Modified Elman Neural Network Research Articles

Enhancing Breast Cancer Diagnosis using a Modified Elman Neural Network with Optimized Algorithm Integration

Enhancing Breast Cancer Diagnosis using a Modified Elman Neural Network with Optimized Algorithm Integration

An IDS based on modified chaos Elman’s neural network approaches for securing mobile ad hoc networks against DDoS attack

A mobile ad hoc network (MANETs) is a collection of moving nodes that combine into a network with no predefined infrastructure. There are many types of attacks that could target MANETS, one among them is Distributed Denial of service attacks (DDoS). DDoS is defined as attacking routing functions and taking down the entire operation of the mobile ad hoc network. The two primary victims of DDoS attacks are the functions of routing and battery capacity. The DDoS attack can cause routing table overflow which in turn can potentially cause the infected node floods. The routing overflow is followed by creating a fake route packet to consume the available resources of the participating active nodes. This cause disrupts the normal functioning of legitimate routes. In recent years, different approaches are implemented to improve the security level of MANET. In this work, the Cuckoo Search Algorithm-based Modified Elman’s Neural Network (CSA - MENN) approaches have been proposed to overcome DDoS attacks. The CSA - MENN approaches consists of three-part which are Cuckoo search algorithm clustering area to enhance the route from source to destination, chaos theory module is used to detect the abnormal nodes, then the Modified Elman Neural Network (MENN) is employed to prevent a malicious node from sending data to the destination by determining node that consumed more resources. Packets could be lost or the victim could reset the path between the attacker and itself. CICIDS dataset has been used to test and evaluate the performance of the proposed approach based on the criteria of accuracy, packet loss, and jitter. The data set, CICIDS 2017, used in this article divides the data into 7 groups: 5 for training, 1 for validation, and 1 for generalization. In summary, approximately 71.4 percent of data is used for training and 28.6 percent for validation and generalization.

A data-driven method for IGBT open-circuit fault diagnosis for the modular multilevel converter based on a modified Elman neural network

Modular multilevel converter is widely used in electrical energy with many advantages, its safety and reliability has become a research hotspot. Since the structure of MMC is composed of multiple cascaded sub-modules, including a large number of IGBTs and capacitors. Therefore, fault diagnosis measures must be taken to quickly eliminate the faults. In order to solve this problem, a data-driven method is proposed based on a modified Elman neural network. By comparing the distance Ek between the predicted and true value of bridge arm current, this method can quickly realize fault detection. The original contribution of this paper is using the modified cuckoo search (MCS) to optimize the parameters of Elman model, so as to achieve the optimal balance between fault diagnosis accuracy and diagnosis speed. The simulation results proved that it can quickly detect the open-circuit fault of IGBT by data-driven, and the detection time is about 20 ms.

Intelligent Sine Cosine Optimization with Deep Transfer Learning Based Crops Type Classification Using Hyperspectral Images

Hyperspectral Remote Sensing (HRS) is an emergent, multidisciplinary paradigm with several applications, which are developed on the basis of material spectroscopy, radiative transfer, and imaging spectroscopy. HRS plays a vital role in agriculture for crops type classification and soil prediction. The recently developed artificial intelligence techniques can be used for crops type classification using HRS. This study develops an Intelligent Sine Cosine Optimization with Deep Transfer Learning Based Crop Type Classification (ISCO-DTLCTC) model. The ISCO-DTLCTC technique comprises initial preprocessing step to extract the region of interest. The information gain-based feature reduction technique is employed to reduce the dimensionality of the original hyperspectral images. In addition, a fusion of 3 deep convolutional neural networks models namely, VGG16, SqueezeNet, and Dense-EfficientNet perform feature extraction process. Furthermore, sine cosine optimization (SCO) algorithm with Modified Elman Neural Network (MENN) model is applied for crops type classification. The design of SCO algorithm helps to proficiently select the parameters involved in the MENN model. The performance validation of the ISCO-DTLCTC model is carried out using benchmark datasets and the results are inspected under several measures. Extensive comparative results demonstrated the betterment of the ISCO-DTLCTC model over the state of art approaches with maximum accuracy of 99.99%.

Design and Implementation of a Machine-Learning Observer for Sensorless PMSM Drive Control

Information about rotor positions is critical when controlling a permanent-magnet synchronous motor (PMSM). This information can be gathered using a sensor or through an estimation without using a sensor. This article discusses a machine learning technique for estimating rotor positions. The proposed machine learning observer was constructed using a modified Elman neural network as the main algorithm. The network was trained offline with training data obtained from PMSM field-oriented control simulations and was tested using a validation data set. The PMSM control simulation results revealed that the rotor position estimated through machine learning was comparable with the simulated rotor position; the average error was 0.0127 per unit position. Furthermore, the machine learning model was implemented in an experimental PMSM-control hardware platform. Both the simulation and experimental results indicate that the proposed machine learning observer has an acceptable performance.

