Traditional Extreme Learning Machine Research Articles

Spatial-spectral graph convolutional extreme learning machine for hyperspectral image classification

ABSTRACT Hyperspectral image has excellent spectral information and abundant spatial information, and its feature quality is one of the key factors affecting the classification performance. Extreme learning machine (ELM) is widely used in hyperspectral classification problems. However, traditional ELM is usually based on regular Euclidean data, ignoring the inherent structured information between hyperspectral pixels, resulting in poor robustness. In this paper, we propose a new supervised extreme learning machine framework, termed spatial-spectral graph convolutional ELM (SSG-ELM), based on using graph convolution to extend ELM into the non-Euclidean domain. The method inherits all the advantages from ELM, and consists of a random graph convolutional layer followed by a graph convolutional regression layer, enabling it to model complex intra class variations. Otherwise, a local spectral-spatial context integration and reshaping mechanism is incorporated into the hidden layer feature representation by using a context-aware bilateral filtering procedure. Experimental results show that the proposed algorithm obtains a competitive performance and outperforms other state-of-the-art ELM-based methods.

Gas Path Fault Diagnosis of Turboshaft Engine Based On Novel Transfer Learning Methods

Abstract Data-driven fault diagnosis method is widely used in the field of engine health management, which uses engine sensor data as input and engine faulty components as output for component-level fault diagnosis of the engine. The application premise of the general data-driven fault diagnosis method is that all data come from the same working conditions, that is, they belong to the same distribution. However, this assumption is not valid in the actual engine fault diagnosis, because the engine state will change with the increase of running time. In the meantime, collecting engine data is usually expensive, time-consuming, and laborious. To solve these problems, extreme learning machine (ELM) based two transfer learning methods for fault diagnosis of turboshaft engines are proposed in this paper. One is joint solving ELM (JSELM), which regards the information of the target domain and source domain as similar and different parts respectively, and knowledge is extracted from them at the same time. The other is model transfer-based ELM (MTELM), which uses the idea of pretraining. First, a general ELM classifier is trained with the source domain data and then fine-tuned with the target domain data. Both methods have a good real-time performance as the traditional ELM. When there are a few data in the target domain, they achieve much better classification accuracy than traditional ELM. Finally, experiments are carried out with turboshaft engine simulation data. The results show that both methods are effective, especially MTELM, which has better classification accuracy.

Mitigating Overfitting in Extreme Learning Machine Classifier Through Dropout Regularization

Achieving optimal machine learning model performance is often hindered by the limited availability of diverse datasets, a challenge exacerbated by small sample sizes in real-world scenarios. In this study, we address this critical issue in classification tasks by integrating the Dropout technique into the Extreme Learning Machine (ELM) classifier. Our research underscores the effectiveness of Dropout-ELM in mitigating overfitting, especially when data is scarce, leading to enhanced generalization capabilities. Through extensive experiments on synthetic and real-world datasets, our findings consistently demonstrate that Dropout-ELM outperforms traditional ELM, yielding significant accuracy improvements ranging from 0.19% to 16.20%. By strategically implementing dropout during training, we promote the development of robust models that reduce reliance on specific features or neurons, resulting in increased adaptability and resilience across diverse datasets. Ultimately, Dropout-ELM emerges as a potent tool to counter overfitting and bolster the performance of ELM-based classifiers, particularly in scenarios with limited data. Its established efficacy positions it as a valuable asset for enhancing the reliability and generalization of machine learning models, providing a robust solution to the challenges posed by constrained training data.

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.

