Search

Evaluating and forecasting stability across different conditions is essential since smart grid stabilization is among the most significant characteristics that could be employed to assess the functionality of smart grid design. Some intelligent methods to foresee stability are required to mitigate unintended instability in a smart grid design. This is due to the rise in domestic and commercial constructions and the incorporation of green energy into smart grids. It is currently hard to forecast the stability of the smart grid. In this framework, a smart grid with reliable mechanisms is being implemented to meet the fluctuating energy demands as well as providing more availability. The involvement of consumers and producers is one of the many factors influencing the grid's stability. This study suggested a novel approach for locating stability statistics in smart grid systems utilizing machine learning frameworks was presented. This paper outlined the multi-layer perceptron-Extreme Learning Machine (MLP-ELM) methodology to predict the sustainability of the smart grid. Additionally, this utilized the principal component analysis (PCA) approach for extracting features. In addition to an empirical assessment and a comparison to various approaches, this article presents an implementation result for smart grid stability. Simulation findings demonstrate that the suggested MLP-ELM approach outperforms traditional machine learning techniques, with accuracy reaching up to 95.8%, precision at 90%, recall at 88%, and F-measure at 89%. [ABSTRACT FROM AUTHOR]

Digital forensic aims to provide an assistance for making decisions about a crime by looking at a file content which usually involves image files such as GIF, BMP, JPEG and etc. JPEG is a very popular image file format. It has less structured contents than other images which makes its recovery possible in the absence of some file system metadata. However, an essential problem of which is fragmented JPEG file intertwined with non-JPEG files and/or Bifragmented in the scan area. This paper proposes RX_myKarve as a new file carving framework for solving a number of forensic recovery problems including fragmentation. The RX_myKarve basic design includes a structure-based and content-based carving approaches. It adopts machine learning and evolutionary algorithms in its main components of identification validation and reassembling. The identification and validation techniques encompass an Extreme Learning Machine (ELM) for identifying and filtering the image data in the scan area. The reassembling technique encompasses a genetic algorithm to reconstruct the data from fragmented pieces to a complete image. The main contribution of the paper lies on the reassembling of fragmented image file clusters in the scan area. The RX_myKarve is tested and evaluated by using the Digital Forensic Research Workshop (DFRWS) 2006 and 2007 forensic challenge datasets. The results show that the RX_myKarve is able to carve and fully recover all the giving cases of the DFRWS-2006 dataset, which are 19 images, and all the relevant cases of the DFRWS-2007 dataset, which are 18 images. This improvement in file carving is mostly attributed to the novel identification and reassembling techniques. [ABSTRACT FROM AUTHOR]

Stock price prediction is a significant index which helps to achieve maximum benefit with minimum risk by increasing the decision making capability of financial investigators and investors. However, the problem of short term stock price prediction is a complex task due to its uncertainty, discontinuity, and random nonlinear nature. In this paper, a prediction model is proposed to predict random nonlinear stock market price using Intrinsic Time-Scale Decomposition (ITD), Cluster based Modified Crow Search Algorithm (CMCSA), and Optimized Extreme Learning Machine (OELM). ITD is adopted to decompose the non-stationary stock price data into some Proper-Rotation-Components (PRCs) and a residual component. ITD is used to convert non-stationary stock price data to stationary data which are simpler and steady for analysis. The CMCSA is proposed by modifying Crow Search Algorithm (CSA) with better capability to select optimal weight and biases of ELM. Thereafter, the optimized ELM is used to predict the PRCs and residual component individually which are then incorporated to predict closing price of short term stocks. The effectiveness of proposed CMCSA is tested and validated by solving benchmark problems. The experimental study indicates that the proposed ITD-CMCSA-OELM model outperforms the CMCSA-OELM, CSA-OELM, DE-OELM (Differential Evolution optimized ELM) and ANN models. [ABSTRACT FROM AUTHOR]

In this paper soft computing fuzzy proposition/rule based adaptive extreme learning is proposed. This article illustrates the impact of agricultural solar panel (AgSP) and its operating condition/state during the farming seasons and hence safety of energy system sustained. Extreme learning machine (ExLM) used as learning machine (LM) for artificial intelligence (AI) training to predict the operating state of applied AgSP green energy unit. soft computing Fuzzy rules are framed for every instant of leaning machine to identifying the lower mismatch conditions and avoid the false prediction. Higher and lower limits of adaptive resonance theory (ART) support LM (ART-LM) is properly used by providing unusual dust formation (UnDFR) data and usual/normal dust formation (UsDFR) data for AI training. Outcome of AI neural net is determined by resonant neuron net (RSNN). Predicted variable from ART-LM is calculated with higher and lower limits of dataset captured from applied energy common node (CN). Many test conditions of dust formation on solar photovoltaic (PV) has been validated to predict the state of applied energy system. For any UnDFR confirmation, entire AgSP based distributed generator (DG) unit will isolate from common node/utility grid. Proposed ART-LM based AI algorithm has been validated even for charging state events of electrical vehicle (EV) during the abnormal conditions. • Operating state of PV energy system is identified using ART-LM for all dust conditions. • Accurate mismatch extracted by fuzzy rule extreme learning to protect PV energy system panels. • Fuzzy propositions are confirmed by fractional fuzzy inference reasoning during identification. • SOC of electrical vehicle during abnormal conditions is assessed to obtain energy system safety. [ABSTRACT FROM AUTHOR]

• A hybrid method is proposed for accurate detection of high impedance fault. • Empirical mode decomposition is used for feature extraction. • EMD with deep learning technique obtained better accuracy in distribution system. • Approximate fault location also identified by proposed technique. An uninterrupted and well-managed energy distribution system requires an effective protection system against various faults and uncertainties. Power system networks have a built-in issue called High Impedance Faults (HIFs), which can't be detected by standard protection mechanisms. This paper deals with the aforementioned issue by combining a deep learning technique (DLT) with a signal decomposition method known as Empirical Mode Decomposition (EMD). This approach utilizes the EMD for the extraction of multiple features from the input current signal, and LSTM neural network is employed for the accurate classification of HIF signals. The comparison results with various EMD methods and various switching events are also performed. Finally, this paper proposes an approximate location identification of HIFs. The simulation results demonstrate the effectiveness of the proposed method for detection in various fault scenarios. [Display omitted] [ABSTRACT FROM AUTHOR]

Longitudinal impulse, as a common dynamic problem of heavy haul trains, could induce the lateral instability of the coupler and the separation of the locomotive and wagon connection and thus seriously hinder the train running safety. The coupler force undergoes complex changes during longitudinal impulse transmission and exhibits strong nonlinear characteristics, which poses significant challenges to the identification of the coupler force. To address these issues, this paper reports a novel quantitative method for the coupler force identification of heavy haul locomotives. Firstly, the moving average filtering method is used to preprocess the signal of longitudinal relative displacement between the coupler and carbody (LRDCC), and the approximate relative velocity (ARV) feature is also extracted from the preprocessed signal. Then, a Convolutional Neural Network (CNN) model is constructed to extract high-level features from LRDCC and ARV. The model with randomly initialized weight parameters does not require additional training and thus reduces the computational cost. Finally, an Extreme Learning Machine (ELM) is used as the regression layer to process the extracted high-level features and further improve the identification performance. Additionally, the dung beetle algorithm is used to obtain the optimal model parameters to improve the coupler force identification performance. Not only a dynamics simulation but a field test is carried out to show that the proposed method could accurately detect the coupler force of heavy haul locomotives. Furthermore, the proposed method shows promising prospects in replacing the traditional monitoring method under the actual long-term working conditions of trains. • An indirect measurement scheme is proposed for coupler force dynamic identification. • The proposed network model presents high identification Accuracy and efficiency. • Method showcases strong generalization under complex, long-term train operations. [ABSTRACT FROM AUTHOR]

