Elman Recurrent Neural Network Research Articles

Artificial neural network‐based adaptive control for nonlinear dynamical systems

SummaryThis research article presents an artificial neural network (ANN)‐based indirect adaptive control method for nonlinear dynamical systems. In this article, a modified Elman recurrent neural network (MERNN) is proposed as an identifier and controller for controlling nonlinear systems. The architecture of the proposed controller is a modified form of the existing Elman recurrent neural network. The parameter training of ANN‐based controllers is obtained by using the most popular optimization algorithm which is known as the back‐propagation algorithm. A comparative study includes Elman, Diagonal, Jordan, feed‐forward neural network (FFNN), and radial basis function network (RBFN)‐based controllers to compare with the proposed MERNN controller. To determine the controller's robustness, parameter variations, and disturbance signals have been considered. The performance analysis of the proposed controller is illustrated by two simulation examples. The simulation results reveal that MERNN can not only identify the unknown dynamics of the plant but also adaptively control it compared to the others.

Improved Elman Deep Learning Model for Intrusion Detection System in Internet of Things

Many researchers have developed intrusion detection systems in the past using conventional techniques such as artificial neural networks, fuzzy clustering, evolutionary algorithms, association rule mining, and support vector machines. However, in terms of false negative rates and detection rates, these methods did not yield the best outcomes. To address these problems, we proposed a hybrid deep learning model (HDLM) based on intrusion detection and prevention in IoT devices. Initially, the data are collected from KDDCup-99 and NSL-KDD datasets. Then, the important features are extracted from the dataset using the Forward Feature Selection Algorithm (FFSA). Finally, the extracted features are given to the HDLM classifier. The proposed HDLM is a combination of Elman Recurrent Neural Network (ERNN) and Subtraction-Average-Based Optimizer (SABO). The performance of the suggested method is assessed using performance metrics including precision, recall, accuracy, sensitivity, specificity, and F_Measure. The experimental results show that the proposed method attained the maximum intrusion detection accuracy of 98.52%.

Ovarian Cancer Detection Based on Elman Recurrent Neural Network

The early detection of cancers increases the possibility of health recovery and prevents the disease from becoming a silent killer. This study introduces an effective method for identifying ovarian cancer (OC) using Elman Recurrent Neural Network (ERNN), which can recognize cancer via mass spectrometry data. The network has a topology of 100 input neurons for receiving data, five neurons for hidden and context layers, and two output nodes to indicate the status. The proposed method uses reduced-size features, including ion concentration levels at specific mass/charge values, which are trained using various learning algorithms to determine the suitable one that achieves the best results. The experimental results show that all the training algorithms achieve about 100% performance rate, with the Levenberg Marquardt (LM) being the most accurate and fastest algorithm, which converges after six epochs and achieves 0.0035, 0.0045 and 0.0045 mean square errors for training, validation, and test performances, respectively. Based on comparative results, the proposed LM-ERNN method outperforms other OC detection methods and holds promise for detecting other types of cancer.

Enhancing cybersecurity in cloud-assisted Internet of Things environments: A unified approach using evolutionary algorithms and ensemble learning

<abstract> <p>Internet of Things (IoT) security is an umbrella term for the strategies and tools that protect devices connected to the cloud, and the network they use to connect. The IoT connects different objects and devices through the internet to communicate with similarly connected machines or devices. An IoT botnet is a network of infected or cooperated IoT devices that can be remotely organized by cyber attackers for malicious purposes such as spreading malware, stealing data, distributed denial of service (DDoS) attacks, and engaging in other types of cybercrimes. The compromised devices can be included in any device connected to the internet and communicate data with, e.g., cameras, smart home appliances, routers, etc. Millions of devices can include an IoT botnet, making it an attractive tool for cyber attackers to launch attacks. Lately, cyberattack detection using deep learning (DL) includes training neural networks on different datasets to automatically detect patterns indicative of cyber threats, which provides an adaptive and proactive approach to cybersecurity. This study presents an evolutionary algorithm with an ensemble DL-based botnet detection and classification (EAEDL-BDC) approach. The goal of the study is to enhance cybersecurity in the cloud-assisted IoT environment via a botnet detection process. In the EAEDL-BDC technique, the primary stage of data normalization using Z-score normalization is performed. For the feature selection process, the EAEDL-BDC technique uses a binary pendulum search algorithm (BPSA). Moreover, a weighted average ensemble of three models, such as the modified Elman recurrent neural network (MERNN), gated recurrent unit (GRU), and long short-term memory (LSTM), are used. Additionally, the hyperparameter choice of the DL approaches occurs utilizing the reptile search algorithm (RSA). The experimental outcome of the EAEDL-BDC approach can be examined on the N-BaIoT database. The extensive comparison study implied that the EAEDL-BDC technique reaches a superior accuracy value of 99.53% compared to other approaches concerning distinct evaluation metrics.</p> </abstract>