A Novel Hybrid Model Combining Improved VMD and ELM with Extended Maximum Correntropy Criterion for Prediction of Dissolved Gas in Power Transformer Oil

The prediction of dissolved gas change trends in power transformer oil is very important for the diagnosis of transformer faults and ensuring its safe operation. Considering the time series and nonlinear features of the gas change trend, this paper proposes a novel robust extreme learning machine (ELM) model combining an improved data decomposition method for gas content forecasting. Firstly, the original data with nonlinear and sudden change properties will make the forecasting model unstable, and thus an improved variational modal decomposition (IPVMD) method is developed to decompose the original data to obtain the multiple modal dataset, in which the marine predators algorithm (MPA) optimization method is utilized to optimize the free parameters of the VMD. Second, the ELM as an efficient and easily implemented tool is used as the basic model for dissolved gas forecasting. However, the traditional ELM with mean square error (MSE) criterion is sensitive to the non-Gaussian measurement noise (or outliers). In addition, considering the nonlinear non-Gaussian properties of the dissolved gas, a new learning criterion, called extended maximum correntropy criterion (ExMCC), is defined by using an extended kernel function in the correntropy framework, and the ExMCC as a learning criterion is introduced into the ELM to develop a novel robust regression model (called ExMCC-ELM) to improve the ability of ELM to process mutational data. Third, a gas-in-oil prediction scheme is proposed by using the ExMCC-ELM performed on each modal obtained by the proposed IPVMD. Finally, we conducted several simulation studies on the measured data, and the results show that the proposed method has good predictive performance.

A study on muti-strategy predator algorithm for passenger traffic prediction with big data

Abstract In this paper, we study the big data multi-strategy predator algorithm for tourist flow prediction and explore the application of the algorithm in optimizing the tourist flow prediction model to improve the prediction accuracy and efficiency. An adversarial learning strategy extends the search space, an adaptive weighting factor balances the global and local search ability, and a variance operation combined with differential evolution is used to avoid local optimal traps. The experiment adopts variables such as network booking volume and search index as inputs for passenger flow prediction. The predator algorithm is trained by Extreme Learning Machine (ELM) to optimize the input weights and biases to build the FMMPAELM model. The results show that on the training samples, the FMMPA-ELM model predictions are highly consistent with the actual values, with a maximum prediction index of 200.On the test samples, although there are errors, the FMMPA-ELM model exhibits better prediction ability than the traditional ELM model. It is concluded that the FMMPAELM model can effectively improve the accuracy of passenger flow prediction and provide powerful decision support for the tourism industry.

Capacity prediction of Lithium-ion batteries based on adaptive sliding window pooling extreme learning machine algorithm

Abstract Considering the safety and reliability, it is especially important to accurately predict the capacity decline trend of lithium-ion batteries. In this paper, a simple and easy-to-operate singular value decomposition technique is used to extract the health indicators (HIs) that are correlated with the capacity from the measurable parameters of battery, and then the HIs that have a high Pearson correlation coefficient with the capacity are selected for predicting the battery capacity. Aiming at the problems of low prediction accuracy and random dispersion of traditional extreme learning machine (ELM), this paper proposes an adaptive sliding window pooling extreme learning machine (ASW-PELM) algorithm. The algorithm first adaptively adjusts the window length according to the fluctuation of local data, and then dynamically traverses the data with the sliding window for data enhancement, and this adaptive sliding window mechanism provides effective data for the model prediction stage. Then it combines the pooling operation and the ELM to replace the random factor between the input layer and the hidden layer, which effectively solves the problem of random dispersion in the original learning model. The results of lithium battery capacity prediction under two sets of different experimental conditions show that the method has the highest prediction accuracy compared with other generalized algorithms.

