Study on Optimized Elman Neural Network Classification Algorithm Based on PLS and CA

The Sixth International Symposium on Neural Networks (ISNN 2009)

Non-linear projection to latent structures revisited (the neural network PLS algorithm)

Principal component analysis (PCA) and the non-hierarchical clustering analysis (K-means) were used to characterize the most important variables from carcass and meat quality traits of crossbred cattle. Additionally, partial least square (PLS) regression analysis was applied between the carcass measurements and meat quality traits on the classes defined by the cluster analysis. Ninety-seven non-castrated F1 Angus-Nellore bulls feedlot finished were used. After slaughter, hot carcass weight, carcass yield, cold carcass weight, carcass weight losses, pH, and backfat thickness (BFT) were measured. Subsequently, samples of the longissimus thoracis were collected to analyze shear force (SF), cooking loss (CL), meat color (L*, chroma, and hue), intramuscular fat, protein, collagen, moisture, and ashes. Principal component 1 (PC1) was correlated with colorimetric variables, while PC2 was correlated with carcass weights. Afterwards, three clusters (k = 3) were formed and projected in the gradient defined by PC1 and PC2 and allowed distinguishing groups with divergent values for collagen, protein, moisture, CL, SF, and BFT. Animals from high chroma group presented meat with more attractive colors and tenderness (SF = 1.97 to 4.84kg). Subsequently, the PLS regression on the three chroma groups revealed a good fitness and the coefficients are used to predict the chroma variable from the explanatory variables, which may have practical importance in attempts to predict meat color from carcass and meat quality traits. Thus, PCA, K-means, and PLS regression confirmed the relationship between meat color and tenderness.

In order to estimate daily solar radiation, this paper proposes Elman (ENN) and Feed forward backpropagation (FNN) neural networks. The time series data from the location of Kenitra City, Morocco is used to train the created models. Fletcher-Powell Conjugate Gradient (CGF), Scaled Conjugate Gradient (SCG), Resilient Backpropagation (RB), Conjugate gradient with Powell-Beale restarts (CGB), Levenberg-Marquardt (LM), Polak-Ribi´ere Conjugate Gradient (CGP), and One Step Secant (OSS) are also used with both, the ENN and FNN to identify the best and effective training function for each. The models with various training algorithms are tested by using evaluation metrics root mean square error (RMSE), mean square error (MSE) and mean absolute error (MAE). The study showed that the Elman Neural Network had an excellent daily solar radiation prediction for Kenitra city. Good results have been obtained with Levenberg-Marquardt algorithm.

Short-term power load forecasting based on Elman neural network with particle swarm optimization

Knowledge base operator support system for nuclear power plant fault diagnosis

Artificial neural networks (ANNs) and partial least squares (PLS) regression in the quantitative analysis of cocrystal formulations by Raman and ATR-FTIR spectroscopy

Accurate estimation of the state of charge (SOC) of lithium batteries is the research hotspot. As a dynamic recurrent neural network, Elman neural network has a simple structure and can adapt to time-varying characteristics, which have led to its widespread application in the field of SOC prediction. However, the simple network structure can also cause problems such as low learning efficiency, easy to fall into local extremes, and difficulty converge to the optimal weight solution. This paper proposes to combine the whale optimization algorithm (WOA) with genetic algorithm (GA) to optimize the weights and thresholds of the Elman neural network, thus improving the learning speed and prediction accuracy. We select three parameters of current, voltage and temperature as system variables, and simulate the experimental data. The experimental results show that, compared with the traditional Elman neural network and the Elman neural network optimized only by genetic algorithm, the hybrid algorithm performs best. The number of network iterations is small, and the average error drops below 1%.

As an important tumor suppressor protein, reactivating mutated p53 was found in many kinds of human cancers and that restoring active p53 would lead to tumor regression. In recent years, more and more data extracted from biophysical simulations, which makes the modelling of mutant p53 transcriptional activity suffering from the problems of huge amount of instances and high feature dimension. Incremental feature extraction is effective to facilitate analysis of large-scale data. However, most current incremental feature extraction methods are not suitable for processing big data with high feature dimension. Partial Least Squares (PLS) has been demonstrated to be an effective dimension reduction technique for classification. In this paper, we design a highly efficient and powerful algorithm named Incremental Partial Least Squares (IPLS), which conducts a two-stage extraction process. In the first stage, the PLS target function is adapted to be incremental with updating historical mean to extract the leading projection direction. In the last stage, the other projection directions are calculated through equivalence between the PLS vectors and the Krylov sequence. We compare IPLS with some state-of-the-arts incremental feature extraction methods like Incremental Principal Component Analysis, Incremental Maximum Margin Criterion and Incremental Inter-class Scatter on real p53 proteins data. Empirical results show IPLS performs better than other methods in terms of balanced classification accuracy.

