Feedback Neural Network Research Articles

Using Neural Networks to Obtain Indirect Information about the State Variables in an Alcoholic Fermentation Process

This work provides a manual design space exploration regarding the structure, type, and inputs of a multilayer neural network (NN) to obtain indirect information about the state variables in the alcoholic fermentation process. The main benefit of our application is to help experts reduce the time needed for making the relevant measurements and to increase the lifecycles of sensors in bioreactors. The novelty of this research is the flexibility of the developed application, the use of a great number of variables, and the comparative presentation of the results obtained with different NNs (feedback vs. feed-forward) and different learning algorithms (Back-Propagation vs. Levenberg–Marquardt). The simulation results show that the feedback neural network outperformed the feed-forward neural network. The NN configuration is relatively flexible (with hidden layers and a number of nodes on each of them), but the number of input and output nodes depends on the fermentation process parameters. After laborious simulations, we determined that using pH and CO2 as inputs reduces the prediction errors of the NN. Thus, besides the most commonly used process parameters like fermentation temperature, time, the initial concentration of the substrate, the substrate concentration, and the biomass concentration, by adding pH and CO2, we obtained the optimum number of input nodes for the network. The optimal configuration in our case was obtained after 1500 iterations using a NN with one hidden layer and 12 neurons on it, seven neurons on the input layer, and one neuron as the output. If properly trained and validated, this model can be used in future research to accurately predict steady-state and dynamic alcoholic fermentation process behaviour and thereby improve process control performance.

M&A Short-Term Performance Based on Elman Neural Network Model: Evidence from 2006 to 2019 in China

Based on the event study method, this paper conducts the analysis on the short-term performance of 1302 major mergers and acquisitions (M&A) in China from 2006 to 2019 and takes the cumulative abnormal return (CAR) as the measurement index. After comparing the five abnormal return (AR) calculation models, it is found that the commonly used market model method and the market adjustment method have statistical defects while the Elman feedback neural network model is capable of good nonlinear prediction ability. The study shows that M&A can create considerable short-term performance for Chinese listed company shareholders. The CAR in window period reached 14.45% with a downward trend, which is the win-win result achieved through the cooperation between multiple parties and individuals driven by their respective rights and interests in the current macro-microeconomic environment in China.

Application of LSTM approach for modelling stress–strain behaviour of soil

This paper presents a new trial to reproduce soil stress–strain behaviour by adapting a long short-term memory (LSTM) deep learning method. LSTM is an approach that employs time sequence data to predict future occurrences, and it can be used to consider the stress history of soil behaviour. The proposed LSTM method includes the following three steps: data preparation, architecture determination, and optimisation. The capacity of the adapted LSTM method is compared with that of feedforward and feedback neural networks using a new numerical benchmark dataset. The performance of the proposed LSTM method is verified through a dataset collected from laboratory tests. The results indicate that the LSTM deep-learning method outperforms the feed forward and feedback neural networks based on both accuracy and the convergence rate when reproducing the soil’s stress–strain behaviour. One new phenomenon referred to as “bias at low stress levels”, which was not noticed before, is first discovered and discussed for all neural network-based methods.

Collective Neurodynamic Optimization for Image Segmentation by Binary Model with Constraints

Threshold method is an important image segmentation method, which has been widely used in image segmentation. For this method, it is very important to choose a good threshold. The traditional threshold segmentation algorithm is implemented by exhaustive method, which makes the solution efficiency very low. This paper presents a collective neurodynamic optimization algorithm to solve the problem of binary optimization in the image segmentation. The problem of image segmentation based on threshold is transformed into binary optimization with constraints. Then, a collective neurodynamic optimization algorithm is introduced which combined with feedback neural network and particle swarm optimization (PSO) algorithm. And the linear programming relaxation constraint method is used to relax binary constraints. It is proved by numerical simulation that the feedback neural network algorithm can converge to the exact local optimal solution of the model and the PSO algorithm can get a better local optimal solution. Finally, several sets of comparative experiments are presented. The feasibility of our proposed method is verified; the experimental results demonstrate the effectiveness of our approach in image segmentation. In this study, a collective neurodynamic optimization was proposed for the image segmentation problem. In the future, we expect that multiple centralized neurodynamic models and intelligent algorithms can be used to solve the problem and improve the convergence speed of the solved model.

