Optimally Pruned Extreme Learning Machine Research Articles

River water temperature prediction using hybrid machine learning coupled signal decomposition: EWT versus MODWT

Accurate prediction of water temperature (Tw) will greatly help in improving our understanding of the overall thermal regime fluctuation, and it can help in making sound decisions. While great efforts have been devoted to the development of Tw models, further improvement in the prediction accuracy is challenging. Here, we propose a new hybrid machine learning (ML) models for predicting Tw from air temperature (Ta). First, two signal decomposition algorithms, i.e., the empirical wavelet transform (EWT) and maximum overlap discrete wavelet transform (MODWT) are used for decomposing the Ta into several subsequences. Second, the obtained subsequences are used as input variables for four ML models, i.e., the feedforward neural network (FFNN), the optimally pruned extreme learning machine (OPELM), the adaptive boosting (AdaBoost), and the bootstrap aggregating (Bagging). The development of the hybrid models is based on measured data form five measurement stations distributed over Poland. The experimental results show that, the new hybrid ML models achieved high predictive accuracies with Pearson correlation coefficient (R), Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE) and mean absolute error (MAE) of approximately ≈0.99, ≈0.98, ≈0.718 °C, and ≈0.599 °C, respectively. Finally, the experimental results have demonstrated that, the MAE and RMSE of the single models were reduced by 66.12% and 65.30%, while the R and NSE values were improved by 4.85% and 10.02%, respectively, showing a very promising prediction performance. Our new modelling approach proposed in the present study clearly highlight the high contribution of the EWT and MODWT in improving the Tw estimation that is most strongly influenced by Ta. The significant difference between single and hybrid models can be explained by the ability of the EWT and MODWT to capture the high nonlinearity between Ta and Tw. Our new approach is of interest for water resources management and for assessing the variability of Tw over time and space. Finally yet importantly, this is the first study in the literature for which EWT and MODWT were used for modelling Tw, through which we have demonstrated that, an important amount of information is available and cannot be captured using single ML models, and signal decomposition have helped to overcome this challenge.

Short-Term Electrical Load Forecasting of 150 kV Ternate System Using Optimally Pruned Extreme Learning Machine (OPELM)

Short-term electrical loads forecasting is one of the most important factors in the design and operation of electrical systems. The purpose of electric load forecasting is to balance electricity demand and electricity supply. The load characteristics of Ternate City vary, so this study uses the Optimally Pruned Extreme Learning Machine (OPELM) method to predict electrical loads. The advantages of OPELM are the fast-learning speed and the selection of the right model, even though the data has a non-linear pattern. The accuracy of the OPELM method can be determined using a comparison method, namely the ELM method. Mean Absolute Percentage Error (MAPE) is used as the accuracy criterion. The results of the comparison of accuracy criteria show that the predictive performance of OPELM is better than that of ELM. The minimum error average of the OPELM forecast test results shows a MAPE of 5,2557%, for Saturday's forecast, while the ELM method gives a MAPE of 6.4278% on the same day.

A New Insight for Daily Solar Radiation Prediction by Meteorological Data Using an Advanced Artificial Intelligence Algorithm: Deep Extreme Learning Machine Integrated with Variational Mode Decomposition Technique

