Search

Extreme learning machines (ELMs), single hidden-layer feedforward neural networks, are renowned for their speed and efficiency in classification and regression tasks. However, their generalization ability is often undermined by the random generation of hidden layer weights and biases. To address this issue, this paper introduces a Hierarchical Learning-based Chaotic Crayfish Optimization Algorithm (HLCCOA) aimed at enhancing the generalization ability of ELMs. Initially, to resolve the problems of slow search speed and premature convergence typical of traditional crayfish optimization algorithms (COAs), the HLCCOA utilizes chaotic sequences for population position initialization. The ergodicity of chaos is leveraged to boost population diversity, laying the groundwork for effective global search efforts. Additionally, a hierarchical learning mechanism encourages under-performing individuals to engage in extensive cross-layer learning for enhanced global exploration, while top performers directly learn from elite individuals at the highest layer to improve their local exploitation abilities. Rigorous testing with CEC2019 and CEC2022 suites shows the HLCCOA's superiority over both the original COA and nine renowned heuristic algorithms. Ultimately, the HLCCOA-optimized extreme learning machine model, the HLCCOA-ELM, exhibits superior performance over reported benchmark models in terms of accuracy, sensitivity, and specificity for UCI breast cancer diagnosis, underscoring the HLCCOA's practicality and robustness, as well as the HLCCOA-ELM's commendable generalization performance. [ABSTRACT FROM AUTHOR]

The randomization-based feedforward neural network has raised great interest in the scientific community due to its simplicity, training speed, and accuracy comparable to traditional learning algorithms. The basic algorithm consists of randomly determining the weights and biases of the hidden layer and analytically calculating the weights of the output layer by solving a linear overdetermined system using the Moore–Penrose generalized inverse. When processing large volumes of data, randomization-based feedforward neural network models consume large amounts of memory and drastically increase training time. To efficiently solve the above problems, parallel and distributed models have recently been proposed. Previous reviews of randomization-based feedforward neural network models have mainly focused on categorizing and describing the evolution of the algorithms presented in the literature. The main contribution of this paper is to approach the topic from the perspective of the handling of large volumes of data. In this sense, we present a current and extensive review of the parallel and distributed models of randomized feedforward neural networks, focusing on extreme learning machine. In particular, we review the mathematical foundations (Moore–Penrose generalized inverse and solution of linear systems using parallel and distributed methods) and hardware and software technologies considered in current implementations. [ABSTRACT FROM AUTHOR]

The echo state network (ESN) is a recurrent neural network that has yielded state-of-the-art results in many areas owing to its rapid learning ability and the fact that the weights of input neurons and hidden neurons are fixed throughout the learning process. However, the setting procedure for initializing the ESN's recurrent structure may lead to difficulties in designing a sound reservoir that matches a specific task. This paper proposes an improved pre-training method to adjust the model's parameters and topology to obtain an adaptive reservoir for a given application. Two strategies, namely global random selection and ensemble training, are introduced to pre-train the randomly initialized ESN model. Specifically, particle swarm optimization is applied to optimize chosen fixed and global weight values within the network, and the reliability and stability of the pre-trained model are enhanced by employing the ensemble training strategy. In addition, we test the feasibility of the model for time series prediction on six benchmarks and two real-life datasets. The experimental results show a clear enhancement in the ESN learning results. Furthermore, the proposed global random selection and ensemble training strategies are also applied to pre-train the extreme learning machine (ELM), which has a similar training process to the ESN model. Numerical experiments are subsequently carried out on the above-mentioned eight datasets. The experimental findings consistently show that the performance of the proposed pre-trained ELM model is also improved significantly. The suggested two strategies can thus enhance the ESN and ELM models' prediction accuracy and adaptability. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is a feedforward neural network that utilizes a single hidden layer to effectively tackle the learning speed challenges commonly associated with conventional gradient-based neural networks. ELM has been reported to achieve faster learning rates and better performance than traditional neural networks. However, it is susceptible to unreliable solutions when applied to real-world input data with inconsistent noise, resulting in overfitting. To mitigate these limitations, we investigate various regularization techniques that can be employed in conjunction with ELM, including Tikhonov regularization, a well-established method in the field. However, one of the main drawbacks of Tikhonov regularization is its assumption of the input data's noise to be white and Gaussian, which may not be the case in real-world applications. This assumption can lead to suboptimal regularization and poor generalization performance of the model. Therefore, we propose using an exponential filtering method in conjunction with ELM to overcome this limitation and improve the model's reliability. We compare our approach with Tikhonov regularization and other existing methods to evaluate its efficacy. Our experimental results demonstrate that our proposed strategy achieves superior accuracy and generalization capability compared to the other methods. Moreover, we provide statistical evidence to support the significance of our findings. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) as a type of feedforward neural network has been widely used to obtain beneficial insights from various disciplines and real-world applications. Despite the advantages like speed and highly adaptability, instability drawbacks arise in case of multicollinearity, and to overcome this, additional improvements were needed. Regularization is one of the best choices to overcome these drawbacks. Although ridge and Liu regressions have been considered and seemed effective regularization methods on ELM algorithm, each one has own characteristic features such as the form of tuning parameter, the level of shrinkage or the norm of coefficients. Instead of focusing on one of these regularization methods, we propose a combination of ridge and Liu regressions in a unified form for the context of ELM as a remedy to aforementioned drawbacks. To investigate the performance of the proposed algorithm, comprehensive comparisons have been carried out by using various real-world data sets. Based on the results, it is obtained that the proposed algorithm is more effective than the ELM and its variants based on ridge and Liu regressions, RR-ELM and Liu-ELM, in terms of the capability of generalization. Generalization performance of proposed algorithm on ELM is remarkable when compared to RR-ELM and Liu-ELM, and the generalization performance of the proposed algorithm on ELM increases as the number of nodes increases. The proposed algorithm outperforms ELM in all data sets and all node numbers in that it has a smaller norm and standard deviation of the norm. Additionally, it should be noted that the proposed algorithm can be applied for both regression and classification problems. [ABSTRACT FROM AUTHOR]

The extreme learning machine (ELM), a new learning algorithm for single hidden layer feedforward neural networks (SLFN), has drawn interest of a large number of researchers, especially due to its training speed and good generalization performances compared to known machine learning methods. The ELM model generates a solution to a linear optimization problem for the hidden layer output weights by randomly generating input weights and biases, instead of iteratively adjusting the network parameters (weights and biases) such as the backpropagation neural network model using the backpropagation algorithm and gradient descent learning. However, random determination of input weights and hidden layer bias can result in non-optimal parameters that have an adverse impact on the final results or require a higher number of hidden nodes for the neural network. In this study, a new hybrid method is proposed to overcome the drawbacks caused by non-optimal input weights and hidden biases. This hybrid method, which is called CPN-ELM algorithm, uses the counter propagation network (CPN) model to systematically optimize input weights, hidden layer neurons and hidden biases. The performance of CPN-ELM compared to traditional ELM method was examined on three benchmark regression datasets and we observed that the model produced higher accuracy values for each datasets. [ABSTRACT FROM AUTHOR]