Implementing key engineering solutions to optimise the operation of energy industries requires daily electricity demand forecasting and including uncertainty, to promote markets insight analysis as part of their strategic planning, regulating and supplying electricity to consumers. This paper proposes hybrid artificial intelligence models combining convolutional neural networks (CNN) as a feature extraction algorithm with extreme learning machines (ELM) as a framework to predict electricity demand with confidence intervals generated by Kernel Density Estimation (KDE) approaches. In order to develop CELM-KDE model, time-lagged series of daily electricity demand with local climate variables based on the air temperature, atmospheric vapour pressure, evaporation, solar radiation, humidity and sea level pressures are used to train the proposed CELM-KDE hybrid model. In order to fully evaluate the newly developed model from a point-based, as well as a probabilistic prediction strategy, the observed and predicted electricity demand as well as the probability distribution of errors are analysed using KDE method that operates without prior data distribution assumptions. Based on observed and predicted electricity demand and the relevant probabilistic confidence intervals generated by the CELM-KDE model, the final results show that the proposed method attains significantly better probability interval predictions than traditionally-used point-based models. The proposed CELM-KDE model is demonstrated to be highly effective in providing a comprehensive coverage of predicted errors, as well as providing greater insights into the average bandwidth and detailed predicted electricity demand in the testing stage. The results also indicate that the proposed hybrid model is a reliable decision support tool to develop engineering solutions in area of energy modelling, monitoring and forecasting, which could potentially be useful to the industry policymakers. We show that the point-and probabilistic-based electricity demand predictive models can be employed as an effective tool to improve accuracy of forecasting and provision of insights for national electricity markets and key energy industry stakeholder application tools. [Display omitted] • A hybrid deep learning model for daily electricity demand prediction is proposed. • A Kernel Density Estimation is applied to derive probabilistic prediction intervals. • The algorithm quantifies uncertainties in point-based electricity demand predictions. • The proposed model outperforms deep learning models using statistical uncertainty indicators. [ABSTRACT FROM AUTHOR]

The force feedback technology has a crucial impact on the precise control of teleoperation system. Robots in fields such as minimally invasive surgery and nuclear waste cannot integrate force sensors to obtain force feedback due to their end size and harsh working environment. In order to obtain end-effector force feedback in sensorless situation, a sensorless force estimation model based on artificial neural network is defined in this paper. For improving the model prediction ability, a new Multi-layer Depth Extreme Learning Machine (MDELM) is proposed. Firstly, the network structure of the extreme learning machine is redesigned, and the smoothing function and Gauss-Laplacian function are constructed as the feature extraction layer and enhancement layer of the MDELM model. Then, to further improve the prediction performance of MDELM, an improved Sooty Tern Optimization Algorithm (STOA) is introduced to optimize the parameters of the model. The results show that the proposed force estimator outperforms the existing model with an MAE of less than 0.205, which is at least 18.65% lower than the existing model. In addition, when the acceleration of the remote operating system is a fixed constant or the information is not available，a sensorless force feedback system can be constructed by combining motor torque, joint position and joint velocity parameter. In general, this study provides an effective force estimation solution for teleoperation system without force sensor. • An effective force estimation model based on artificial neural network is proposed. • Smoothing and Gauss-Laplacian function are used to redesign the structure of ELM. • An improved sooty tern optimization is applied to optimize the model. • The proposed model can be constructed by different parameter combinations. [ABSTRACT FROM AUTHOR]

Energy demand prediction of building heating is conducive to optimal control, fault detection and diagnosis and building intelligent. In this paper, the prediction models are developed using machine learning methods including extreme learning machine (ELM), multiple linear regression, support vector regression and BP neural network. The feature variable sets are optimized through correlation analysis and supplementing indoor temperature. Besides, this paper proposed a strategy to determine the time ahead of prediction model. The thermal response time of building is used as the prediction time step of model. The prediction performances of ELM models with different hidden layer nodes are analyzed and contrasted. The actual data of the building heating using ground source heat pump system are collected and used to test the performances of the models. The results show that the thermal response time of the building is about 40 minutes. Four feature sets are obtained and performances of models with FS4 are better. For different machine learning methods, the performances of ELM models are better than others. In addition, the optimal number of hidden layer nodes is 11 for the ELM model with FS4. [ABSTRACT FROM AUTHOR]

Climate change is the biggest challenge faced by the world. It has already started affecting the weather patterns leading to disruption of normal life. Detecting change helps to monitor and plan the Earth's resources in an efficient manner. An important factor in climate change is the change in the green cover. Non-availability of standard datasets and limited labeled data points makes it difficult to attain high accuracies in change detection. In this paper, we have proposed a modified ensemble of extreme learning machines (mAEELM) for change detection in green cover to increase the accuracy of the change detection process. It uses Extreme Learning Machine (ELM) as the base classifier. Different ELMs are trained with different configuration so that they have different learning capabilities. These ELMs are combined to create an ensemble and it is then adapted based on the accuracy of the individual ELMs. The ensemble is then pruned to eliminate the ELMs which are not contributing towards the overall result of the ensemble, to make it more efficient. The proposed algorithm has been applied for detecting change on two areas of Gandhuan, Punjab and Chaparkaura Kham, Uttar Pradesh, India. The algorithm shows an average accuracy of 97.8% on both the datasets. [ABSTRACT FROM AUTHOR]

In this paper, a novel bearing fault diagnosis approach based on pseudo fourth-order moment is proposed and verified. Based on the wavelet decomposition of different vibration signals, the pseudo fourth-order moment is calculated, and a new fault feature—the feature angle is proposed. Feature angle between these pseudo fourth-order moments is obtained, and corresponding working condition maybe characterized by this feature angle. The ranges of these feature angles are determined by simulation experiments with a large amount of data. An assessment index (namely selection index of optimal data size) is constructed to select the optimal amount of computational data. Meanwhile, extreme learning machine (ELM) model is established to classify different working conditions. According to the ELM model obtained from training data, the accuracy of test data classification reaches 95.42%, which proves the effectiveness of present bearing fault diagnosis method. • Effective feature angle between pseudo fourth-order moment is constructed. • A novel assessment index is developed to determine the optimal data amount. • Gaussian kernel function is carried out to reconstruct the feature angle. • Diagnosis accuracy up to 95.8% is obtained on basis of this new feature. [ABSTRACT FROM AUTHOR]