Objective. Partial Least Squares (PLS) regression is a suitable linear decoder model for correlated and high dimensional neural data. This algorithm has been widely used in the application of brain–computer interface (BCI) for the decoding of motor parameters. PLS does not consider nonlinear relations between brain signal features. The nonlinear version of PLS that considers a nonlinear relationship between the latent variables has not been proposed for the decoding of intracranial data. This nonlinear model may cause overfitting in some cases due to a larger number of free parameters. In this paper, we develop a new version of nonlinear PLS, namely nonlinear sparse PLS (NLS PLS) and test it in BCI applications. Approach. In motor related BCI systems, improving the decoding accuracy of both kinetic and kinematic parameters of movement is crucial. To do this, two BCI datasets were chosen to decode the force amplitude and position of hand trajectory using the nonlinear and sparse versions of PLS algorithm. In our new NLS PLS method, we considered a polynomial relationship between the latent variables and used the lasso penalization in the latent space to avoid overfitting and to improve the decoding accuracy. Main results. Some linear and nonlinear based PLS models and our new proposed method, NLS PLS, were applied to the two datasets. According to our results, significant improvement from the NLS PLS method is confirmed over other methods. Our results show that nonlinear PLS outperforms generic PLS in the force decoding but it has lower accuracy in the hand trajectory decoding because of high dimensional feature space. By using lasso penalization, we presented a sparse nonlinear PLS-based model that outperforms generic PLS in both datasets and improves the coefficient of determination, 34% in the force decoding and 10% in the hand trajectory decoding. Significance. We constructed a simple PLS-based model that considers a nonlinear relationship between features and it is also robust to overfitting because of using the lasso penalty in the latent space. This model is suitable for a high dimensional and correlated datasets, like intracranial data and can improve the accuracy of estimation.

Gross domestic product (GDP) can well reflect the development of the economy, and predicting GDP can help better grasp the future economic trends. In this article, three different neural network models, the genetic algorithm – back-propagation neural network model, the particle swarm optimization (PSO) – Elman neural network (Elman NN) model, and the bat algorithm – long short-term memory model, were analyzed based on neural networks. The GDP data of Sichuan province from 1992 to 2020 were collected to compare the performance of the three models in predicting GDP. It was found that the mean absolute percentage error values of the three models were 0.0578, 0.0236, and 0.0654, respectively; the root-mean-square error values were 0.0287, 0.0166, and 0.0465, respectively; and the PSO-Elman NN model had the best performance in GDP prediction. The experimental results demonstrate that neural networks were reliable in predicting GDP and can be used for further applications in practice.

Keywords: Time series estimation, Flow Estimation, Elman Neural Networks Abstract: This paper investigates the application of partially recurrent artificial neural networks (ANN) in the flow estimation for Sao Francisco River that feeds the hydroelectric power plant of Sobradinho. An Elman neural network was used suitably arranged to receive samples of the flow time series data available for Sao Francisco River shifted by one month. For that, the neural network input had a delay loop that included several sets of inputs separated in periods of five years monthly shifted. The considered neural network had three hidden layers. There is a feedback between the output and the input of the first hidden layer that enables the neural network to present temporal capabilities useful in tracking time variations. The data used in the application concern to the measured Sao Francisco river flow time series from 1931 to 1996, in a total of 65 years from what 60 were used for training and 5 for testing. The obtained results indicate that the Elman neural network is suitable to estimate the river flow for 5 year periods monthly. The average estimation error was less than 0.2 %

Fuzzy PID controller is difficult in implementation for its computational complexity. In this paper, for the dynamic modeling and parallel computation ability of Elman NN (Neural Network), the authors utilized an equivalent Elman NN to accurately approximate the dynamics of a known fuzzy PID controller. Consequently, the same process model was controlled by the fuzzy PID controller and the remodeling Elman NN, respectively. The results show that the control qualities of two different controllers were extremely similar. Thus, the fuzzy PID controller can be simplified to a remodeling Elman NN in purpose of reducing the computational complexity, solving the curse of dimensionality and improving the real-time performance.

The electric power industry is closely related to the development of national economy. With the development of economy, the social electricity situation is increasingly complicated, which brings great test to the prediction of electric load system. Accurate short-term power load forecasting plays an important role in production scheduling and safe and stable operation of power system. In this paper, Elman neural network based on genetic algorithm is established and a short-term power load forecasting model is established. The actual history data of municipal power grid are simulated, the experimental results show that compared with the BP neural network and Elman neural network commonly, Elman neural network based on genetic algorithm to solve the problem of random initial weights of the Elman neural network, can effectively enhance the power load forecasting accuracy and meet the needs of the actual production and work.

In order to solve some complex nonlinear systems in the practice application, a nonlinear function equation method based on Elman neural network is proposed. A limited number of input and output data of nonlinear function equations were used to train the Elman neural network, so that the network could express the nonlinear function. Finally, the output of nonlinear functions is predicted by using a trained neural network. The results show that the nonlinear function based on Elman neural network has a good fitting effect.