The purpose of this work is to compare predictive performance of neural networks trained using the relatively novel technique of training single hidden layer feedforward neural networks (SFNN), called Extreme Learning Machine (ELM), with commonly used backpropagation-trained recurrent neural networks (RNN) as applied to the task of financial market prediction. Evaluated on a set of large capitalisation stocks on the Australian market, specifically the components of the ASX20, ELM-trained SFNNs showed superior performance over RNNs for individual stock price prediction. While this conclusion of efficacy holds generally, long short-term memory (LSTM) RNNs were found to outperform for a small subset of stocks. Subsequent analysis identified several areas of performance deviations which we highlight as potentially fruitful areas for further research and performance improvement. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. In this paper, we hope to present a comprehensive review on ELM. Firstly, we will focus on the theoretical analysis including universal approximation theory and generalization. Then, the various improvements are listed, which help ELM works better in terms of stability, efficiency, and accuracy. Because of its outstanding performance, ELM has been successfully applied in many real-time learning tasks for classification, clustering, and regression. Besides, we report the applications of ELM in medical imaging: MRI, CT, and mammogram. The controversies of ELM were also discussed in this paper. We aim to report these advances and find some future perspectives. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) is a single hidden layer feedforward neural network and is proved to be a good machine learning tool. However, the singularity of the ELM activation function results in the poor generalization ability of the systems. This study proposes a least squares ELM with derivative characteristics (DLSELM). The activation function of the network consists of the original and derivative functions due to the introduction of derivative characteristics in the network. All weights and biases of the network are determined by a twice least squares method. Derivative characteristics increase the diversity of activation functions in the network. The regression accuracy of the network and the generalization ability of the system were greatly improved due to the weighs and biases of the DLSELM calculated by twice least methods. DLSELM is applied to different datasets for verifying their performance. Moreover, DLSELM possesses the best regression accuracy, stability, and generalization performance compared with the other networks. [ABSTRACT FROM AUTHOR]

It is a challenging task to optimize network structure and connection parameters simultaneously in a single hidden layer feedforward neural network (SLFN). Extreme learning machine (ELM) is a popular non-iterative learning method in recent years, which often provides good generalization performance of a SLFN at extremely fast learning speed, yet only for fixed network structure. In this work, a cooperative binary-real genetic algorithm (CGA) based on ELM, called CGA-ELM, is proposed to adjust the structure and parameters of a SLFN simultaneously for achieving a compact network with good generalization performance. In CGA-ELM, a hybrid coding scheme is designed to evolve the network structure and input parameters, i.e., input weights between input nodes and hidden nodes as well as the biases of hidden nodes. Then output parameters, i.e., output weights between hidden nodes and output nodes, are determined by the ELM. A combination of training error and network complexity is taken as the fitness function to evaluate the performance of a SLFN. A binary GA is responsible for optimizing network structure, while a real GA and the ELM optimize collaboratively network parameters. Experimental results on classification applications demonstrate that CGA-ELM outperforms CGA and ELM significantly in terms of the generalization ability. Also, CGA-ELM has more competitive capacity when compared with other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Compared with signals collected by the single sensor, the collected multivariate signals contain more information to reflect the state of mechanical equipment, which has a positive effect on fault diagnosis. However, different acquisition channels and various operating conditions interfere with the extraction of fault features of rotating machinery. To solve this problem, taking rolling bearings as an example in this paper, a novel method is adopted to alleviate these interferences and combined with an improved extreme learning machine (ELM) to achieve intelligent fault diagnosis of rolling bearings under various operating conditions. First, adaptive projection intrinsically transformed multivariate empirical mode decomposition is used to decompose multivariate signals and obtain intrinsic mode functions of each channel to construct feature matrices. Then, nuisance attribute projection (NAP) is employed to alleviate the interference components in the feature matrix, which are originated from different channels and operating conditions. Finally, vectors belonging to the processed feature matrix as samples are input into the proposed weighted extreme learning machine (WELM) for intelligent fault classification. The weighted matrix of the WELM can compress the dimension of the sample and extract sensitive features, and the effectiveness of the proposed fault diagnosis model via the above methods is verified by experiments. Furthermore, comparative experiments show that the proposed fault diagnosis model has higher accuracy than the model combined with NAP and traditional single-hidden layer feedforward neural network or ELM. Therefore, the proposed fault diagnosis model may potentially aid experts on fault diagnosis of rotating machinery under various operating conditions. [ABSTRACT FROM AUTHOR]

In this article, a technique for cooperative spectrum sensing (CSS) using the Extreme Learning Machine (ELM) is proposed. ELMs are feedforward neural networks where the hidden layer parameters are not tuned, and only output weights are optimized. The simulations were done for both the fading and non-fading environments. Different combination of activation function and weight initialization scheme is deployed for calculating channel occupancy detection. The obtained results are compared with popular fusion schemes and well-known Machine Learning (ML) techniques. Further, the proposed algorithm's performance is compared with some of the recent CSS techniques in the literature. The primary metrics for comparison were the receiver operating characteristic (ROC) curve, the area under the curve (AUC), detection performance, and energy consumption. We obtained the ELM model's computational performance during the training phase and calculated the channel detection probability. These results demonstrate the potential superiority of ELM over established methods. In particular, the work presented here shows a better trade-off between training time and detection performance. [ABSTRACT FROM AUTHOR]

In this paper, we consider a real-time deep learning-based symbol detection approach for MIMO-OFDM systems. To exploit the temporal correlation of the wireless channel and the time-frequency structure of OFDM signals, a recurrent neural network (RNN) with deep feedforward output layers is introduced, where the recurrent layers and feedforward output layers are designed to process time-domain and frequency-domain information respectively. Reservoir computing (RC), a special type of RNN, and extreme learning machine (ELM), a special type of feedforward neural network, are chosen as the corresponding building blocks to facilitate over-the-air training. An online training loss objective is introduced to recursively update the neural weights in real-time. We believe this is the first work in the literature to realize real-time machine learning for MIMO-OFDM symbol detection, i.e., conducting NN-based symbol detection on an OFDM symbol basis. We demonstrate that (1) the IEEE standardized WiFi training sequence can be directly applied as the real-time training sequence (2) the symbol detection performance can be further improved by using our theoretically derived pilot pattern. Evaluation results show that our RC-ELM-based symbol detection method outperforms traditional model-based techniques as well as state-of-the-art learning-based approaches in highly dynamic channel environments for real-time symbol detection. [ABSTRACT FROM AUTHOR]