Smart element aware gate controller for intelligent wheeled robot navigation

<p>The directing of a wheeled robot in an unknown moving environment with physical barriers is a difficult proposition. In particular, having an optimal or near-optimal path that avoids obstacles is a major challenge. In this paper, a modified neuro-controller mechanism is proposed for controlling the movement of an indoor mobile robot. The proposed mechanism is based on the design of a modified Elman neural network (MENN) with an effective element aware gate (MEEG) as the neuro-controller. This controller is updated to overcome the rigid and dynamic barriers in the indoor area. The proposed controller is implemented with a mobile robot known as Khepera IV in a practical manner. The practical results demonstrate that the proposed mechanism is very efficient in terms of providing shortest distance to reach the goal with maximum velocity as compared with the MENN. Specifically, the MEEG is better than MENN in minimizing the error rate by 58.33%.</p>

Automatic identification of atrial fibrillation based on the modified Elman neural network with exponential moving average algorithm

Atrial fibrillation is a most common arrhythmia. An early and accurate detection for the cure and even spread of this disease is considerably critical. The visual examination of electrocardiogram signals is the most extensively used diagnosis approach, but this method is cumbersome and low-efficient. In this work, we propose an intelligent network model based on the modified Elman neural network for signals discrimination. Motivated from the exponential moving average strategy, the proposed model is capable of fully modeling the information feedback and also effectively and efficiently striking a balance between current information representation and historical information representation in original Elman neural network. To evaluate its practicability, the model is also plugged into a convolutional neural network framework and two control subjects are established for a fair comparison. Experiments on the MIT-BIH atrial fibrillation and arrhythmia databases show that the proposed model can enjoy a consistent improvement in classification performance with the accuracy of 98.2% and 97.2% respectively and exhibit lower convergence rate than existing Elman network. Thanks to its high model performance, we are planning to develop the model into a computer-aided diagnosis system to assist physicians.

Vehicle state estimation for INS/GPS aided by sensors fusion and SCKF-based algorithm

To improve the safety and stability of land vehicles, this paper explores the estimation problem for vehicle states, including lateral velocity and attitude. First, a robust sliding mode observer is introduced to improve the adaptability for uncertain inputs, especially for the varying parameters in the vehicle dynamic model and longitudinal velocity. Furthermore, theoretical studies are performed to enhance the capability of the observer. In order to mitigate errors with the integrated navigation system, sensor drift model is primarily established based on a modified Elman neural network, so as to investigate the coupling between driving motion and errors. In addition, an extended square-root cubature Kalman filter is proposed to combine measurements from different sensors, utilizing a fusion strategy, to deal with severe driving motion and state estimation problems. Finally, simulation and field tests are carried out under a variety of maneuvers and conditions. The approach is compared with existing methods and evaluated experimentally, which indicates its effectiveness in improving the accuracy of vehicle state estimation.

Design of an Adaptive Neural Predictive Nonlinear Controller for Nonholonomic Mobile Robot System Based on Posture Identifier in the Presence of Disturbance

This paper proposes an adaptive neural predictive nonlinear controller to guide a nonholonomic wheeled mobile robot during continuous and non-continuous gradients trajectory tracking. The structure of the controller consists of two models that describe the kinematics and dynamics of the mobile robot system and a feedforward neural controller. The models are modified Elman neural network and feedforward multi-layer perceptron respectively. The modified Elman neural network model is trained off-line and on-line stages to guarantee the outputs of the model accurately represent the actual outputs of the mobile robot system. The trained neural model acts as the position and orientation identifier. The feedforward neural controller is trained off-line and adaptive weights are adapted on-line to find the reference torques, which controls the steady-state outputs of the mobile robot system. The feedback neural controller is based on the posture neural identifier and quadratic performance index optimization algorithm to find the optimal torque action in the transient state for N-step-ahead prediction. General back propagation algorithm is used to learn the feedforward neural controller and the posture neural identifier. Simulation results show the effectiveness of the proposed adaptive neural predictive control algorithm; this is demonstrated by the minimised tracking error and the smoothness of the torque control signal obtained with bounded external disturbances.