Detection of Human Stress Using Optimized Feature Selection and Classification in ECG Signals

An autonomic nervous system (ANS) of humans is majorly affected by psychological stress. The changes in ANS may cause several chronic diseases in humans. The electrocardiogram (ECG) signal is used to observe the variation in ANS. Numerous techniques are presented for an ECG stress signal handling feature extraction and classification. This work managed a heart rate variability feature acquired from smaller peak waveforms such as P, Q, S, and T waves. Also, the R peak is detected, which is a significant part of the ECG waveform. In this work, the proposed stress classification work has been categorized into two main processes: feature selection (FS) and classification. The main aim of the proposed work is to propose an optimized FS and classifier model for the detection of stress in ECG signals. The Metaheuristics model of the African vulture optimization (AVO) technique is presented to perform an FS. This selection is made to choose the required features and minimize the data for classification. The AVO-based modified Elman recurrent neural network (MERNN) technique is proposed to perform an efficient classification. The AVO is used for fine-tuning the weight of the MERNN technique. The experimental result of this technique is evaluated in terms of Recall (91.56%), Accuracy (92.43%), Precision (92.78%), and F1 score (95.86%). Thus, the proposed performance achieved a superior result than the conventional techniques.

Archimedes optimization-based Elman Recurrent Neural Network for detection of post-traumatic stress disorder

Post-traumatic stress disorder (PTSD) is a stress-based disorder that occurs when a person is vulnerable to undesirable traumatic events like injury or harm. Numerous research works reported dissimilar complex issues for detecting PTSD severity in patients which makes the PTSD diagnosis process a complicated task. So, a novel Multi-Strategy Seeker Archimedes Optimization-based Elman Recurrent Neural Network (MSSAO-ERNN) technique to detect PTSD symptoms in earlier stages using speech samples. Our proposed MSSAO-ERNN technique efficiently identifies PTSD symptoms from the dataset and helps the physician to diagnose accurately. The proposed approach constitutes various significant phases that include the pre-processing phase, feature extraction phase, and classification phase to detect the presence of PTSD in the datasets. The performance of the proposed method is determined by computing various metrics for the accurate identification of PTSD. Finally, three different datasets namely the NNE dataset, the FME hospital dataset as well as TIMIT dataset are employed in this paper for PTSD diagnosis. The experimental results revealed that the proposed method attained a superior accuracy of 97% under different PTSD techniques.

Eligibility of village fund direct cash assistance recipients using artificial neural network

<p>Bantuan Langsung Tunai Dana Desa (BLT-DD), or known as Village Fund Direct Cash Assistance is assistance from the Indonesian government which causes problems and conflicts in the community when the assistance is not on target. The classification algorithm is proven to use in determining BLT-DD recipients. In this study, the radial basis function (RBF) and elman recurrent neural network (ERNN) models compare to classify the eligibility of BLTDD recipients. In the experiment, the optimal performance of the RBF and ERNN compare in determining the eligibility of BLT-DD recipients. Also, it’s compared with the classification algorithm that implements the same data, namely BLT-DD data for Kubu Raya District. The experimental results show the effectiveness of the RBF model in recognizing test data, while the ERNN model is effective in identifying test data. The RBF and ERNN models can achieve the same total accuracy of 98.10%.</p>

DDoS attack detection in IoT environment using optimized Elman recurrent neural networks based on chaotic bacterial colony optimization

DDoS attack detection in IoT environment using optimized Elman recurrent neural networks based on chaotic bacterial colony optimization

Billiard based optimization with deep learning driven anomaly detection in internet of things assisted sustainable smart cities

