Extreme Learning Machine Neural Network Research Articles

Prediction of permeability of various geotechnical materials under different temperatures based on physical characteristics and machine learning

Accurately and efficiently predicting permeability at different temperatures is crucial in the fuel science, as it enables optimization of production efficiency, and ensures safety and stability during storage and transportation. There remains a deficiency in predictive methods using comprehensive and reasonable training datasets and validating their applicability across different materials, particularly when considering stress and temperature. This study presents a machine learning-based method to predict permeability, incorporating physical characteristics such as microscopic image features and damage factors. The image sample data augmentation method was improved for a sufficient and meaningful training dataset, and gas permeability of sandstone under different pressure conditions after various temperature treatments were obtained. After summarizing the variation patterns of each characteristic with temperature, the necessity of using selected predictive features was validated, and sample sets were constructed. We trained an extreme learning machine neural network for sandstone’s permeability under different conditions, and the relative error was compared with other representative machine learning methods. Subsequently, the same data acquisition and prediction process were applied to granite and bentonite to validate the proposed method's applicability. The findings indicate that the proposed predictive method can stably provide accurate gas permeability predictions for various geomaterials, with relatively small prediction error rates (sandstone-4.1782%, granite-4.1782%, bentonite-3.2479%). Moreover, the stability of the relative error is steadily better than other representative machine learning methods. This approach achieves an effective prediction of gas permeability under various conditions, and can potentially simulate the evolution of gas permeability for fuel sector.

Machine Language Approach for Modeling and Predicting Rainfall in Different Zones of Kerala

The forecasting of rainfall is said to be the most difficult of other hydrological processes due to sudden changes in atmospheric processes. The rainfall directly and indirectly influences agriculture and allied sectors. Sudden changes in rainfall or an uneven distribution of rainfall can lead to crop loss. In order to avoid such problems and take the necessary precautions, it is mandatory to forecast the rainfall using various models with maximum precision. In this study, rainfall for northern, central and southern Kerala, India, was predicted using an artificial neural network (ANN) with a multi-layer perceptron (MLP) feed-forward neural network and an extreme learning machine (ELM) neural network. The monthly rainfall data was collected for a period of 39 years (1982–2020) from the regional agricultural research stations (RARS), Pilicode and Pattambi, for the northern and central zones of Kerala, respectively, whereas for the southern zone of Kerala, data was collected from RARS, Vellayani, for a period of 36 years (1985–2020). For the rainfall data collected from three different zones of Kerala, the MLP and ELM were applied. The comparison and validation of MLP and ELM models was done based on the error values of mean square error (MSE), root mean square error (RMSE), and mean absolute error(MAE). The results indicated that for three different zones in Kerala, ANN with MLP showed better performance in forecasting rainfall compared to the ELM model. The best-selected model was also used for forecasting the next 5 years rainfall in each zone of Kerala.

MIMO Detection using Optimized Neural Network model for 5G Communication

Multiple Input Multiple Output (MIMO) Wireless communication uses several antennas in the transmitter and receiver end. Multiple antennas at each end of the communication circuit work together to reduce errors, increase data speed, and improve radio transmission efficiency. MIMO techniques, which increases the number of antennas at the base station, will be used in 5G. Interference between users, which reduces a wireless link's spectral efficiency (SE), poses a major challenge during uplink communications with mm-wave systems. A linear MIMO detector such as maximum ratio (MR) or minimum mean square error (MMSE) cannot resolve this phenomenon. Therefore, this paper proposes a MIMO detection method based on an optimised extreme learning machine neural network (OELMNN). The Adaptive Rat Optimization algorithm is used to optimise the weight and bias values of ELMNN to improve its performance. The proposed scheme's performance is measured in terms of SNR, MSE, BER, and spectral efficiency.

Intelligent risk identification for drilling lost circulation incidents using data-driven machine learning

In drilling operations, lost circulation (LC) poses a significant challenge, potentially leading to severe accidents such as overflow or blowouts if not accurately identified and controlled. This study introduces a method for identifying LC risk severity using data-driven machine learning and statistical algorithms, specifically demonstrated in the Ying-Qiong Basin of the South China Sea. The method begins with variance filtering to eliminate invalid data, followed by the application of the Pearson correlation coefficient to remove redundant data. This process results in the selection of 12 logging parameters out of the initial 38. Combined with indirect judgments of LC severity based on relevant prior knowledge, the data is labeled to construct the original dataset. A feature extraction and optimization method is proposed, which employs sliding time windows to extract 21 features. These features are then selected and optimized using a random forest algorithm to construct the optimal feature set. To enhance the controllability of the Extreme Learning Machine (ELM) model, the sparrow search algorithm is integrated. Additionally, several fitness functions are introduced for both regression and classification models, resulting in the development of the improved ELM (IELM) model. The dataset is split into training and test sets, and the performance of the IELM model is compared to that of the standard ELM and BP neural network models. The results indicate that the IELM model outperforms the other two, achieving an impressive test F1 score of 97.22 % for accurately identifying LC severity. Moreover, the model trained using the optimal feature set demonstrates higher accuracy and faster convergence. The proposed feature extraction and optimization method effectively increases the amount of information contained in the data, thereby enhancing the model's performance.