Replicator Neural Network (RNN) is a popular algorithm for anomaly detection, but finding optimal number of hidden layers and then finding optimal number of neurons in each hidden layer is quite a challenging and time-consuming task. Extreme Learning Machines (ELM) are neural networks with single-hidden layer but the learning algorithm is different and faster than back-propagation. ELM-based RNNs solve our problem of determining the number of hidden layers and the learning algorithm is also faster than gradient-descent based RNN. The problem of identifying the optimal number of neurons in the hidden layer can be solved by Garson algorithm. In this work, the author propose an optimal Replicator Neural Network which is optimized using ELM learning and Garson algorithm for anomaly detection. The experimental results show that the proposed method is fast as well as highly accurate. [ABSTRACT FROM AUTHOR]

This paper introduces a novel approach to learn multi-task regression models with constrained architecture complexity. The proposed model, named RFF-BLR, consists of a randomised feedforward neural network with two fundamental characteristics: a single hidden layer whose units implement the random Fourier features that approximate an RBF kernel, and a Bayesian formulation that optimises the weights connecting the hidden and output layers. The RFF-based hidden layer inherits the robustness of kernel methods. The Bayesian formulation enables promoting multioutput sparsity: all tasks interplay during the optimisation to select a compact subset of the hidden layer units that serve as common non-linear mapping for every tasks. The experimental results show that the RFF-BLR framework can lead to significant performance improvements compared to the state-of-the-art methods in multitask nonlinear regression, especially in small-sized training dataset scenarios. [ABSTRACT FROM AUTHOR]

• We thoroughly review the employment of ELM in IDS development in the last decade. • We examine ELM-based IDS applications, extensions, attacks, and security issues. • We show the flexibility of ELM-based IDS to multiple algorithms and techniques. • We provide extensive comparative studies for ELM technology in defensive security. The ever-increasing interconnectedness of our world, fueled by technological advancements across industries, has made network security a paramount concern. This concern stems from the evolving tactics of cybercriminals and our dependence on interdependent systems. Extreme Learning Machines (ELMs) have recently been renamed Single-Hidden-Layer Feedforward Neural Networks (SLNFs) to achieve a rapid learning rate by randomly initializing weights and deviations. For a decade, researchers have been primarily focused on the investigations of ELM, which offers a distinctive use that prompted academics to investigate its possible application in various disciplines. Considering the Intrusion Detection System (IDS) framework, ELM provides an enticing path for constructing effective and adaptable IDS models capable of analyzing enormous amounts of network data in real-time. ELMs are based on feedforward networks using single or Multi-Hidden Layers (MHLs). ELM-based IDS assists in safeguarding networks, systems, and web applications against cyber-attacks, phishing, and cyber threats. As a result, during the last decade, ELM has taken center stage for development as an exciting technology for effective and accurate classification tasks. ELM represents a subset of the Machine Learning (ML) algorithms utilized by IDSs, which makes our work contribute significantly to the field of network security. First, we investigate the ELM-based IDS throughout the previous decade, including the idea, scope, and rationale of ELM. Second, our study aims to identify abnormal and malicious actions in network traffic while offering real-time protection against potential threats, including detecting Distributed Denial of Services (DDoS) attacks and phishing attacks that use malicious URLs and payloads for successful attacks. Finally, our work encompasses applications, extensions, attacks, security issues, and a comparative analysis showcasing the versatility of ELM within various algorithms. This underscores ELM's evolution as a promising technology for accurate and effective classification tasks, particularly in network security research. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to propose a new aerodynamic parameter estimation methodology based on neural network and output error method, while the output error method is improved based on particle swarm algorithm. Design/methodology/approach: Firstly, the algorithm approximates the dynamic characteristics of aircraft based on feedforward neural network. Neural network is trained by extreme learning machine, and the trained network can predict the aircraft response at (k + 1)th instant given the measured flight data at kth instant. Secondly, particle swarm optimization is used to enhance the convergence of Levenberg–Marquardt (LM) algorithm, and the improved LM method is used to substitute for the Gauss Newton algorithm in output error method. Finally, the trained neural network is combined with the improved output error method to estimate aerodynamic derivatives. Findings: Neither depending on the initial guess of the parameters to be estimated nor requiring numerical integration of the aircraft motion equation, the proposed algorithm can be used for unstable aircraft and is successfully applied to extract aerodynamic derivatives from both simulated and real flight data. Research limitations/implications: The proposed method requires iterative calculation and can only identify parameters offline. Practical implications: The proposed method is successfully applied to estimate aircraft aerodynamic parameters and can also be used as a new algorithm for other optimization problems. Originality/value: In this study, the output error method is improved to reduce the dependence on the initial value of parameters and expand its application scope. It is applied in aircraft aerodynamic parameter identification together with neural network. [ABSTRACT FROM AUTHOR]

An accurate estimation of the state of health (SOH) of lithium-ion batteries is essential for the safe and reliable operation of electric vehicles. As a single hidden-layer feedforward neural network, extreme learning machine (ELM) has the advantages of a fast learning speed and good generalization performance. The bat algorithm (BA) is a swarm intelligence optimization algorithm based on bat echolocation for foraging. In this study, BA was creatively applied to improve the ELM neural network, forming a BA-ELM model, and it was applied to SOH estimation for the first time. First, through Pearson and Spearman correlation analysis, six variables were determined as the input variables of the model. The actual remaining capacity of the battery was determined as the output variable. Second, BA was used to optimize the connection weights and bias in ELM to construct the BA-ELM model. Third, the battery data set was trained and tested with BA-ELM, ELM, Elman, back propagation (BP), radial basis function (RBF), and general regression neural network (GRNN) models. Five statistical error indicators, and the radar chart, scatter plot, and violin diagram were used to compare the estimation effects. The results show that the evaluation function of BA-ELM can converge quickly and effectively optimize the network model of ELM. The RMSE of the BA-ELM model was 0.5354%, and the MAE was 0.4326%, which is the smallest among the 6 models. The RMSE values of the other model were 2.27%, 3.53%, 3.07%, 3.86%, 3.24%, respectively, indicating the BA-ELM has good potential for future applications. [ABSTRACT FROM AUTHOR]

Accurate demand prediction of bike-sharing is an important prerequisite to reducing the cost of scheduling and improving the user satisfaction. However, it is a challenging issue due to stochasticity and non-linearity in bike-sharing systems. In this paper, a model called pseudo-double hidden layer feedforward neural networks is proposed to approximately predict actual demands of bike-sharing. Specifically, to overcome limitations in traditional back-propagation learning process, an algorithm, an extreme learning machine with improved particle swarm optimization, is designed to construct learning rules in neural networks. The performance is verified by comparing with other learning algorithms on the dataset of Streeter Dr bike-sharing station in Chicago. [ABSTRACT FROM AUTHOR]

