Hybrid Extreme Learning Machine Research Articles

A Novel Hybrid Extreme Learning Machine Approach Improved by K Nearest Neighbor Method and Fireworks Algorithm for Flood Forecasting in Medium and Small Watershed of Loess Region

Sudden floods in the medium and small watershed by a sudden rainstorm and locally heavy rainfall often lead to flash floods. Therefore, it is of practical and theoretical significance to explore appropriate flood forecasting model for medium and small watersheds for flood control and disaster reduction in the loess region under the condition of underlying surface changes. This paper took the Gedong basin in the loess region of western Shanxi as the research area, analyzing the underlying surface and floods characteristics. The underlying surface change was divided into three periods (HSP1, HSP2, HSP3), and the floods were divided into three grades (great, moderate, small). The paper applied K Nearest Neighbor method and Fireworks Algorithm to improve the Extreme Learning Machine model (KNN-FWA-ELM) and proposed KNN-FWA-ELM hybrid flood forecasting model, which was further applied to flood forecasting of different underlying surface conditions and flood grades. Results demonstrated that KNN-FWA-ELM model had better simulation performance and higher simulation accuracy than the ELM model for flood forecasting, and the qualified rate was 17.39% higher than the ELM model. KNN-FWA-ELM model was superior to the ELM model in three periods and the simulation performance of three flood grades, and the simulation performance of KNN-FWA-ELM model was better in HSP1 stage floods and great floods.

Daily reference evapotranspiration prediction based on hybridized extreme learning machine model with bio-inspired optimization algorithms: Application in contrasting climates of China

Reliable and accurate prediction of reference evapotranspiration (ETo) is a precondition for the efficient management and planning of agricultural water resources as well as the optimal design of irrigation scheduling. This study evaluated the performances of four bio-inspired algorithm optimized extreme learning machine (ELM) models, i.e. ELM with genetic algorithm (ELM-GA), ELM with ant colony optimization (ELM-ACO), ELM with cuckoo search algorithm (CSA) and ELM with flower pollination algorithm (ELM-FPA), for predicting daily ETo across China by using a five-fold cross-validation approach. These models were further compared with the classical ELM model parameterized by the grid search method to demonstrate their capability and efficiency. Daily maximum and minimum ambient temperatures, wind speed, relative humidity and global solar radiation data during 2001–2015 collected from eight meteorological stations in contrasting climates of China were utilized to train, validate and test the models. The results showed that ETo values predicted by all ELM models agreed well with the corresponding FAO-56 Penman–Monteith values, with R2, RMSE, NRMSE and MAE ranging 0.9766–0.9967, 0.0896–0.2883 mm day−1, 3.2910%-11.7653% and 0.0708–0.1998 mm day−1, respectively. The ELM-FPA model (R2 = 0.9930, RMSE = 0.1589 mm day−1, NRMSE = 5.5406% and MAE = 0.1188 mm day−1) slightly outperformed the ELM-CSA model (R2 = 0.9922, RMSE = 0.1619 mm day−1, NRMSE = 5.6864% and MAE = 0.1200 mm day−1) during testing, both of which were superior to the ELM-ACO (R2 = 0.9912, RMSE = 0.1730 mm day−1, NRMSE = 6.0816% and MAE = 0.1254 mm day−1) and ELM-GA (R2 = 0.9889, RMSE = 0.1895 mm day−1, NRMSE = 6.7197% and MAE = 0.1310 mm day−1) models, followed by the standalone ELM model (R2 = 0.9856, RMSE = 0.2104 mm day−1, NRMSE = 7.1693% and MAE = 0.1408 mm day−1). The four hybrid ELM models exhibited higher improvements in daily ETo prediction in the temperate monsoon and (sub)tropical monsoon climates (with average decrease in RMSE of 14.0%, 25.1%, 31.4% and 33.1%, respectively), compared with those in the temperate continental and mountain plateau climates (with average decrease in RMSE of 5.2%, 9.8%, 12.9% and 14.1%, respectively). The results advocated the capability of bio-inspired optimization algorithms, especially the FPA and CSA algorithms, for improving the performance of the conventional ELM model in daily ETo prediction in contrasting climates of China.

