Wavelets-based non-linear model for real-time daily flow forecasting in Krishna River

In this study, a multi-scale non-linear model based on coupling a discrete wavelet transform (DWT) and the second-order Volterra model, i.e. the wavelet Volterra coupled (WVC) model, is applied for daily inflow forecasting at Krishna Agraharam, Krishna River, India. The relative performance of the WVC model was compared with regular artificial neural networks (ANN), wavelet-artificial neural networks (WA-ANN) models and other baseline models such as auto-regressive moving average with exogenous variables (ARMAX) for lead times of 1–5 days. The models were applied for the forecasting of daily streamflow at Krishna Agraharam Station at Krishna River. The WVC performed very well, especially when compared with the WA-ANN model for lead times of 4 and 5 days. The results indicate that the WVC model is a promising alternative to the other traditional models for short-term flow forecasting.

Download Full-text

Modelling and Predicting Backstroke Start Performance Using Non-Linear And Linear Models

Journal of Human Kinetics ◽

10.1515/hukin-2017-0133 ◽

2018 ◽

Vol 61 (1) ◽

pp. 29-38 ◽

Cited By ~ 2

Author(s):

Karla de Jesus ◽

Helon V. H. Ayala ◽

Kelly de Jesus ◽

Leandro dos S. Coelho ◽

Alexandre I.A. Medeiros ◽

...

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Linear Model ◽

Mean Absolute Percentage Error ◽

Validation Dataset ◽

Percentage Error ◽

Start Time ◽

Absolute Percentage Error ◽

Non Linear ◽

Artificial Neural

AbstractOur aim was to compare non-linear and linear mathematical model responses for backstroke start performance prediction. Ten swimmers randomly completed eight 15 m backstroke starts with feet over the wedge, four with hands on the highest horizontal and four on the vertical handgrip. Swimmers were videotaped using a dual media camera set-up, with the starts being performed over an instrumented block with four force plates. Artificial neural networks were applied to predict 5 m start time using kinematic and kinetic variables and to determine the accuracy of the mean absolute percentage error. Artificial neural networks predicted start time more robustly than the linear model with respect to changing training to the validation dataset for the vertical handgrip (3.95 ± 1.67 vs. 5.92 ± 3.27%). Artificial neural networks obtained a smaller mean absolute percentage error than the linear model in the horizontal (0.43 ± 0.19 vs. 0.98 ± 0.19%) and vertical handgrip (0.45 ± 0.19 vs. 1.38 ± 0.30%) using all input data. The best artificial neural network validation revealed a smaller mean absolute error than the linear model for the horizontal (0.007 vs. 0.04 s) and vertical handgrip (0.01 vs. 0.03 s). Artificial neural networks should be used for backstroke 5 m start time prediction due to the quite small differences among the elite level performances.

Download Full-text

Threshold single multiplicative neuron artificial neural networks for non-linear time series forecasting

Journal of Applied Statistics ◽

10.1080/02664763.2020.1869702 ◽

2021 ◽

pp. 1-17

Author(s):

Asiye Nur Yildirim ◽

Eren Bas ◽

Erol Egrioglu

Keyword(s):

Neural Networks ◽

Time Series ◽

Artificial Neural Networks ◽

Linear Time ◽

Time Series Forecasting ◽

Non Linear ◽

Artificial Neural

Download Full-text

Over-parameterisation, a major obstacle to the use of artificial neural networks in hydrology?

Hydrology and Earth System Sciences ◽

10.5194/hess-7-693-2003 ◽

2003 ◽

Vol 7 (5) ◽

pp. 693-706 ◽

Cited By ~ 44

Author(s):