Reliable and precise estimation of solar energy as one of the green, clean, renewable and inexhaustible types of energies can play a vital role in energy management, especially in developing countries. Also, solar energy has less impact on the earth’s atmosphere and environment and can help to lessen the negative effects of climate change by lowering the level of emissions of greenhouse gas. This study developed thirteen different artificial intelligence models, including multivariate adaptive regression splines (MARS), extreme learning machine (ELM), Kernel extreme learning machine (KELM), online sequential extreme learning machine (OSELM), optimally pruned extreme learning machine (OPELM), outlier robust extreme learning machine (ORELM), deep extreme learning machine (DELM), and their versions combined with variational mode decomposition (VMD) as integrated models (VMD-DELM, VMD-ORELM, VMD-OPELM, VMD-OSELM, VMD-KELM, and VMD-ELM), for solar radiation estimation in Kurdistan region, Iraq. The daily meteorological data from 2017 to 2018 were used to implement suggested artificial models at Darbandikhan and Dukan stations, Iraq. The input parameters included daily data for maximum temperature (MAXTEMP), minimum temperature (MINTEMP), maximum relative humidity (MAXRH), minimum relative humidity (MINRH), sunshine duration (SUNDUR), wind speed (WINSPD), evaporation (EVAP), and cloud cover (CLOUDCOV). The results show that the proposed VMD-DELM algorithm considerably enhanced the simulation accuracy of standalone models’ daily solar radiation prediction, with average improvement in terms of RMSE of 13.3%, 20.36%, 25.1%, 27.1%, 34.17%, 38.64%, and 48.25% for Darbandikhan station and 5.22%, 10.01%, 10.26%, 21.01%, 29.7%, 35.8%, and 40.33% for Dukan station, respectively. The outcomes of this study reveal that the VMD-DELM two-stage model performed superiorly to the other approaches in predicting daily solar radiation by considering climatic predictors at both stations.

Modelling coagulant dosage in drinking water treatment plant using advance machine learning model: Hybrid extreme learning machine optimized by Bat algorithm.

Despite the high importance of coagulation process in drinking water treatment plant (DWTP), challenge remains in effectively linking raw water quality measured at the inlet of the DWTP with coagulant dosage rate. This study proposes an integral modelling framework using hybrid extreme learning machine and Bat metaheuristic algorithm (ELM-Bat) for modelling coagulant dosage rate using water temperature, pH, specific conductance, dissolved oxygen, and water turbidity. The aluminum sulphate (Al2 (SO4)3.18H2O) coagulant is determined using conventional Jar-Test procedure. Results obtained using the hybrid ELM-Bat were compared to those obtained using standalone ELM, outlier robust extreme learning machine (ORELM), online sequential extreme learning machine (OSELM), optimally pruned extreme learning machine (OPELM), and kernel extreme learning machine (KELM). First, the models have been calibrated during the training stage and in a second stage; they are validated using various statistical metrics, i.e., RMSE, MAE, the correlation coefficient (R), and the Nash-Sutcliffe model efficiency (NSE). We found that the hybrid ELM-Bat was significantly more accurate and it has yielded accuracy higher than all other models. During the validation stage, the R and NSE values calculated using the ELM-Bat were ≈0.959 and ≈0.918 exhibiting an improvement rates of approximately (≈15.26% and ≈33.82%), (≈10.35% and ≈21.92%), (≈14.98% and ≈31.89%), (≈7.63% and ≈16.35%), (≈10.99% and ≈23.05%), compared to the values obtained using the ELM, OPELM, OSELM, KELM and ORELM, respectively. Besides, the new ELM-Bat model has shown to have high predictive capabilities, which can be used optimally for calculating the optimal coagulant dosage with high accuracy.

Hybrid Artificial Neural Networks for Modeling Shallow-Water Bathymetry via Satellite Imagery

Accurate bathymetric mapping for shallow-water areas is essential for coastal and maritime engineering applications. However, traditional multibeam or light detection and ranging (LiDAR) survey techniques used to produce high-quality bathymetric maps are expensive. Satellite-derived bathymetry provides a fast and inexpensive method for the large-scale mapping of shallow-water areas and can overcome the complexities of traditional bathymetric mapping methods in these areas. Traditionally, linear regression models, most commonly the Stumpf model, are used for satellite-based bathymetric modeling. However, nonlinear artificial neural network (ANN) models have been recently developed and implemented for satellite-based bathymetric modeling and are under significant investigation to develop the most accurate and optimal model. This article proposes two new hybrid ANN-based models for bathymetric modeling and investigates their performance using satellite imagery data and “truth” depth data for a coastal shallow-water study area. Two-hybrid ANN algorithms are developed, namely, particle swarm optimization (PSO)-ANN and optimally pruned extreme learning machine (OPELM), and their results are compared with the traditional Stumpf method and current state-of-the-art ANN model. The study area dataset comprises the “truth” depth data from a nautical chart of the Alqumriyah Island study area in Saudi Arabia and the corresponding spectral reflection values of green, blue, and near-infrared bands from the free-of-charge Level-1C product of Sentinel-2A images used to train and validate the two newly developed models and the traditional models. The results show that the developed OPELM method can accurately derive the bathymetry and is superior to the developed PSO-ANN model, the current state-of-the-art ANN model, and the traditional Stumpf model by 12.10%, 18.76%, and 32.46%, respectively. The OPELM model can also be used for bathymetric modeling of shallow-water areas with depths up to 30 m with a high level of accuracy compared with the current state-of-the-art ANN and traditional methods. The significant contribution of this research is that it is the first investigation of the artificial intelligence-based hybrid OPELM method for accurate bathymetric modeling and will certainly encourage further investigations of hybrid models. Moreover, this research explores whether these developed hybrid models can meet the International Hydrographic Organization standards for hydrographic survey applications.

