Extreme Learning Machine Approach Research Articles

Toward estimating standard enthalpy of combustion of pure chemical compounds: extreme learning machine approach

ABSTRACT One of the effective thermochemical properties in the determination of heat process efficiency is the combustion enthalpy changes during complete combustion of the compounds. According to the importance of this property in different processes, the main aim of this work is selected as the development of extreme learning machine (ELM) approach to predict the combustion enthalpy in terms of functional groups. To achieve this goal, a comprehensive data set containing 4,590 experimental enthalpy points is used for the preparation and validation of ELM. To investigate the accuracy of the ELM approach in the estimation of the enthalpy, various visual and statistical comparisons are used. These comparisons lead into R 2 value of one and low error values for overall phase. The standard deviation, root mean squared error, and mean relative error for overall phase are determined to be 11.18, 14.92, and 0.28, respectively. The relative deviations between the estimated and actual enthalpy points are below 8%. According to the statistical and graphical results, ELM algorithm has great potential in the prediction of enthalpy of combustion for pure chemical materials.

Combined i-Vector and Extreme Learning Machine Approach for Robust Speaker Identification and Evaluation with SITW 2016, NIST 2008, TIMIT Databases

In this article, a novel combined i-vector and an Extreme Learning Machine (ELM) is proposed for speaker identification. The ELM is chosen because it is fast to train and has a universal approximator property. Four combinations of features based on Mel Frequency Cepstral Coefficient and Power Normalized Cepstral Coefficient are used. Besides, seven fusion methods are exploited. The system is evaluated with three different databases, namely: the SITW 2006, NIST 2008, and the TIMIT database. This work employs the 2016 SITW database for the first time for speaker identification using the integration between the ELM and i-vector approach. From each database, 120 speakers with 1200 speech utterances are used (overall 360 speakers with 3600 speech utterances). Furthermore, comprehensive evaluations are exploited with a wide range of realistic background noise types (Stationary noise AWGN and Non-Stationary Noise types) with the handset effect. The proposed system is compared with the Gaussian Mixture Model-Universal Background Model (GMM-UBM) and other states of the art approaches. The results show that the i-vector method outperforms the GMM-UBM approach and other state- of-the-art methods under specific conditions, and that fusion techniques can be used to improve robustness to noise and handset effects.

Short/medium term solar power forecasting of Chhattisgarh state of India using modified TLBO optimized ELM

The solar power generation (SPG) prediction is indispensable to establish a reliable and secure power grid. The intelligent and knowledgeable techniques are required to forecast the most nonlinear and volatile SPG due to its dependency on fluctuating weather conditions (solar irradiance and temperature). In this work, an optimized Extreme Learning Machine (ELM) is employed to forecast real-time SPG of Chhattisgarh state of India by conceding weather conditions. The performance of ELM approach is enhanced by exploring relevant parameters such as weights, biases, and numbers of hidden layers. It requires computational techniques which are proficient enough to deal with high dimensional and complex problems. Teaching Learning Based Optimization (TLBO) technique is modified with two novel approaches to enhance the exploration and exploitation proficiency of TLBO algorithm. The collaboration of modified TLBO (MTLBO) and optimizable ELM technique is implemented to forecast SPG for four different case studies such as an hour ahead, a day ahead, a month ahead and three months ahead forecasting. The performance measures such as mean absolute error (MAE), mean squared error (MSE), mean absolute percentage error (MAPE), mean arctangent absolute percentage error (MAAPE), and correlation of determination (R2) are used to demonstrate the performance of proposed approach. Diebold-Mariano (DM) test and forecasting effectiveness are employed to hypothetically corroborate the capability of MTLBO based ELM model to outperform different optimization based ELM, ELM (with randomly fixed weights and biases) and ANN models. The simulation results contribute the evidence of excel performance of proposed approach for SPG forecasting.