The past decade has witnessed an explosive growth of data streams in Internet, biometrics, remote sensing and other fields. Nowadays many supervised incremental/online learning approaches have been developed, to avoid retraining and reduce the computational complexity when data come chunk by chunk. However, these methods can’t obtain satisfied performance when the labeled samples are limited. In this paper, we propose an Incremental Laplacian Regularization Extreme Learning Machine (ILR-ELM) for semi-supervised online learning, by utilizing both labeled and unlabeled samples. Unlike most of the existing semi-supervised incremental/online learning algorithms, this paper not only proposes incremental/online learning mechanism for data chunk containing both labeled and unlabeled samples but also proposes incremental/online learning mechanism for data chunk containing only unlabeled samples. The latter case is more common in practical applications because there is usually no enough time to label the samples for continuously arriving data stream. The alternative analytical solutions of ILR-ELM for the two incremental/online learning mechanisms are also presented. The performance of ILR-ELM is evaluated on three benchmark machine learning data, and the results show that it can achieve near accurate and robust classification/regression with a small number of labeled data, and outperforms the incremental/online learning approaches. Compared with the supervised and the comparative semi-supervised incremental/online learning methods, the generalization accuracy of ILR-ELM is increased by nearly 9% and 2% respectively for the classification problem. For the regression problem, the generalization error of ILR-ELM is reduced by nearly 14% than the supervised incremental/online learning methods and 1% than compared semi-supervised incremental/online learning methods Furthermore, ILR-ELM can achieve comparable prediction to semi-supervised batch learning, using less time and Random Access Memory (RAM). [ABSTRACT FROM AUTHOR]

As clean energy facilities are increasingly integrated into power distribution networks, the incidence of multiple power quality disturbances (MPQDs) is on the rise. Currently, most MPQDs classification models rely on supervised learning, which demands a substantial amount of labeled data. However, obtaining labeled MPQDs data from the real world is often a time-consuming and labor-intensive process, requiring annotation by experienced engineers, particularly for events involving MPQDs. To tackle this challenge, we introduce an innovative active learning (AL) approach known as Adaptive Weighting Multi-Strategy AL (AWMSAL) for MPQDs classification. In our framework, AWMSAL simultaneously considers multiple strategies using rank aggregation to select MPQDs data that is both full-information and highly representative for labeling. In addition, our method employs a unique weight calculation function to dynamically adjust weights based on the differences in data values observed with various strategies during the AL process. To enhance the classifier performance, we incorporate the Laplacian manifold regularizer into the Extreme Learning Machine in both supervised and unsupervised settings. We compared the performance of the AWMSAL method against several state-of-the-art active learning algorithms using synthetic and hardware-generated data sets. The results demonstrated that AWMSAL achieved recognition rates exceeding 99% in a shorter number of iterations. When the same termination condition was met, AWMSAL outperformed other active learning algorithms by 2.45% to 18.33% in terms of accuracy. • This is the first study to explore active learning methods for classifying multiple power quality disturbances. • Rank aggregation approach is used to combine different categories of active learning sampling strategy. • The corresponding weights are adjusted adaptively in different stages of the active learning process. • This paper proposes a classification method for multiple power quality disturbances based on Laplacian Extreme Learning Machine. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) has better operation efficiency in fault diagnosis. However, the recognition accuracy of ELM algorithm is actually affected by the activation function. Moreover, most of the testing dataset are coming from high precision and expensive sensors. In this paper, raw data are collected by a low-cost attitude sensor, which is installed on the mobile platform of a delta 3D printer. A doublet activation function is proposed to improve the performance of ELM, named doublet ELM (DELM). The proposed method is evaluated using experimental data collected from the 3D printer, and its advantages are demonstrated by comparing with other activation functions. The experimental results indicate that the proposed method leads to the highest accuracy in different hidden nodes and the testing classification rate achieves 93% and 96% using only 8.33% of the dataset for model training, for R75 and R90 sub-datasets, respectively. Moreover, compared with peer methods, such as random forest, echo state network, and so on, the results show that the present DELM exhibits the best performance in small-sample and improves the accuracy of the 3D printer fault diagnosis. • An attitude sensor was mounted on the moving platform to monitor printer conditions. • A doublet ELM activation function is proposed based on the attitude data. • The proposed method yields the highest classification rates in the small-sample case. [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]

Myoelectric signal generated by muscles is one of the bio-signals which is used by humans to control equipments. To achieve this purpose, a good myoelectric pattern recognition (M-PR) is required. The applied classifier and extracted feature sets greatly affect the success of M-PR. This paper proposes a hybrid and fast classifier, extreme learning machine (ELM) which is enhanced by improved hybrid particle swarm optimization with wavelet mutation (improved swarm-wavelet). ELM is, in essence, a single-hidden layer feed-forward neural network that keeps off iterative learning to save the training time. In addition to improving the actual performance of M-PR, we also evaluate the optimization of ELM using improved swarm-wavelet in this paper. The swarm-wavelet is improved by using the particle refresh and applying velocity improvement to avoid trapped in local minima. In ELM, the improved swarm-wavelet is used to find the most suitable parameters to increase the classification accuracy. Furthermore, this paper provides comparisons of improved swarm-wavelet-ELM, swarm-wavelet-ELM and standard swarm-ELM. The experimental results show that the improved swarm-wavelet-ELM, our proposed method, is the most accurate classifier with mean accuracy of 99.6%. [ABSTRACT FROM AUTHOR]

This paper presents a performance enhancement scheme for the recently developed extreme learning machine (ELM) for classifying power system disturbances using particle swarm optimization (PSO). Learning time is an important factor while designing any computational intelligent algorithms for classifications. ELM is a single hidden layer neural network with good generalization capabilities and extremely fast learning capacity. In ELM, the input weights are chosen randomly and the output weights are calculated analytically. However, ELM may need higher number of hidden neurons due to the random determination of the input weights and hidden biases. One of the advantages of ELM over other methods is that the parameter that the user must properly adjust is the number of hidden nodes only. But the optimal selection of its parameter can improve its performance. In this paper, a hybrid optimization mechanism is proposed which combines the discrete-valued PSO with the continuous-valued PSO to optimize the input feature subset selection and the number of hidden nodes to enhance the performance of ELM. The experimental results showed the proposed algorithm is faster and more accurate in discriminating power system disturbances. [ABSTRACT FROM AUTHOR]

Extreme learning machine is a popular machine learning technique for single hidden layer feed-forward neural network. However, due to the assumption of equal misclassification cost, the conventional extreme learning machine fails to properly learn the characteristics of the data with skewed category distribution. In this paper, to enhance the representation of few-shot cases, we break down that assumption by assigning penalty factors to different classes, and minimizing the cumulative classification cost. To this end, a case-weighting extreme learning machine is developed on a sparse cost matrix with a diagonal form. To be more actionable, we formulate a multi-objective optimization with respect to penalty factors, and optimize this problem using an evolutionary algorithm combined with an error bound model. By doing so, this proposed method is developed into an adaptive cost-sensitive learning, which is guided by the relation between the generalization ability and the case-weighting factors. In a broad experimental study, our method achieves competitive results on benchmark and real-world datasets for software bug reports identification. • A new imbalanced learning. • Adaptive cost-sensitive learning. • Error bound model for fitness function. • Deriving the relation between the generalization ability and the weighting factors. • Good performance on imbalanced issues. [ABSTRACT FROM AUTHOR]

The growing volume of data on the computer network led to increasing the challenges for intrusion detection systems to deal with high dimensions that contain irrelevant and redundant features. This consumes time and difficulty in detecting the attack correctly, with increasing false alarms rate. This problem can be solved by applying dimensionality reduction. In this paper, a wrapper feature selection model based on Differential Evolution technique is proposed for intrusion detection systems. It reduces the number of features by finding the minimum number of features without effecting on the performance of the system. The main idea is to select some features from 41 features of NSL-KDD datasets using Differential Evolution and evaluate these features by computing the accuracy using Extreme Learning Machine. Differential Evolution is continued until obtaining the minimum number of features that satisfy a high accuracy. The results have shown a better detection rate with reduced false alarm rate in five and binary classification. The proposed system achieved an accuracy of 80.15 % and 87.53 for five and binary classification respectively with a reduction in training and testing time. [ABSTRACT FROM AUTHOR]