Existence of Periodic Solutions for an Output Hidden Feedback Elman Neural Network

We first recall the sufficient conditions for the existence of a periodic output of a modified Elman neural network with a periodic input found by using Mawhin’s continuation theorem of coincidence degree theory. Using this result, we obtain sufficient conditions for the existence of a periodic output for an output hidden feedback Elman neural network with a periodic input. Examples illustrating these sufficient conditions are given.

A deep learning approach for atrial fibrillation signals classification based on convolutional and modified Elman neural network

Atrial fibrillation (AF) is one of the main causes of life-threatening heart disease. Its detection and diagnosis have been highly concerned by physicians in recent years. However, the conventional AF detection through visual inspection of electrocardiogram (ECG) data by expert cardiologists is low-efficient and time-consuming. In this work, we develop a novel approach for the automated AF detection based on an 11-layers neural network. The network structure is primarily stacked by convolutional neural network (CNN) and the modified Elman neural network (MENN), while automatically performing end-to-end signals classification. To verify the superiority of the proposed model, two relevant deep network models were specially constructed for comparison. Moreover, ten-fold cross-validation was employed to evaluate the classification performance of the model on the MIT-BIH AF database. Compared with the two relevant models and several state-of-the-art methods, the model yielded excellent classification performance with the accuracy, sensitivity and specificity of 97.4%, 97.9%, and 97.1%, respectively. To the best of our knowledge, this is also the first time to stack CNN and MENN for ECG signals analysis and AF detection in particular. Its outstanding performance demonstrates that the proposed model has great potential as an efficient and robust identification system to assist physicians and reduce mortality.

Design of New Hybrid Neural Controller for Nonlinear CSTR System based on Identification

This paper proposes improving the structure of the neural controller based on the identification model for nonlinear systems. The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems. Two learning algorithms are used to adjust the parameters weight of the hybrid neural structure with its serial-parallel configuration; the first one is supervised learning algorithm based Back Propagation Algorithm (BPA) and the second one is an intelligent algorithm namely Particle Swarm Optimization (PSO) algorithm. The numerical simulation results show that the hybrid NARMA-L2 controller with PSO algorithm is more accurate than BPA in terms of achieving fast learning and adjusting the parameters model with minimum number of iterations, minimum number of neurons in the hybrid network and the smooth output one step ahead prediction controller response for the nonlinear CSTR system without oscillation.

Design of New Hybrid Neural Structure for Modeling and Controlling Nonlinear Systems

This paper proposes a new structure of the hybrid neural controller based on the identification model for nonlinear systems. The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems. Weight parameters of the hybrid neural structure with its serial-parallel configuration are adapted by using the Back propagation learning algorithm. The ability of the proposed hybrid neural structure for nonlinear system has achieved a fast learning with minimum number of epoch, minimum number of neurons in the hybrid network, high accuracy in the output without oscillation response as well as useful model for a one step ahead prediction controller for the nonlinear CSTR system that is used in the MATLAB simulation.

A Cognitive System Design for Mobile Robot Based on an Intelligent Algorithm

This paper presents a cognitive system based on a nonlinear Multi-Input Multi- Output (MIMO) Proportion Integral Derivative (PID) Modified Elman Neural Network (MENN) controller and the Square Road Map (SRM) method to guide the mobile robot during the continuous path-tracking with collision-free navigation through static obstacles. The proposed cognitive system consists of two parts: the first part is to plan the desired path for the mobile robot with the static obstacle environment in order to determine the target point and to avoid the obstacles based on the proposed square road map algorithm. The second part is to guide and track the wheeled mobile robot on the desired path equation based on the proposed nonlinear MIMO-PID-MENN controller with the intelligent algorithm. The Particle Swarm Optimization (PSO) is used to on-line tune the variable control parameters of the proposed controller to get the optimal torques actions for the mobile robot platform. Based on using the MATLAB package (2017), the numerical simulation results show that the proposed cognitive system has high accuracy for planning the desired path equation in terms of avoiding the static obstacles with smooth and short distance and generating a perfect torque action of (0.7 N.m) without a saturation state of (3.07 N.m), which leads to minimize the tracking pose error for the mobile robot to the zero value approximation. These results were confirmed by a comparative study with different nonlinear PID controller types in terms of number of iterations and the performance index.

Modified Elman Neural-PID Controller Design for DC-DC Buck Converter System Based on Dolphin Echolocation Optimization

This paper describes a new proposed structure of the Proportional Integral Derivative (PID) controller based on modified Elman neural network for the DC-DC buck converter system which is used in battery operation of the portable devices. The Dolphin Echolocation Optimization (DEO) algorithm is considered as a perfect on-line tuning technique therefore, it was used for tuning and obtaining the parameters of the modified Elman neural-PID controller to avoid the local minimum problem during learning the proposed controller. Simulation results show that the best weight parameters of the proposed controller, which are taken from the DEO, lead to find the best action and unsaturated state that will stabilize the Buck converter system performance and achieve the desired output. In addition, there is a minimization for the tracking voltage error to zero value of the Buck converter output, especially when changing a load resistance by 10%.