A Review on Large-Scale Data Processing with Parallel and Distributed Randomized Extreme Learning Machine Neural Networks

A Review on Large-Scale Data Processing with Parallel and Distributed Randomized Extreme Learning Machine Neural Networks

Deep Learning-Based Optimal Scheduling Scheme for Distributed Wind Power Systems

For maintenance of distributed wind power networks, it remains important to realize intelligent operation scheduling strategies for wind power equipments according to their working status. As a consequence, this paper proposes a deep learning-based optimal scheme for distributed wind power networks. First of all, an adaptive status assessment model is constructed to identify time-varying operation status for unit components. Then, based on the predicted operation risk of unit components, a preventive maintenance decision model is formulated to realize flexible decision-making of maintenance tasks. Finally, a dynamic maintenance task scheduling model based on extreme learning machine (ELM) neural network is designed. The ELM neural network-based scheduling approach is expected to use a historical strategy library to assist in revising realtime voltage control strategy. Also, we conduct some experiments to evaluate the performance of the proposed method through simulation modeling. The obtained results show that real-time voltage control accuracy for wind power networks with an incomplete observation area is improved.

Exploring effect of scale dependency in LST downscaling – using convolution neural network-extreme learning machine (CNN-ELM)

Exploring effect of scale dependency in LST downscaling – using convolution neural network-extreme learning machine (CNN-ELM)

Research on Spraying Quality Prediction Algorithm for Automated Robot Spraying Based on KHPO-ELM Neural Network

In the intelligent transformation of spraying operations, the investigation into the robotic spraying process holds significant importance. The spraying process, however, falls within the realm of experience-driven technology, characterized by high complexity, diverse parameters, and coupling effects. Moreover, the quality of manual spraying processes relies entirely on manual experience. Thus, the crux of the intelligent transformation of spraying robots lies in establishing a mapping model between the spraying process and the resultant spraying quality. To address the challenge of intelligently transforming empirical spraying processes and achieving the mapping from the spraying process to spraying quality, an algorithm employing an enhanced extreme learning machine-based neural network is proposed for predicting spraying process parameters with respect to the evaluation index of spraying quality. In this approach, an algorithmic model based on the Extreme Learning Machine (ELM) neural network is initially constructed utilizing five spraying process parameters: spraying speed, spraying height, spraying width pressure, atomization pressure, and oil spraying pressure. Two spraying quality evaluation indexes, namely average film thickness at the center point and surface roughness, are also incorporated. Subsequently, the prediction neural network is optimized using the K-means improved predator optimization algorithm (KHPO) to enhance the model’s prediction accuracy. This optimization step aims to improve the efficiency of the model in predicting spraying quality based on the specified process parameters. Finally, data collection and model validation for the spraying quality prediction algorithm are conducted using a designed robotic automated waterborne paint spraying experimental system. The experimental results demonstrate a significant reduction in the prediction error of the KHPO-ELM neural network model for the average film thickness center point, showcasing a decrease of 61.95% in comparison to the traditional ELM neural network and 50.81% in comparison to the BP neural network. Likewise, the improved neural network model yields a 2.31% decrease in surface roughness prediction error compared to the traditional ELM neural network and a substantial 54.0% reduction compared to the BP neural network. Consequently, the KHPO-ELM neural network, incorporating the prediction algorithm, effectively facilitates the prediction of multi-spraying process parameters for the center point of average film thickness and surface roughness in automated robot spraying. Notably, the prediction algorithm exhibits a commendable level of accuracy in these predictions.