• The ELM model is applied to predict the ionospheric propagation factor M(3000)F2. • The ELM achieves slightly higher accuracy at a faster training speed than BPNN. • Better average accuracy of ELM over the IRI in high and low solar activity years. This paper presents an novel extreme learning machine (ELM)-based prediction model for the ionospheric propagation factor M(3000)F2 at Darwin station (12.4°S, 131.5°E; −44.5°dip) in Australia. The proposed ELM model is trained with hourly daily values of M(3000)F2 from the period 1998–2014 except 2001 and 2009. The hourly daily values of 2001 (high solar activity) and 2009 (low solar activity) are used for validating the prediction accuracy. The proposed ELM for modeling M(3000)F2 can achieve faster training process and similar testing accuracy compared with backward propagation neural network (BPNN). In addition, the performance of the ELM is verified by comparing the predicted values of M(3000)F2 with observed values and the international reference ionosphere (IRI −2016) model predicted values. Based on the error differences (the root mean square error (RMSE) and the M(3000)F2 percentage improvement values M(3000)F2 IMP (%)), the result demonstrates the effectiveness of the ELM model compared with the IRI-2016 model at hourly, daily, monthly, and yearly in high (2001) and low (2009) solar activity years. The ELM also shows good agreement with observations compared with the IRI during disturbed magnetic activity. [ABSTRACT FROM AUTHOR]

• Clustering the features into some sets with highly related features and low innerredundancy. • Defining a neural tree exploiting an ELM and an inference engine in any node. • Transferring the rules extracted from any ELM to other nodes of neural tree. • Proposing Peer-to-Peer (P2P) and Server-Client (SC) models for knowledge transferring. • Classifying high dimensional data with high accuracy and without overfitting. Classification of the high-dimensional data by a new expert system is followed in the current paper. The proposed system defines some non-disjoint clusters of highly relevant features with the least inner-redundancy. For each cluster, a neural tree is implemented exploiting an Extreme Learning Machine (ELM) together an inference engine in any node. The derived classification rules from ELM are stored in the rule-base of the inference engine to recognize the classes. A majority voting is used to unify the results of the different neural trees. This structure is refereed as the Forest of Extreme Learning Machines with Rule-base Transferring (FELM-RT). The contribution of FELM-RT is to decrease the duplicated computations by using two novel interaction models between the neural trees. In the first interaction model, namely Peer-to-Peer (P2P) model, each node can share its rule-base with the other nodes of the various neural trees. In the second that is referred as Server-to-Client (S2C) model, a neural tree that works on a cluster with the best relevancy and redundancy, shares the rules with the other neural trees. In both of the models, a fuzzy aggregation technique is used to adjust the certainty of the rules. The processing time of FELM-RT decreases essentially and it improves the classification accuracy. The high results of F-measure and G-mean, show that FELM-RT classifies the high-dimensional datasets without over-fitting. The comparison between FELM-RT and some state-of-the-art classifiers reveals that FELM-RT overcomes them specially on the datasets with more than 3 million features. [ABSTRACT FROM AUTHOR]

• Breast cancer diagnosis using evolving deep convolutional neural network. • Evolution of ZFNet network using extreme learning machine for breast cancer diagnosis. • The development of an Extreme Learning Machine using an improved Chimp Optimization Algorithm. • Investigating the effectiveness of Wiener and CALHE filters in identifying breast cancer. • Development and improvement of the chimp optimization algorithm using dynamic control parameters. Today, diagnostic systems based on artificial intelligence play a significant role in confirming doctors' recommendations. These systems are becoming effective tools in clinical treatment. In this paper, we propose a new method for identifying atypical breast cancer based on the ZFNet network for breast mammography images. Initially, the Wiener and CALHE filters are used in order to evaluate the effectiveness of the preprocessing step. Following this, a pre-trained ZFNet was modified and trained on the CBIS-DDSM dataset. Furthermore, an extreme learning machine (ELM) was used to replace the remaining few layers at the very end. Moreover, a method was presented for estimating the optimum number of layers that should be replaced in the structure. In the end, ELM was developed in order to enhance the classification performance. This was accomplished by utilizing an improved version of the Chimp Optimization Algorithm (called SWChOA), along with four other benchmark meta -heuristic optimization algorithms. These algorithms were WSO, COA, AVOA, and AHA. Accuracy, precision, specificity, sensitivity, Matthew's correlation coefficient (MCC), and F1-score were the six popular metrics that were used to investigate the diagnostic performance of our method and to compare it to the performance of other well-known methods. Precision-recall curves and area of interest (ROI) curves were also utilized in this investigation. The approach known as ZFNet-SWChOA-ELM was shown to have the highest level of performance based on the findings of investigations that made use of a 10 hold-out validation. [ABSTRACT FROM AUTHOR]

Organ transplantation is the ultimate option to treat terminal illness by transplanting the deceased or damaged organs with healthy organs for improving the patient's life expectancy. The number of organs needed and the organs available for transplantation vary enormously. The tremendous advancements in utilizing big data analytics in the healthcare system make it efficient to explore decision-making information. To make optimal decisions in organ transplantation, this paper proposes a modified convolutional neural network-hybrid extreme learning machine (MCNN-HELM) based prediction model. The proposed MCNN-HELM model utilizes three different real-time datasets as inputs which contain records of liver, heart, and lung transplantation details of the donor and recipient. At first, the missing values and inaccurate data present in real-time datasets are removed via pre-processing. The pre-processed data are then trained using the MCNN-HELM model that efficiently determines the suitable donor for the recipient by minimizing the waiting time of the recipient for the matching organ donor. Moreover, the MCNN-HELM model gives initial preference to patients with high-risk rates to improve their quality of life. The proposed MCNN-HELM model achieves training accuracy of 97.5% with a computational time of 2.2 s, while the precision value of estimated factual outcomes, potential outcomes, and the accuracy of the best donor type are obtained by 16.3582, 16.1401, and 0.6784 which are more efficient than other state-of-the-art methods. [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]

Promoting low-carbon development in the iron and steel industry (ISI) is essential for China to achieve the carbon neutrality targets. This paper separately adopts the Logarithmic Mean Divisia Index (LMDI) technique and the Mean Impact Value (MIV) method to analyze the impact of driving factors on the CO 2 emissions of ISI in the historical and future dimensions. Furthermore, this paper establishes the extreme learning machine model optimized by the bat algorithm (BA-BP) to explore the carbon emission reduction pathways of ISI in the business-as-usual (BAU) scenario, the low-speed, medium-speed and high-speed development scenarios considering the constraints of carbon neutrality targets. The results reveal that: (1) Production capacity and energy efficiency are important drivers of CO 2 emissions in ISI; (2) The emission reduction situation is not optimistic under the BAU scenario, and it is difficult to accomplish the carbon neutrality goals by 2060; (3) Under the most ideal emission reduction pathway (corresponding to the high-speed development scenario), ISI will reach its peak in 2022 with the peak value of 2143.42 MtCO 2. Compared to the peak year, the CO 2 emissions will be reduced by 654.69 MtCO 2 and 1558.61 MtCO 2 in 2030 and 2050, respectively. Moreover, the achievement of short-term and long-term emission reduction targets depends on production capacity decline and technological progress, respectively. The optimal emission reduction pathway provides a reference for ISI to formulate periodic emission reduction targets. • The improved extreme learning machine is employed to predict the carbon emissions. • The emission reduction pathways are explored under the carbon neutrality target. • Controlling production capacity is a crucial reduction strategy. • The energy rebound effect is supposed to be weakened. • The application of advanced technologies will greatly promote emission reduction. [ABSTRACT FROM AUTHOR]