Blind Equalization for Chaotic Signals Based on Echo State Network and Kalman Filter Under Nonlinear Channels

For nonlinear channels, we propose a new blind equalization method for chaotic signals based on echo state network(ESN) and Kalman filter(KF) in this letter. Using the short-term predictability of chaotic signals, ESN, a new feedback neural network, is used to approximate unknown chaotic maps and predict the output of the equalizer. Furthermore, KF combined with the finite impulse response(FIR) is used as the equalizer in this letter, and its parameters are adjusted by minimizing the prediction error of ESN. Simulation results show that compared with other blind equalization methods for chaotic signals, the proposed method has the advantages of smaller mean square error and faster convergence rate, and is suitable for strong nonlinear channels.

Deep Neural Network Algorithm Feedback Model with Behavioral Intelligence and Forecast Accuracy

When attempting to apply a large-scale database that holds the behavioral intelligence training data of deep neural networks, the classification accuracy of the artificial intelligence algorithm needs to reflect the behavioral characteristics of the individual. When a change in behavior is recognized, that is, a feedback model based on a data connection model is applied, an analysis of time series data is performed by extracting feature vectors and interpolating data in a deep neural network to overcome the limitations of the existing statistical analysis. Using the results of the first feedback model as inputs to the deep neural network and, furthermore, as the input values of the second feedback model, and interpolating the behavioral intelligence data, that is, context awareness and lifelog data, including physical activities, involves applying the most appropriate conditions. The results of this study show that this method effectively improves the accuracy of the artificial intelligence results. In this paper, through an experiment, after extracting the feature vector of a deep neural network and restoring the missing value, the classification accuracy was verified to improve by about 20% on average. At the same time, by adding behavioral intelligence data to the time series data, a new data connection model, the Deep Neural Network Feedback Model, was proposed, and it was verified that the classification accuracy can be improved by about 8 to 9% on average. Based on the hypothesis, the F (X′) = X model was applied to thoroughly classify the training data set and test data set to present a symmetrical balance between the data connection model and the context-aware data. In addition, behavioral activity data were extrapolated in terms of context-aware and forecasting perspectives to prove the results of the experiment.

Thermal comfort control via air conditioning system using fuzzy neural network feedback controller

<span>Despite their complexity and uncertainty, air conditioning systems should provide the optimal thermal conditions in a building. These controller systems should be adaptable to changes in environmental parameters. In most air conditioning systems, today, there are On/Off controllers or PID in more advanced types, which, due to different environmental conditions, are not optimal and cannot provide the optimal environmental conditions. Controlling thermal comfort of an air conditioning system requires estimation of thermal comfort index. In this study, fuzzy controller was used to provide thermal comfort in an air conditioning system, and neural network was used to estimate thermal comfort in the feedback path of the controller. Fuzzy controller has a good response given the non-linear features of air conditioning systems. In addition, the neural network makes it possible to use thermal comfort feedback in a real-time control.</span>

Robust optimal feedback control design for uncertain systems based on artificial neural network approximation of the Bellman’s value function

In this study, a local approximated solution for the Hamilton–Jacobi–Bellman equation based on differential neural networks is proposed. The approximated Value function is used to obtain a feedback control law for a class of uncertain dynamical systems. The approach to deal with the uncertainties of the dynamical system is a min–max method that yields obtaining a robust-like solution for an optimal control problem. The proposed cost functional is presented in the Bolza form and the necessary and sufficient conditions for getting the min–max optimal solution with the designed robust version of the dynamic programming approach are provided. Moreover, the effect of the neural network approximation is studied. All the analysis considers a smoothness assumption regarding the Value function. The practical stability of the system with the neural network feedback optimal control is formally demonstrated by means of the Lyapunov method. Finally, the performance of the control law is compared in simulation with a classical optimal controller. The proposed controller overcomes the results produced by the classical controller, which is confirmed by the functional evaluation.