Magnetostrictive-based multimodal tactile sensors for object recognition

Tactile perception of the human hand plays a critical role in everyday object recognition. The development of multimodal tactile sensors that can sense stimuli with high sensitivity and low cost is important for intelligent perception. In this article, a multimodal tactile sensor attached on a mechanical hand is studied, which consists of a magnetostrictive tactile sensor, a temperature sensor, and a flex sensor. By applying multimodal tactile sensors to a robotic hand to grasp objects, the output voltage of the magnetotactictive tractile tactile sensor can be used for object shape and softness recognition. The bending angle of the knuckles can be obtained by the flex sensor for object contour size recognition, while the temperature distribution of objects can be obtained through temperature sensors. In order to improve the accuracy, a 1-D convolutional neural network-extreme learning machine (CNN-ELM) pattern recognition model based on the combination of 1-D CNN and ELM is presented, with the accuracy of 97.14% for 21 objects. This multimodal tactile sensor has promising applications in the field of tactile intelligence and humanoid robotics.

Prediction model of the large commercial building cooling loads based on rough set and deep extreme learning machine

Efficient prediction of building air conditioning cooling loads contributes to optimizing and controlling heating, ventilation, and air conditioning (HVAC) systems. In this paper, the K-means++ algorithm is used to classify the air conditioning cooling loads to determine the number of discretization intervals and influencing factors of cooling loads. Then, the rough set (RS) theory is used to screen out the critical influencing factors of cooling loads to reduce the input dimensions of the prediction model. Finally, the particle swarm optimization (PSO) algorithm is used to optimize the weights and thresholds between input layers and hidden layers of the deep extreme learning machine (DELM) neural network. Based on the above methods, a K-means++-RS-PSO-DELM prediction model is established for building air conditioning cooling loads. In this paper, a total of 50 large commercial buildings are investigated to find the critical influencing factors of air conditioning cooling loads. Data from a large commercial building in Guilin is collected to train and test the proposed model. Meanwhile, the comparisons between the proposed model and the K-means++-RS-BP, the K-means++-RS-PSO-BP, the K-means++-RS-Elman, the K-means++-RS-PSO-Elman, the K-means++-RS-ELM, the K-means++-RS-PSO-ELM, and the K-means++-RS-DELM models are conducted to validate the applicability of the prediction model. Results show that the prediction deviation of the proposed model is 1.0016 and 0.9942 in short-term and medium-term predictions, which are smaller than that of other prediction models. The proposed model has a strong generalization ability to predict the air conditioning cooling load in large commercial buildings, which is beneficial for online optimal control of the HVAC system.

Predicting Chinese stock prices using convertible bond: an evidence-based neural network approach

PurposeThe primary objective of this study is to investigate whether the inclusion of convertible bond prices as important inputs into artificial neural networks can lead to improved accuracy in predicting Chinese stock prices. This novel approach aims to uncover the latent potential inherent in convertible bond dynamics, ultimately resulting in enhanced precision when forecasting stock prices.Design/methodology/approachThe authors employed two machine learning models, namely the backpropagation neural network (BPNN) model and the extreme learning machine neural networks (ELMNN) model, on empirical Chinese financial time series data.FindingsThe results showed that the convertible bond price had a strong predictive power for low-market-value stocks but not for high-market-value stocks. The BPNN algorithm performed better than the ELMNN algorithm in predicting stock prices using the convertible bond price as an input indicator for low-market-value stocks. In contrast, ELMNN showed a significant decrease in prediction accuracy when the convertible bond price was added.Originality/valueThis study represents the initial endeavor to integrate convertible bond data into both the BPNN model and the ELMNN model for the purpose of predicting Chinese stock prices.

Intelligent manufacturing quality prediction model and evaluation system based on big data machine learning

This study addresses the challenges in the development of intelligent manufacturing by constructing a quality prediction model and evaluation system. To build the quality prediction model and evaluation system, we effectively investigated the construction of the intelligent manufacturing quality prediction model and evaluation system using extreme learning machine neural network and particle swarm optimization algorithms, combined with a big data machine learning system. The prediction results of the system were experimentally analysed to verify its performance. The experimental data showed that the prediction results of the system for each evaluation index of product quality were consistent with the actual product quality detection results. Importantly, the prediction results of the system can meet the requirements and are of great significance to the development of intelligent manufacturing.

A novel interval decomposition correlation particle swarm optimization-extreme learning machine model for short-term and long-term water quality prediction