Online sequential extreme learning machine (OS-ELM) is one of the most popular real-time learning strategy for feedforward neural networks with single hidden layer due to its fast learning speed and excellent generalization ability. When dealing with quaternion signals, traditional real-valued learning models usually provide only suboptimal solutions compared with their quaternion-valued counterparts. However, online sequential quaternion extreme learning machine (OS-QELM) model is still lacking in literature. To fill this gap, this paper aims to establish a framework for the derivation and the design of OS-QELM. Specifically, we first derive a standard OS-QELM, and then propose two augmented OS-QELM models which can capture the complete second-order statistics of noncircular quaternion signals. The corresponding regularized models and two approaches to reducing the computational complexity are also derived and discussed respectively. Benefiting from the quaternion algebra and the augmented structure, the proposed models exhibit superiority over OS-ELM in simulation results on several benchmark quaternion regression problems and colour face recognition problems. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) is an emerging machine learning algorithm for training single-hidden-layer feedforward networks (SLFNs). The salient features of ELM are that its hidden layer parameters can be generated randomly, and only the corresponding output weights are determined analytically through the least-square manner, so it is easier to be implemented with faster learning speed and better generalization performance. As the online version of ELM, online sequential ELM (OS-ELM) can deal with the sequentially coming data one by one or chunk by chunk with fixed or varying chunk size. However, OS-ELM cannot function well in dealing with dynamic modeling problems due to the data saturation problem. In order to tackle this issue, in this paper, we propose a novel OS-ELM, named adaptive OS-ELM (AOS-ELM), for enhancing the generalization performance and dynamic tracking capability of OS-ELM for modeling problems in nonstationary environments. The proposed AOS-ELM can efficiently reduce the negative effects of the data saturation problem, in which approximate linear dependence (ALD) and a modified hybrid forgetting mechanism (HFM) are adopted to filter the useless new data and alleviate the impacts of the outdated data, respectively. The performance of AOS-ELM is verified using selected benchmark datasets and a real-world application, i.e., device-free localization (DFL), by comparing it with classic ELM, OS-ELM, FOS-ELM, and DU-OS-ELM. Experimental results demonstrate that AOS-ELM can achieve better performance. [ABSTRACT FROM AUTHOR]

Close proximity operations around small bodies are extremely challenging due to their uncertain dynamical environment. Autonomous guidance and navigation around small bodies require fast and accurate modeling of the gravitational field for potential on-board computation. In this paper, we investigate a model-based, data-driven approach to compute and predict the gravitational acceleration around irregular small bodies. More specifically, we employ Extreme Learning Machine (ELM) theories to design, train and validate Single-Layer Feedforward Networks (SLFN) capable of learning the relationship between the spacecraft position and the gravitational acceleration. ELM-base neural networks are trained without iterative tuning therefore dramatically reducing the training time. Analysis of performance in constant density models for asteroid 25143 Itokawa and comet 67/P Churyumov-Gerasimenko show that ELM-based SLFN are able learn the desired functional relationship both globally and in selected localized areas near the surface. The latter results in a robust neural algorithm for on-board, real-time calculation of the gravity field needed for guidance and control in close-proximity operations near the asteroid surface. [ABSTRACT FROM AUTHOR]

• A pre-trained MobileNetV2 was leveraged to extract features from brain MRIs automatically. • The optimal feature layer in MobileNetV2 was obtained by experiment. • Three random neural networks: ELM, RVFL and SNN were trained for classification. • A novel chaotic bat algorithm was employed to improve the performance of classifiers. • The trained model can serve as a visual question answering system and produce accurate results. Computer aided diagnosis systems are playing an important part in clinical treatment. They can help the doctors and physicians to verify the diagnosis decisions. In this study, a new classification algorithm for the brain magnetic resonance image is proposed. Initially, we utilized a MobileNetV2 to extract features from the input brain images, which was pre-trained on ImageNet dataset. Instead of training the deep network, we simply calculate the output of its certain layer to form the feature vector. The optimal feature layer is obtained by the experiment. Then, three different feedforward networks: extreme learning machine, Schmidt neural network and random vector functional-link net, are trained for classification. Chaotic bat algorithm was proposed to optimize the weights and biases in the three randomized neural networks to boost their classification accuracy. The result from 5×hold-out validation reveals that our method can achieve good generalization performance which is comparable to state-of-the-art pathological brain detection methods. The trained model can serve as a visual question answering system and produce accurate results. [ABSTRACT FROM AUTHOR]

The extreme learning machine (ELM), a typical machine learning algorithm based on feedforward neural network, has been widely used in classification, clustering, regression and feature learning. However, the traditional ELM learns all samples at once, and sample weights of traditional methods are defined before the learning process and they will not change during the learning process. So, its performance is vulnerable to noisy data and outliers, finding a way to solve this problem is meaningful. In this work, we propose a model of self-paced ELM named SP-ELM for binary classification and multi-classification originated from the self-paced learning paradigm. Concretely, the algorithm takes the importance of samples into account according to the loss of predicted value and real value, and it establishes the model from the simple samples to complex samples. By setting certain restrictions, the influence of complex data on the model is reduced. Four different self-paced regularization terms are adopted in the paper to select the instances. Experimental results demonstrate the effectiveness and of the proposed method by comparing it with other improved ELMs. [ABSTRACT FROM AUTHOR]

Incremental extreme learning machine (I-ELM) randomly obtains the input weights and the hidden layer neuron bias during the training process. Some hidden nodes in the ELM play a minor role in the network outputs which may eventually increase the network complexity and even reduce the stability of the network. In order to avoid this issue, this paper proposed an enhanced method for the I-ELM which is referred to as the improved incremental extreme learning machine (II-ELM). At each learning step of original I-ELM, an additional offset k will be added to the hidden layer output matrix before computing the output weights for the new hidden node and analysed the existence of the offset k. Compared with several improved algorithms of ELM, the advantages of the II-ELM in the training time, the forecasting accuracy, and the stability are verified on several benchmark datasets in the UCI database. [ABSTRACT FROM AUTHOR]

The extreme learning machine (ELM) is a type of machine learning algorithm for training a single hidden layer feedforward neural network. Randomly initializing the weight between the input layer and the hidden layer and the threshold of each hidden layer neuron, the weight matrix of the hidden layer can be calculated by the least squares method. The efficient learning ability in ELM makes it widely applicable in classification, regression, and more. However, owing to some unutilized information in the residual, there are relatively huge prediction errors involving ELM. In this paper, a deep residual compensation extreme learning machine model (DRC‐ELM) of multilayer structures applied to regression is presented. The first layer is the basic ELM layer, which helps in obtaining an approximation of the objective function by learning the characteristics of the sample. The other layers are the residual compensation layers in which the learned residual is corrected layer by layer to the predicted value obtained in the previous layer by constructing a feature mapping between the input layer and the output of the upper layer. This model is applied to two practical problems: gold price forecasting and airfoil self‐noise prediction. We used the DRC‐ELM with 50, 100, and 200 residual compensation layers respectively for experiments, which show that DRC‐ELM does better in generalization and robustness than classical ELM, improved ELM models such as GA‐RELM and OS‐ELM, and other traditional machine learning algorithms such as support vector machine (SVM) and back‐propagation neural network (BPNN). [ABSTRACT FROM AUTHOR]