Forecasting model of power generated by wind power plants

The power generated by wind power plants is unstable so forecasting is needed to maintain the power balance in an interconnected system. The purpose of this research is to predict the power generated at the Sidrap and Jeneponto wind power plants. The method used is an optimally pruned extreme learning machine (OPELM). The extreme learning machine (ELM) method is used as a comparison method. The mean absolute percentage error (MAPE) method is used to assess the level of forecasting accuracy. Forecasting power generation with Sidrap wind power plant data using the OPELM method is 0.8970% more accurate than the ELM which is 1.0853%. In general, the OPELM method is more accurate. Forecasting power generation with data from the Jeneponto wind power plant using the OPELM method is 2.4887% more accurate than the ELM method is 2.9984%. These results indicate that linear, sigmoid, and Gaussian activation in the OPELM method can increase accuracy. The OPELM method can be tested in forecasting the power generation at the Sidrap and Jeneponto wind power plants to maintain a power balance in the Sulselbar power grid system.

Rainfall prediction using optimally pruned extreme learning machines

Rainfall impacts local water quantity and quality. Accurate and timely prediction of rainfall is highly desirable in water management and hydrogeologic hazards mitigation, which is critical for the environmentally sustainable development. Previous rainfall prediction processes are complex and computationally costly for its intrinsic high uncertainty and variability. In this paper, a data-driven approach is applied to predict the rainfall based on historic data via time-series modeling and optimally pruned extreme learning machine (OP-ELM). The rainfall datasets collected from six counties within Three Georges Reservoir are utilized as case studies in this research, first, the rainfall data is pre-processed with outlier removal and missing value imputation, and the monthly ahead difference is computed based on the instant average of monthly rainfall. Next, the autocorrelation function and partial autocorrelation function were computed and the Ljung–Box test statistic is utilized to explore the significance of the historic lagged-series. All the statistically significant historic lags are selected as inputs for prediction algorithms. Last, an OP-ELM algorithm is developed to predict the monthly rainfall with tenfold cross validation. Four activation functions: the sigmoid, sine, hardlim, and radial basis function, are considered in the OP-ELM. The prediction performance is evaluated with metrics including mean absolute error, mean absolute percentage error, root mean square error, and max error rate. Overall, the computational results indicate the proposed framework outperforms the other benchmarking machine learning algorithms through six case studies in Three Gorges Reservoir, China.

A multilevel hybrid anomaly detection scheme for industrial wireless sensor networks

SummaryReal‐time sensing plays an important role in ensuring the reliability of industrial wireless sensor networks (IWSNs). Sensor nodes in IWSNs have inherent limitations that give rise to different anomalies in the network. These anomalies can lead to disastrous and harmful situations or even serious system failures. This article presents a formulation to the design of an anomaly detection scheme for detecting the anomalous node along with the type of anomaly. The proposed scheme is divided into two major parts. First, spatiotemporal correlation within a cluster is obtained for the normal and anomalous behavior of sensor nodes. Second, the multilevel hybrid classifier is used by combining the sequential minimal optimization support vector machine (SMO‐SVM) as a binary classifier with optimally pruned extreme learning machine (OP‐ELM) as a multiclass classifier for detection of an anomalous node and type of anomalies, respectively. Mahalanobis distance‐based lightweight K‐Medoid clustering is used to build a new set of training datasets that represents the original training dataset, by significantly reducing the training time of a multilevel hybrid classifier. Results are analyzed using standard WSN datasets. The proposed model shows high accuracy, i.e., 94.79% and detection rate, i.e., 94.6% with a reduced false positive rate as compared to existing hybrid methods.