Development of efficient methods for processing the online data is interesting as well as challenging in the computing scenario of data intensive applications, especially in streaming. Because of the inherent computational nature of Extreme Learning Machine, the non-iterative learning mechanism, it has undergone serous studies and exploitation especially in the domain of online data analysis. This paper gives a simple and effective strategy for updating the learned parameters, the knowledge of a machine learning system, in a computationally better perspective comparing with the existing state-of-the-art learning techniques. The performance of different measures for the central tendency is analyzed in this work. It is found that the results are comparable in respect of normal models. The overall performance of the proposed method with LIBSVM data sets gives an interesting direction for the improvement of learning machines for online data processing. [ABSTRACT FROM AUTHOR]

When extreme learning machine (ELM) is used to cope with classification problems, the ±1 is commonly used to construct the label vector. Since ELM adopts the square loss function, this means that it tends to force the margins of all the training samples exactly equaling one from the perspective of margin learning theory, which is unreasonable to some extent. To overcome this hard margin flaw, in this paper a soft extreme learning machine (SELM) is proposed, which flexibly sets a soft target margin for each training sample. Through solving a series of regularized ELMs (RELMs), SELM can be computed efficiently. Based on SELM, an improved SELM (ISELM) is proposed to deal with imbalanced classification problems, which can keep the same computational efficiency as SELM via solving a series of weighted RELMs. From the experimental results on benchmark data sets, the effectiveness and feasibility of SELM and ISELM are confirmed. More importantly, when they are applied to fault detection of aircraft engine, they are promising to be developed as the candidate techniques for it, and ISELM is especially in favor. [ABSTRACT FROM AUTHOR]

• Continuous double auction is applied to facilitate prosumer-consumer interactions. • A market prediction model is designed to model the market from a data perspective. • The market predictor is successfully integrated into the prosumer operation model. • The proposed model simultaneously improves the prosumer operation and market profit. With increasing prosumers employed with flexible resources, advanced demand-side management has become of great importance. To this end, integrating demand-side flexible resources into electricity markets is a significant trend for smart energy systems. The continuous double auction (CDA) market is viewed as a promising P2P (peer to peer) market mechanism to enable interactions among demand side prosumers and consumers in distribution grids. To achieve optimal operations and maximize profits, prosumers in the electricity market must act as price makers to simultaneously optimize their operations and trading strategies. However, the CDA-based market is difficult to model explicitly because of its information-based clearing mechanism and the stochastic bidding behaviors of its participants. To facilitate prosumers actively participating in the CDA market, this paper proposes a novel prediction-integration strategy optimization (PISO) model. A surrogate market prediction model based on Extreme Learning Machine (ELM) is developed, which learns the interaction relationship between prosumer bidding actions and market responses from historical transaction data. Moreover, the prediction model can be conveniently transformed and integrated into the prosumer operation optimization model in the form of constraints. Therefore, prosumer operations and market trading strategies can be jointly optimized through the proposed approach, facilitating the integration of flexible resources into electricity markets. Numerical studies demonstrate the effectiveness of the proposed model by comparing with existing CDA trading strategies under various market conditions. [ABSTRACT FROM AUTHOR]

Abstract Contemporary face recognition system is often based on either 2D (texture) or 3D (texture + shape) face modality. An alternative modality that utilizes range (depth) facial images, namely 2.5D face recognition emerges. In this paper, we propose a 2.5D face descriptor that based on the Regional Covariance Matrix (RCM), a powerful means of feature fusion technique and a novel classifier dubbed Random Maxout Extreme Learning Machine (RMELM). The RCM of interest is constructed based on the Principal Component Analysis (PCA) filters responses of facial texture and/or range image, wherein the PCA filters are learned from a two-layer PCA network. The RMELM is an ELM variant where the activation function is based on the locally linear maxout function, in place of typical global non-linear functions in ELM. Since the RCM is a special case of symmetric positive definite matrix that resides on the Tensor manifold; a gap exists in between RCM and RMELM, which is a vector-based classifier. To bridge the gap, we flatten the manifold by transforming the RCM to a feature vector via a matrix logarithm operator. Experimental results from two public 3D face databases, FRGC v2.0 database and Gavab database, validated our proposed method is promising in 2.5D face recognition. Graphical abstract Highlights • A learning-based Regional Covariance Matrix (RCM) based on Principal Component Analysis (PCA) is proposed as a feature descriptor for 2.5D face recognition problem. • PCARCM is demonstrated as an intra-feature (range features) and inter-feature (range and texture features) fusion container. • Random Maxout Extreme Learning Machine as classifier is proposed to couple with PCARCM on the Tensor Manifold. [ABSTRACT FROM AUTHOR]

Abstract With the frequent occurrence of extreme weather, power transmission line icing, a general phenomenon during winter which may bring serious economic losses to the electric power system, has attracted increasing attention. However, owing to the complexity nature of wire ice covering, it is essential to establish an icing thickness forecasting model with high-accuracy for guaranteeing the security and stability of the power grid. Hence, this paper proposes a hybrid model that combines wavelet transform (WT) with extreme learning machine optimized by bat algorithm (BA-ELM). The original icing data containing icing thickness and meteorological factors are first denoised by WT and then divided into several stages based on the characteristics of icing period. Bivariate correlation analysis and partial auto correlation function (PACF) are used to select the inputs of different stages. Subsequently, ELM whose input weights and bias threshold were optimized BA is built to forecast icing thickness. To verify the developed model, icing data from two power transmission lines located in Hunan province are applied for experiments. The simulation results demonstrate that not only the proposed model shows a better performance but also the staged modeling can highly improve icing thickness prediction accuracy. [ABSTRACT FROM AUTHOR]

Abstract In the visual Internet of Things (VIoT), imaging sensors must achieve a balance between limited bandwidth and useful information when images contain heavy noise. In this paper, we address the problem of removing heavy noise and propose a novel hierarchical extreme learning machine-based image denoising network, which comprises a sparse auto-encoder and a supervised regression. Due to the fast training of a hierarchical extreme learning machine, an effective image denoising system that is robust for various noise levels can be trained more efficiently than other denoising methods, using a deep neural network. Our proposed framework also contains a non-local aggregation procedure that aims to fine-tune noise reduction according to structural similarity. Compared to the compression ratio in noisy images, the compression ratio of denoised images can be dramatically improved. Therefore, the method can achieve a low communication cost for data interactions in the VIoT. Experimental studies on images, including both hand-written digits and natural scenes, have demonstrated that the proposed technique achieves excellent performance in suppressing heavy noise. Further, it greatly reduces the training time, and outperforms other state-of-the-art approaches in terms of denoising indexes for the peak signal-to-noise ratio (PSNR) or the structural similarity index (SSIM). Highlights • We address the heavy noise removing problem faced in visual Internet of Things by using the hierarchical extreme learning machine. The proposed framework contains a sparse auto-encoder and a supervised regression and a non-local aggregation. • We provide an effective patch-to-patch image denoising networks which are robust for dealing with various noise levels in both clipped and unclipped noisy model. The key advantage of this denoising network is fast training. • Experimental studies on images including both hand-written digits and natural scenes have shown that our method achieves excellent performance both in quality and efficiency. The nice performance can improve the compression ratio for data interactions in the visual Internet of Things. [ABSTRACT FROM AUTHOR]