Device-free localization (DFL) is becoming one of the new techniques in wireless localization field, due to its advantage that the target to be localized does not need to attach any electronic device. One of the key issues of DFL is how to characterize the influence of the target on the wireless links, such that the target's location can be accurately estimated by analyzing the changes of the signals of the links. Most of the existing related research works usually extract the useful information from the links through manual approaches, which are labor-intensive and time-consuming. Deep learning approaches have attempted to automatically extract the useful information from the links, but the training of the conventional deep learning approaches are time-consuming, because a large number of parameters need to be fine-tuned multiple times. Motivated by the fast learning speed and excellent generalization performance of extreme learning machine (ELM), which is an emerging training approach for generalized single hidden layer feedforward neural networks (SLFNs), this paper proposes a novel hierarchical ELM based on deep learning theory, named multilayer probability ELM (MP-ELM), for automatically extracting the useful information from the links, and implementing fast and accurate DFL. The proposed MP-ELM is stacked by ELM autoencoders, so it also keeps the very fast learning speed of ELM. In addition, considering the uncertainty and redundant links existing in DFL, MP-ELM outputs the probabilistic estimation of the target's location instead of the deterministic output. The validity of the proposed MP-ELM-based DFL is evaluated both in the indoor and the outdoor environments, respectively. Experimental results demonstrate that the proposed MP-ELM can obtain better performance compared with classic ELM, multilayer ELM (ML-ELM), hierarchical ELM (H-ELM), deep belief network (DBN), and deep Boltzmann machine (DBM). [ABSTRACT FROM AUTHOR]

A novel, nonlinear soft sensor based on a localized, adaptive single‐layer feedforward neural network with random hidden layer weights, also called an extreme learning machine, combined with the recursive partial least squares algorithm to update the linear output layer weights, is explored. The soft sensor is highly adaptive with minimal operator input, and automated mechanisms are included to self‐correct numerous aspects of the underlying model. For instance, mechanisms are put in place to automatically select an optimized local model region describing the current process dynamics from the historical data when the current prediction error reaches an adaptively computed threshold. Additionally, the new soft sensor simultaneously employs an ensemble of models with diverse recursive partial least squares forgetting factors with automated and adaptive reweighting of the models in the ensemble, thus enabling real‐time model memory adjustment. The validity of the method is shown by comparison with numerous other soft sensor methods for the prediction of the activity of a polymerization catalyst. We report a novel, highly adaptive, nonlinear soft sensor based on an extreme learning machine, a localized, adaptive single‐layer feedforward neural network with random hidden layer weights, that is combined with the recursive partial least squares algorithm to update the linear output layer weights. This new soft sensor simultaneously employs an ensemble of automated, adaptively re‐weighted models, thus enabling real‐time model memory adjustment. The method is compared with other soft sensor methods. [ABSTRACT FROM AUTHOR]

This paper is concerned with the sparsification of the input-hidden weights of ELM (extreme learning machine). For ordinary feedforward neural networks, the sparsification is usually done by introducing certain regularization technique into the learning process of the network. However, this strategy cannot be applied for ELM, since the input-hidden weights of ELM are supposed to be randomly chosen rather than iteratively learned. To this end, we propose a modified ELM, called ELM-LC (ELM with local connections), which is designed for the sparsification of the input-hidden weights as follows: The hidden nodes and the input nodes are divided respectively into several corresponding groups, and each input node group is fully connected with its corresponding hidden node group, but is not connected with any other hidden node group. As in the usual ELM, the input-hidden weights are randomly given, and the hidden-output weights are obtained through a least square learning. In the numerical simulations on some benchmark problems, the new ELM-LC behaves better than the traditional ELM and the ELM with normal sparse input-hidden weights. [ABSTRACT FROM AUTHOR]

• Biased estimators may be powerful tools in extreme learning machine studies. • Ridge based regression estimators may outperform the extreme machine learning. • Choice of ridge regularization parameter is effective to obtain more stable results. • Generalization performance of ELM depend on selection of regularization parameter. The extreme learning machine (ELM) which is a single layer feedforward neural network provides extremely fast training speed and good generalization performance. The ELM however, has its respective drawback: it is known to be sensitive to the ill-conditioned data. To overcome the ill-conditioning problem in ELM, ELM based on ridge regression (RR-ELM) was proposed. Since RR-ELM is a biased method, ELM based on almost unbiased ridge regression (AUR-ELM) was accordingly proposed to reduce the bias in a certain extent. RR-ELM and AUR-ELM introduced in the existence of multicollinearity, depend on the regularization parameter. The regularization parameter affects the performance of both RR-ELM and AUR-ELM. There is no consensus on the selection of the regularization parameter. Although there are various methods in linear regression to select the regularization parameter, only one method based on the selection minimizing the mean squared error was used in RR-ELM. In this study, AIC, BIC and CV criteria in the context of RR-ELM and AUR-ELM were proposed as alternative methods for the selection of the regularization parameter. An experimental study was conducted on eight data sets which are widely known and used in machine learning studies. The analyzes are considered as purposive for regression studies which are the most important fields of expert systems and machine learning. The results obtained demonstrate that the selection method of the regularization parameter is significantly effective on both the generalization and particularly stability performance of RR-ELM and AUR-ELM when compared to ELM [ABSTRACT FROM AUTHOR]