Hybrid extreme learning machine approach for heterogeneous neural networks

In this paper, a hybrid learning approach, which combines the extreme learning machine (ELM) with a genetic algorithm (GA), is proposed. The utilization of this hybrid algorithm enables the creation of heterogeneous single layer neural networks (SLNNs) with better generalization ability than traditional ELM in terms of lower mean square error (MSE) for regression problems or higher accuracy for classification problems. The architecture of this method is not limited to traditional linear neurons, where each input participates equally to the neuron’s activation, but is extended to support higher order neurons which affect the network’s generalization ability. Initially, the proposed heterogeneous hybrid extreme learning machine (He-HyELM) algorithm creates a number of custom created neurons with different structure, which are used for the creation of homogeneous SLNNs. These networks are trained with ELM and an application specific GA evolves them into heterogeneous networks according to a fitness criterion utilizing the uniform crossover operator for the recombination process. After the completion of the evolution process, the network with the best fitness is selected as the most optimal. Experimental results demonstrate that the proposed learning algorithm can get better results than traditional ELM, homogeneous hybrid extreme learning machine (Ho-HyELM) and optimally pruned extreme learning machine (OP-ELM) for homogeneous and heterogeneous SLNNs.

Multi-step short-term wind speed forecasting approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA optimization and ELM

Accurate wind speed prediction possesses a significant impact on reasonable scheduling and safe operation of power system. For this purpose, a novel hybrid approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA (IHGWOSCA) algorithm and extreme learning machine (ELM) is proposed for multi-step short-term wind speed prediction, in which the multi-scale dominant ingredient chaotic analysis combines the proposed optimal variational mode decomposition (OVMD), singular spectrum analysis (SSA) and phase space reconstruction (PSR). To begin with, the mode number and updating step of VMD are pre-determined by center frequency observation method and the proposed least-squares error index (LSEI), thus decomposing the non-stationary wind speed series into a set of intrinsic mode functions (IMFs). Later, the extraction of the dominant ingredient and residuary ingredient for each sub-series is implemented by SSA for the construction of forecasting components. Subsequently, the proposed IHGWOSCA algorithm coded with discrete integers and real-valued are investigated to search optimal parameters in PSR and ELM successively. Lastly, the ultimate forecasting results of the original wind speed are calculated by accumulating results of all the predicted components. Furthermore, seven data sets from Sotavento Galicia and Inner Mongolia have been employed to evaluate the proposed approach. The results illustrate that: (1) the proposed OVMD-based models obtained better RMSE, MAE and MAPE indexes comparing with the benchmark models through weakening the non-stationary of the original signal; (2) the proposed dominant ingredient chaotic analysis combining SSA and PSR enhanced the multi-steps prediction performance effectively; (3) the proposed IHGWOSCA optimization algorithm possessed good capability for optimal parameters searching and fast convergence.

Two-phase extreme learning machines integrated with the complete ensemble empirical mode decomposition with adaptive noise algorithm for multi-scale runoff prediction problems