Highlights • The adaptive weight strengthens search ability of whale optimization algorithm. • The carbon price is decomposed via multi-resolution singular value decomposition. • An improved extreme learning machine is built to predict the carbon price. • The proposed approach can be applied in China and EU ETS simultaneously. Abstract Precise prediction of carbon prices by means of single forecasting models may be difficult due to the inherent non-stationary and nonlinearity characteristics of the carbon price. This paper i proposes an innovative hybrid model for predicting the carbon price. The prediction was made through the extreme learning machine optimized by the adaptive whale optimization algorithm based on the multi-resolution singular value decomposition. The multi-resolution singular value decomposition was used to eliminate the high frequency components of the previous carbon price data. Afterwards, the carbon price was successfully decomposed into two time series—the approximation series and the detailed series. The partial auto-correlation function was employed in the approximation series for determining the input variables of the extreme learning machine. The adaptive whale optimization algorithm was utilized to optimize both the input weight matrix and the bias matrix to improve the robustness and accuracy of extreme learning machines. The empirical simulation based on four diverse types of carbon prices under carbon trading pilot programs in China found that the proposed model outperformed the other benchmark methods. Four different matured carbon future prices under the European Union national emissions trading scheme (EU ETS) were also selected for forecasting. The results showed that the proposed model performed fairly well in forecasting the EU carbon price. [ABSTRACT FROM AUTHOR]

• The main issues of aging prestressed concrete bridges are related to tendon durability. • Real-time monitoring can ensure adequate levels of control over the structural integrity. • We show that a problem-specific Extreme Learning Machine algorithm can analyze stress data to detect and localize damages affecting the prestressing system. • We propose a novel layout-aware weight generating procedure that yields statistically significant improvement over the classical Extreme Learning Machine. In the past few years, several works focused on the integration of methodologies within the field of Structural Health Monitoring to build reliable automatic damage-assessment procedures. Within this context, only a few papers specifically refer to the automatic assessment of tendon malfunctions in prestressed concrete (PSC) structures, despite the key role that this construction paradigm plays in modern infrastructure networks. This paper describes a novel Extreme Learning Machine (ELM) framework characterized by a layout-aware weight generating procedure (LA-ELM), that analyzes stress data to accurately detect and localize damages affecting the prestressing system of a target PSC bridge. A comprehensive computational study is conducted, testing the proposed methodology of three structural specimens, and comparing the proposed LA-ELM with classical Machine Learning algorithms. The numerical results evidence that the proposed methodology achieves remarkable accuracies in short computational times, and the LA-ELM obtains statistically significant improvements compared to the classical ELM implementation. [ABSTRACT FROM AUTHOR]

Parkinson's disease consists in the degeneration of the mesencephalic black substance, affecting the dopaminergic vias. Its causes are varied, including exposure to pesticides, genetic factors and, one of the most influential ones, age. Given the decrease in dopamine levels, the most common symptoms are the appearance of tremors and muscle rigidity. Due to the rigidity of the muscles, the patient has voice alterations which have great potential for non-invasive and early diagnosis of the disease. In addition, considering the low cost of the sound recorder respect to the clinical studies, this approach allows the diagnosis of Parkinson's disease in a large number of people. Recent works, which present the analysis of voice recordings through Convolutional Neural Networks, show high level of accuracy in the diagnosis of Parkinson's disease. Convolutional Neural Networks use a Multilayer Neural Network to classify convolutional feature vectors. In order to improve the training time of the classifier, in this paper the use Extreme Learning Machines are proposed. Experiments considering 4 types of spectrograms with AlexNet, VGG-16, SqueezeNet, Inception V3 and ResNet-50 Convolutional Neural Networks models. In the experiments, hit rate, training and testing time, sensitivity and the specificity indicators of all the neural architectures involved in the work are objectively compared. It is shown that the Extreme Learning Machine have a high level of accuracy in the diagnosis of Parkinson's disease but with reduced training time. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is swiftly gaining popularity as a way to train Single hidden Layer Feedforward Networks (SLFN) for its attractive properties. ELM is a fast learning network with remarkable generalization performance. Although ELM generally can outperform traditional gradient descent-based algorithms such as Backpropagation, its performance can be highly affected by the random selection of the input weights and hidden biases of SLFN. Moreover, ELM networks tend to have more hidden neurons due to this random selection. In this paper, we propose a new model that uses Competitive Swarm Optimizer (CSO) to optimize the values of the input weights and hidden neurons of ELM. Two versions of ELM are considered: the classical ELM and the regularized version. The goal of the model is to increase the generalization performance, stabilize the classifier, and to produce more compact networks by reducing the number of neurons in the hidden layer. The proposed model is experimented based on 15 medical classification problems. Experimental results demonstrate that the proposed model can achieve better generalization performance with smaller number of hidden neurons and with higher stability. In addition, it requires much less training time compared to other metaheuristic based ELMs. [ABSTRACT FROM AUTHOR]

This paper presents distress classification of class-imbalanced inspection data via correlation-maximizing weighted extreme learning machine (CMWELM). For distress classification, it is necessary to extract semantic features that can effectively distinguish multiple kinds of distress from a small amount of class-imbalanced data. In recent machine learning techniques such as general deep learning methods, since effective feature transformation from visual features to semantic features can be realized by using multiple hidden layers, a large amount of training data are required. However, since the amount of training data of civil structures becomes small, it becomes difficult to perform successful transformation by using these multiple hidden layers. On the other hand, CMWELM consists of two hidden layers. The first hidden layer performs feature transformation, which can directly extract the semantic features from visual features, and the second hidden layer performs classification with solving the class-imbalanced problem. Specifically, in the first hidden layer, the feature transformation is realized by using projections obtained by maximizing the canonical correlation between visual and text features as weight parameters of the hidden layer without designing multiple hidden layers. Furthermore, the second hidden layer enables successful training of our classifier by using weighting factors concerning the class-imbalanced problem. Consequently, CMWELM realizes accurate distress classification from a small amount of class-imbalanced data. [ABSTRACT FROM AUTHOR]

Energy demand prediction of building heating is conducive to optimal control, fault detection and diagnosis and building intelligentization. In this study, energy demand prediction models are developed through machine learning methods, including extreme learning machine, multiple linear regression, support vector regression and backpropagation neural network. Seven different meteorological parameters, operating parameters, time and indoor temperature parameters are used as feature variables of the model. Correlation analysis method is utilized to optimize the feature sets. Moreover, this paper proposes a strategy for obtaining the thermal response time of building, which is used as the time ahead of prediction models. The prediction performances of extreme learning machine models with various hidden layer nodes are analyzed and contrasted. Actual data of building heating using a ground source heat pump system are collected and used to test the performances of the models. Results show that the thermal response time of the building is approximately 40 min. Four feature sets are obtained, and the performances of the models with feature set 4 are better. For different machine learning methods, the performances of extreme learning machine models are better than others. In addition, the optimal number of hidden layer nodes is 11 for the extreme learning machine model with feature set 4. [ABSTRACT FROM AUTHOR]