Modified Elman Neural-PID Controller Design for DC-DC Buck Converter System Based on Dolphin Echolocation Optimization

This paper describes a new proposed structure of the Proportional Integral Derivative (PID) controller based on modified Elman neural network for the DC-DC buck converter system which is used in battery operation of the portable devices. The Dolphin Echolocation Optimization (DEO) algorithm is considered as a perfect on-line tuning technique therefore, it was used for tuning and obtaining the parameters of the modified Elman neural-PID controller to avoid the local minimum problem during learning the proposed controller. Simulation results show that the best weight parameters of the proposed controller, which are taken from the DEO, lead to find the best action and unsaturated state that will stabilize the Buck converter system performance and achieve the desired output. In addition, there is a minimization for the tracking voltage error to zero value of the Buck converter output, especially when changing a load resistance by 10%.

Modified Elman Neural-PID Controller Design for DC-DC Buck Converter System Based on Dolphin Echolocation Optimization

This paper describes a new proposed structure of the Proportional Integral Derivative (PID) controller based on modified Elman neural network for the DC-DC buck converter system which is used in battery operation of the portable devices. The Dolphin Echolocation Optimization (DEO) algorithm is considered as a perfect on-line tuning technique therefore, it was used for tuning and obtaining the parameters of the modified Elman neural-PID controller to avoid the local minimum problem during learning the proposed controller. Simulation results show that the best weight parameters of the proposed controller, which are taken from the DEO, lead to find the best action and unsaturated state that will stabilize the Buck converter system performance and achieve the desired output. In addition, there is a minimization for the tracking voltage error to zero value of the Buck converter output, especially when changing a load resistance by 10%.

A modified Elman neural network with a new learning rate scheme

Abstract Elman neural network (ENN) is one of recurrent neural networks (RNNs). Comparing to traditional neural networks, ENN has additional inputs from the hidden layer, which forms a new layer–the context layer. So the standard back-propagation (BP) algorithm used in ENN is called Elman back-propagation algorithm (EBP). ENN can be applied to solve prediction problems of discrete time sequence. However, the EBP algorithm suffers from low convergence speed and poor generalization performance. To solve this problem, a new learning rate scheme is proposed, the convergence of new proposed scheme is proved. Furthermore, the contrast experiment is utilized to demonstrate the effectiveness of the proposed scheme from the aspects of convergence speed and consumption time with some popular schemes such as the original ENN, and PSO–ENN which uses PSO algorithm to search the best structure of ENN. The experience shows that the modified method proposed in this paper works best.

A Nonlinear MIMO-PID Neural Controller Design for Vehicle Lateral Dynamics model based on Modified Elman Neural Network

This paper presents a new design of a nonlinear multi-input multi-output PID neural controller of the active brake steering force and the active front steering angle for a 2-DOF vehicle model based on modified Elman recurrent neural. The goal of this work is to achieve the stability and to improve the vehicle dynamic’s performance through achieving the desired yaw rate and reducing the lateral velocity of the vehicle in a minimum time period for preventing the vehicle from slipping out the road curvature by using two active control actions: the front steering angle and the brake steering force. Bacterial forging optimization algorithm is used to adjust the parameters weights of the proposed controller. Simulation results based Maltab package show the control methodology has effectiveness performance in terms of the excellent dynamic behavior of the vehicle model by minimizing the tracking error and smoothness control signals without saturation state obtained, especially when adding a bounded external disturbances to the vehicle model.

Modeling and Simulation of Gas Emission Based on Recursive Modified Elman Neural Network

For the purpose of achieving more effective prediction of the absolute gas emission quantity, this paper puts forward a new model based on the hidden recurrent feedback Elman. The recursive part of classic Elman cannot be adjusted because it is fixed. To a certain extent, this drawback affects the approximation ability of the Elman, so this paper adds the correction factors in recursive part and uses the error feedback to determine the parameters. The stability of the recursive modified Elman neural network is proved in the sense of Lyapunov stability theory, and the optimal learning rate is given. With the historical data of mine actual monitoring to experiment and analysis, the results show that the recursive modified Elman neural network model can effectively predict the gas emission and improve the accuracy and efficiency of prediction compared with the classic Elman prediction model.