The feedforward neural network based on randomization has been of great interest in the scientific community, particularly extreme learning machines, due to its simplicity, training speed, and levels of accuracy comparable to traditional learning algorithms. Extreme learning machines (ELMs) are a type of artificial neural network (ANN) with one or more hidden layers that are trained under supervised, unsupervised, or semi-supervised learning approaches. These networks are widely used in various research areas, such as medical image processing (MI). This research work presents an exhaustive review of extreme learning machines (ELM) and medical image processing (MI), due to the high impact that these networks have had on the scientific community and the importance of MI for physicians who use them to diagnose different injuries and diseases. First, the theoretical construct of ELMs is developed based on the types of supervised, unsupervised, and semi-supervised learning. Then, the importance of MI for the diagnosis of a disease or classification of the most commonly used imaging modalities is analyzed for articles concerning radiography, computed tomography (CT), magnetic resonance (MR), ultrasound (US), and mammography (MG). Next, the reference data sets linked to various human body organs, such as the brain, lungs, skin, eyes, breasts, and cervix are described. Then, a review, analysis, and classification of the development of the last 6 years (2017–2022) of ELMs, based on learning types and MI, is performed. With the information obtained above, a construction of summary tables of the articles, classified according to the type of learning, is performed, highlighting the organ, reference, year, methodology, database, modality, and results. Finally, the discussion, conclusions and challenges related to this topic are presented. The findings indicate that the review articles reported in the literature have not addressed the relationship between ELMs and medical imaging in depth and have excluded key aspects, which are developed in this article. These aspects include a comprehensive analysis of the most popular imaging modalities, a detailed description of both the most popular databases and the most relevant databases for the machine learning community and, finally, the incorporation of schemes that explain the fundamentals of the main learnings considered when generating ELM-based trained smart models, which can be useful for medical image processing. • Papers on Extreme Learning Machine medical imaging applications are discussed. • Supervised, unsupervised and semi-supervised learning are considering. • The evolution of pseudo-inverse idea is examined. • Image repositories using in medical imaging are reviewed • Research trends on Extreme Learning Machine medical imaging are presented. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is a class of machine learning systems or methods based on feedforward neural networks, which are suitable for supervised learning problems. The ELM is regarded as a special kind of FNN in the research, which is characterized by the fact that the weights of hidden layer nodes are randomly or artificially given. As a result, the ELM feature mapping is random. The generic approximation theorem states that any nonlinear piecewise continuous function may be used as the feature map. By introducing the theory of granular computing, this paper proposes a new granulation method of random sigmoid function. The Granular Sigmoid Extreme Learning Machine (GSELM) algorithm was proposed by combining the random sigmoid function with the extreme learning machine algorithm. After granulated data sets are processed by GSELM, the granulated multi-feature data will form granular vectors. The granular vector is processed in parallel, which makes the granular sigmoid extreme learning machine parallel computing. The GSELM is utilized to address the fundamental real-time issue of weather forecasting. The GSELM algorithm can predict whether the next day will be sunny or rainy more accurately and quickly, which is crucial to the field of meteorology. Several UCI data sets are used to test the feasibility of the GSELM algorithm. The verified GSELM algorithm is applied to the Australian weather forecast data set. According to the experimental findings, the GSELM algorithm can predict whether the next day will be sunny or rainy more accurately and quickly. • We propose a new granulation method of random sigmoid function. • The GSELM algorithm is to predict whether the next day will be sunny or rainy more accurately and quickly. • The algorithm has better classification performance and lower prediction error. • The correctness and effectiveness of the GSELM are verified by multi-angle experiments. [ABSTRACT FROM AUTHOR]

• Machine learning models to predict pressure in SI engine were applied. • Extreme Learning Machine (ELM) learns with single iteration and is very fast. • Proposed BBO approach was adopted in ELM design optimization. • ELM produces good results with different sets of input variables. • ELM produces better results than other employed methods. In this study, the cyclic of a spark ignition engine using octane fuel is modeled using extreme learning machine, an emergent technology related to single-hidden layer feedforward neural networks (SLFNs). The experimental engine case study was operated with five different engine speeds from 1000 to 3000 rpm, and crankshaft angle from −360° to 360° without exhaust gas recirculation. The mean effective pressure was used to indicate the cyclic variability for the mean of 100 consecutive cycles. In this study the extreme learning machine (ELM), the regularized extreme learning machine and the outlier robust extreme learning machine were applied to predict the conditions of a combustion parameter used to reflect pressure information for entire cycle in a single-cylinder compression ignition naturally aspirated engine. Prediction by ELM models is normally faster than mathematical models employed to solve a set of differential equations by iterative numerical methods. The essence of ELM is that the hidden layer of SLFNs need not be tuned. Nevertheless, the selection of an appropriate ELM topology is crucial in terms of simplicity, velocity and accuracy. The suitable determination of the number of hidden layer nodes (neurons), type of activation function, and sparse connection structure of weights and biases were obtained using a modified biogeography-based optimization approach (BBO), a population-based metaheuristic algorithm inspired on the mathematical model of organism distribution in biological systems. The experimental dataset were used to train ELM models, and the reliability of these models was assessed and compared for two case studies based on performance criteria related to accuracy, sparsity and complexity using a cross-validation procedure. After training, experimental results show that the pressure can be modeled with reasonable accuracy. The results analysis indicated that the proposed optimized ELM and its variants optimized by BBO approaches have potential for prediction the mean effective pressure showed reasonable consistency with the experimental results. [ABSTRACT FROM AUTHOR]

Increasing temperature from climate change can bring a number of different risks such as more droughts and heat waves, and increasing sea level rise. Assessment of climate change with future scenarios is essential to adapt these impacts. To provide climate change information through the outputs of general circulation models at finer resolution, a reliable and accurate downscaling model has always been of great interest. Meeting this need, artificial neural network (ANN) has been commonly employed in downscaling for nonlinear models. Extreme learning machine (ELM), a recently developed ANN, is an efficient learning algorithm for generalized single hidden layer feedforward neural networks. In light of its simple learning algorithm, we introduced a useful approach to combine the stepwise feature selection method into ELM for temperature downscaling, as stepwise ELM (SWELM), since model complexity and computational time consumption of a traditional ANN impedes application of stepwise feature selection. This SWELM is able to identify the most influential predictors in a dataset and use them to train a nonlinear model while removing the irrelevant ones. The ELM and SWELM as well as regular ANN were tested in a simulation study. Results indicated that ELM even with randomness of weights and biases in the nodes of input and hidden layers better performed than did ANN. Also, SWELM presents a capability to select the influential predictors and remove the unrelated variables. A case study with downscaling temperature of Wisconsin, USA, showed that ELM was a comparable alternative to ANN. SWELM outperformed the ANN algorithm for temperature downscaling and sometimes predicted the temperature increase larger than did others for future scenarios. The current study of temperature downscaling with the statistical tool allows assessing the possible impacts of climate change in a local scale and some developing countries where sophisticate research cannot be eligible. [ABSTRACT FROM AUTHOR]

Abstract Global advocacy to mitigate climate change impacts on pristine environments, wildlife, ecology, and health has led scientists to design technologies that harness solar energy with remotely sensed, freely available data. This paper presents a study that designed a regionally adaptable and predictively efficient extreme learning machine (ELM) model to forecast long-term incident solar radiation (ISR) over Australia. The relevant satellite-based input data extracted from the Moderate Resolution Imaging Spectroradiometer (i.e., normalized vegetation index, land-surface temperature, cloud top pressure, cloud top temperature, cloud effective emissivity, cloud height, ozone and near infrared-clear water vapour), enriched by geo-temporal input variables (i.e., periodicity, latitude, longitude and elevation) are applied for a total of 41 study sites distributed approximately uniformly and paired with ground-based ISR (target). Of the 41 sites, 26 are incorporated in an ELM algorithm for the design of a universal model, and the remainder are used for model cross-validation. A universally-trained ELM (with training data as a global input matrix) is constructed, and the spatially-deployable model is applied at 15 test sites. The optimal ELM model is attained by trial and error to optimize the hidden layer activation functions for feature extraction and is benchmarked with competitive artificial intelligence algorithms: random forest (RF), M5 Tree, and multivariate adaptive regression spline (MARS). Statistical metrics show that the universally-trained ELM model has very good accuracy and outperforms RF, M5 Tree, and MARS models. With a distinct geographic signature, the ELM model registers a Legates & McCabe's Index of 0.555–0.896 vs. 0.411–0.858 (RF), 0.434–0.811 (M5 Tree), and 0.113–0.868 (MARS). The relative root-mean-square (RMS) error of ELM is low, ranging from approximately 3.715–7.191% vs. 4.907–10.784% (RF), 7.111–11.169% (M5 Tree) and 4.591–18.344% (MARS). Taylor diagrams that illustrate model preciseness in terms of RMS centred difference, error analysis, and boxplots of forecasted vs. observed ISR also confirmed the versatility of the ELM in generating forecasts over heterogeneous, remote spatial sites. This study ascertains that the proposed methodology has practical implications for regional energy modelling, particularly at national scales by utilizing remotely-sensed satellite data, and thus, may be useful for energy feasibility studies at future solar-powered sites. The approach is also important for renewable energy exploration in data-sparse or remote regions with no established measurement infrastructure but with a rich and viable satellite footprint. Highlights • Solar energy from Australia's 41 metro, remote, & regional sites modelled with ELM. • ELM enriched with geo-temporal input (periodicity, latitude, longitude, elevation). • ELM (Random Forest, M5 Tree, & MARS) accuracies follow distinct geographic signatures. • ELM can predict solar energy in data-sparse regions with viable satellite footprints. • ELM can greatly benefit sites with unestablished measurement infrastructure. [ABSTRACT FROM AUTHOR]