In this paper, a robust extreme learning machine is proposed. In comparison with the original extreme learning machine and the regularized extreme learning machine, this robust algorithm minimizes both the mean and variance of modeling errors in the objective function to overcome the bias-variance dilemma. As a result, its generalization performance and robustness are enhanced, and these merits are further proved theoretically. In addition, this proposed algorithm can keep the same computational efficiency as the original extreme learning machine and the regularized extreme learning machine. Then, several benchmark data sets are used to test the effectiveness and soundness of the proposed algorithm. Finally, it is employed to model a real small-scale turbojet engine. This engine is fit well. Especially, on the idle phase, where the signal-to-noise ratio is low and it is very hard to model, the proposed algorithm performs well and its robustness is sufficiently showcased. All in all, the proposed algorithm provides a candidate technique for modeling real systems. [ABSTRACT FROM AUTHOR]

Extreme Learning Machines (ELM) have been successfully applied to variety of classification problems by utilizing a single descriptor type. However, a single descriptor may be insufficient for the visual classification task, due to the high level of intra-class variability coupled with low inter-class distance. Although several studies have investigated methods for combining multiple descriptors by ELM, they predominantly apply a simple concatenation of descriptors before classifying them. This type of descriptor fusion may impose problems of descriptor compatibility, high dimensionality and restricted accuracy. In this paper, we propose a hierarchical descriptors fusion strategy at the decision level (“late-fusion”), which relies on ELM ensembles (ELM-E). The proposed method, denoted as H-ELM-E, effectively combines multiple complementary descriptors by a two-level ELM-E based architecture, which ensures that a more informative descriptors will gain more impact on the final decision. In the first level, a separate ELM-E classifier is trained for every image descriptor. In the second level, the output scores from the previous level are aggregated into the mid-level representation which is conducted to an additional ELM-E classifier. The exhaustive experimental evaluation confirmed that the proposed hierarchical ELM-E based strategy is superior to the single-descriptor methods as well as “early fusion” of multiple descriptors, for the visual classification task. Additionally, it was shown that significant accuracy improvement is achieved by integrating ensembles of ELM as a basic classifier, instead of using a single ELM. [ABSTRACT FROM AUTHOR]

This paper proposes a novel and efficient method for traffic sign recognition based on combination of complementary and discriminative feature sets. The extracted features are the histogram of oriented gradients (HOG) feature, Gabor feature and Compound local binary pattern (CLBP) feature. The classification is performed using the extreme learning machine (ELM) algorithm. Performances of the proposed approach are evaluated on both German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification (BTSC) Datasets respectively. The results of the experimental work demonstrate that each feature yields fairly high accuracy and the combination of three features has shown good complementariness and yielded fast recognition rate and is more adequate for real-time application as well. [ABSTRACT FROM AUTHOR]

Dandelion Algorithm (DA) is a novel swarm intelligent optimization algorithm. In evolutionary process of DA, the quality of the seeds generated by dandelions is uneven, and the excellent seeds are expected to be retained and evaluated, while the poor seeds should be discarded without evaluation. In order to determine whether a seed is excellent or not, an improvement of evolution process of dandelion algorithm with extreme learning machine (ELMDA) is proposed in this paper. In ELMDA, firstly, the dandelion population can be partitioned into excellent dandelions and poor dandelions based on fitness values. Then, the excellent dandelions and poor dandelions are assigned corresponding labels (i.e. +1 if excellent or -1 if poor), which can be regarded as a training set, and the training model is built based on ELM. Finally, the model is applied to classify the seeds as excellent or poor, and the excellent seeds are chosen to participate in evolution process. Meanwhile, the robustness of the proposed algorithm is analyzed in this paper. Experimental results performed on test functions show that the proposed algorithm is competitive to its peers. Moreover, the proposed algorithm is demonstrated on three engineering designed problems, and the results indicate that the proposed algorithm has better performance in solving them. • An improvement of evolution process of dandelion algorithm is proposed. • Extreme learning machine is introduced to judge the quality of the solution. • The robustness of the proposed algorithm is analyzed. • The convergence analysis of the proposed algorithm is given. • Experimental results indicate a competitive performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Acid rain is a serious threat to terrestrial ecosystems. To provide more accurate early warning information for acid rain prevention, urban planning, and travel planning, a novel air pollutant prediction model was proposed in this paper to predict NO 2 and SO 2. First, the data were decomposed into several sub-sequences by a complete ensemble empirical mode decomposition with adaptive noise. Second, the subsequences are reconstructed by variational mode decomposition and sample entropy. Then, the new subsequences are predicted by the extreme learning machine combined with the whale optimization algorithm. The empirical analysis was carried out through 8 data sets. According to the experimental results, three main conclusions can be drawn. First, the proposed model in this paper has excellent prediction performance and robustness. In all the comparison experiments, the R2 and RMSE of the proposed model are the best among all the models. Second, data preprocessing is very necessary. After adding the decomposition algorithm, the average improvement levels of R2 and RMSE were 897.57% and 50.78%, respectively. Third, the re-decomposition of IMF1 is an effective method to improve prediction accuracy. After the re-decomposition of IMF1, R2 can be improved by 13.64% on average on the original basis, and RMSE can be reduced by 31.99% on average. The results of this study can provide a valuable reference for the research of air pollutant prediction. In future work, the application of the proposed model in other air pollutants or other regions can be explored. Image 1 • Whale optimization algorithm can better optimize the extreme learning machine. • Secondary decomposition break through the limitation of the decomposition algorithm. • The first intrinsic mode function has the highest sample entropy. • Signal processing technology can improve the accuracy of prediction. [ABSTRACT FROM AUTHOR]

Fixed placements of inertial sensors have been utilized by previous human activity recognition algorithms to train the classifier. However, the distribution of sensor data is seriously affected by the sensor placement. The performance will be degraded when the model trained on one placement is used in others. In order to tackle this problem, a fast and robust human activity recognition model called TransM-RKELM (Transfer learning mixed and reduced kernel Extreme Learning Machine) is proposed in this paper; It uses a kernel fusion method to reduce the influence by the choice of kernel function and the reduced kernel is utilized to reduce the computational cost. After realizing initial activity recognition model by mixed and reduced kernel extreme learning model (M-RKELM), in the online phase M-RKELM is utilized to classify the activity and adapt the model to new locations based on high confident recognition results in real time. Experimental results show that the proposed model can adapt the classifier to new sensor locations quickly and obtain good recognition performance. [ABSTRACT FROM AUTHOR]

Counting pedestrians in surveillance videos has become an urgent safety concern in critical areas. However, surveillance videos of subway spaces suffer from severe crowd occlusion and perspective distortion. In this paper, a novel double-region learning algorithm is presented to overcome these challenges. The main idea of this algorithm is to identify the best two-region boundary and then design a reasonable pedestrian-counting method in each separated region. First, a separate line is obtained via possibility learning, and each frame is divided into a nearby region and a distant region to eliminate the influence of perspective distortion. Second, in the nearby region, we apply the improved aggregate channel feature detection to count the number of pedestrians N 1 . In the distant region, we employ the Extreme Learning Machine and Gaussian Process regression methods to estimate the number of pedestrians N 2 . Finally, the total number of pedestrians in each frame can be obtained with high accuracy according to N 1 and N 2 . We establish a subway pedestrian video dataset about several typical subway stations in Shanghai to validate the algorithm performance. Various experimental results demonstrate that the accuracy of the proposed approach surpasses that of compared methods, which means that our algorithm can meet the management requirements of subway stations. [ABSTRACT FROM AUTHOR]