Internet of Things (IoT) technology involves a network of interconnected devices and sensors that gather and exchange information. In smart cities, IoT devices were utilized in several fields including energy, transportation, waste management, healthcare, etc., to improve the overall quality of life and sustainability of the populace. But, as the usage of IoT increases, the cybersecurity and data privacy become a concern of safety. An anomaly detection system helps to identify possible data breaches or cyber-attacks by identifying abnormal data patterns. Deep learning (DL) driven anomaly detection has emerged as an effective and powerful method for identifying abnormal behaviours or patterns in the data domain. This technique leverages the abilities of a deep neural network for automated learning of complex patterns and representations from data, which make it better for anomaly detection task where irregularities cannot be easily defined by handcrafted rules. This paper establishes a new Billiard Based Optimization with Deep Learning Driven Anomaly Detection and Classification (BBODL-ADC) technique in IoT-assisted Sustainable Smart Cities. The goal of the BBODL-ADC technique lies in the proper recognition and classification of anomalies in the IoT-assisted smart city. To obtain that, the BBODL-ADC system applies a binary pigeon optimization algorithm (BPEO) algorithm for the effectual selection of features. Besides, the BBODL-ADC technique utilizes Elman recurrent neural network (ERNN) approach for the recognition and classification of anomalies. Moreover, the BBO system can be used for better parameters chosen by the ERNN algorithm. The stimulation value of the BBODL-ADC algorithm can be executed benchmark database. The achieved outcomes demonstrate the remarkable outcome of the BBODL-ADC methodology of 95.69% and 99.21% compared to existing models under dataset-1 and dataset-2.

Salp Swarm Optimized Hybrid Elman Recurrent Neural Network (SSO-ERNN) based MPPT Controller for Solar PV

Renewable energy technologies provide clean and abundant energy that can be self-renewed from natural sources; more support from the public to replace fossil fuels with various renewable energy sources to protect the environment. Although solar energy has less impact on the environment than other renewable sources, the output efficiency is lower due to the different weather conditions. So to overcome that, the MPPT controller is used for tracking peak power and better efficiency. Some conventional methods in MPPT controllers provide less tracking efficiency, and steady-state oscillations occur in maximum power tracking due to the sudden variations in solar irradiance. Thus, in this work salp swarm optimized (SSO) based Elman recurrent neural network (ERNN) controller is proposed to track the maximum power form PV with high efficiency. The weight parameter of ERNN layer is optimized with the help of SSO, which solve the complex problems and give maximum efficiency. The proposed method is performed in MATLAB/Simulink environment, which differs from existing plans and gives a better output efficiency. Using this proposed controller, the system can achieve high tracking efficiency of 99.74% compared to conventional processes.

Monthly sodium adsorption ratio forecasting in rivers using a dual interpretable glass-box complementary intelligent system: Hybridization of ensemble TVF-EMD-VMD, Boruta-SHAP, and eXplainable GPR

The sodium adsorption ratio (SAR) is the most crucial irrigation water quality indicator to diagnose the suitability of agricultural water resources. Due to this reason, accurate forecasting of SAR in the absence of its time series, based on limited input sequences, is recently considered a challenging environmental issue on a monthly scale. This research developed a dual eXplainable multivariate expert framework for the first time to forecast monthly SAR at Zayanderud River, Iran. The framework (i.e., BS-GPR-E.TVF-EMD-VMD) consisting of a Boruta coupled with SHapley Additive exPlanations (Boruta-SHAP) feature selection, an ensemble of time-varying filter-based empirical mode decomposition (TVF-EMD) and variational modal decomposition (VMD), namely (E.TVF-EMD-VMD), and eXplainable Gaussian process regression (GPR). The main novelty of this framework is converting the “black-box” nature of the forecasting model to a dual interpretable “glass box” before and during the learning process. For this purpose, among nine hydrometric and water quality parameters associated with Zayanderud River at two stations (Regulating dam and Zaman Khan) over the period of 1969 to 2016, the significant two-month antecedent information (lags) signals were extracted using the Boruta-SHAP feature selection. Afterwards, the optimal inputs signal lags for each station were decomposed into sub-components to reduce the complexity and non-stationary of original signals using three pre-processing techniques (i.e., E.TVF-EMD-VMD, TVF-EMD, and VMD). The decomposed predictors were employed as inputs into the multilayer perceptron neural network (MLP), Random Forest (RF), Elman recurrent neural network (ERNN), and eXplainable GPR approaches. Statistical validation and infographic tools revealed that the BS-GPR-E.TVF-EMD-VMD regarding the best performance in the Regulating dam (R = 0.9817, RMSE = 0.1431, and NSE = 0.8866) and Zaman Khan (R = 0.9632, RMSE = 0.0610, and NSE = 0.9233) stations, outperformed the other complementary and standalone counterpart frameworks followed by the BS-GPR-TVF-EMD and BS-ERNN-E.TVF-EMD-VMD, respectively. SHAP explainer through the GPR model clearly interpreted the effect of the lagged-time sub-components related to each predictor and represented the impact of each decomposition technique on the input signals through E.TVF-EMD-VMD aiming to forecast SAR in standalone and complementary frameworks.