The potential of ensemble WT-EEMD-kernel extreme learning machine techniques for prediction suspended sediment concentration in successive points of a river

Abstract Sediment transport is one of the most important issues in river engineering. In this study, the capability of the Kernel Extreme Learning Machine (KELM) approach for predicting the river daily Suspended Sediment Concentration (SSC) and Discharge (SSD) was assessed. Three successive hydrometric stations of Mississippi river were considered and based on the sediment and flow characteristics during the period of 2005–2008. Several models were developed and tested for SSC and SSD modeling. For improving the applied model efficiency, two post-processing techniques, namely Wavelet Transform (WT) and Ensemble Empirical Mode Decomposition (EEMD), were used. Also, two states of modeling based on stations' own data (state 1) and previous stations' data (state 2) were considered. The single and integrated KELM model results comparison indicated that the integrated WT and EEMD-KELM models resulted in more accurate outcomes. Results showed that data processing with WT was more effective than EEMD in increasing the models' efficiency. Data processing enhanced the models' capability by up to 15%. The results showed that the state 1 modeling led to better results, however, using the integrated KELM approaches the previous stations data could be applied successfully for SSC and SSD modeling when the stations' own data were not available. HIGHLIGHT The suspended sediment concentration (SSC) and suspended sediment discharge (SSD) were predicted via artificial intelligence approach in successive hydrometric stations. The data pre-processing impacts on models' efficiency improvement was assessed. The sensitivity analysis showed the most effective subseries was obtained from pre-processing models.

Extreme Learning Machine for Heartbeat Classification with Hybrid Time-Domain and Wavelet Time-Frequency Features.

Automatic heartbeat classification via electrocardiogram (ECG) can help diagnose and prevent cardiovascular diseases in time. Many classification approaches have been proposed for heartbeat classification, based on feature extraction. However, the existing approaches face the challenges of high feature dimensions and slow recognition speeds. In this paper, we propose an efficient extreme learning machine (ELM) approach for heartbeat classification with multiple classes, based on the hybrid time-domain and wavelet time-frequency features. The proposed approach contains two sequential modules: (1) feature extraction of heartbeat signals, including RR interval features in the time-domain and wavelet time-frequency features, and (2) heartbeat classification using ELM based on the extracted features. RR interval features are calculated to reflect the dynamic characteristics of heartbeat signals. Discrete wavelet transform (DWT) is used to decompose the heartbeat signals and extract the time-frequency features of the heartbeat signals along the timeline. ELM is a single-hidden layer feedforward neural network with the hidden layer parameters randomly generated in advance and the output layer parameters calculated optimally using the least-square algorithm directly using the training samples. ELM is used as the heartbeat classification algorithm due to its high accuracy training accuracy, fast training speed, and good generalization ability. Experimental testing is carried out using the public MIT-BIH arrhythmia dataset to perform a 16-class classification. Experimental results show that the proposed approach achieves a superior classification accuracy with fast training and recognition speeds, compared with existing classification algorithms.

Intelligent Software-Defined Network for Cognitive Routing Optimization using Deep Extreme Learning Machine Approach

In recent years, the infrastructure, instruments, and resources of network systems are becoming more complex and heterogeneous, with the rapid development of current internet and mobile communication technologies. In order to efficaciously prepare, control, hold and optimize networking systems, greater intelligence needs to be deployed. However, due to the inherently dispensed characteristic of conventional networks, Machine Learning (ML) techniques are hard to implement and deployed to govern and operate networks. Software-Defined Networking (SDN) brings us new possibilities to offer intelligence in the networks. SDN’s characteristics (e.g., logically centralized control, global network view, software-based site visitor analysis, and dynamic updating of forwarding rules) make it simpler to apply machine learning strategies. Various perspectives of fiber-optic communications including fiber nonlinearity coverage, optical performance checking, cognitive shortcoming detection/anticipation, and arranging and improvement of software-defined networks are examined in Machine Learning (ML) applications. This research paper has presented an imaginative framework concept called Intelligent Software Defined Network (ISDN) for Cognitive Routing Optimization (CRO) using Deep Extreme Learning Machine (DELM) approach (ISDN-CRO-DELM) in light of the new challenges in the development and operation of communication systems, and capturing motivation from how living creatures deal with difficulty and usability. The proposed methodology develops around the planned applications of progressive DELM methods and, specifically, probabilistic generative models for framework wide learning, demonstrating, improvement, and information description. Furthermore, ISDN-CRO-DELM, suggest to integrate this learning framework with the ISDN for CRO and reconfiguration approaches at the system level. MATLAB 2019a is used for DELM simulation and superior results show the effectiveness of the proposed framework.