An FCM based weather type classification method considering photovoltaic output and meteorological characteristics and its application in power interval forecasting

AbstractWith the increasing installation of photovoltaic (PV) systems, the impact of their randomness and volatility on power system has become a significant concern. To effectively quantify the uncertainty of PV output, it is crucial to develop reliable PV power interval forecasting technology. However, the complex relationship between PV output and meteorological factors makes it challenging for a single forecasting model to meet the forecasting demand. To solve this problem, this paper proposes a weather classification method that takes into account both PV output and meteorological characteristics. Initially, the relationship between PV output and meteorological factors is analyzed, and weather types are classified using fuzzy c‐means algorithm (FCM). Then, an extreme learning machine (ELM) is employed to establish point forecasting model. By combining kernel density estimation, a PV power generation interval forecasting model is derived. The results demonstrate that the FCM‐ELM model achieves higher forecasting accuracy and narrower interval width compared to traditional ELM models, with accuracy improvement of more than 2%. Additionally, the proposed method outperforms seasonal models with an accuracy improvement of more than 1%. The contribution of this paper includes identifying the limitations of traditional weather classification methods, proposing a novel multi‐model approach for PV interval forecasting.

Weighted Two-Hidden-Layer Extreme Learning Machine Method with Improved Gray Wolf Optimization for Complex Data Classification

Extreme Learning Machine (ELM) is widely popular for its advantages such as fast training speed and good generalization performance. However, the randomness of hidden layer parameters in ELM leads to unstable prediction performance of the model. We propose a novel two-hidden-layer extreme learning machine (TELM) for complex data classification. Firstly, the idea of weighting is introduced into TELM, and a weighted two-hidden-layer extreme learning machine (WTELM) model is proposed to improve the classification accuracy of the model. Secondly, the convergence factor and position update formula in gray wolf optimization algorithm (GWO) are adjusted to enhance the optimization algorithm’s ability to search for optimal parameters. Finally, an improved gray wolf optimization (IGWO) is utilized to search for the optimal parameters of the WTELM model. The impact of different intelligent optimization algorithms on the model’s classification results is compared. The experimental results demonstrate that the classification accuracy of the WTELM model has been improved by about 11–18% compared to traditional ELM models. Moreover, compared to the WTELM model, the classification accuracy of the IGWO-WTELM model has improved by about 1–19%. This indicates that the method proposed in this paper is significantly superior to traditional ELM methods and their variants, improving the stability, training speed and classification accuracy of the model.

Performance assessment of Sn-based lead-free solder composite joints based on extreme learning machine model tuned by Aquila optimizer

The impact of multi-walled carbon nanotubes (MWCNTs) on the development of the intermetallic compound (IMC) at the interface of the Sn5Sb/Cu solder joint was investigated. Reflow soldering was used to produce the samples, which were subsequently isothermally aged at different temperatures. The presence of MWCNTs in the Sn-5Sb solder alloy significantly prevented IMC formation at the interface and enhanced the shear strength, according to empirical observations, which were supported by the excellent properties of MWCNTs. An extreme learning machine (ELM) prediction approach refined by Aquila optimizer (AO), a new cutting-edge metaheuristic optimization algorithm was utilized to develop a prediction model for the performance assessment of the developed solder composites. The AO-ELM model's input parameters included a number of significant variables, such as MWCNTs addition, aging temperature, and aging period that have an impact on the IMC thickness and the shear strength of the solder composite joints. In terms of the statistical accuracy measures, it was observed that the AO-ELM outperformed the traditional ANN and ELM models in predicting the IMC thickness and shear strength of MWCNTs-reinforced Sn5Sb/Cu composite solder joints. The novelty of the approach recommended stems from the accuracy attained by modifying hyper-parameters with AO that has been paired with the fast processing speed of ELM.

Magnetic Flux Leakage Testing Method for Pipelines with Stress Corrosion Defects Based on Improved Kernel Extreme Learning Machine

This study aims to study the safety of oil and gas pipelines under stress corrosion conditions and grasp the corrosion damage situation timely and accurately. Consequently, a non-destructive testing method combining magnetic flux leakage testing technology and a kernel function extreme learning machine improved by genetic algorithm (GA-KELM) is proposed. Firstly, the variation of the corrosion defect dimension and profile with time is obtained by numerical simulation. At the same time, the distribution of the magnetic flux leakage signal under different defect conditions is analyzed and studied. Finally, feature selection is carried out on the magnetic flux leakage signal distribution curve, and GA-KELM is used to predict the depth and length of corrosion defects so as to realize the non-destructive testing of the pipeline defects. The results show that different geometric features result in different magnetic flux leakage signal distributions. There is a corresponding relationship between the defect dimension and extreme value, area, and peak width of the magnetic flux leakage signal distribution curve. The GA-KELM prediction model can effectively predict the depth and length of corrosion defects, and the prediction accuracy is better than the traditional extreme learning machine prediction model.