Identification of epilepsy from intracranial EEG signals by using different neural network models

In this work, a framework is provided for identifying intracranial electroencephalography (iEEG) seizures based on discrete wavelet transform (DWT) analysis of iEEG signals using forward propagation and feedback neural networks. The performance of 5 different data sets combination classifications is studied using the probabilistic neural network (PNN), learning vector quantization neural network (LVQ) and Elman neural network (ENN). Different feature combinations serve as the input vectors of the classifiers to obtain the best outcomes. It has been found that PNN has less running time and provides better classification accuracy (CA) than ENN and LVQ classifiers for all 5 classification problems. It is worth noticing that the CA for the C-D classification task, which shows the status of pre-ictal versus post-ictal, has been greatly improved, and reached 83.13%. Hence, the epilepsy iEEG signals pattern recognition based on DWT statistical features using the PNN classifier is more suitable for forming a reliable, automatic classification system in order to assist doctors in diagnosis.

A neurodynamic algorithm to optimize residential demand response problem of plug-in electric vehicle

This paper proposes a nonconvex mixed-integer programming(MIP) electricity model of household load that is classified into base load and plug-in electric vehicle (PEV). The main objective of this model is to minimize the electricity cost of domestic user by adjusting the charging and discharging strategy of PEV according to the information of real-time price(RTP). In order to settle this problem, a neurodynamic algorithm which combines feedback neural network and inertial neural subnetwork is used. In this algorithm, the feedback neural networks are given as subnetworks to find a local optimal point and the inertial neural subnetwork can obtain different local optimal points by adjusting the inertial factor in global scope. The validity and the feasible of the proposed algorithm can be proven by performance evaluation of simulation results.

A Systemic Study of Pattern Recognition System Using Feedback Neural Networks

The evolution of artificial intelligence has led to the developments of various smart applications such as the pattern recognition models. Pattern recognition techniques has as widely applied in many real life applications such character recognition, speech recognition, and bio-metric authentication as well person identification. In this paper, we report on the detailed design of pattern recognition system using Hopfield Feedback Neural Network (HFNN) with the least possible recognition error. As a case study, we have applied the proposed HFNN model to recognize the decimal digits 0 - 9 where each image digit comprises a 12x10 pixels. The developed HFNN model has been efficiently used in recognizing the patterns with 20% random bit noise at maximum recognition accuracy. However, to assure the the least possible recognition error, we have trained our HFNN through the digit patterns’ perdition phase of 0% noisy patterns and the system was able to correctly predict all the patterns without any bit error. Finally, we have plotted all output patterns including the desired patterns, the training patterns, the 20% noisy patterns and recognized patterns, for comparison purposes and to gain more insights about the accuracy achieved by applying the proposed HFNN.

Model Predictive Control via Output Feedback Neural Network for Improved Multi-Window Greenhouse Ventilation Control.

Maintaining environmental conditions for proper plant growth in greenhouses requires managing a variety of factors; ventilation is particularly important because inside temperatures can rise rapidly in warm climates. The structure of the window installed in a greenhouse is very diverse, and it is difficult to identify the characteristics that affect the temperature inside the greenhouse when multiple windows are driven, respectively. In this study, a new ventilation control logic using an output feedback neural-network (OFNN) prediction and optimization method was developed, and this approach was tested in multi-window greenhouses used for strawberry production. The developed prediction model used 15 inputs and achieved a highly accurate performance (R2 of 0.94). In addition, the method using an algorithm based on an OFNN was proposed for optimizing considered six window-opening behavior. Three case studies confirmed the optimization performance of OFNN in the nonlinear model and verified the performance through simulations. Finally, a control system based on this logic was used in a field experiment for six days by comparing two greenhouses driven by conventional control logic and the developed control logic; a comparison of the results showed RMSEs of 3.01 °C and 2.45 °C, respectively. It confirmed the improved control performance in comparison to a conventional ventilation control system.