Data-Driven Tabulation for Chemistry Integration Using Recurrent Neural Networks.

Due to the wide range of time scales involved in the ordinary differential equations (ODEs) describing chemical reaction kinetics, multidimensional numerical simulation of chemical reactive flows using detailed combustion mechanisms is computationally expensive. To confront this issue, this article presents an economic data-driven tabulation algorithm for fast combustion chemistry integration. It uses the recurrent neural networks (RNNs) to construct the tabulation from a series of current and past states to the next state, which takes full advantage of RNN in handling long-term dependencies of time series data. The training data are first generated from direct numerical integrations to form an initial state space, which is divided into several subregions by the K-means algorithm. The centroid of each cluster is also determined at the same time. Next, an Elman RNN is constructed in each of these subregions to approximate the expensive direct integration, in which the integration routine obtained from the centroid is regarded as the basis for a storing and retrieving solution to ODEs. Finally, the alpha-shape metrics with principal component analysis (PCA) are used to generate a set of reduced-order geometric constraints that characterize the applicable range of these RNN approximations. For online implementation, geometric constraints are frequently verified to determine which RNN network to be used to approximate the integration routine. The advantage of the proposed algorithm is to use a set of RNNs to replace the expensive direct integration, which allows to reduce both the memory consumption and computational cost. Numerical simulations of a H₂/CO-air combustion process are performed to demonstrate the effectiveness of the proposed algorithm compared to the existing ODE solver.

Scrutinizing the Performances of Hybrid ANN Models for Forecasting Condition of Bridges

AbstractBridges all over the world are vulnerable to severe deterioration agents meanwhile their maintenance budgets are being tightened. This state of affairs necessitates the establishment of an autonomous deterioration model to predict the performance condition of bridges. This research paper explores the implementation of a set of intelligent data driven models to analyze the future condition ratings of bridge decks. These models comprise support vector machines, Gaussian process regression, regression tree, back propagation artificial neural network, Elman recurrent neural network, cascade forward neural network, long short‐term memory network and deep convolutional neural network. The performance comparison is carried out using five evaluation metrics of root mean squared percentage error, mean absolute percentage error, root mean squared error mean absolute error and relative absolute error. The models herein are developed and validated using the structural deterioration information retrieved from the National Bridge Inventory (NBI). It can be argued that the developed deterioration model could be implemented by departments of transportation to analyze and monitor the performance condition behavior of bridge components over their useful lifetime.

The hydrogen sensing capability of zinc oxide-containing sensors: Modeling by the general regression artificial neural network

This research applies general regression (GR) neural networks to model the hydrogen sensing capability of pure zinc oxide (ZnO) and ZnO nanocomposites containing different additives. The sensor's topology/composition, temperature, and hydrogen concentration in the atmosphere are the independent features of the GR models. Sensitivity analysis approves that the Gaussian spread value must adjust to 23.5 × 10−6 to achieve the most accurate predictions. This model forecasts 297 actual responses of ten ZnO-containing sensors with mean absolute error, relative absolute error, and regression coefficient of 0.29, 1.56%, and 0.9977, respectively. These prediction accuracies are better than those obtained by cascade feedforward, radial basis, Elman recurrent, and multilayer perceptron neural networks. The relevancy test shows that the sensor's hydrogen detection ability improves with the sensor geometry and ZnO additive dose. ZnO–Co3O4 is the best sensor composition to detect even low hydrogen concentrations. Also, the nanowire and nanofiber are the best sensor topologies for the considered task.