Imbalanced data appear in many real-world applications, from biomedical application to network intrusion or fraud detection, etc. Existing methods for Parkinson’s disease (PD) diagnosis are usually more concerned with overall accuracy (ACC), but ignore the classification performance of the minority class. To alleviate the bias against performance caused by imbalanced data, in this paper, an effective method named AABC-KWELM has been proposed for PD detection. First, based on a fast classifier extreme learning machine (ELM), weighted strategy is used for dealing with imbalanced data and non-linear mapping of kernel function is used for improving the extent of linear separation. Furthermore, both binary version and continuous version of an adaptive artificial bee colony (AABC) algorithm are used for performing feature selection and parameters optimization, respectively. Finally, PD data set is used for evaluating rigorously the effectiveness of the proposed method in accordance with specificity, sensitivity, ACC, G-mean and F-measure. Experimental results demonstrate that the proposed AABC-KWELM remarkably outperforms other approaches in the literature and obtains better classification performance via 5-fold cross-validation (CV), with specificity of 100%, sensitivity of 98.62%, ACC of 98.97%, G-mean of 99.30%, and F-measure of 99.30%. [ABSTRACT FROM AUTHOR]

This paper proposes a multivariate chaotic Extreme Learning Machine (ELM) model for the prediction of the displacement of reservoir landslides. The displacement time series of the Baishuihe and Bazimen landslides in the Three Gorges Reservoir Area in China are used as examples. The results show that there are evidences of chaos in the displacement time series. The univariate chaotic ELM model and the multivariate chaotic model based on Particle Swarm Optimization and Support Vector Machine (PSO-SVM) model are also applied for the purpose of comparison. The comparisons show that the multivariate chaotic ELM model achieves higher prediction accuracy than the univariate chaotic ELM model and the multivariate chaotic PSO-SVM model. [ABSTRACT FROM AUTHOR]

Since extreme learning machine is a non-iterative estimation procedure, it is faster than gradient-based algorithms which are iterative. Moreover, the extreme learning machine does not have any design parameters such as learning rate, covariance matrix, etc. The rigorous proof of universal approximation of extreme learning machine with much milder conditions makes it a preferable choice in many different approaches. Although this algorithm is optimal for the parameters which appear linearly in the consequent part of interval type-2 fuzzy logic systems, it is not optimal for the parameters of the antecedent part as it uses random parameters. In this paper, heuristic optimization approaches such as genetic algorithm and artificial bee colony are used to optimize the parameters of the antecedent part of interval type-2 fuzzy logic systems. As these methods are global optimizers, there is less possibility that they will fall in a local minima and are suitable for the selection of the parameters of the antecedent part. A comparative analysis of the optimal parameters with the randomly and manually generated parameters is presented here using noise-free and noisy Mackey-Glass time series data sets and a real world data set. Simulation results support this idea over randomly and manually generated parameters. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) has been widely used for various classification problems. However, the traditional ELMs are typically based on the regular Euclidean data, thus ignoring the intrinsic structured information among data and resulting in poor robustness. In this paper, we present a novel semi-supervised learning framework, termed Graph Convolutional Extreme Learning Machines (GCELM), based on extending the traditional ELM to the non-Euclidean domain. Technically, we recast ELM layers into a randomized graph convolutional embedding layer followed by a graph convolutional regression layer, which endows ELM with the capability to handle graphs in the non-Euclidean domain. Benefiting from the diversity of the randomized graph convolution, we further propose an enhanced GCELM, i.e., Voting-based GCELM (V-GCELM), by using a simple voting ensemble strategy. The proposed methods preserve the advantages of ELMs, thus being more efficient than the gradient-based graph convolutional networks but without loss of graph learning ability. Extensive experiments on 36 benchmark datasets demonstrate that the proposed methods significantly outperform many previous semi-supervised classification methods. • Classic ELM is generalized into the non-Euclidean domain by using graph convolution. • An ensemble-based graph convolutional ELM is proposed for semi-supervised learning. • The proposed methods are benchmarked on 36 standard UCI datasets. • Our methods significantly outperform many existing methods by a large margin. [ABSTRACT FROM AUTHOR]

Brain–computer interfaces (BCI) assist communication for the handicapped and disabled. Previous work has shown that it is usually non-intuitive, and it frequently employs Electroencephalogram (EEG) based motor imagery. Ensemble learning has been shown to be reliable in a variety of BCI classification tasks, including motor imagery and P300 event-related potential. The purpose of ensemble learning, according to past research, is to get trained accurate but diverse base classifiers to increase generalization performance. Extreme Learning Machine (ELM) with fast learning speed has been proven effective in classification applications and suitable for ensemble learning due to its randomness. The suitability of ensemble methods for intuitive BCI communication using EEG data of different covert speech words is investigated in this work. To achieve this goal, we construct a random rotation based kernel ELM ensemble, resulting in very diverse classifiers which can learn through transformed spaces. Minimize error ensemble pruning is used to prune low complementarity classifiers, and consequently, combining the remaining high complementarity classifiers to get the final ensemble classifier. Eight subjects performed covert speech tasks which involved mentally repeating five words namely; 'left', 'right', 'up', 'down', and 'stop'. We achieved classification accuracy with pruning and without pruning of 63.67% and 57.13% respectively. Experimental results show that, in comparison to other classification techniques, the proposed technique produces competitive results. Our findings indicate the potential of random rotation kernel ELM ensemble pruning to effectively classify EEG-based covert speech signals. This proposed research involving an ensemble method for the classification of covert speech words can make a significant contribution towards intuitive BCI development using silent speech. [Display omitted] • This paper presents EEG-based Covert Speech decoding for Intuitive BCI communication. • We model the system using Random Rotation Extreme Learning Machine Ensemble technique. • The system is examined with pruning and without pruning for Ensemble techniques. • The proposed technique produces competitive results in comparison to previous classification techniques. [ABSTRACT FROM AUTHOR]

Data streams classification is an important approach to get useful knowledge from massive and dynamic data. Because of concept drift, traditional data mining techniques cannot be directly applied in data streams environment. Extreme learning machine (ELM) is a single hidden layer feedforward neural network (SLFN), comparing with the traditional neural network (e.g. BP network), ELM has a faster speed, so it is very suitable for real-time data processing. In order to deal with the challenge in data streams classification, a new approach based on extreme learning machine is proposed in this paper. The approach utilizes ELMs as base classifiers and adaptively decides the number of the neurons in hidden layer, in addition, activation functions are also randomly selected from a series of functions to improve the performance of the approach. Finally, the algorithm trains a series of classifiers and the decision results for unlabeled data are made by weighted voting strategy. When the concept in data streams keeps stable, every classifier is incrementally updated by using new data; if concept drift is detected, the classifiers with weak performance will be cleared away. In the experiment, we used 7 artificial data sets and 9 real data sets from UCI repository to evaluate the performance of the proposed approach. The testing results showed, comparing with the conventional classification methods for data streams such as ELM, BP, AUE2 and Learn++.MF, on most data sets, the new approach could not only be simplest in the structure, but also get a higher and more stable accuracy with lower time consuming. [ABSTRACT FROM AUTHOR]