A hybrid wavelet-optimally-pruned extreme learning machine model for the estimation of international roughness index of rigid pavements

ABSTRACT International Roughness Index (IRI) is a key parameter in pavement performance evaluation. This study investigates developing a reliable prediction model that can be used to estimate IRI of rigid pavements using innovative machine learning techniques. Optimally Pruned Extreme Learning Machine (OP-ELM) and Wavelet analysis are integrated to improve the OP-ELM results and design a novel hybrid Wavelet-OPELM (WOPELM) model for the IRI prediction. The proposed model is compared statistically to the OP-ELM and conventional feed-forward Artificial Neural Network (ANN) as well as regression model with respect to their efficiency to predict IRI of jointed plain concrete pavement (JPCP) sections in USA. The relevant data was collected from the Long-Term Pavement Performance (LTPP) database. Eight input variables, initial IRI, pavement age, transverse cracks, percent joints spalled, flexible and rigid patching areas, total joint faulting, freeze index, and percent subgrade passing No. 200 U.S. sieve, are assessed and used to predict the IRI. The results show that the initial IRI, total joint faulting, and freezing index are the most significant parameters for IRI prediction. The WOPELM is found to be a robust and more accurate modelling technique compared to OP-ELM, ANN, and regression for IRI prediction with only a 7% prediction error.

A competitive swarm optimizer with hybrid encoding for simultaneously optimizing the weights and structure of Extreme Learning Machines for classification problems

Extreme Learning Machine (ELM) is a learning algorithm proposed recently to train single hidden layer feed forward networks (SLFN). It has many attractive properties that include better generalization performance and very fast learning. ELM starts by assigning random values to the input weights and hidden biases and then in one step it determines the output weights using Moore-Penrose generalized inverse. Despite the aforementioned advantages, ELM performance might be affected by the random initialization of weights and biases or by the large generated network which might contain unnecessary number of neurons. In order to increase the generalization performance and to produce more compact networks, a hybrid model that combines ELM with competitive swarm optimizer (CSO) is proposed in this paper. The proposed model (CSONN-ELM) optimizes the weights and biases and dynamically determines the most appropriate number of neurons. To evaluate the effectiveness of the CSONN-ELM, it is experimented using 23 benchmark datasets, and compared to a set of static rules extracted from literature that are used to determine the number of neurons of SLFN. Moreover, it is compared to two dynamic methods that are used to enhance the performance of ELM, that are Optimally pruned ELM (OP-ELM) and metaheuristic based ELMs (Particle Swarm Optimization-ELM and Differential Evolution-ELM). The obtained results show that the proposed method enhances the generalization performance of ELM and overcomes the static and dynamic methods.

Enhancing the Prediction Accuracy of Data-Driven Models for Monthly Streamflow in Urmia Lake Basin Based upon the Autoregressive Conditionally Heteroskedastic Time-Series Model