Human Environment based on Symmetric Connection Network and Feedback Neural Network

Human Environment based on Symmetric Connection Network and Feedback Neural Network

An Approach to Ship Behavior Prediction Based on AIS and RNN Optimization Model

AIS (Automatic Identification System) is a mandatory navigational equipment on board according to SOLAS (Safety of Life at Sea) convention. It is an automatic tracking system that uses VHF (Very High Frequency) transponders on ships and is used by VTS (Vessel Traffic Services) for monitor vessel movements. Existing AIS data has some principle defects due to radio propagation. This paper provides an approach to predict ship behavior with AIS data. In order to solve the problem that traditional ship behavior prediction needs to establish complex ship motion model, a new ship behavior prediction method based on LSTM (Long Short-Term Memory, LSTM) neural network model of machine learning is proposed. LSTM is the optimization model of RNN (Recurrent Neural Networks). Unlike standard feedback neural networks, LSTM has feedback connections. It can not only process single data points, but also entire sequences of data. These prominent features just match the characteristics of AIS data. The LSTM neural network prediction model is established and the shore is used. Based on the real data of AIS (Automatic Identification System) which ships engaged in the waters of South China Sea, the time series of ship behavior characteristics are extracted to train the model and validate the data. The training data is grouped by MMSI (Maritime Mobile Service Identity) and ensure the equal interval requirements of the ship's navigation behavior sequence data. This paper presents 4 figures with the parameter course, speed, position and the loss curve of LSTM training and testing. The results show that the model has a high accuracy and avoids the complicated process of ship motion modeling. The predicted results can improve the supervision of VTS (Vessel Traffic Services) and play a high practical application value in early warning of ship collision, SAR (Search and Rescue) operation and safety-related issues.

Double-Hidden-Layer Recurrent Neural Network Fractional-Order Sliding Mode Control of Shunt Active Power Filter

In this paper, a fractional-order sliding mode control scheme based on a double-hidden-layer recurrent neural network is proposed for a single-phase shunt active power filter. Considering the shortcomings of traditional neural networks that the approximation accuracy is not high and weight and center vector of neural networks are unchangeable, a new double-hidden-layer recurrent neural network structure which contains two hidden layers to make the network have more powerful fitting ability, is designed to approximate the unknown nonlinearities. An original output feedback neural network with two hidden layers is designed to estimate the uncertainties regardless of unknown system characteristics and external disturbances. A fractional-order term is added to the sliding mode controller to have more adjustable space and better optimization space. Experimental results verified the validity of the designed controller and proved that it can complete the current compensation well with acceptable current tracking error, demonstrating the outstanding compensation performance and strong robustness

Data Mining Based on Chinese Traditional Calendar in the Han Dynasty Yang Mausoleum Museum

The Outer Burial Pits of the Han Dynasty Yang Mausoleum is the first fully enclosed site museum in China. The Internet of things sensor installed in the pavilion has accumulated more than 7,000,000 heterogeneous data. Traditional algorithms, such as temperature prediction model, only use statistical value to predict the trend of temperature change, so the data utilization rate is insufficient. In addition, the accuracy of prediction model is also relatively low. The extreme learning machine is a single layer feedback neural network learning method. Using extreme learning machine to analyze and model data is an effective prediction algorithm for preventive protection. However, due to the mismatch between solar calendar characteristics and temperature changes, the accuracy of the prediction model is unsatisfactory. To solve the above problem, a temperature prediction model based on lunar calendar characteristics is proposed in this paper. A large number of measured data show that the model can more accurately predict the future temperature variation trend and detailed characteristics. Its performance is better than that of the model based on solar calendar characteristics. In this paper, a new prediction model is proposed. The advantages of lunar calendar in natural data recording and processing are preliminarily verified, which provides reference for the label selection of follow-up monitoring data.

