scholarly journals Prognostication of Shortwave Radiation Using an Improved No-Tuned Fast Machine Learning

2021 ◽  
Vol 13 (14) ◽  
pp. 8009
Author(s):  
Isa Ebtehaj ◽  
Keyvan Soltani ◽  
Afshin Amiri ◽  
Marzban Faramarzi ◽  
Chandra A. Madramootoo ◽  
...  
Keyword(s):  
Extreme Learning Machine ◽  
Land Surface ◽  
Weather Forecasting ◽  
Google Earth ◽  
Shortwave Radiation ◽  
Energy Budgets ◽  
Percentage Error ◽  
Estimation Uncertainty ◽  
Learning Machine ◽  
Hidden Neurons

Shortwave radiation density flux (SRDF) modeling can be key in estimating actual evapotranspiration in plants. SRDF is the result of the specific and scattered reflection of shortwave radiation by the underlying surface. SRDF can have profound effects on some plant biophysical processes such as photosynthesis and land surface energy budgets. Since it is the main energy source for most atmospheric phenomena, SRDF is also widely used in numerical weather forecasting. In the current study, an improved version of the extreme learning machine was developed for SRDF forecasting using the historical value of this variable. To do that, the SRDF through 1981–2019 was extracted by developing JavaScript-based coding in the Google Earth Engine. The most important lags were found using the auto-correlation function and defined fifteen input combinations to model SRDF using the improved extreme learning machine (IELM). The performance of the developed model is evaluated based on the correlation coefficient (R), root mean square error (RMSE), mean absolute percentage error (MAPE), and Nash–Sutcliffe efficiency (NSE). The shortwave radiation was developed for two time ahead forecasting (R = 0.986, RMSE = 21.11, MAPE = 8.68%, NSE = 0.97). Additionally, the estimation uncertainty of the developed improved extreme learning machine is quantified and compared with classical ELM and found to be the least with a value of ±3.64 compared to ±6.9 for the classical extreme learning machine. IELM not only overcomes the limitation of the classical extreme learning machine in random adjusting of bias of hidden neurons and input weights but also provides a simple matrix-based method for practical tasks so that there is no need to have any knowledge of the improved extreme learning machine to use it.

scholarly journals An Expert Diagnosis System for Parkinson Disease Based on Genetic Algorithm-Wavelet Kernel-Extreme Learning Machine

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Derya Avci ◽  
Akif Dogantekin
Keyword(s):  
Genetic Algorithm ◽  
Parkinson Disease ◽  
Extreme Learning Machine ◽  
Classification Accuracy ◽  
Disease Diagnosis ◽  
Major Public Health Problem ◽  
Diagnosis System ◽  
Kernel Extreme Learning Machine ◽  
Learning Machine ◽  
Hidden Neurons

Parkinson disease is a major public health problem all around the world. This paper proposes an expert disease diagnosis system for Parkinson disease based on genetic algorithm- (GA-) wavelet kernel- (WK-) Extreme Learning Machines (ELM). The classifier used in this paper is single layer neural network (SLNN) and it is trained by the ELM learning method. The Parkinson disease datasets are obtained from the UCI machine learning database. In wavelet kernel-Extreme Learning Machine (WK-ELM) structure, there are three adjustable parameters of wavelet kernel. These parameters and the numbers of hidden neurons play a major role in the performance of ELM. In this study, the optimum values of these parameters and the numbers of hidden neurons of ELM were obtained by using a genetic algorithm (GA). The performance of the proposed GA-WK-ELM method is evaluated using statical methods such as classification accuracy, sensitivity and specificity analysis, and ROC curves. The calculated highest classification accuracy of the proposed GA-WK-ELM method is found as 96.81%.