Hybrid CNN-SVD Based Prominent Feature Extraction and Selection for Grading Diabetic Retinopathy Using Extreme Learning Machine Algorithm

This paper exploits the extreme learning machine (ELM) approach to address diabetic retinopathy (DR), a medical condition in which impairment occurs to the retina caused by diabetes. DR, a leading cause of blindness worldwide, is a sort of swelling leakage due to excessive blood sugar in the retina vessels. An early-stage diagnosis is therefore beneficial to prevent diabetes patients from losing their sight. This study introduced a novel method to detect DR for binary class and multiclass classification based on the APTOS-2019 blindness detection and Messidor-2 datasets. First, DR images have been pre-processed using Ben Graham’s approach. After that, contrast limited adaptive histogram equalization (CLAHE) has been used to get contrast-enhanced images with lower noise and more distinguishing features. Then a novel hybrid convolutional neural network-singular value decomposition model has been developed to reduce input features for classifiers. Finally, the proposed method uses an ELM algorithm as the classifier that minimizes the training time cost. The experiments focus on accuracy, precision, recall, and F1-score and demonstrate the feasibility of adopting the proposed scheme for DR diagnosis. The method outperforms the existing techniques and shows an optimistic accuracy and recall of 99.73% and 100%, respectively, for binary class. For five stages of DR classification, the proposed model achieved an accuracy of 98.09% and 96.26% for APTOS-2019 and Messidor-2 datasets, respectively, which outperformed the existing state-of-art models.

Cobal -A Novel Design of CNN Basedgait Feature Extraction Using Bat-Elm for Human Tracking System

Human gait recognition is one of the promising non-invasive biometric traits. Owing to its uniqueness, effectiveness and possession of rich discriminative features even in low resolution data, it is considered among the popular choicefor authentication purposes. The sensitivity of the model is the challenging attribute in gait recognition. Also, it is difficult to discriminate the view angle and motion of human gait in varying illumination conditions. Addressing these issues, a hybrid Convolutional Neural Network (CNN) adapted evolutionary Bat Optimized Extreme Learning Machine approach is proposed. This hybrid structure works in two folds, such that the novel spatiotemporal features including spatial and morphological features are extracted by the CNN structure. The output of the CNN is incorporated in to the Bat optimized learning scheme as a single feed forward loop to attain classification of gait movements for recognition. Extensive experiments shows reduced error rate, increasing the rate of recognition than most of the existing hybrid algorithms.

Modeling uniaxial compressive strength of some rocks from turkey using soft computing techniques

Uniaxial compressive strength (UCS) is substantially used mechanical parameters to observe and classification of rocks, but this test is subsersive, taking a long time and required well equipped laboratory conditions and properly prepared samples. Therefore it is important to estimate this parameter from other physico-mechanical rock parameters that are nondestructive, easy to prepare samples and required less time. Machine learning methods which are among these methods and increase their importance and validty are Multilayer Perceptron Neural Network (MLPNN), M5 Model Tree (M5MT), Extreme Learning Machine (ELM) methods. In this study, Brazilian tensile strength, ultrasonic P-wave velocity, shore hardness tests of different rock types (Basalt, limestone, dolostone) were performed. The results were used for estimating UCS using MLPNN, M5MT, ELM methods. The validation of models were checked root mean squared error (RMSE), mean absolute error (MAE), variance account for (VAF) and coefficient of determination (R2) and a10-index. Weights and bias values for MLPNN and ELM approaches and the tree structure for the M5MT method are presented. The result indicated MLPNN model outperforms the other models. Based on the result of predictive models with RMSE, MAE, VAF and R2 equal to RMSE: 1.3421, MAE: 0.7985, VAF: 99.7409, R2: 0.9982%.

(Invited) Regression and Optimization by Analogue In-memory Computing in Crosspoint Arrays