Abstract This paper presents side scan sonar (SSS) image segmentation and synthesis methods based on extreme learning machine (ELM). As an algorithm derived from single-hidden layer feedforward neural networks (SLFNs), ELM has superior performance and fast learning speed with randomly generated hidden layer parameters. The SSS image segmentation uses ELM as a classifier with features generated by convolutional neural network (CNN) of multiple pathways. The CNN of multiple pathways can learn local and global features from SSS images adaptively. Taking these features as input, ELM assigns the central pixel of each input image patch of CNN to one class. Moreover, the presented SSS image synthesis method utilizes ELM as a regression algorithm, in which the non-parametric sampling algorithm is used first to synthesize coarse SSS images according to segmentation maps and sample images for each class. Then ELM trained with the coarse synthesis images and their ground truth maps (the Gaussian-filtered SSS images) synthesizes fine SSS images. Furthermore, peak signal to noise ratio (PSNR) of the synthetic SSS images with the Gaussian-filtered SSS images as ref is used as one evaluation metric for segmentation performance. Experimental results demonstrate that the SSS image segmentation method combining convolutional features with ELM outperforms typical CNN and support vector machine (SVM), and the presented SSS image synthesis method and the evaluation metric are applicable. [ABSTRACT FROM AUTHOR]

In this work, we address some issues in the classification of varying length patterns of speech represented as sets of continuous-valued feature vectors using kernel methods. Kernels designed for varying length patterns are called as dynamic kernels. We propose two dynamic kernels namely segment-level pyramid match kernel (SLPMK) and segment-level probabilistic sequence kernel (SLPSK) for classification of long duration speech, represented as varying length sets of feature vectors using extreme learning machine (ELM). SLPMK and SLPSK are designed by partitioning the speech signal into increasingly finer segments and matching the corresponding segments. SLPSK is built upon a set of Gaussian basis functions, where half of the basis functions contain class-specific information while the other half implicates the common characteristics of all the speech utterances of all classes. The computational complexity of SVM training algorithms is usually intensive, which is at least quadratic with respect to the number of training examples. It is difficult to deal with the immense amount of data using traditional SVMs. For reducing the training time of classifier we propose to use a simple algorithm namely ELM. ELM refers to a wider type of generalized single hidden layer feedforward networks (SLFNs) whose hidden layer need not be tuned. In our work, we proposed to explore kernel based ELM to exploit dynamic kernels. We study the performance of the ELM-based classifiers using the proposed SLPSK and SLPMK for speech emotion recognition and speaker identification tasks and compare with other kernels for varying length patterns. Experimental studies showed that proposed ELM-based approach offer a 10-12% of relative improvement over baseline approach, and a 3-9% relative improvement over ELMs/SVMs using other state-of-the-art dynamic kernels. [ABSTRACT FROM AUTHOR]

The two-dimensional morphology of the cladding layer has an important influence on the quality of the cladding layer and the crack tendency. Using the powerful nonlinear processing ability of the single hidden layer feedforward neural network, a prediction model between the cladding technological parameters and the two-dimensional morphology of the cladding layer is established. Taking the cladding parameters as the input and the two-dimensional morphology of the cladding as the output, the experimental data is used to train the network to achieve a high-level mapping of the input and output. On this basis, the algorithm of extreme learning machine is used to optimize the single hidden layer feedforward neural network to overcome the problems of slow convergence speed, more network training parameters and easy local convergence in back-propagation algorithm. The results show that the relationship between the cladding process parameters and the two-dimensional morphology of the cladding layer can be roughly reflected by the back-propagation algorithm. However, the prediction results are not stable and the error rate is between 10% and 40%. The neural network optimized by the extreme learning machine is utilized to get a better prediction result. The error rate is 10–20%. [ABSTRACT FROM AUTHOR]

Highlights • Compiled survey data of 415 events from 52 rivers which span across 3 continents. • The GEP and ELM approaches are applied. • Model input variables include friction slope and relative smoothness. • Developed a model for the Darcy–Weisbach friction factor for ungauged streams. • The new models out-performs past models of similar parameters. Abstract The most uncertain parameter in determining the stage-discharge relationship of an ungauged stream is the friction factor, a parameter for which a gauged stream can be back-calculated using hydrometric survey data that has been compiled over a wide range of flow conditions. The existing friction factor models for ungauged streams that do not require hydrometric survey data as input can have very large prediction errors. In this study, 415 streamflow events collected from 52 rivers across three continents were assembled to allow for the use of a suitable global dataset size/range to develop a robust model for the prediction of the friction factor in ungauged streams using two machine learning algorithms (Gene Expression Programing (GEP) and Extreme Learning Machine (ELM)). The new GEP and ELM models outperformed existing models with significantly improved R-squared values of 0.76 and 0.78, respectively. The combination of the two input parameters (relative smoothness and the friction slope) allowed the new models to more accurately predict the friction factor for a wider range of streams and flow conditions. The forecasting uncertainty of the developed GEP and ELM models were compared with past models and found to be the least uncertain, with Width Uncertainty Band (WUB) values of ±0.0536 and ±0.0504, respectively. For the first time in this field of research, partial derivative sensitivity analysis was applied to the trends of the friction factor estimation by GEP and ELM. It was found that GEP and ELM models are extremely sensitive to friction slope in comparison with relative smoothness. The GEP and ELM model results for predicting the Darcy–Weisbach friction factor were compared with different existing relationships, and the superior performance of the proposed models was illustrated. [ABSTRACT FROM AUTHOR]