Modeling of Drying Process of Bittim Nuts (pistacia terebinthus) in a Fixed Bed Dryer System by Using Extreme Learning Machine

2012 ◽  
Vol 8 (4) ◽  
Author(s):  
Asım Balbay ◽  
Engin Avci ◽  
Ömer Şahin ◽  
Resul Coteli
Keyword(s):  
Extreme Learning Machine ◽  
Fixed Bed ◽  
Experimental Studies ◽  
Learning Rule ◽  
Activation Function ◽  
Optimal Topology ◽  
Gradient Based ◽  
Learning Machine ◽  
Pistacia Terebinthus ◽  
Hidden Neurons

Abstract Artificial neural networks (ANNs) have been widely used in modeling of various systems. Training of ANNs is commonly performed by backpropagation based on a gradient-based learning rule. However, it is well-known that such learning rule has several shortcomings such as slow convergence and training failures. This paper proposes a modeling technique based on Extreme Learning Machine (ELM) eliminating disadvantages of backpropagation based on a gradient-based learning rule for the drying of bittim (pistacia terebinthus). The samples for ELM based model are obtained by experimental studies. In experimental studies, the sample mass loss rate as a function time was investigated in different air velocities (0.5 and 1 m/s) and air temperatures (40, 60 and 80°C) in a designed dryer system. The obtained samples from experiments are used for training and testing of ELM. Further, some parameters of ELM such as type of activation function and the number of hidden neurons are set to obtain the best possible modelling results. The obtained prediction results show that ELM algorithm with tangent sigmoid activation function and 20 hidden neurons is appeared to be most optimal topology since maximum R2 and minimum rms (0.0500) and cov (0.2256) values are obtained. Thus, it is concluded that ELM can be used as an effective modelling tool in the drying of bittim (pistacia terebinthus) in fixed bed dryer system.

scholarly journals Palm Oil Prediction Production Using Extreme Learning Machine

2019 ◽  
Author(s):  
Ronal Watrianthos
Keyword(s):  
Extreme Learning Machine ◽  
Palm Oil ◽  
Oil Production ◽  
Training Data ◽  
Total Production ◽  
Land Area ◽  
Technical Data ◽  
Learning Machine ◽  
Hidden Neurons ◽  
Production Problems

The total production of Indonesian palm oil (CPO) in 2018 reached 43.9 million tons, with a land area of 12.3 million hectares.However, every month there are still many companies that have problems in predicting palm oil production. Problems in predicting thisproduction can be solved by calculation methods in the field of artificial neural networks, namely the Extreme Learning Machine (ELM)method. This method can solve linear and non-linear data problems and provide better average computation compared to other methods inpredicting oil palm production. The data used is palm oil production data at PT Indo Palm Oil Labuhan Batu with a total of 297 in the period2017-2018. While the parameters used are planting age, land area, number of trees, and yields. The results of the best-hidden neuron testare 13 with 2 technical data features and the training data pattern is pattern 1. The average MAPE value is 20.1% with the fastestcomputing time is the use of the number of hidden neurons 2. So based on the test results, the method ELM has a predictive model withquite good performance because the MAPE value is in the range of 20% -50%.

Auto Associative Extreme Learning Machine Based Hybrids for Data Imputation

2020 ◽  
pp. 867-893
Author(s):  
Chandan Gautam ◽  
Vadlamani Ravi
Keyword(s):  
Extreme Learning Machine ◽  
Principal Component ◽  
Rank Test ◽  
Percentage Error ◽  
Data Imputation ◽  
Gray System Theory ◽  
Signed Rank ◽  
Random Weights ◽  
Signed Rank Test ◽  
Learning Machine

This chapter presents three novel hybrid techniques for data imputation viz., (1) Auto-associative Extreme Learning Machine (AAELM) with Principal Component Analysis (PCA) (PCA-AAELM), (2) Gray system theory (GST) + AAELM with PCA (Gray+PCA-AAELM), (3) AAELM with Evolving Clustering Method (ECM) (ECM-AAELM). Our prime concern is to remove the randomness in AAELM caused by the random weights with the help of ECM and PCA. This chapter also proposes local learning by invoking ECM as a preprocessor for AAELM. The proposed methods are tested on several regression, classification and bank datasets using 10 fold cross validation. The results, in terms of Mean Absolute Percentage Error (MAPE,) are compared with that of K-Means+Multilayer perceptron (MLP) imputation (Ankaiah & Ravi, 2011), K-Medoids+MLP, K-Means+GRNN, K-Medoids+GRNN (Nishanth & Ravi, 2013) PSO_Covariance imputation (Krishna & Ravi, 2013) and ECM-Imputation (Gautam & Ravi, 2014). It is concluded that the proposed methods achieved better imputation in most of the datasets as evidenced by the Wilcoxon signed rank test.