Water quality prediction plays a crucial role in pollution treatment. However, inaccurate long-term prediction resulting from complex information patterns and insufficient feature extraction may lead to unnecessary environmental costs. In this study, a novel Interval Decomposition Correlation Particle Swarm Optimization-Extreme Learning Machine (IDCPSO-ELM) model is proposed to improve long-term water quality prediction ability. We employ Multivariate Variational Mode Decomposition (MVMD), Variational Mode Decomposition (VMD), Sliding Correlation and Permutation Entropy to reconstruct features to reduce complexity. Seasonal and Trend decomposition using Loess-Empirical Wavelet Transform decomposition (STL-EWT) is applied to target variables to improve feature extraction ability. Particle Swarm Optimization-Extreme Learning Machine (PSO-ELM) is used to predict high-frequency components based on the reconstructive features, and Back Propagation Neural Network-Extreme Learning Machine (BPNN-ELM) is employed to predict the trend and lowest-frequency components. Grey Wolf Optimization Algorithm (GWO) is used to combine these results. Six stations with high potential pollution threats in the Haihe River basin of Beijing from 2021 to 2022 are taken into model competition. The results show that: (1) In short-term prediction, average MAPE, RMSE and NSE of IDCPSO-ELM model reach 0.0934, 0.0410 and 0.8061, respectively, which are better than Genetic Algorithm-Elman Network (GA-ELMAN), Cuckoo Search Algorithm-Back Propagation Neural Network (CS-BPNN), PSO-ELM and Sparrow Search Algorithm-Kernel Extreme Learning Machine (SSA-KELM) short-term prediction models. (2) In long-term prediction, average MAPE, RMSE and NSE of IDCPSO-ELM model reach 0.1114, 0.0420 and 0.8268, respectively, which are better than the Radial Basis Function Neural Network (RBFNN), Grey Wolf Optimization-Support Vector Machine Regression (GWO-SVR), Whale Optimization Algorithm-Deep Extreme Learning Machine (WOA-DELM), Wavelet Transform decomposition-GWO-SVR-BPNN (WT-GWO-SVR-BPNN) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise-PSO-ELM-Long Short-Term Memory (CEEMDAN-PSO-ELM-LSTM) long-term prediction models. IDCPSO-ELM model is considered competitive and promising for long-term water quality prediction, particularly in areas with high potential pollution threats.

The impact of different service states of tunnel lighting on traffic safety

The service states of tunnel lighting will directly affect the lighting conditions, which affect traffic safety. Therefore, it is imperative to evaluate and predict traffic safety accurately in different lighting states. In this research, three hundred experimental scenarios of the service states of tunnel lighting were designed and implemented to evaluate the impact of different service states of tunnel lighting on traffic safety. The evaluation was achieved through a visual identification experiment in a physical tunnel. The experimental results show higher simulated vehicle speeds pose a greater threat to traffic safety. The severity of lighting attenuation contributes to an increased risk to traffic safety. An increase in the number of luminaires failure also poses a greater threat to traffic safety. The newly proposed traffic safety factor was employed to evaluate traffic safety quantitatively in road tunnels. To improve the accuracy and comprehensiveness of the traffic safety factor prediction in different lighting service states, an advanced neural network prediction system was developed. The prediction system was constructed using the Sparrow Search Algorithm (SSA) to optimize Extreme Learning Machine (ELM) neural network, and the dataset from the experiment was used for the prediction model. The SSA-ELM neural network model is a reliable model that can predict the traffic safety factor comprehensively and accurately. The recommended threshold value for the traffic safety factor is 0.6. When the value falls below 0.6, it shows that the service states of tunnel lighting pose a threat to traffic safety in the tunnel. These findings can provide insights into the safe and energy-efficient maintenance of road tunnels.

Time discretization in the solution of parabolic PDEs with ANNs

We investigate the resolution of parabolic PDEs via Extreme Learning Machine (ELMs) Neural Networks. An Artificial Neural Network (ANN) is an interconnected group of nodes -where activation functions act- organized in numbered layers. From a mathematical point of view, an ANN represents a combination of activation functions that is linear if only one hidden layer is admitted. In the present paper, the ELMs setting is considered, and this gives that a single hidden layer is admitted and that the ANN can be trained at a modest computational cost as compared to Deep Learning Neural Networks. Our approach addresses the time evolution by applying classical ODEs techniques and uses ELM-based collocation for solving the resulting stationary elliptic problems. In this framework, the θ-method and Backward Differentiation Formulae (BDF) techniques are investigated on some linear parabolic PDEs that are challenging problems for the stability and accuracy properties of the methods. The results of numerical experiments confirm that ELM-based solution techniques combined with BDF methods can provide high-accuracy solutions of parabolic PDEs.