Gear fault levels are an important issue and can show the operating status of gears. In this paper, the extreme learning machine (ELM) learning method is regarded as a basic algorithm for classifying gear fault levels. In order to improve the generalisation of the ELM and obtain a better classification performance, the wavelet kernel concept was introduced to the ELM and thereby a structure called a wavelet kernel extreme learning machine (WK-ELM) was constructed. In terms of the WK-ELM, because the dilation factor of the wavelet kernel and the number of hidden neurons of the ELM are important for the classification performance, particle swarm optimisation (PSO) was used to search for the most appropriate values of the solved problem. What is more, PSO was also optimised by a self-adaptive inertia weight that formed a novel structure, that is, self-adaptive inertia weight particle swarm optimisation (SAPSO). So far, an automatic fault diagnosis system for gear fault levels based on the SAPSO-WK-ELM has been proposed in this paper. Aimed at recognising different gear fault levels at different rotational speeds, ranking mutual information (RMI) and standardised mutual information (SMI) techniques were applied to select sensitive features for gear fault levels. Compared with other relational algorithms previously used, the results of this study, including simulation and experimental data, have demonstrated that the SAPSO-WK-ELM can achieve an outstanding classification performance. [ABSTRACT FROM AUTHOR]

Fairly recently, extreme learning machine (ELM) has been proposed as a single-hidden layer feedforward neural network (SLFN), where the input weights are randomly initiated and never updated, and the output weights are analytically computed. Setting the parameters of the hidden layer randomly may not be always effective if the function that is learned is not simple and the amount of labeled data is not small, even if theoretical studies have shown that ELM maintains the universal approximation capability. To address this issue, we propose a new approach inspired by the Bayesian paradigm as an alternative to the random initiation of the hidden node parameters. The idea behind this model is that we can use the information (prior knowledge) about a certain labeled data through the correlation between attributes and decision classes. The prior knowledge is acquired through the Goodman-Kruskal Gamma rank correlation between attributes and labels, assuming that the input weights should be related to the inuence of attributes upon labels. Five publicly available high-dimensional datasets regarding cancer (breast, lung, colon, and ovarian) related to cDNA arrays, DNA microarray, and mass spectroscopy are used for experimentation and model assessment. We compared the performance of this classifier with that of three 'neighboring' algorithms, such as a basic ELM, a SLFN trained by backpropagation (BP) algorithm, and a radial basis function network (RBF). The experimental results undoubtedly indicated that the proposed variant of ELM is very effective and its performance is superior to that of the comparison models. [ABSTRACT FROM AUTHOR]

Dysphagia is a common complication of cerebrovascular accidents, and greatly affects the prognosis of patients. To meet the portability requirement for instruments used in the diagnosis of dysphagia in clinical settings, a novel sensor for measuring tongue pressure is designed to help doctors evaluate the severity of dysphagia. A sensor with a special beam structure converts the deformation of strain gauges to analog voltage signals through a Wheatstone bridge, then translates the result to a value for tongue pressure. The relationship between the tongue pressure and voltage is fitted by a least squares method and also by using an extreme learning machine. The two sets of results are compared and the superiority of using the extreme learning machine is verified. For the designed tongue-pressure sensor with an outer diameter of 10 mm and a thickness of 3 mm, the detection range is from 0 to 15 kPa, and the relative error of measurement can be controlled within 0.91%. [ABSTRACT FROM AUTHOR]

Copyright of Electric Machines & Control / Dianji Yu Kongzhi Xuebao is the property of Electric Machines & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Extreme learning machine (ELM) was proposed for training single hidden layer feedforward neural networks (SLFNs), and can provide an efficient learning solution for regression problem. However, the prediction error of ELM is unavoidable due to its limited modeling capability, and the nonlinear and stochastic nature of the regression problem. In this paper, a novel ELM, residual compensation ELM (RC-ELM), is proposed for regression problem by employing a multilayer structure with the baseline layer for building the feature mapping between the input and the output, and the other layers for residual compensation layer by layer iteratively. Two real world applications, device-free localization (DFL) and gas utilization ratio (GUR) prediction in blast furnace, are used for experimental testing of the proposed RC-ELM. Experimental results show that RC-ELM has better generalization performance and robustness than other machine learning approaches, including the classic ELM, weighted K-nearest neighbor (WKNN), support vector machine (SVM), and back propagation neural network (BPNN). [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) can be considered as a single-hidden layer feedforward neural network (FNN)-type learning system, whose input weights and hidden layer biases are randomly assigned, while output weights need tuning. In the framework of regression, a fundamental problem of ELM learning is whether the ELM estimator is universally consistent, that is, whether it can approximate arbitrary regression function to any accuracy, provided the number of training samples is sufficiently large. The aim of this paper is two-fold. One is to verify the strongly universal consistency of the ELM estimator, and the other is to present a sufficient and the necessary condition for the activation function, where the corresponding ELM estimator is strongly universally consistent. The obtained results underlie the feasibility of ELM and provide a theoretical guidance of the selection of activation functions in ELM learning. [ABSTRACT FROM AUTHOR]

An extreme learning machine (ELM) is a popular analytic single hidden layer feedforward neural network because of its rapid learning capacity. However, vanilla dense ELMs are affected by the overfitting problem when the number of hidden neurons is high. Further direct consequences of the density are decreases in both the training and prediction speeds. In this study, we propose an incremental method for sparsifying the ELM using a newly devised indicator driven by the condition number in the ELM design matrix, in which we call sparse pseudoinverse incremental-ELM (SPI-ELM). SPI-ELM exhibits better generalization performance and lower run-time complexity compared with ELM. However, the sparsification process may negatively affect the learning speed of SPI-ELM; thus, we introduce an iterative matrix decomposition algorithm to address this issue. We also demonstrate that there is a useful relationship between the condition number in the ELM design matrix and the number of hidden neurons. This relationship helps to understand the random weights and nonlinear activation functions in ELMs. We evaluated the SPI-ELM method based on 20 benchmark data sets from the University of California Irvine repository and three real-world databases from the computer vision domain. [ABSTRACT FROM AUTHOR]

One of the most important issues for the development of a motor-imagery based brain-computer interface (BCI) is how to design a powerful classifier with strong generalization capability. Extreme learning machine (ELM) has recently proven to be comparable or more efficient than support vector machine for many pattern recognition problems. In this study, we propose a multi-kernel ELM (MKELM)-based method for motor imagery electroencephalogram (EEG) classification. The kernel extension of ELM provides an elegant way to circumvent calculation of the hidden layer outputs and inherently encode it in a kernel matrix. We investigate effects of two different kernel functions (i.e., Gaussian kernel and polynomial kernel) on the performance of kernel ELM. The MKELM method is subsequently developed by integrating these two types of kernels with a multi-kernel learning strategy, which can effectively explore the supplementary information from multiple nonlinear feature spaces for more robust classification of EEG. An extensive experimental comparison with two public EEG datasets indicates that the MKELM method gives higher classification accuracy than those of the other competing algorithms. The experimental results confirm that superiority of the proposed MKELM-based method for accurate classification of EEG associated with motor imagery in BCI applications. Our method also provides a promising and generalized solution to investigate the complex and nonlinear information for various applications in the fields of expert and intelligent systems. [ABSTRACT FROM AUTHOR]