scholarly journals Barium Titanate Semiconductor Band Gap Characterization through Gravitationally Optimized Support Vector Regression and Extreme Learning Machine Computational Methods

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Sunday O. Olatunji ◽  
Taoreed O. Owolabi
Keyword(s):  
Barium Titanate ◽  
Band Gap ◽  
Support Vector Regression ◽  
Extreme Learning Machine ◽  
Energy Gap ◽  
Gravitational Search Algorithm ◽  
High Rate ◽  
Percentage Error ◽  
Support Vector ◽  
Learning Machine

Barium titanate (BaTiO3) is a class of ceramic multifunctional materials with unique thermal stability, prominent piezoelectricity constant, excellent dielectric constant, environmental friendliness, and excellent photocatalytic activities. These features have rendered barium titanate indispensable in many areas of applications such as electromechanical devices, thermistors, multilayer capacitors, and electrooptical devices. The photocatalytic activity of barium titanate semiconductor is hindered by its large band gap and high rate of charge recombination. Doping of the parent barium titanate compound for band gap tuning is challenging and consumes appreciable time and other valuable resources. This present work relates the influence of foreign material incorporation into the parent barium titanate with the corresponding energy band gap by developing extreme learning machine- (ELM-) based models and hybridization of support vector regression (SVR) with gravitational search algorithm (GSA) using the structural lattice distortion that emanated from doping as model descriptors. The developed gravitationally optimized SVR (GSVR) is characterized with a low value of mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) of 0.036 ev, 1.145 ev, and 0.122 ev, respectively. The developed GSVR model outperforms ELM-Sine and ELM-Sig models using various performance evaluators. The developed GSVR model investigates the significance of iodine and samarium incorporation on the band gap of the parent barium titanate and the attained energy gaps conform excellently to the experimentally reported values. The demonstrated precision of the developed GSVR as measured from the closeness of its estimates with the measured values provides a quick and accurate method of energy gap characterization with circumvention of experimental stress and conservation of valuable time as well as other resources.

scholarly journals Change Detection for Heterogeneous Remote Sensing Images with Improved Training of Hierarchical Extreme Learning Machine (HELM)

2021 ◽  
Vol 13 (23) ◽  
pp. 4918
Author(s):  
Te Han ◽  
Yuqi Tang ◽  
Xin Yang ◽  
Zefeng Lin ◽  
Bin Zou ◽  
...  
Keyword(s):  
Change Detection ◽  
Extreme Learning Machine ◽  
State Of The Art ◽  
Sample Selection ◽  
Training Sample ◽  
Google Earth ◽  
Detection Methods ◽  
Feature Maps ◽  
Optical Images ◽  
Learning Machine

To solve the problems of susceptibility to image noise, subjectivity of training sample selection, and inefficiency of state-of-the-art change detection methods with heterogeneous images, this study proposes a post-classification change detection method for heterogeneous images with improved training of hierarchical extreme learning machine (HELM). After smoothing the images to suppress noise, a sample selection method is defined to train the HELM for each image, in which the feature extraction is respectively implemented for heterogeneous images and the parameters need not be fine-tuned. Then, the multi-temporal feature maps extracted from the trained HELM are segmented to obtain classification maps and then compared to generate a change map with changed types. The proposed method is validated experimentally by using one set of synthetic aperture radar (SAR) images obtained from Sentinel-1, one set of optical images acquired from Google Earth, and two sets of heterogeneous SAR and optical images. The results show that compared to state-of-the-art change detection methods, the proposed method can improve the accuracy of change detection by more than 8% in terms of the kappa coefficient and greatly reduce run time regardless of the type of images used. Such enhancement reflects the robustness and superiority of the proposed method.