Probabilistic outlier detection for robust regression modeling of structural response for high-speed railway track monitoring

Outlier detection is an important procedure taken in structural health monitoring (SHM) to create clean and reliable data. A robust time series outlier detection method incorporating a Bayesian perspective and an extreme learning machine (ELM) neural network model is proposed, with application to long-term monitoring data of ballastless tracks for high-speed railway systems. A robust sparse Bayesian ELM (SBELM) model is first established by computing the posterior probability density function of the ELM weight parameters and then marginalizing over the prediction-error precision parameter to obtain a robust nonlinear regression model between the track temperature and structural response. Both the posterior mean and the associated uncertainties of the robust SBELM model are then taken into account to compute the outlier probability for each suspicious data point, which quantifies their degree of data “outlier-ness.” It effectively takes into account the prediction uncertainty of the SBELM regression model. The method is applied to long-term monitoring data for track temperatures, and track strain and relative displacement responses, from two high-speed rail track systems where there are both slight and serious outliers. The results demonstrate that the proposed method can reliably detect outliers by quantifying the outlier probability and that the final results are robust to the selection of the “thresholds.” It is also shown that our new algorithm produces significantly improved model prediction performance after the outliers are detected and removed.

Compressor Performance Prediction Based on the Interpolation Method and Support Vector Machine

Compressors are important components in various power systems in the field of energy and power. In practical applications, compressors often operate under non-design conditions. Therefore, accurate calculation on performance under various operating conditions is of great significance for the development and application of certain power systems equipped with compressors. To calculate and predict the performance of a compressor under all operating conditions through limited data, the interpolation method was combined with a support vector machine (SVM). Based on the known data points of compressor design conditions, the interpolation method was adopted to obtain training samples of the SVM. In the calculation process, preliminary screening was conducted on the kernel functions of the SVM. Two interpolation methods, including linear interpolation and cubic spline interpolation, were used to obtain sample data. In the subsequent training process of the SVM, the genetic algorithm (GA) was used to optimize its parameters. After training, the available data were compared with the predicted data of the SVM. The results show that the SVM uses the Gaussian kernel function to achieve the highest prediction accuracy. The prediction accuracy of the SVM trained with the data obtained from linear interpolation was higher than that of cubic spline interpolation. Compared with the back propagation neural network optimized by the genetic algorithm (GA-BPNN), the genetic algorithm optimization of extreme learning machine neural network (GA-ELMNN), and the genetic algorithm optimization of generalized regression neural network (GA-GRNN), the support vector machine optimized by the genetic algorithm (GA-SVM) has a better generalization, and GA-SVM is more accurate in predicting boundary data than the GA-BPNN. In addition, reducing the number of original data points still enables the GA-SVM to maintain a high level of predictive accuracy.

A Review of multilayer extreme learning machine neural networks

A Review of multilayer extreme learning machine neural networks

Aerodynamic Parameter Identification of Projectile Based on Improved Extreme Learning Machine and Ensemble Learning Theory

The firing accuracy of the projectile has a positive relation with aerodynamic parameters. Due to the complex dynamic characteristics of projectiles, there is an overfitting risk when a single extreme learning machine (ELM) is used to identify the aerodynamic parameters of the projectile, and the identification results oscillate transonic region. To obtain the aerodynamic parameters of the projectile accurately, an aerodynamic parameter identification model based on ensemble learning theory and ELM optimized by improved particle swarm optimization is proposed. The improved particle swarm optimization algorithm (IPSO) with an adaptive update strategy is used to optimize the weight and threshold of ELM. Combined with the ensemble learning theory, the improved ELM neural network is regarded as a weak learner to generate a strong learner. The structural parameters of the strong learner were continuously optimized through training, and an aerodynamic parameter identification model of projectile based on ensemble learning theory is obtained. The simulation results show that the introduction of the IPSO and ensemble learning theory enables the model to exhibit excellent generalization ability. The proposed identification model can accurately describe the variation of aerodynamic parameters with the Mach number.

MRI Brain Scans Classification Using Extreme Learning Machine on LBP and GLCM

The primary goal of this study is to predict the presence of a brain tumor using MRI brain images. These images are first pre-processed to remove the boundary borders and the undesired regions. Gray-Level Co-Occurrence Matrix (GLCM) and Local Binary Pattern method (LBP) approaches are mixed for extracting multiple local and global features. The best features are selected using the ANOVA statistical approach, which is based on the largest variance. Then, the selected features are applied to many state of arts classifiers as well as to Extreme Learning Machine (ELM) neural network model, where the weights are optimized via the regularization of RELM using a suitable ratio of Cross Validation (CV) for the images' classification into one of two classes, namely normal (benign) and abnormal (malignant). The proposed ELM algorithm was trained and tested with 800 images of BRATS 2015 datasets types, and the experimental results demonstrated that this approach has better performance on several evaluation criteria, including accuracy, stability, and speedup. It reaches to 98.87% accuracy with extremely low classification time. ELM can improve the classification performance by raising the accuracy more than 2% and reducing the number of processes needed by speeding up the algorithm by a factor of 10 for an average of 20 trials.