Timescale Ensemble Performance Enhancement through use of Artificial Neural Network

AbstractA timescale is the estimate of phase and frequency of the “perfect” clock derived from the phase and frequency of the clocks which participate in the ensemble. An ensemble of clocks is the first step towards the realization of a timescale. In the past, several methodologies have been developed to solve the timescale problem such as KAS‐2, Multi‐scale Ensemble Timescale (METS), ALGOS (BIPM), AT1 (NIST) and algorithm for UTC (CRL). An adaptive ensemble algorithm based on Artificial Neural Network (ANN) has been developed which shows improvements in terms of betterment of frequency stability of the ensemble. The Neural Network in the ensemble algorithm learns differently for different sample spaces of the input phase data that is provided. The weights of the participating clocks are derived from their respective Allan deviations. The weights formulated for the ensemble undergo a regressive iteration to obtain the training data set for parameterization of weights. A single‐layer perceptron feedback Neural Network that is proposed in this paper, dynamically adapts the weights assigned to the participating clocks based on the paper clock performance.This paper dwells on the comparison of performances between the ANN‐based algorithms with that of two other algorithms, namely Reduced Kalman filter based algorithm and METS. Results of ANN‐based algorithm for different clock combinations are also presented. The behavior of this algorithm in the event of measurement data outage has also been presented in the paper.

Worst-case Satisfaction of STL Specifications Using Feedforward Neural Network Controllers

In this paper, a reinforcement learning approach for designing feedback neural network controllers for nonlinear systems is proposed. Given a Signal Temporal Logic (STL) specification which needs to be satisfied by the system over a set of initial conditions, the neural network parameters are tuned in order to maximize the satisfaction of the STL formula. The framework is based on a max-min formulation of the robustness of the STL formula. The maximization is solved through a Lagrange multipliers method, while the minimization corresponds to a falsification problem. We present our results on a vehicle and a quadrotor model and demonstrate that our approach reduces the training time more than 50 percent compared to the baseline approach.

Adverse Drug Event Detection Using a Weakly Supervised Convolutional Neural Network and Recurrent Neural Network Model

Social media and health-related forums, including the expression of customer reviews, have recently provided data sources for adverse drug reaction (ADR) identification research. However, in the existing methods, the neglect of noise data and the need for manually labeled data reduce the accuracy of the prediction results and greatly increase manual labor. We propose a novel architecture named the weakly supervised mechanism (WSM) convolutional neural network (CNN) long-short-term memory (WSM-CNN-LSTM), which combines the strength of CNN and bi-directional long short-term memory (Bi-LSTM). The WSM applies the weakly labeled data to pre-train the parameters of the model and then uses the labeled data to fine-tune the initialized network parameters. The CNN employs a convolutional layer to study the characteristics of the drug reviews and active features at different scales, and then the feed-forward and feed-back neural networks of the Bi-LSTM utilize these salient features to output the regression results. The experimental results effectively demonstrate that our model marginally outperforms the comparison models in ADR identification and that a small quantity of labeled samples results in an optimal performance, which decreases the influence of noise and reduces the manual data-labeling requirements.

Double Hidden Layer Output Feedback Neural Adaptive Global Sliding Mode Control of Active Power Filter

In this paper, a self-regulated double hidden layer output feedback neural network (DHLFNN) is presented to control an active power filter (APF) system as a current controller, which is conducive to the improvement of the response characteristic and power quality. First, a global sliding mode controller is introduced because it is effective in achieving overall robustness during the system response. A new output feedback neural structure that has two hidden layers is proposed to make the parameters adaptively adjust themselves and stabilize to their best values. A higher accuracy and stronger generalization ability can be also obtained by reducing the number of network weights and accelerating the network training speed owing to the strong fitting and presentation ability of two-layer activation functions. Furthermore, the designed feedback loops of the neural network play a significant role in possessing associative memory and rapid system convergence. This proposed double hidden layer output feedback neural based global sliding mode controller is simulated on the model of APF and the results show the excellent static and dynamic properties. Experimental results under three cases and comparisons are provided using a fully digital control system to validate the superior performance of the proposed DHLFNN controller.