Improved Feed-Forward Backpropagation Neural Network Based on Marine Predators Algorithm for Tuning Automatic Voltage Regulator

This research will discuss the application of an automatic voltage regulator based on the feed-forward back propagation neural network (FFBNN), which is enhanced by the marine predator algorithm (MPA). The marine predators algorithm is a method that adopts marine ecosystem life that is identified in the relationship between predators and prey. MPA is adopting a natural approach to arranging the best food search strategies and finding the latest strategy. The focus of the research is on the performance of speed and rotor angle. The performance of the proposed method will be tested using hidden layer variations. In addition, the proposed method will be compared with the feed-forward backpropagation neural network (FFBNN), cascade-forward backpropagation neural network (CFBNN), Elman recurrent neural network (E-RNN), and Focused Time Delay neural network (FTDNN). The speed and rotor angle of the proposed method have good values. The MPA-FFBNN results are not much different from other methods. The experimental results show that the performance of the proposed method has promising results.

Design of optimal Elman Recurrent Neural Network based prediction approach for biofuel production

Renewable sources like biofuels have gained significant attention to meet the rising demands of energy supply. Biofuels find useful in several domains of energy generation such as electricity, power, or transportation. Due to the environmental benefits of biofuel, it has gained significant attention in the automotive fuel market. Since the handiness of biofuels become essential, effective models are required to handle and predict the biofuel production in realtime. Deep learning techniques have become a significant technique to model and optimize bioprocesses. In this view, this study designs a new optimal Elman Recurrent Neural Network (OERNN) based prediction model for biofuel prediction, called OERNN-BPP. The OERNN-BPP technique pre-processes the raw data by the use of empirical mode decomposition and fine to coarse reconstruction model. In addition, ERNN model is applied to predict the productivity of biofuel. In order to improve the predictive performance of the ERNN model, a hyperparameter optimization process takes place using political optimizer (PO). The PO is used to optimally select the hyper parameters of the ERNN such as learning rate, batch size, momentum, and weight decay. On the benchmark dataset, a sizable number of simulations are run, and the outcomes are examined from several angles. The simulation results demonstrated the suggested model's advantage over more current methods for estimating the output of biofuels.

Shunt faults detection and classification in electrical power transmission line systems based on artificial neural networks

PurposeThis study aims to focus on an adaptive method for fault detection and classification of fault types that trigger in three-phase transmission lines using artificial neural networks (ANNs). The proposed scheme can detect and classify several types of faults, including line-to-ground, line-to-line, double-line-to-ground, triple-line and triple-line-to-ground faults.Design/methodology/approachThe fundamental components of three-phase current and voltage were used as inputs in the ANNs. An analysis of the impact of variations in the fault resistance, fault type and fault inception time was conducted to evaluate the ANNs performance. The survey compares the performance of the multi-layer perceptron neural network (MLPNN) and Elman recurrent neural network trained with the backpropagation learning technique to improve each of the three phases of the fault detection and classification process. A detailed analysis validates the choice of the ANNs architecture based on the variation in the number of hidden neurons in each step.FindingsThe mean square error, root mean square error, mean absolute error and linear regression are measured to improve the efficiency of the ANN models for both fault detection and classification. The results indicate that the MLPNN can detect and classify faults with a satisfactory performance.Originality/valueThe smart adaptive scheme is fast and accurate for fault detection and classification in a single circuit transmission line when faced with different conditions and can be useful for transmission line protection schemes.

Surface water electrical conductivity and bicarbonate ion determination using a smart hybridization of optimal Boruta package with Elman recurrent neural network

