Principal Component Analysis (Pca) for Estimating Chlorophyll Concentration Using Forward and Generalized Regression Neural Networks

Zounemat‐Kermani, Mohammad

doi:10.1080/08839514.2014.862771

Cited by 23 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using Principal Components Analysis (PCA) the selection of ANN’s input parameters is done [ 35 , 36 ]. PCA is often combined with ANN modelling, because by that way dimension reduction is enabled and the model’s computational complexity is reduced, so the possibility of a model’s misconvergence and poor accuracy is eliminated [ 37 ].…”

Section: Methodsmentioning

confidence: 99%

Assessing the Contribution of the Environmental Parameters to Eutrophication with the Use of the “PaD” and “PaD2” Methods in a Hypereutrophic Lake

Hadjisolomou

Stefanidis

Papatheodorou

et al. 2016

IJERPH

View full text Add to dashboard Cite

Lake Pamvotis (Greece) is a shallow hypereutrophic lake with a natural tendency to eutrophication. Several restoration measures were applied, but with no long-term success. To examine the causes for this an Artificial Neural Network (ANN) was created in order to simulate the chlorophyll-a (Chl-a) levels and to investigate the role of the associated environmental parameters. The ANN managed to simulate with good correlation the simulated Chl-a and can be considered as a reliable predictor. The relative importance of the environmental parameters to the simulated Chl-a was calculated with the use of the “Partial Derivatives” (“PaD”) sensitivity method. The water temperature (WT) and soluble reactive phosphorus (SRP) had the highest relative importance, with values of 50% and 17%, respectively. The synergistic effect of the paired parameters was calculated with the use of the “PaD2” algorithm. The SRP-WT paired parameter was the most influential, with a relative contribution of 22%. The ANN showed that Lake Pamvotis is prone to suffer the effects of climatic change, because of the major contribution of WT. The ANN also revealed that combined nutrients reduction would improve water quality status. The ANN findings can act as an advisory tool regarding any restoration efforts.

show abstract

Section: Methodsmentioning

confidence: 99%

Assessing the Contribution of the Environmental Parameters to Eutrophication with the Use of the “PaD” and “PaD2” Methods in a Hypereutrophic Lake

Hadjisolomou

Stefanidis

Papatheodorou

et al. 2016

IJERPH

View full text Add to dashboard Cite

show abstract

“…The generalized regression neural network (GRNN), as a modified form of the RBFNN, was proposed by Specht (1991). The GRNN approximates any arbitrary function between the input and output variables, drawing the function estimate directly from the training data (Zounemat-Kermani, 2014). Like the RBFNN, this network does not require an iterative procedure.…”

Section: Generalized Regression Neural Networkmentioning

confidence: 99%

Geoid undulation prediction using Gaussian Processes Regression: A case study in a local region in Turkey

Konakoǧlu¹

2021

Acta Geodynamica Et Geomaterialia

View full text Add to dashboard Cite

In order to convert ellipsoidal heights obtained by the Global Navigation Satellite System (GNSS) to orthometric heights, it is necessary to know the distance between the ellipsoidal and geoid surface, called the geoid undulation. The geoid undulation can be predicted using emerging mathematics tools and algorithms. The objective of this study was to develop a model for predicting the geoid undulation using Gaussian Process Regression (GPR), one of the soft machine learning algorithms having different covariance functions. This method was then compared with the radial basis function neural network (RBFNN), generalized regression neural network (GRNN), and the interpolation method of inverse distance to a power (IDP) with the power of 1, 2, 3, 4, and 5. First, 70 % of GNSS/leveling data (422 points) were used in the training phase. The remaining 185 points were used as testing data to check the effectiveness of the constructed model. In the GPR modeling, ten covariance functions (Materniso d= 1, 3, 5; Maternard d= 1, 3, 5; SEiso; SEard; RQiso; and RQard) were tested for prediction on this dataset. The GPR based on the Materniso (d = 1) covariance function model was introduced as an effective method for predicting geoid undulation and provided the best results (RMSE = 8.32 cm, MAE = 5.51 cm, R 2 = 0.98968) when compared with the other developed GPR models. In addition, the statistical findings showed that the accuracy of all the GPR models was also better in predicting geoid undulation than the RBFNN, GRNN, and IDP with the power of 1, 2, 3, 4, and 5.

show abstract

“…The number of the rest is 500, defined as the testing set. We preset the learning rate and the maximum training cycle by referring to [ 21 , 29 , 30 ]; then we have done the experiment repeatedly on the training set of different index data; different numbers of neural nodes in the hidden layer are chosen as the optimal; see Table 1 . The maximum training iterations number K is 300, different dataset has different learning rate η , and, here, after many times experiments of the training data we choose 0.001, 0.001, 0.05, and 0.01 for SSE, TWSE, KOSPI, and Nikkei225, respectively.…”

Section: Forecasting and Statistical Analysis Of Stock Pricementioning

confidence: 99%

“…r” stands for learning rate. The hidden number is also chosen by referring to [ 21 , 29 , 30 ]. The experiments have been done repeatedly to determine hidden nodes and training cycle in the training process.…”

Section: Forecasting and Statistical Analysis Of Stock Pricementioning

confidence: 99%

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks

Wang

Wen

et al. 2016

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.

show abstract

Principal Component Analysis (Pca) for Estimating Chlorophyll Concentration Using Forward and Generalized Regression Neural Networks

Cited by 23 publications

References 16 publications

Assessing the Contribution of the Environmental Parameters to Eutrophication with the Use of the “PaD” and “PaD2” Methods in a Hypereutrophic Lake

Assessing the Contribution of the Environmental Parameters to Eutrophication with the Use of the “PaD” and “PaD2” Methods in a Hypereutrophic Lake

Geoid undulation prediction using Gaussian Processes Regression: A case study in a local region in Turkey

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks

Contact Info

Product

Resources

About