Hydrological modeling is one of the important subjects in managing water resources and the processes of predicting stochastic behavior. Developing Data-Driven Models (DDMs) to apply to hydrological modeling is a very complex issue because of the stochastic nature of the observed data, like seasonality, periodicities, anomalies, and lack of data. As streamflow is one of the most important components in the hydrological cycle, modeling and estimating streamflow is a crucial aspect. In this study, two models, namely, Optimally Pruned Extreme Learning Machine (OPELM) and Chi-Square Automatic Interaction Detector (CHAID) methods were used to model the deterministic parts of monthly streamflow equations, while Autoregressive Conditional Heteroskedasticity (ARCH) was used in modeling the stochastic parts of monthly streamflow equations. The state of art and innovation of this study is the integration of these models in order to create new hybrid models, ARCH-OPELM and ARCH-CHAID, and increasing the accuracy of models. The study draws on the monthly streamflow data of two different river stations, located in north-western Iran, including Dizaj and Tapik, which are on Nazluchai and Baranduzchai, gathered over 31 years from 1986 to 2016. To ascertain the conclusive accuracy, five evaluation metrics including Correlation Coefficient (R), Root Mean Square Error (RMSE), Nash–Sutcliffe Efficiency (NSE), Mean Absolute Error (MAE), the ratio of RMSE to the Standard Deviation (RSD), scatter plots, time-series plots, and Taylor diagrams were used. Standalone CHAID models have better results than OPELM methods considering sole models. In the case of hybrid models, ARCH-CHAID models in the validation stage performed better than ARCH-OPELM for Dizaj station (R = 0.96, RMSE = 1.289 m3/s, NSE = 0.92, MAE = 0.719 m3/s and RSD = 0.301) and for Tapik station (R = 0.94, RMSE = 2.662 m3/s, NSE = 0.86, MAE = 1.467 m3/s and RSD = 0.419). The results remarkably reveal that ARCH-CHAID models in both stations outperformed all other models. Finally, it is worth mentioning that the new hybrid “ARCH-DDM” models outperformed standalone models in predicting monthly streamflow.

A Novel PPA Method for Fluid Pipeline Leak Detection Based on OPELM and Bidirectional LSTM

Pipeline leak detection has attracted great research interests for years in the energy industry. Continuous pressure monitoring is one of the most straightforward approaches in leak detection which utilizes pressure point analysis (PPA) algorithms to exploit the transient pressure characteristics and identify leak events. However, a critical issue that jeopardizes the deployment of PPA based methods is the high false alarm rate. In this paper, a novel PPA based leak detection method is proposed which can accurately detect the leak events and dramatically decrease the number of false alarms compared to existing methods. Firstly, the proposed method takes advantage of the good approximation ability and fast learning speed of optimally-pruned extreme learning machine (OPELM) to produce a preliminary leak detection result. Then, the strong memorizing ability of bidirectional long-short term memory (BiLSTM) network is exploited to identify the true positive from the preliminary detection result, hence significantly decrease the number of false alarms. Furthermore, a feature extraction mechanism is also proposed to obtain both the dynamic and static characteristics from raw pressure wave. Experiments and verifications are performed on different real world data sets obtained from pipeline leak tests. It shows that the proposed method can achieve higher detection accuracy with significantly less false alarms. It enhances the practicality of pressure monitoring based leak detection schemes.

Least square support vector machine and multivariate adaptive regression splines for streamflow prediction in mountainous basin using hydro-meteorological data as inputs

Monthly streamflow prediction is very important for many hydrological applications in providing information for optimal use of water resources. In this study, the prediction accuracy of new heuristic methods, optimally pruned extreme learning machine (OP-ELM), least square support vector machine (LSSVM), multivariate adaptive regression splines (MARS) and M5 model tree (M5Tree), is examined in modeling monthly streamflows using precipitation and temperature inputs. Data collected from Kalam and Chakdara stations at a mountainous basin, Swat River Basin, Pakistan are utilized as case study. The prediction accuracy of all four methods are validated and tested using four different input scenarios and evaluated using combined accuracy (CA), a newly used criterion in addition to root-mean-square error (RMSE), normalized RMSE, mean absolute error (MAE) and Nash-Sutcliffe efficiency (NSE). The test results of both stations show that the LSSVM and MARS-based models provide more accurate prediction results compared to OP-ELM and M5Tree models. LSSVM decreases the RMSE of the MARS, OP-ELM and M5Tree by 9.12%, 25.64% and 35.15% for the Kalam station while the RMSEs of the LSSVM, OP-ELM and M5Tree is decreased by 2.12%, 34.81% and 32.52% using MARS, for the Chakdara Station, respectively. It is observed that the monthly streamflows of Kalam Station can be successfully predicted using only temperature data. Only precipitation inputs also provide good accuracy for Kalam Station while they produce inaccurate predictions for the Chakdara Station. The prediction capabilities of the applied methods are also examined in estimating streamflow of downstream station using upstream data. The results prove the dominancy of LSSVM and MARS-based models over OP-ELM and M5Tree in prediction streamflow data without local input data. Heuristic methods are also compared with stochastic method of seasonal auto regressive moving average (SARIMA). The OP-ELM, LSSVM, MARS perform superior to the SARIMA in monthly streamflow prediction. Based on the overall results, the LSSVM and MARS are recommended for monthly streamflow prediction with or without local data.