In-memory computing (IMC) is gaining momentum for low-power acceleration of data intensive problems, particularly in the frame of artificial intelligence (AI). Analogue matrix-vector multiplication (MVM) in crosspoint arrays allows to dramatically improve energy efficiency in neural networks for inference and training [1]. Recently, it has been shown that a feedback configuration of MVM can accelerate the solution of generic linear matrix problems, such as linear systems, matrix inversion and eigenvector calculation, with a single computational step [2,3]. This is achieved by the high parallelism of MVM in the memory array, combined with the physical iteration executed naturally in the feedback loop. Eigenvector extraction allows to address general problems, such as PageRank of internet webpages, with complexity O(1), i.e., the time to solve a ranking problem remains fixed irrespective of the size of the coefficient matrix [4]. In this work, we address two specific problems of AI acceleration, namely regression and optimization.Linear regression can be viewed as one of the most basic problems of machine learning: given a sequence of points, one must predict the value of the next point in the sequence. This problem can be solved in just one computational step by using the closed-loop crosspoint array of Fig. 1, where the independent variables x_i are physically written within the two crosspoint arrays, while the dependent variables y_i are applied externally as input currents. The crosspoint arrays are connected within a closed-loop configuration by using operational amplifiers (OAs) in the rows and the columns of the arrays. The OA output yields the coefficients of the best fitting line along the sequence, i.e., the coefficients a and b in the line equation y= ax + b providing the least mean squares (LMS) regression of the sequence. This problem can be extended to any arbitrary dimension, i.e., not only data on x-y plane, but also data on x-y-z space and any hyperspace of n dimensions. The problem can also be extended to logistic regression, which enables classification in one computational step. In particular, the crosspoint regression circuit allows the training of a 2-layer perceptron in just one step, by assuming random weights in the first layer according to the extreme learning machine (ELM) approach. In-memory computing thus appears as a promising option for accelerating neural network training with complexity O(1).The continuous-time, analogue closed-loop approach can be extended to a discrete-time, digital recurrent neural network (RNN) for addressing optimization problems [5]. The RNN allows the efficient solution of constraint satisfaction problems (CSPs), such as Sudoku, by taking advantage of analogue MVM in the crosspoint array. In the RNN, stochastic iterations can allow the minimization of the cost function, hence the number of violated constraints, thus leading to the global minimum. Noise can be injected as spike jitter by phase change memory devices as integrate-and-fire neurons. The convergence to the solution can be efficiently accelerated by a 2-layer RNN, where the first layer is programmed to prevent the violation of constraints in the CSP. In-memory solution of CSPs can dramatically improve the energy efficiency and speed of data intensive optimization in transport, industry, and society in general.

An efficient flow-based multi-level hybrid intrusion detection system for software-defined networks

Software-defined networking (SDN) is a novel networking paradigm that provides enhanced programming abilities, which can be used to solve traditional security challenges on the basis of more efficient approaches. The most important element in the SDN paradigm is the controller, which manages the flows of each correspondence forwarding element (switch or router). Flow statistics provided by the controller are considered to be useful information that can be used to develop a network-based intrusion detection system. Therefore, in this paper, we propose a 5-level hybrid classification system based on flow statistics in order to attain an improvement in the overall accuracy of the system. For the first level, we employ the k-nearest neighbor approach (kNN); for the second level, we use the extreme learning machine (ELM); and for the remaining levels, we utilize the hierarchical extreme learning machine (HELM) approach. In comparison with conventional supervised machine learning algorithms and other state-of-the-art methodologies based on the NSL-KDD benchmark dataset, the experimental study showed that our system achieves a good accuracy (84.29%), with an ability to detect new attacks that reaches 77.18%. Therefore, our approach presents an efficient approach for intrusion detection in SDNs.

Writer verification based on simple graphemes and extreme learning machine approaches

mTraditional literature presents complex biometric sources, descriptors, and classifiers to solve the writer’s verification problem. The simple graphemes have been studied recently considering classifiers such as multilayer perceptron, support vector machine and convolutional neural network, which allow a high level of performance but with high computational cost in the training. In this paper, we propose the use of extreme learning neural networks to verify the writer identity based on simple graphemes with the aim of achieve a better descriptor performance in a less training time. The proposal allows verify peoples identity through the analysis of handwritten text in order to fakes detect, authorship identification, fakes, threats and thefts in documents. The experimental results show that this type of classifiers achieve a rate of success greater to the 95% for all five characters in the problem addressed, but with significantly less training times than traditionally used techniques.

An optimal extreme learning-based classification method for power quality events using fractional Fourier transform

Mitigation of power quality events (PQEs) needs an accurate, faster, and efficient detection and classification technique for designing the compensating devices as a remedial measure to the problem. This study motivates on this issue to formulate a better technique based on fractional Fourier transform (FRFT) and extreme learning machine (ELM). FRFT is considered for relevant feature extraction due to its characteristics like enhanced order control and capability to provide time, frequency, and intermediate time–frequency depictions for any non-stationary power signals. The possibility of multi-domain feature extraction capability due to its easy order control arrives at a robust feature matrix, which makes the classification more accurate. An optimal ELM-based classifier is designed by tuning its system parameters applying modified teaching–learning-based optimization (MTLBO). This optimal ELM is implemented in this study along with FRFT to formulate the proposed approach denoted as FRFT–MTLBO–ELM. To give a good reason for the enhanced performance of the proposed technique, noisy and hybrid synthetic signals of ten PQEs are generated and tested considering fully all real-time condition cases. At last, a comparative result is presented with other applied signal processing-based approaches and it is found that the proposed FRFT–MTLBO–ELM approach is very effective and comparatively better justifying its real-time implementation in the monitoring systems.