Expert systems adopted in real-time multi-scale runoff prediction are useful decision-making tools for hydrologists but the stochastic nature of any hydrological variable can pose significant challenges in attaining a reliable predictive model. This paper advocates a data-driven approach used to design two-phase hybrid model (i.e., CVEE-ELM). The model utilizes complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) coupled with the variational mode decomposition (VMD) algorithms for better frequency resolution of the input datasets and the extreme learning machine (ELM) algorithm as the objective predictive model. In the first stage of the presented model design, notable frequencies in the predictor-target data series are uncovered, utilizing the CEEMDAN algorithm where the model’s inputs are decomposed into their respective Intrinsic Mode Functions (IMFs) and the Residual (Res) series. The second stage entails a VMD approach, used to decompose the yet-unresolved high frequencies (i.e., IMF1) into their variational modes, further discerning and establishing the data attributes to be incorporated into the ELM model to simulate the respective IMFs, Res and VM data series, aggregated as an integrative tool for multiscale runoff prediction. In the model evaluative phase, the hybrid CVEE-ELM is cross-validated with a single-phase hybrid ELM and an autoregressive integrated moving average (ARIMA) model to benchmark its accuracy for predicting 1-, 3- and 6-month ahead runoff in Yingluoxia watershed, Northwestern China. Two-phase hybrid model exhibits superior accuracy at all lead times, to accord with high degree of correlations between the observed and the forecasted runoff, a relatively large Nash-Sutcliffe and the Legate-McCabe Index. Taylor diagrams depict the two-phase hybrid CVEE-ELM model generated forecasts located close to a reference (i.e., a perfect) model, with a lower root-mean square centered difference, and a correspondingly large correlation for all forecast horizons, although the model’s accuracy for shorter lead times (1-month), as expected, are better than the 3- and 6-month horizon. The study shows that the two-phase hybrid CVEE-ELM model where an integration of two frequency resolution algorithms are made, is a preferred data-driven tool that can be explored for real-life decision-system design, particularly for hydrological forecasting problems that have significantly stochastic data features, and thus, will require reliable forecasts to be generated at multi-step horizons.

A Novel Hybrid Cuckoo Search- Extreme Learning Machine Approach for Modulation Classification

This paper presents a novel hybrid extreme learning machine (ELM) with cuckoo search algorithm (CSA) for the classification purposes of the digitally modulated signals, such as phase shift keying (PSK), frequency shift keying (FSK), and quadrature amplitude modulation (QAM). Nine modulation schemes having different orders have been considered for this paper. First, the Gabor filter is used to extract the key features from the received signal which are then optimized by the CSA. Finally, the ELM is used to classify the modulation schemes using these optimized features. Our proposed CSA-ELM approach is not only fast convergent and robust but also manifests improved percentage classification accuracy at low SNRs and lower sample size for both AWGN and Rayleigh fading channels.

Multi Objective Optimization for Turning Operation using Hybrid Extreme Learning Machine and Multi Objective Genetic Algorithm

Turning operation, a type of machining process using Computer Numerical Control (CNC) machine in which a cutting tool, typically a non-rotary tool bit, moves to describe a helix toolpath while the cylindrical metal workpiece rotates. Numerous conflicting performance functions such as maximizing material removal rate, minimizing the product’s quality, maximizing the tool life and others, remains crucial for a system to optimize in order to obtain optimum benefit. The machinist is required to assign the optimal cutting parameters in CNC turning machine which have direct influence on the performance of each cutting process and machined product. It is very crucial for optimal parameters selection to maximize the performance function. A new optimisation model has been proposed in this paper. This model, uses Box Behnken Design (BBD) for design of experiment and the prediction model has been developed using Extreme Learning Machine (ELM) which is tuned using Particle Swarm Optimization. A powerful and effective, Multi Objective Genetic Algorithm (MOGA) will act as an optimizer of the developed model. Turning input parameters such as feed rate, cutting speed and depth of cut were considered as input variables and surface roughness, specific power consumption and cutting force were used as output variables. This novel approach, BBD-ELM-PSO-MOGA can predict the optimal cutting parameters as demonstrated in our case studies with less number of tunable parameters and number of experiments. Therefore, it is fast, less time consuming and easy to be implemented.

Hybrid extreme learning machine approach for homogeneous neural networks

Hybrid extreme learning machine approach for homogeneous neural networks

Development of hybrid extreme learning machine based chemo-metrics for precise quantitative analysis of LIBS spectra using internal reference pre-processing method

