquid to binder ratio of 0.35 and ambient curing temperature ($28^{\circ}C$) is maintained for all the mixtures. In ANN, back-propagation training technique was employed for updating the weights of each layer based on the error in the network output. Levenberg-Marquardt algorithm was used for feed-forward back-propagation. MARS model was developed by establishing a relationship between a set of predictors and dependent variables. MARS is based on a divide and conquers strategy partitioning the training data sets into separate regions; each gets its own regression line. Six models based on ANN and MARS were developed to predict the compressive strength of bacteria incorporated GPC for 1, 3, 7, 28, 56 and 90 days. About 70% of the total 84 data sets obtained from experiments were used for development of the models and remaining 30% data was utilized for testing. From the study, it is observed that the predicted values from the models are found to be in good agreement with the corresponding experimental values and the developed models are robust and reliable.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.382-388
• /
• 2022

Satellite communication for high altitude platform stations (HAPS) and low earth orbit (LEO) systems suffer from dust and sand (DU&SA) storms in the desert regions such as Saudi Arabia. These attenuations have a distorting effect on signal fidelity at high frequency of operations. This results signal to noise ratio (SNR) to dramatically decreasing and leads to wireless transmission error. The main focus in this paper is to propose common relations between HAPS and LEO for the atmospheric impairments affecting the satellite communication networks operating above Ku-band crossing the propagation path. A double phase three dimensional relationship for HAPS and LEO systems is then presented. The comparison model present the analysis of atmospheric attenuation with specific focus on sand and dust based on particular size, visibility, adding gaseous effects for different frequency, and propagation angle to provide system operations with a predicted vision of satellite parameters' values. Skillful decision and control system (SD&CS) is proposed to control applied parameters that lead to improve satellite network performance and to get the ultimate receiving wireless signal under bad weather condition.

• Computers and Concrete
• /
• 제29권 6호
• /
• pp.433-444
• /
• 2022

Concrete's compressive strength is widely studied in order to understand many qualities and the grade of the concrete mixture. Conventional civil engineering tests involve time and resources consuming laboratory operations which results in the deterioration of concrete samples. Proposing efficient non-destructive models for the prediction of concrete compressive strength will certainly yield advancements in concrete studies. In this study, the efficiency of using radial basis function neural network (RBFNN) which is not common in this field, is studied for the concrete compressive strength prediction. Complementary studies with back propagation neural network (BPNN), which is commonly used in this field, have also been carried out in order to verify the efficiency of RBFNN for compressive strength prediction. A total of 13 input parameters, including novel ones such as cement's and fly ash's compositional information, have been employed in the prediction models with RBFNN and BPNN since all these parameters are known to influence concrete strength. Three different train: test ratios were tested with both models, while different hidden neurons, epochs, and spread values were introduced to determine the optimum parameters for yielding the best prediction results. Prediction results obtained by RBFNN are observed to yield satisfactory high correlation coefficients and satisfactory low mean square error values when compared to the results in the previous studies, indicating the efficiency of the proposed model.

• Geomechanics and Engineering
• /
• 제29권4호
• /
• pp.435-449
• /
• 2022

In this paper, unreinforced and geogrid-reinforced soil foundations were modeled by discrete element method and this performed under surface strip footing loads. The effects of horizontal position of geogrid, vertical position, thickness, number, confining pressure have been investigated on the footing settlement and propagation of tensile force along the geogrids. Also, interaction between rectangular tunnel and strip footing with and without presence of geogrid layer has been analyzed. Experimental results of the literature were used to validation of relationships between the numerically achieved footing pressure-settlement for foundations of reinforced and unreinforced soil. Models and micro input parameters which used in the numerical modelling of reinforced and unreinforced soil tunnel were similar to parameters which were used in soil foundations. Model dimension was 1000 mm* 600 mm. Normal and shear stiffness of soils were 5*10⁵ and 2.5 *10⁵ N/m, respectively. Normal and shear stiffness of geogrid were 1*10⁹ and 1*10⁹ N/m, respectively. Loading rate was 0.001 mm/sec. Micro input parameters used in numerical simulation gain by try and error. In addition of the quantitative tensile force propagation along the geogrids, the footing settlements were visualized. Due to collaboration of three layers of geogrid reinforcements the bearing capacity of the reinforced soil tunnel was greatly improved. In such practical reinforced soil formations, the qualitative displacement propagations of soil particles in the soil tunnel and the quantitative vertical displacement propagations along the soil layers/geogrids represented the geogrid reinforcing impacts too.