The capacity estimation and cycle life prediction of lithium-ion batteries using a new broad extreme learning machine approach

Lithium-ion batteries have become the main power source of many electronic devices. Accurate capacity estimation and cycle life prediction of lithium-ion batteries are of great significance to ensure the reliability of electronic devices. Extreme learning machine(ELM) is a kind of single hidden layer feedforward neural network with fast learning speed and good generalization performance. Considering the shortcomings of deep learning and the increasing size of battery datasets, this paper introduces the idea of Broad Learning(BL) and develops a new ELM model: Broad Learning-Extreme Learning Machine(BL-ELM). First, an ELM network is constructed, and the feature nodes are produced by feature mapping of the input data. Second, the enhancement operation is performed on the mapped features to produce the enhancement nodes. Next, all these two kinds of nodes are merged to become the new input layer of the network, so that the model can quickly and fully obtain effective feature information from the input data. Finally, experiments are performed with different battery datasets. The results show that BL-ELM method can not only ensure the accuracy of estimation and prediction but also save time greatly. Further comparisons with other algorithms show that this novel model is more effective and competitive.

Microgrid Fault Detection and Classification: Machine Learning Based Approach, Comparison, and Reviews

Accurate fault classification and detection for the microgrid (MG) becomes a concern among the researchers from the state-of-art of fault diagnosis as it increases the chance to increase the transient response. The MG frequently experiences a number of shunt faults during the distribution of power from the generation end to user premises, which affects the system reliability, damages the load, and increases the fault line restoration cost. Therefore, a noise-immune and precise fault diagnosis model is required to perform the fast recovery of the unhealthy phases. This paper presents a review on the MG fault diagnosis techniques with their limitations and proposes a novel discrete-wavelet transform (DWT) based probabilistic generative model to explore the precise solution for fault diagnosis of MG. The proposed model is made of multiple layers with a restricted Boltzmann machine (RBM), which enables the model to make the probability reconstruction over its inputs. The individual RBM layer is trained with an unsupervised learning approach where an artificial neural network (ANN) algorithm tunes the model for minimizing the error between the true and predicted class. The effectiveness of the proposed model is studied by varying the input signal and sampling frequencies. A level of considered noise is added with the sample data to test the robustness of the studied model. Results prove that the proposed fault detection and classification model has the ability to perform the precise diagnosis of MG faults. A comparative study among the proposed, kernel extreme learning machine (KELM), multi KELM, and support vector machine (SVM) approaches is studied to confirm the robust superior performance of the proposed model.

Comparisons of extreme learning machine and backpropagation-based i-vector approach for speaker identification

The extreme learning machine (ELM) is one of the machine learning applications used for regression and classification systems. In this paper, an extended comparison between an ELM and the backpropagation neural network (BPNN)-based i-vector is given in terms of a closed-set speaker identification task using 120 speakers from the TIMIT database. The system is composed of the mel frequency cepstal coefficient (MFCC) and power normalized cepstal coefficient (PNCC) approaches to form the feature extraction stage, while the cepstral mean variance normalization (CMVN) and feature warping are applied in order to mitigate the linear channel effect. The system is utilized with equal numbers of speakers of both genders with 120 speakers with eight dialects from the TIMIT database. The results demonstrate that the combination of the i-vector with the ELM for different features has the highest speaker identification accuracy (SIA) compared with the combination of the BPNN with the i-vector. The results also show that the i-vector with ELM approach is faster than the BPNN-based i-vector and it has the highest SIA.