Li-Ion Battery State of Charge Prediction for Electric Vehicles Based on Improved Regularized Extreme Learning Machine

Battery state of charge prediction is one of the most essential state quantities of a battery management system. It is a prerequisite for the operation of a battery management system, but it becomes difficult to make an exact prediction of its state due to its characteristics, which cannot be measured directly. For the exact assessment of the Li-ion battery state of charge, the research proposes an extreme learning machine algorithm based on the alternating factor multiplier method with improved regularization. This method constructs a suitable online Li-ion battery state of charge prediction model using the alternating factor multiplier method in gradient form. The experiment demonstrates that the algorithm in the study has a reduction in the number of nodes in the implicit layer relative to the traditional extreme learning machine algorithm. The error fluctuations of the algorithm under two different excitation functions range from [−0.005, 0.005] and [0.082, 0.265]; The root mean square error of the data set in which the algorithm performs well is 1.9516 and 0.6157, respectively. The real simulation scenario created the predicted values of the state of charge in the realistic simulation scenario that fit the real value curve by 99.99%. The average and maximum errors of the proposed state of charge prediction model are the smallest compared to the long and short-term memory networks and gated cyclic units, 0.58% and 2.97%, respectively. The experiment demonstrates that the presented algorithm can reduce the computational burden while guaranteeing the state of charge model prediction.

A novel combined intelligent algorithm prediction model for the tunnel surface settlement

To ensure the safety and stability of the shield tunnel construction process, the ground settlement induced by the shield construction needs to be effectively predicted. In this paper, a prediction method combining empirical mode decomposition (EMD), chaotic adaptive sparrow search algorithm (CASSA), and extreme learning machine (ELM) is proposed. First, the EMD is used to decompose the settlement sequence into trend vectors and fluctuation vectors to fully extract the effective information of the sequence; Second, the sparrow search algorithm is improved by introducing Cubic chaotic mapping to initialize the population and adaptive factor to optimize the searcher’s position formula, and the chaotic adaptive sparrow search algorithm is proposed; Finally, the CASSA-ELM prediction model is constructed by using CASSA to find the optimal values of weights and thresholds in the extreme learning machine. The fluctuation components and trend components decomposed by EMD are predicted one by one, and the prediction results are superimposed and reconstructed to obtain the predicted final settlement. Taking a shield interval in Jiangsu, China as an example, the meta-heuristic algorithm-optimized ELM model improves the prediction accuracy by 10.70% compared with the traditional ELM model. The combined EMD-CASSA-ELM prediction model can greatly improve the accuracy and speed of surface settlement prediction, and provide a new means for safety monitoring in shield tunnel construction. Intelligent prediction methods can predict surface subsidence more automatically and quickly, becoming a new development trend.

BE-ELM: Biological ensemble Extreme Learning Machine without the need of explicit aggregation

Extreme learning machines (ELMs) are commonly adopted as base learners in ensemble methods due to unstable results and fast learning speed. However, most existing ensemble structures require explicit aggregation of ELM base learners’ results before the final decision. This study proposes a novel Biological Ensemble ELMs called BE-ELM from a biological perspective for the first time and exploit the superiority of assembling multiple ELM base learners in parallel without the need for explicit aggregation, and thus simplifying the learning procedure. BE-ELM’s structure is inspired by recent MIT neuroscience findings of brain learning mechanisms. The expression of the analytical solution of BE-ELM is similar to that of basic ELMs, which allows it to inherit their fast learning speed in the ensemble structure. Moreover, BE-ELM also has the added advantage of superior performance. Our theoretical analysis shows that BE-ELM consisting of multiple ELM base learners built on subsets of the original features is equivalent to a more complex ELM on the original feature space. We prove that BE-ELM, even without any explicit aggregation, can guarantee enhanced generalization capabilities. To confirm our findings, we conducted extensive experiments on various datasets. The results demonstrate that BE-ELM outperforms traditional ELMs and other state-of-the-art ensemble ELMs in terms of generalization performance on most datasets. These findings suggest that BE-ELM has the potential to improve prediction outcomes in practical applications.