E. Gaume ◽

R. Gosset

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Conceptual Model ◽

Linear Model ◽

Case Studies ◽

Stream Flow ◽

River Flow ◽

Prediction Models ◽

Rainfall Runoff ◽

Artificial Neural

Abstract. Recently Feed-Forward Artificial Neural Networks (FNN) have been gaining popularity for stream flow forecasting. However, despite the promising results presented in recent papers, their use is questionable. In theory, their “universal approximator‿ property guarantees that, if a sufficient number of neurons is selected, good performance of the models for interpolation purposes can be achieved. But the choice of a more complex model does not ensure a better prediction. Models with many parameters have a high capacity to fit the noise and the particularities of the calibration dataset, at the cost of diminishing their generalisation capacity. In support of the principle of model parsimony, a model selection method based on the validation performance of the models, "traditionally" used in the context of conceptual rainfall-runoff modelling, was adapted to the choice of a FFN structure. This method was applied to two different case studies: river flow prediction based on knowledge of upstream flows, and rainfall-runoff modelling. The predictive powers of the neural networks selected are compared to the results obtained with a linear model and a conceptual model (GR4j). In both case studies, the method leads to the selection of neural network structures with a limited number of neurons in the hidden layer (two or three). Moreover, the validation results of the selected FNN and of the linear model are very close. The conceptual model, specifically dedicated to rainfall-runoff modelling, appears to outperform the other two approaches. These conclusions, drawn on specific case studies using a particular evaluation method, add to the debate on the usefulness of Artificial Neural Networks in hydrology. Keywords: forecasting; stream-flow; rainfall-runoff; Artificial Neural Networks

Download Full-text

Non-linear Pitch Modification in Voice Conversion Using Artificial Neural Networks

Advances in Nonlinear Speech Processing - Lecture Notes in Computer Science ◽

10.1007/978-3-642-38847-7_13 ◽

2013 ◽

pp. 97-103 ◽

Cited By ~ 2

Author(s):

Bajibabu Bollepalli ◽

Jonas Beskow ◽

Joakim Gustafson

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Voice Conversion ◽

Non Linear ◽

Artificial Neural

Download Full-text

Analysis of Cantilever Beam Deflection under Uniformly Distributed Load using Artificial Neural Networks

MATEC Web of Conferences ◽

10.1051/matecconf/201925506004 ◽

2019 ◽

Vol 255 ◽

pp. 06004

Author(s):

T.M.Y.S Tuan Ya ◽

Reza Alebrahim ◽

Nadziim Fitri ◽

Mahdi Alebrahim

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Cantilever Beam ◽

Training Data ◽

Beam Deflection ◽

Problem Solver ◽

Distributed Load ◽

Uniformly Distributed Load ◽

Non Linear ◽

Artificial Neural

In this study the deflection of a cantilever beam was simulated under the action of uniformly distributed load. The large deflection of the cantilever beam causes the non-linear behavior of beam. The prupose of this study is to predict the deflection of a cantilever beam using Artificial Neural Networks (ANN). The simulation of the deflection was carried out in MATLAB by using 2-D Finite Element Method (FEM) to collect the training data for the ANN. The predicted data was then verified again through a non linear 2-D geometry problem solver, FEM. Loads in different magnitudes were applied and the non-linear behaviour of the beam was then recorded. It was observed that, there is a close agreement between the predicted data from ANN and the results simulated in the FEM.

Download Full-text

Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals

Sensors ◽

10.3390/s110201721 ◽

2011 ◽

Vol 11 (2) ◽

pp. 1721-1743 ◽

Cited By ~ 40

Author(s):

Birsel Ayrulu-Erdem ◽

Billur Barshan

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Classification Accuracy ◽

Discrete Wavelet ◽

Daubechies Wavelet ◽

Motion Classification ◽

Artificial Neural ◽

Leg Motion ◽

Function Selection ◽

Selection Of

We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a prototype wavelet function, selection of the wavelet type can influence the performance of wavelet-based applications significantly. We also investigate the effect of selecting different wavelet families on classification accuracy and ANN complexity and provide a comparison between them. The maximum classification accuracy of 97.7% is achieved with the Daubechies wavelet of order 16 and the reverse bi-orthogonal (RBO) wavelet of order 3.1, both with similar ANN complexity. However, the RBO 3.1 wavelet is preferable because of its lower computational complexity in the DWTdecomposition and reconstruction.

Download Full-text