An Extreme Learning Machine Model Approach on Airbnb Base Price Prediction

The base price of Airbnb properties prediction is still a new area of prediction research, especially with the Extreme Learning Machine (ELM). The previous studies had several suggestions for the advantages of ELM, such as good generalization performance, fast learning speed, and high prediction accuracy. This paper proposes how the ELM approach is used as a prediction model for Air BnB base price. Generally, the steps are setting hidden neuron numbers, randomly assigning input weight and hidden layer biases, calculating the output layer; and the entire learning measure finished through one numerical change without iteration. The performance of the model is estimated utilizing mean squared error, mean absolute percentage error, and root mean squared error. Experiment with Airbnb dataset in London with twenty-one features as input generates a faster learning speed and better accuracy than the existing model.

Dynamic User Preference Parameters Selection and Energy Consumption Optimization for Smart Homes Using Deep Extreme Learning Machine and Bat Algorithm

The advancements in electronic devices have increased the demand for the internet of things (IoT) based smart homes, where the connecting devices are growing at a rapid pace. Connected electronic devices are more common in smart buildings, smart cities, smart grids, and smart homes. The advancements in smart grid technologies have enabled to monitor every moment of energy consumption in smart buildings. The issue with smart devices is more energy consumption as compared to ordinary buildings. Due to smart cities and smart homes' growth rates, the demand for efficient resource management is also growing day by day. Energy is a vital resource, and its production cost is very high. Due to that, scientists and researchers are working on optimizing energy usage, especially in smart cities, besides providing a comfortable environment. The central focus of this paper is on energy consumption optimization in smart buildings or smart homes. For the comfort index (thermal, visual, and air quality), we have used three parameters, i.e., Temperature (°F), illumination (lx), and CO2 (ppm). The major problem with the previous methods in the literature is the static user parameters (Temperature, illumination, and CO2); when they (parameters) are assigned at the beginning, they cannot be changed. In this paper, the Alpha Beta filter has been used to predict the indoor Temperature, illumination, and air quality and remove noise from the data. We applied a deep extreme learning machine approach to predict the user parameters. We have used the Bat algorithm and fuzzy logic to optimize energy consumption and comfort index management. The predicted user parameters have improved the system's overall performance in terms of ease of use of smart systems, energy consumption, and comfort index management. The comfort index after optimization remained near to 1, which proves the significance of the system. After optimization, the power consumption also reduced and stayed around the maximum of 15-18wh.

Extreme learning machine for a new hybrid morphological/linear perceptron

Morphological neural networks (MNNs) can be characterized as a class of artificial neural networks that perform an operation of mathematical morphology at every node, possibly followed by the application of an activation function. Morphological perceptrons (MPs) and (gray-scale) morphological associative memories are among the most widely known MNN models. Since their neuronal aggregation functions are not differentiable, classical methods of non-linear optimization can in principle not be directly applied in order to train these networks. The same observation holds true for hybrid morphological/linear perceptrons and other related models. Circumventing these problems of non-differentiability, this paper introduces an extreme learning machine approach for training a hybrid morphological/linear perceptron, whose morphological components were drawn from previous MP models. We apply the resulting model to a number of well-known classification problems from the literature and compare the performance of our model with the ones of several related models, including some recent MNNs and hybrid morphological/linear neural networks.

Intelligent routing between capsules empowered with deep extreme machine learning technique

A container is a gathering of neurons whose action vector speaks to the instantiation parameters of a particular kind of substance, for example, an item or an article part. We utilize the length of the action vector to speak to the likelihood that the substance exists and its introduction to speak to the instantiation parameters. Compelling cases at one dimension make expectations, utilizing change networks, for the instantiation parameters of more elevated amount containers. At the point when different forecasts concur, a higher amount of container ends up dynamic. We demonstrate that a discriminatively prepared, multilayer case framework accomplishes best in class execution on Modified National Institute of Standards and Technology (MNIST) and is extensively superior to a deep learning algorithm at perceiving exceedingly covering digits. Deep learning algorithms encouraged by the function and structure of the brain. The deep extreme learning machine (DELM) approach is used to construct a compound that has the least error and highest reliability. All layers are jointly or greedily optimized, depending on the strategy. Deep extreme learning learns all the layers. This paper shows research on the expectation of the MNIST dataset using a DELM. In this article to predict digits better, we have used feedforward and backward propagation deep learning neural networks. When the results were considered, it was observed that deep extreme learning neural network has the highest accuracy rate with 70% of training (42,000 samples), 30% of test and validation (28,000 examples). When comparing the results, it was seen that the intelligent routing between capsules empowered with DELM (IRBC DELM) has the highest precision rate of 97.8%. Simulation results validate the prediction effectiveness of the proposed DELM strategy.