Daily streamflow prediction using optimally pruned extreme learning machine

Daily streamflow prediction is important for flood warning, navigation, sediment control, reservoir operations and environmental protection. The current paper examines the prediction and estimation capability of a new heuristic method, optimally pruned extreme learning machine (OP-ELM) model, for daily streamflows of Fujiangqiao and Shehang stations at Fujiang River. Prediction accuracy of OP-ELM method is compared with other soft computing models, i.e. adaptive neuro-fuzzy inference system-particle swarm optimization (ANFIS-PSO), multivariate adaptive regression splines (MARS) and M5 model tree (M5Tree) using cross validation technique. Prediction results of the both stations reported that the OP-ELM and ANFIS-PSO are the best in modeling daily streamflows of upstream and downstream, respectively. For improving prediction accuracy of the OP-ELM method, various kernel types are tried and the linear, linear + sigmoid + Gaussian and linear + sigmoid provide the best results for both stations. The OP-ELM outperforms the other methods during estimation of downstream streamflow using hydro climatic data as input. The OP-ELM reduces the prediction error of ANFIS-PSO by 12% in estimation of daily streamflow. It is also found that including local data considerably improves the prediction accuracy in estimation of downstream streamflows. The overall results indicate that the OP-ELM method could be successfully used in predicting and estimating daily streamflow by using hydro climatic data as inputs.

Modelling of Maximum Daily Water Temperature for Streams: Optimally Pruned Extreme Learning Machine (OPELM) versus Radial Basis Function Neural Networks (RBFNN)

This study proposed two data-driven models, namely the optimally pruned extreme learning machine (OPELM) and the radial basis functions neural networks (RBFNN) to predict maximum daily water temperature in streams. Air temperature (Ta), flow discharge (Q) and the day of the year (DOY) were used as predictors. Four indicators, including the coefficient of correlation (R), the Willmott index of agreement (d), the root mean squared error (RMSE), and the mean absolute error (MAE) were used in evaluating the performances of different models. The present study was conducted according to four different scenarios. First, the OPELM and RBFNN models were developed and validated for each station separately. For the three other scenarios, the models were developed using data from one station and validated for the two other stations separately. Modelling results showed that in the proposed models Ta and Q may not be sufficiently informative and the addition of DOY significantly contributes to better capturing the seasonal pattern of the maximum daily water temperature in streams. Generally, OPELM models outperformed RBFNN models, and overall, the modelling results indicated that the OPELM models developed in this study can be effectively used for predicting maximum water temperature in streams.

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.

Predicting Daily Pan Evaporation (Epan) from Dam Reservoirs in the Mediterranean Regions of Algeria: OPELM vs OSELM

In the present study, we propose the application of two artificial intelligence models, namely: (i) the optimally pruned extreme learning machine (OPELM); and (ii) the online sequential extreme learning machine (OSELM) models, for estimating daily pan evaporation (Epan). The two models were developed and compared using four climatic data collected at two stations: Ain Dalia and Zit Emba. The maximum and minimum temperatures (Tmax, Tmin), wind speed (U2), relative humidity (RH %) and Epan data were used as inputs to the models. Pan evaporation Epan was directly measured using Class A evaporation pan. The results show that the two models provided different results at the two stations: the OPELM worked well at Ain Dalia while OSELM was more accurate at Zit Emba. More importantly, the inclusion of the periodicity did not lead to a significant improvement in the accuracy of the models. OSELM validation results, with a coefficient of correlation R = 0.872, a root mean square error RMSE =1.698 mm, and a mean absolute error MAE = 1.311 mm outperformed OPELM (R = 0.853, RMSE = 1.813 mm and MAE = 1.403 mm) at Zit Emba. In addition, at Ain Dalia, the results indicate that OPELM model provided slightly higher prediction accuracy compared to the OSELM model (R = 0.808 against 0.800; RMSE = 1.447 mm against 1.471 mm; MAE = 1.091 mm against 1.084 mm). This work demonstrates the ability of the OPELM and OSELM approaches for estimating daily Epan using easily measured climatic variables.

