Latest Research on Artificial Neural Network: Nov – 2019

Electric load forecasting using an artificial neural network

An artificial neural network (ANN) approach is given for electrical load prognostication. The ANN is employed to be told the connection among past, current and future temperatures and hundreds. so as to supply the forecasted load, the ANN interpolates among the load and temperature knowledge in a very coaching knowledge set. the typical absolute errors of the one h and twenty four h-ahead forecasts in tests on actual utility knowledge ar shown to be one.40% and 2.06%, severally. This compares with a median error of four.22% for twenty-four h ahead forecasts with a presently used prognostication technique applied to a similar knowledge. [1]

Artificial Neural Network Modeling of the Rainfall‐Runoff Process

An artificial neural network (ANN) could be a versatile mathematical structure that is capable of distinguishing complicated nonlinear relationships between input and output information sets. ANN models are found helpful and economical, significantly in issues that the characteristics of the processes are tough to explain victimization physical equations. This study presents a brand new procedure (entitled linear statistical method simplex, or LLSSIM) for distinguishing the structure and parameters of three‐layer feed forward ANN models and demonstrates the potential of such models for simulating the nonlinear hydrologic behavior of watersheds. The nonlinear ANN model approach is shown to supply a much better illustration of the rainfall‐runoff relationship of the medium‐size Leaf geographic area near Collins, Mississippi, than the linear ARMAX (autoregressive moving average with exogenous inputs) statistic approach or the abstract SAC‐SMA (Sacramento soil wet accounting) model. [2]

Hydrological modelling using artificial neural networks

This review considers the appliance of artificial neural networks (ANNs) to rainfall-runoff modelling and flood prediction. this can be associate rising field of analysis, characterised by a large sort of techniques, a diversity of geographical contexts, a general absence of intermodel comparisons, and inconsistent coverage of model ability. this text begins by outlining the essential principles of ANN modelling, common network architectures and coaching algorithms. The discussion then addresses connected themes of the division and preprocessing information|of knowledge|of information} for model calibration/validation; data standardization techniques; and strategies of evaluating ANN model performance. [3]

Artificial neural network analysis of the oxygen saturation signal enables accurate diagnostics of sleep apnea

The severity of preventative apnea (OSA) is classed mistreatment apnea-hypopnea index (AHI). correct determination of AHI presently needs manual analysis and complex registration setup creating it big-ticket and labor intensive. partly for these reasons, OSA could be a heavily underdiagnosed sickness as solely seven-membered of girls and eighteen of men littered with OSA have designation. To resolve these problems, we tend to introduce a synthetic neural network (ANN) that estimates AHI and atomic number 8 desaturation index (ODI) mistreatment solely the blood oxygen saturation signal (SpO2), recorded throughout ambulant polygraphy, as Associate in Nursing input. [4]

Modeling of Two-Phase Gas Deviation Factor for Gas-Condensate Reservoir using Artificial Neural Network

In oil engineering, reservoir fluid characterization is of nice importance. correct determination of the two-phase gas deviation issue is crucial in modeling gas-condensate and gas reservoirs, pipeline flow and reserve estimation, this can be as a result of the reservoir fluid is in an exceedingly two-phase state at pressures below the dew-point pressure. Correlations ar replete for predicting single-phase gas deviation issue victimization completely different Equation of State (EOS), however no correlation are found to accurately predict the two-phase gas deviation issue. [5]


[1] Park, D.C., El-Sharkawi, M.A., Marks, R.J., Atlas, L.E. and Damborg, M.J., 1991. Electric load forecasting using an artificial neural network. IEEE transactions on Power Systems, 6(2), (Web Link)

[2] Hsu, K.L., Gupta, H.V. and Sorooshian, S., 1995. Artificial neural network modeling of the rainfall‐runoff process. Water resources research, 31(10), (Web Link)

[3] Dawson, C.W. and Wilby, R.L., 2001. Hydrological modelling using artificial neural networks. Progress in physical Geography, 25(1), (Web Link)

[4] Artificial neural network analysis of the oxygen saturation signal enables accurate diagnostics of sleep apnea
Sami Nikkonen, Isaac O. Afara, Timo Leppänen & Juha Töyräs
Scientific Reports volume 9, Article number: 13200 (2019) (Web Link)

[5] O. Akinsete, O. and A. Omotosho, A. (2018) “Modeling of Two-Phase Gas Deviation Factor for Gas-Condensate Reservoir using Artificial Neural Network”, Advances in Research, 14(1), (Web Link)

Leave a Reply

Your email address will not be published. Required fields are marked *