• 한국구조물진단유지관리공학회 논문집
• /
• 제10권2호
• /
• pp.133-144
• /
• 2006

FRP 판은 외부 부착된 보강 판의 효과적인 부착강도의 증진으로 실질적으로 부착강도에 대한 많은 연구가 수행되어왔다. 선행연구자들은 이러한 부착강도를 알아보기 위하여 다양한 변수를 설정하여 실험을 통하여 FRP 판의 부착강도를 규명하였다. 그러나, 이러한 부착강도를 알아보기 위한 실험은 장비구축의 비용과 시간 소비가 많이 되고 수행하기 어렵기 때문에 국한적으로 수행되고 있다. 본 연구는 선행연구자들의 부착실험 데이터를 다양한 신경망 모형과 알고리즘을 적용하여 최적의 인공신경망 모형을 개발하는데 그 목적이 있다. 인공신경망 모형의 출력층은 부착강도, 입력층은 FRP 판의 두께, 폭, 부착 길이, 탄성계수, 인장강도와 콘크리트의 압축강도, 인장강도, 폭을 변수로 선정하여 학습을 수행하였다. 개발된 인공신경망 모형은 역전파 학습 알고리즘을 적용하였으며, 오차는 0.001범위에 수렴되도록 학습을 하였다. 또한, 일반화 과정은 Bayesian 기법을 도입함으로써 보다 일반화된 방법으로 과대적합의 문제를 해소하였다. 개발된 모형의 검증은 학습에 이용되지 않은 다른 선행연구자들의 부착강도 결과 값과 비교함으로서 실시하였다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권8호
• /
• pp.442-450
• /
• 2000

Active noise control is an approach to noise reduction in which a secondary noise source that destructively interferes with the unwanted noise. In general, active noise control systems rely on multiple sensors to measure the unwanted noise field and the effect of the cancellation. This paper develops an approach that utilizes a single sensor. The noise field is modeled as a stochastic process, and a time-adaptive algorithm is used to adaptively estimate the parameters of the process. Based on these parameter estimates, a canceling signal is generated. Opppenheim model assumed that transfer function characteristics from the canceling source to the error sensor is only propagation delay. But this paper proposes a modified Oppenheim model by considering transfer characteristics of acoustic device and noise path. This transfer characteristics is adaptively cancelled by adaptive model. This is proved by computer simulation with artifically generated random noise and sine wave noise. The details of the proposed architecture, and theoretical simulation and experimental results of the noise cancellation system for three dimension enclosure are presented in the paper.

• Animal cells and systems
• /
• 제16권2호
• /
• pp.121-126
• /
• 2012

In this study, a neural network (NN) modeling approach has been used to predict the mechanical and geometrical behaviors of mouse embryo cells. Two NN models have been implemented. In the first NN model dimple depth (w), dimple radius (a) and radius of the semi-circular curved surface of the cell (R) were used as inputs of the model while indentation force (f) was considered as output. In the second NN model, indentation force (f), dimple radius (a) and radius of the semi-circular curved surface of the cell (R) were considered as inputs of the model and dimple depth was predicted as the output of the model. In addition, sensitivity analysis has been carried out to investigate the influence of the significance of input parameters on the mechanical behavior of mouse embryos. Experimental data deduced by Fl$\ddot{u}$ckiger (2004) were collected to obtain training and test data for the NN. The results of these investigations show that the correlation values of the test and training data sets are between 0.9988 and 1.0000, and are in good agreement with the experimental observations.

• Journal of Information Technology Applications and Management
• /
• 제19권1호
• /
• pp.1-12
• /
• 2012

Data mining is the process of searching and analyzing large quantities of data for finding out meaningful patterns and rules. Artificial Neural Network (ANN) is one of the tools of data mining which is becoming very popular in forecasting the future values. Some of the areas where it is used are banking, medicine, retailing and fraud detection. In finance, artificial neural network is used in various disciplines including stock market forecasting. In the stock market time series, due to high volatility, it is very important to choose a model which reads volatility and forecasts the future values considering volatility as one of the major attributes for forecasting. In this paper, an attempt is made to develop two models - one using feed forward back propagation Artificial Neural Network and the other using Autoregressive Conditional Heteroskedasticity (ARCH) technique for forecasting stock market returns. Various parameters which are considered for the design of optimal ANN model development are input and output data normalization, transfer function and neuron/s at input, hidden and output layers, number of hidden layers, values with respect to momentum, learning rate and error tolerance. Simulations have been done using prices of daily close of Sensex. Stock market returns are chosen as input data and output is the forecasted return. Simulations of the Model have been done using MATLAB$^{(R)}$ 6.1.0.450 and EViews 4.1. Convergence and performance of models have been evaluated on the basis of the simulation results. Performance evaluation is done on the basis of the errors calculated between the actual and predicted values.

• 전자공학회논문지B
• /
• 제33B권1호
• /
• pp.144-152
• /
• 1996

대규모 병렬처리가 가능하고 칩당 뉴론 집적도가 높은 펄스형 디지털 다계층 신경망 구조를 제안하였다. 제안된 신경망에서는 대수적인 신경망연산이 의사-랜덤 펄스 시퀀스(pseudo-random pulse sequences)와 단순 디지털 논리 게이트를 이용하여 확률적 프로세스로 대치되었다. 확률적 프로세스의 결과로 나타나는 신경망 연산의 통계적 모델을 제시하였으며 이를 바탕으로 랜덤잡음의 영향과 연산의 정확도를 분석하였다. 이진인식 문제를 적용하여 제안된 신경망의 성능을 평가하고 제시한 통계적 분석결과의 정당성을 검증하였다. Gate 레벨과 register transfer 레벨로 기술된 신경망의 VHDL 모델의 시뮬레이션 결과는 개발된 통계적모델로 예측된 인식추정치와 실제 인식률이 거의 일치함을 보였으며, 또한 숫자인식률에 있어서도 일반 Back-Propagation 신경망의 인식률과 거의 차이가 없음을 보였다.