Dopant network processing units as tuneable extreme learning machines

Inspired by the highly efficient information processing of the brain, which is based on the chemistry and physics of biological tissue, any material system and its physical properties could in principle be exploited for computation. However, it is not always obvious how to use a material system’s computational potential to the fullest. Here, we operate a dopant network processing unit (DNPU) as a tuneable extreme learning machine (ELM) and combine the principles of artificial evolution and ELM to optimise its computational performance on a non-linear classification benchmark task. We find that, for this task, there is an optimal, hybrid operation mode (“tuneable ELM mode”) in between the traditional ELM computing regime with a fixed DNPU and linearly weighted outputs (“fixed-ELM mode”) and the regime where the outputs of the non-linear system are directly tuned to generate the desired output (“direct-output mode”). We show that the tuneable ELM mode reduces the number of parameters needed to perform a formant-based vowel recognition benchmark task. Our results emphasise the power of analog in-matter computing and underline the importance of designing specialised material systems to optimally utilise their physical properties for computation.

A Machine Learning Approach for Probabilistic Multi-Model Ensemble Predictions of Indian Summer Monsoon Rainfall

Due to the uncertainty associated with Indian summer monsoon rainfall (ISMR), probabilistic seasonal forecasts which can convey the inherent uncertainty of ISMR are more useful to the user community than a single deterministic forecast. While such probabilistic seasonal forecasts can be produced from general circulation model (GCM) output, one single model generally does not represent all sources of error. The probabilistic multi model ensemble (PMME) is a well-accepted way to improve on the skill of probabilistic forecasts by individual GCMs. PMME can be constructed with one of two approaches: non-parametric, or parametric with respect to the occurrence of three categories of seasonal total rainfall—below, near, and above normal as defined by the climatological base period. Both the methods have their limitations. Non-parametric PMME use a smaller ensemble size which results in overconfident forecasts, and parametric PMME make the inaccurate assumption that total rainfall follows a Gaussian distribution. To avoid these problems, we propose the use of the Extreme Learning Machine (ELM), a novel machine learning (ML) approach, to construct PMME for ISMR forecasting. ELM is a state-of-the-art generalized form of single-hidden-layer feed-forward neural network. However, since the traditional ELM network only produces a deterministic outcome, we use a modified version of ELM called Probabilistic Output Extreme Learning Machine (PO-ELM). PO-ELM uses sigmoid additive neurons and slightly different linear programming to make probabilistic predictions. The performance of such PO-ELM based PMME is assessed rigorously in terms of Generalized Receiver Operating Characteristic scores and reliability diagrams over a 37 years period spanning from 1982 to 2018 following a leave-three-year-out cross-validation scheme. It is demonstrated that our new strategy for PMME based on ML is capable of producing skillful MME forecasts over large regions of India.

Joint Transfer Extreme Learning Machine with Cross-Domain Mean Approximation and Output Weight Alignment

With fast learning speed and high accuracy, extreme learning machine (ELM) has achieved great success in pattern recognition and machine learning. Unfortunately, it will fail in the circumstance where plenty of labeled samples for training model are insufficient. The labeled samples are difficult to obtain due to their high cost. In this paper, we solve this problem with transfer learning and propose joint transfer extreme learning machine (JTELM). First, it applies cross-domain mean approximation (CDMA) to minimize the discrepancy between domains, thus obtaining one ELM model. Second, subspace alignment (sa) and weight approximation are together introduced into the output layer to enhance the capability of knowledge transfer and learn another ELM model. Third, the prediction of test samples is dominated by the two learned ELM models. Finally, a series of experiments are carried out to investigate the performance of JTELM, and the results show that it achieves efficiently the task of transfer learning and performs better than the traditional ELM and other transfer or nontransfer learning methods.