Water quality (WQ) monitoring in the surface water resources is a crucial concern as it has an impact on human health and ecosystem equilibrium. An accurate simulation of river WQ indicators as a function of available variables with data mining techniques is not much explored by the researchers. In this study, two smart dual-preprocessing hybridized with Elman recurrent neural network (ERNN) were developed for an accurate simulation of two surface WQ indices including electrical conductivity (EC) and bicarbonate (HCO3-) in the Northern zones of Karun River, Iran. Nine input features including sodium adsorption ratio (SAR), magnesium (Mg2+), Ca+2 (calcium) sum of the anions (Sum.A), SO42-(sulphate) Cl-(chloride), pH, discharge (Q), and Na+ (sodium) were employed to simulate the EC and HCO3- in surface water Two Boruta-data filtering strategies including Boruta-XGBoost (BXGB) and Boruta-Extra Tree (BET) were utilized to extract the most important WQ indicators in available features. The best subset regression (BSR) scheme was utilized to optimize the input combinations of available features to predict EC and HCO3-. Three superior scenarios (C1, C2, and C3) were considered for each target variable to feed the machine learning (ML) models. The dual pre-processing was hybridized with ERNN to compare the results of advanced ML approaches i.e., long short-term memory (LSTM), Kernel ridge repression (KRR), and Elastic net regression (ELNET). Eight hybrid modeling paradigms (BXGB-ERNN, BET-ERNN, BXGB-KRR, BET-KRR, BXGB-ELNET, BET-ELNET, BXGB-LSTM, and BET-LSTM) were evaluated in terms of performance using statistical criterions such as correlation coefficient (R), root mean square error (RMSE), and Kling-Gupta efficiency (KGE). Results revealed that the BET-ERNN-C1 hybrid model outperformed the other models for HCO3- (R = 0.9847, RMSE = 0.0793 mEq/L, and KGE = 0.9782) and EC simulation (R = 0.9543, RMSE = 51.0260 μS/cm, and KGE = 0.9406) in terms of performance efficiency. Results indicated that the BET-ERNN-C1 model resulted in minimum values of IQR for EC (0. 7.455) and HCO3- (0.1819). Overall, the result of modeling showed that the ERNN-C1 model had a superior performance in simulating the WQ indices followed by BXGB-ERNN-C3 and BXGB-KRR approaches. Results of this study suggested that the predictions of WQ indicators using hybrid models can be used to assess the acceptable levels of EC and HCO3- in surface water using appropriate input variables efficiently and reliably.

Development of a Production Machine Maintenance Predictive Model Using the Elman Recurrent Neural Network Algorithm

<table width="593" border="1" cellspacing="0" cellpadding="0"><tbody><tr><td valign="top" width="388"><p>PT Simba Indosnack Makmur is a factory that produces snacks. In the production process the machine has worked very optimally, the problem that is often faced by the Quality Control department is often finding non-standard product weights. This problem is caused by a machine that already requires maintenance. So far, the maintenance process has to get approval from the manager, which sometimes takes quite a long time to be inspected so that the maintenance process is delayed, which results in reduced production targets. By implementing a predictive maintenance model that utilizes time series data in the production process, applying the Elman Recurrent Neural Network will be able to provide notifications for machine maintenance before the machine is inaccurate in snack production. The Elman structure was chosen because it can make iterations much faster, thus facilitating the convergence process. The input vector used uses windows size. The results of the study using a target error of 0.001 show the smallest MSE value of 0.002833 with windows size 11. Then by using 13 neurons in the hidden layer a minimum error value of 0.003725 is obtained.</p></td></tr></tbody></table>

A Dynamic Recurrent Neural Network for Predicting Higher Heating Value of Biomass.

The higher heating value (HHV) is the main property showing the energy amount of biomass samples. Several linear correlations based on either the proximate or the ultimate analysis have already been proposed for predicting biomass HHV. Since the HHV relationship with the proximate and ultimate analyses is not linear, nonlinear models might be a better alternative. Accordingly, this study employed the Elman recurrent neural network (ENN) to anticipate the HHV of different biomass samples from both the ultimate and proximate compositional analyses as the model inputs. The number of hidden neurons and the training algorithm were determined in such a way that the ENN model showed the highest prediction and generalization accuracy. The single hidden layer ENN with only four nodes, trained by the Levenberg-Marquardt algorithm, was identified as the most accurate model. The proposed ENN exhibited reliable prediction and generalization performance for estimating 532 experimental HHVs with a low mean absolute error of 0.67 and a mean square error of 0.96. In addition, the proposed ENN model provides a ground to clearly understand the dependency of the HHV on the fixed carbon, volatile matter, ash, carbon, hydrogen, nitrogen, oxygen, and sulfur content of biomass feedstocks.