Auto Associative Extreme Learning Machine Based Hybrids for Data Imputation

2017 ◽  
pp. 75-99
Author(s):  
Chandan Gautam ◽  
Vadlamani Ravi
Keyword(s):  
Extreme Learning Machine ◽  
Principal Component ◽  
Rank Test ◽  
Percentage Error ◽  
Data Imputation ◽  
Gray System Theory ◽  
Signed Rank ◽  
Random Weights ◽  
Signed Rank Test ◽  
Learning Machine

This chapter presents three novel hybrid techniques for data imputation viz., (1) Auto-associative Extreme Learning Machine (AAELM) with Principal Component Analysis (PCA) (PCA-AAELM), (2) Gray system theory (GST) + AAELM with PCA (Gray+PCA-AAELM), (3) AAELM with Evolving Clustering Method (ECM) (ECM-AAELM). Our prime concern is to remove the randomness in AAELM caused by the random weights with the help of ECM and PCA. This chapter also proposes local learning by invoking ECM as a preprocessor for AAELM. The proposed methods are tested on several regression, classification and bank datasets using 10 fold cross validation. The results, in terms of Mean Absolute Percentage Error (MAPE,) are compared with that of K-Means+Multilayer perceptron (MLP) imputation (Ankaiah & Ravi, 2011), K-Medoids+MLP, K-Means+GRNN, K-Medoids+GRNN (Nishanth & Ravi, 2013) PSO_Covariance imputation (Krishna & Ravi, 2013) and ECM-Imputation (Gautam & Ravi, 2014). It is concluded that the proposed methods achieved better imputation in most of the datasets as evidenced by the Wilcoxon signed rank test.

scholarly journals A Hybrid Method Based on Extreme Learning Machine and Self Organizing Map for Pattern Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Imen Jammoussi ◽  
Mounir Ben Nasr
Keyword(s):  
Extreme Learning Machine ◽  
Inverse Method ◽  
Learning Algorithm ◽  
Self Organizing Map ◽  
Random Parameters ◽  
Fast Learning ◽  
Self Organized ◽  
Learning Machine ◽  
Hidden Layer ◽  
Hidden Neurons

Extreme learning machine is a fast learning algorithm for single hidden layer feedforward neural network. However, an improper number of hidden neurons and random parameters have a great effect on the performance of the extreme learning machine. In order to select a suitable number of hidden neurons, this paper proposes a novel hybrid learning based on a two-step process. First, the parameters of hidden layer are adjusted by a self-organized learning algorithm. Next, the weights matrix of the output layer is determined using the Moore–Penrose inverse method. Nine classification datasets are considered to demonstrate the efficiency of the proposed approach compared with original extreme learning machine, Tikhonov regularization optimally pruned extreme learning machine, and backpropagation algorithms. The results show that the proposed method is fast and produces better accuracy and generalization performances.

scholarly journals Extreme Learning Machine with Multi-Agent System for Regression

2019 ◽  
Vol 9 (2) ◽  
pp. 4149-4153
Keyword(s):  
Extreme Learning Machine ◽  
Learning Algorithm ◽  
Multi Agent System ◽  
Agent System ◽  
Individual Agent ◽  
Learning Speed ◽  
Benchmark Datasets ◽  
Multi Agent ◽  
Learning Machine ◽  
Hidden Neurons

From the point of learning speed as well as generalization, Extreme Learning Machine(ELM) is widely known as an effective learning algorithm than the conventional learning methods. Basically, hidden neurons are not required in neuron alike, instead, weight is the parameter that would need to learn about the link in between output and hidden layers. The creation of an output is to integrate each independent of several ELMs. The precise approach is included in a Multi-Agent System. The novelty of ELM-MAS (extreme learning machine based multi-agent system) is put forward in the paper for solving data regression problems. The ELMs consist of two layers which are the parent agent layer and individual agent layer. The effectiveness of the ELM-MAS model is proved with some activation functions employing benchmark datasets (abalone, strike and space-ga) and real world application (Nox emission). The outcomes indicate that the proposed model is capable to attain improved results than other approaches.

Sign in / Sign up

Export Citation Format

Share Document