Laser induced breakdown spectroscopy (LIBS) is a versatile spectroscopic technique that requires little or no sample preparation and capable of simultaneous elemental sample analysis. Quantitative analysis of its spectra has been a major challenge due to self-absorption of the emitted radiation during plasma cooling and inadequate description of non-linear complex interactions taking place in the laser induced plasma. This work presents a novel chemo-metric tool, extreme learning machine (ELM) and its hybrid HHELM (homogenously hybridized ELM), for the first time in modeling the complex interactions of laser induced plasma and quantification of LIBS spectra. Internal reference preprocessing (IRP) method is also proposed as a novel method of enhancing the performance of ELM based chemo-metrics. Since the proposed chemo-metrics (ELM and HHELM) determine their input weights as well as their hidden biases in a random manner, ELM and HHELM are respectively hybridized with gravitational search algorithm (GSA) for optimization of the number of hidden neurons. Effect of IRP, obtained by normalizing the emission spectra intensities with the emission intensity that has highest upper level excitation energy and lowest transition probability, on the performance of the proposed GSA-ELM and GSA-HHELM chemo-metrics is investigated. The proposed models are implemented using spectra of seven bronze standard samples. Chemo-metrics with IRP (GSA-ELM-IRP and GSA-HHELM-IRP) show better generalization performance than those without IRP (GSA-ELM-WIRP and GSA-HHELM-WIRP) while GSA-HHELM based chemo-metrics perform better than their counterparts. The outstanding performance demonstrated by the proposed chemo-metrics and their self-absorption correction ability would definitely widen the applicability of LIBS and improve its precision for the quantitative analysis.

Evapotranspiration estimation using four different machine learning approaches in different terrestrial ecosystems

Elucidating the biophysical mechanisms governing the exchange of water vapor between land and the atmosphere is particularly crucial for addressing water scarcity under climate change. Owing to the rapid development of machine learning techniques, a series of powerful tools have been proposed over the past two decades, allowing the scientific community to obtain new insights into the patterns of evapotranspiration (ET) on different spatial scales ranging from ecosystem to global. The primary focus of this study was to investigate the feasibility and effectiveness of both extreme learning machine (ELM) and adaptive neuro-fuzzy inference system (ANFIS) to estimate the daily ET with flux tower observations in four main types of ecosystems. A comparative research was undertaken to evaluate the potential of the models compared with the conventional artificial neural network and support vector machine models. All the developed models were evaluated according to the following performance indices: coefficient of determination (R2), Nash-Sutcliffe efficiency (NSE), root mean square error and mean absolute error. The results showed that all the applied models had high performance for modeling daily ET (e.g., R2 = 0.9398–0.9593 and NSE = 0.8877–0.9147 in forest ecosystem). Among the applied ELM models, the three hybrid ELM methods outperformed the original ELM method in most cases at the four sites and the computational time required for learning these ELM models has been considerably reduced. The subtractive clustering and fuzzy c-means clustering algorithms for ANFIS generally performed better than the grid partitioning algorithm. It was concluded that the advanced ELM and ANFIS models can be recommended as important complements to traditional methods due to their robustness and flexibility. Moreover, significant difference regarding the modeling performance existed among the four major ecosystems types. The models generally achieved the best performance in forest ecosystem, while provided the worst in cropland ecosystem.

An Improved Iris Recognition Algorithm Based on Hybrid Feature and ELM

The iris image is easily polluted by noise and uneven light. This paper proposed an improved extreme learning machine (ELM) based iris recognition algorithm with hybrid feature. 2D-Gabor filters and GLCM is employed to generate a multi-granularity hybrid feature vector. 2D-Gabor filter and GLCM feature work for capturing low-intermediate frequency and high frequency texture information, respectively. Finally, we utilize extreme learning machine for iris recognition. Experimental results reveal our proposed ELM based multi-granularity iris recognition algorithm (ELM-MGIR) has higher accuracy of 99.86%, and lower EER of 0.12% under the premise of real-time performance. The proposed ELM-MGIR algorithm outperforms other mainstream iris recognition algorithms.