A novel sound-based belt condition monitoring method for robotic grinding using optimally pruned extreme learning machine

A novel method based on sound signals is proposed to realize realtime quantitative monitoring of abrasive belt conditions in robotic grinding system. Robotic belt grinding experiments are carried out on Inconel 718 alloy workpieces. The belt wear styles are observed under scanning electron microscope (SEM). The belt wear conditions are quantified by the grinding ability factor. During grinding process, sound signals are obtained concurrently by an omnidirectional capacitance microphone. Fast Fourier Transform (FFT) and Discrete Wavelet Decomposition (DWD) are conducted to separate the belt-condition-related sound signals from the raw signals. Then sound features are extracted to establish a novel data-driven model using Optimally Pruned Extreme Learning Machine (OP-ELM). The model is developed to predict the belt grinding ability factor. Experimental datasets are used to train and validate the established model. The results show that the grinding sound in high frequency region from 10 to 15 kHz is sensitive to the belt wear conditions, and that the OP-ELM model speedily and accurately predicts the belt grinding ability factor after optimizing the hidden layer numbers and kernel function type. Compared with experimental results, the mean absolute percentage errors (MAPE) of the predicted grinding ability factor are less than 0.4% and the maximum absolute percentage errors (MAXE) are within 14%. It is thus concluded that the proposed sound-based monitoring approach using the OP-ELM model is robust in accurately predicting the grinding belt condition despite grinding dynamics involving contact pressures.

Intelligent assistance positioning methodology based on modified iSAM for AUV using low-cost sensors

This paper focuses on the application of low-cost sensors for autonomous underwater vehicle (AUV). We propose an intelligent assistance positioning methodology by combining the modified incremental smoothing and mapping (iSAM) and constrained optimally pruned extreme learning machine (OP-ELM) for low-cost sensors, which makes full use of GPS data and produce a variety of correction models. Compared to relinearizing and variable reordering by period batch step in the original iSAM, modified iSAM is implemented variable reordering alone and conducted adaptive relinearization when the value of local Chi-square exceeded a certain threshold. Meanwhile, a novel constrained OP-ELM is presented by mapping the output to the constraint space, which provides full guarantee for generating reliable correction model. When GPS is valid, the constrained OP-ELM is applied to the low-cost sensors to generate correction model. Simultaneous, the correction model of measurement for modified iSAM is also given by this way. Once GPS becomes invalid, the correction models are used to amend the low-cost sensors data and measurement model for getting more accurate location information. Experimental results and analysis show that the proposed method outperforms the traditional algorithm, which RMSE can improve by at most 83.8% than Extended Kalman Filter's (EKF).

Shallow-sea application of an intelligent fusion module for low-cost sensors in AUV

This paper focuses on the application of AUV in shallow-sea, which environment is more complicated than deep-sea. Owing to independence of external signals, inertial navigation system (INS) has become the most suitable navigation and positioning system for underwater vehicles. However, as the excessive reliance on sensor data, the precision of INS can be affected by external environment, especially heading angles from low-cost sensors such as attitude and heading reference system (AHRS) and digital compass are susceptible to waves and magnetic interference. Therefore, how to use data from low-cost sensors becomes the key to improving navigation performance. Optimally pruned extreme learning machine (OP-ELM) was presented as a more robust and general methodology in 2010, which make it possible to fuse data by using a more reliable method. In this paper, we propose an intelligent fusion module which is designed to obtain the full-noise model for AUV. By judging the state of AHRS and TCM heading angles, intelligent fusion module combines full-noise model with credible data by using OP-ELM to improve the accuracy of positioning and navigation. Our method has been demonstrated by a range of real data, which RMSE can at most improve by 86.4% in complex conditions than Extended Kalman Filter's.