An improved ELM-WOA–based fault diagnosis for electric power

Due to its fast learning speed, the extreme learning machine (ELM) plays a very important role in the real-time monitoring of electric power. However, the initial weights and thresholds of the ELM are randomly selected, therefore it is difficult to achieve an optimal network performance; in addition, there is a lack of distance selection when detecting faults using artificial intelligence algorithms. To solve the abovementioned problem, we present a fault diagnosis method for microgrids on the basis of the whale algorithm optimization–extreme learning machine (WOA-ELM). First, the wavelet packet decomposition is used to analyze the three-phase fault voltage, and the energy entropy of the wavelet packet is calculated to form the eigenvector as the data sample; then, we use the original ELM model coupled with the theory of distance selection to locate faults and compared it with the SVM method; finally, the whale algorithm is used to optimize the input weight and hidden layer neuron threshold of the ELM, i.e., the WOA-ELM model, which solves the problem of the random initialization of the input weight and hidden layer neuron threshold that easily affects the network performance, further improves the learning speed and generalization ability of the network, and is conducive to the overall optimization. The results show that 1) the accuracy of selecting the data according to the fault distance is twice that of not selecting data according to it; 2) compared with the BP neural network, RBF neural network, and ELM, the fault diagnosis model based on the WOA-ELM has a faster learning speed, stronger generalization ability, and higher recognition accuracy; and 3) after optimization of the WOA, the WOA-ELM can improve 22.5% accuracy in fault detection when compared to the traditional ELM method. Our results are of great significance in improving the security of smart grid.

Sliding Window Pooling Extreme Learning Machine Based Capacity Prediction of Lithium-ion Batteries

Lithium batteries have been widely used in various fields. Accurately predicting the remaining useful life (RUL) of batteries is greatly significant for the safety, reliability and health management of batteries. Based on the measured parameters in the process of charge and discharge of battery, the extraction method of singular value decomposition (SVD) is used to get the health indicators (HIs) related to capacity. And the traditional extreme learning machine (ELM) method has been used to predict the RUL of lithium battery, but the prediction results are divergent, random and low precision. Therefore, this paper proposes sliding window pooling ELM (SW-PELM) method to solve these problems by adding a sliding window and pooling connections. The simulation experiment was carried out through the data of lithium-ion battery from three different research institutions. Experimental results show that the proposed algorithm can well improve the divergence and random ELM prediction results, and has higher prediction accuracy compared with other improved ELM algorithms.

Lithium-Ion Battery Life Prediction Method under Thermal Gradient Conditions

Thermal gradient is inevitable in a lithium-ion battery pack because of uneven heat generation and dissipation, which will affect battery aging. In this paper, an experimental platform for a battery cycle aging test is built that can simulate practical thermal gradient conditions. Experimental results indicate a high nonlinear degree of battery degradation. Considering the nonlinearity of Li-ion batteries aging, the extreme learning machine (ELM), which has good learning and fitting ability for highly nonlinear, highly nonstationary, and time-varying data, is adopted for prediction. A battery life prediction model based on the sparrow search algorithm (SSA) is proposed in this paper to optimize the random weights and bias of the ELM network and verified by experimental data. The results show that compared with traditional ELM and back-propagation neural networks, the prediction results of ELM optimized by SSA have lower mean absolute error percentages and root mean square errors, indicating that the SSA-ELM model has higher prediction accuracy and better stability and has obvious advantages in processing data with a high nonlinear degree.