Estimating forest carbon fluxes using four different data-driven techniques based on long-term eddy covariance measurements: Model comparison and evaluation

With the recent availability of large amounts of data from the global flux towers across different terrestrial ecosystems based on the eddy covariance technique, the use of data-driven techniques has been viable. In this study, two advanced techniques, namely adaptive neuro-fuzzy inference system (ANFIS) and extreme learning machine (ELM), were developed and investigated for their viability in estimating daily carbon fluxes at the ecosystem level. All the data used in this study were based upon the long-term chronosequence observations derived from the flux towers in eight forest ecosystems. Both ANFIS and ELM methods were further compared with the most widely used artificial neural network (ANN) and support vector machine (SVM) methods. Moreover, we also focused on probing into the effects of internal parameters on their corresponding approaches. Our estimates showed that most variation in each carbon flux could be effectively explained by the developed models at almost all the sites. Moreover, the forecasting accuracy of each method was strongly dependent upon their respective internal algorithms. The best training function for ANN model can be acquired through the trial and error procedure. The SVM model with the radial basis kernel function performed considerably better than the SVM models with the polynomial and sigmoid kernel functions. The hybrid ELM models achieved similar predictive accuracy for the three fluxes and were consistently superior to the original ELM models with different transfer functions. In most instances, both the subtractive clustering and fuzzy c-means algorithms for the ANFIS models outperformed the most popular grid partitioning algorithm. It was demonstrated that the newly proposed ELM and ANFIS models were able to produce comparable estimates to the ANN and SVM models for forecasting terrestrial carbon fluxes.

A Two-Level Intelligent Web Caching Scheme with a Hybrid Extreme Learning Machine and Least Frequently Used

The immense increase in data traffic has created several issues for the Internet community, including long delays and low throughput. Most Internet user activity occurs via web access, thus making it a major source of Internet traffic. Due to a lack of effective management schemes, Internet usage is inefficient. Advances in caching mechanisms have led to the introduction of web proxies that have improved real-time communication and cost savings. Although several traditional caching polices have been implemented to increase speed and simplicity, cache replacement accuracy remains a key limitation due to cache storage constraints. Our contribution concerns the algorithmic investigation of intelligent soft computing schemes to enhance a web proxy system to improve precision for reproducibility. This research also proposes a two-level caching scheme; the first level is least frequently used (LFU), and an extreme learning machine (ELM) is used for the second level. A traditional ELM for web caching is further optimized with object similarity factors. The proposed scheme is evaluated and compared to a traditional caching policy and its integration with intelligent caching using a well-known dataset from IRCache. The method is shown to achieve good performance in terms of high hit and byte hit rates.

A comparison of the performance of some extreme learning machine empirical models for predicting daily horizontal diffuse solar radiation in a region of southern Iran

ABSTRACTThis study uses the empirical models of extreme learning machine (ELM) method to predict daily horizontal diffuse solar radiation (HDSR). As a possibility for modification, the recent hybrid ELM methods such as complex ELM (C-ELM), self-adaptive evolutionary ELM (SaE-ELM), and online sequential ELM (OS-ELM) have been developed for the prediction of the daily HDSR. The empirical model of ELM predicts the HDSR using clearness index as the sole predictor. For this aim, two types of correlations are evaluated: (1) the diffuse fraction-clearness index and (2) the diffuse coefficient-clearness index. The measured diffuse and global solar radiation data sets of southern Iranian cities (Yazd, Shiraz, Bandar Abbas, Bushehr, and Zahedan) are utilized to evaluate the models. The precision of the C-ELM, SaE-ELM, OS-ELM, and ELM models is evaluated for different regions on the basis of five statistical performance evaluation parameters. The results confirm that the performance of hybrid ELM is pretty accurate and trustworthy. Fully complex ELM exhibits the best performance among these hybrid methods, having values of 0.87 and 0.30 for R2 and RMSE measures, respectively, in the testing phase. Therefore, it is able to be recognized as an appropriate tool for daily solar radiation forecasting issues.

Multivariate Chaotic Time Series Prediction Based on ELM–PLSR and Hybrid Variable Selection Algorithm

In this paper, a novel method (Hybrid–ELM–PLSR) is proposed based on hybrid variable selection algorithm and improved extreme learning machine (ELM) for multivariate chaotic time series prediction. The hybrid variable selection algorithm combines the advantages of filter and wrapper, effectively balancing the calculation speed and prediction accuracy. Moreover, for ELM, multicollinearity, which can result in ill-condition, is always existent among the hidden layer output matrix. And the optimal number of hidden nodes is also difficult to be determined. Therefore,in order to overcome these problems, an improved ELM (ELM–PLSR) is proposed based on partial least square regression (PLSR). It can effectively enhance the stability performance and prediction performance of ELM. Hybrid–ELM–PLSR can be divided into three stages. At first, filter is used to rearrange the input variables through the correlations with desired variables. Then wrapper is used to select the optimal variable subset through evaluating the prediction performance of different subsets. Finally, ELM–PLSR is used to build the prediction model. The simulation experiment results based on San Francisco river runoff dataset demonstrate that the proposed method is effective for multivariate chaotic time series. And the prediction accuracy and reliability are higher than other methods.

A Novel Method of Hybrid Extreme Learning Machine for Diabetes Mellitus Diagnosis

Objectives: To design a classifier for the detection of Diabetes Mellitus with optimal cost and precise performance. Method and Analysis: The diagnosis and interpretation of the diabetes data is must because major problem occurs due to this data maintenance. Several researches are made with machine learning but still needs improvements. In this paper a new method is evaluated as hybrid Extreme Learning Machine (HELM) with African Buffalo Optimization (ABO). Findings: ELM is used to select the input data because of fast learning speed. Optimization technique is used for searching and classifying the good diabetic data. The ABO is a population based algorithm in which individual buffalos work together to identify the diabetics data by updating fitness value for best output solution. The proposed HELM technique is successfully implemented for diagnosing diabetes disease. By using this machine learning algorithm, the classification accuracy is achieved for classifying the diabetes patients by using much of the data set for training and few data sets for testing. In order to improve the quality as well as accuracy there is a need for algorithm. The combination of ELM-ABO classifier is applied in training dataset taken from PRIMA Indian dataset for classification and the experimental results are compared with SVM and other ELM classifiers applied on the same database. Improvement: It is observed that the HELM method obtained high accuracy in classification with less execution time along with performance evaluation of parameters such as recall, precision and F-Measure.

Integrated optimization model of laser brazing by extreme learning machine and genetic algorithm

Welding parameters play a significant role in determining the bead geometry and hence the quality of the weld joint. To further improve prediction accuracy and optimization quality of laser brazing, the published experiment results are utilized to build a prediction model of top and bottom width of weld bead and further establish an optimization model by a novel hybrid extreme learning machine and genetic algorithm method. Firstly, about two-third experiment results are used to train the extreme learning machine network for suitable weights, and then the rest one-third experiments are selected as a test set to illustrate the validity and reliability of the prediction network. Then, by regarding the prediction values from the extreme learning machine as the fitness values of genetic algorithm, optimal results of the inputs and outputs are obtained through the procedure of selection, crossover, and mutation. Eventually, the final optimization results are confirmed by verification experiments. Meanwhile, the hybrid model is more accurate and stable than that using back propagation neural network and genetic algorithm. In the whole, the proposed method in this paper is an effective and accurate way for optimizing laser brazing welding parameters and guiding the actual welding process.

English

English

Extreme learning machine towards dynamic model hypothesis in fish ethology research

In this paper, we present one dynamic model hypothesis to perform fish trajectory tracking in the fish ethology research and develop the relevant mathematical criterion on the basis of the Extreme Learning Machine (ELM). It is shown that the proposed scheme can conduct the non-linear and non Gaussian tracking process by multiple historical cues and current predictions – the state vector motion, the color distribution and the appearance recognition, all of which can be extracted from the single-hidden layer feedforward neural network (SLFN) at diverse levels with ELM. The strategy of the hierarchical hybrid ELM ensemble then combines the individual SLFN of the tracking cues for the performance improvements. The simulation results have shown the excellent performance in both robustness and accuracy of the developed approach.