Neural networks with modified backpropagation learning - Applied to structural optimization

An increasing number of applications of dynamic neural networks has been developed for digital signal processing (DSP), dynamic neural networks are feedforward neural networks with commonly used scalar synapses replaced by linear filters. This provides feedforward neural networks with the capability of performing dynamic mappings, which depend on past input values, dynamic neural networks are suitable for time series prediction, nonlinear system identification, and signal processing applications. Their most popular types are Finite Impulse Response (FIR) neural networks, which are obtained by replacing synapses with finite impulse response filters. Due to their guaranteed stability characteristic and easy to minimize error surface they have been used with great success in many applications such as signal enhancement, noise cancellation, classification of input patterns, system identification, prediction, and control.. Most of the works on system identification using neural networks are based on multilayer feedforward neural networks with backpropagation learning or more efficient variations of this algorithm, an elegant method for training layered networks. This paper is based on work in a Dynamic System Modeling (DYSMO) and as an application for speed control of DC motor drive.

A multi-layer feed forward neural network model for accurate prediction of flue gas sulfuric acid dew points in process industries

Space-Division Multiple Access-OFDM based wireless communication has the potential to significantly increase the spectral efficiency, system performance and number of users. Research in the development of efficient multiuser signal detection algorithms for such systems has generated much interest in recent years. This research proposes MUD schemes utilizing three neural network (NN) models like Feed Forward NN (FNN) without any hidden layer, FNN with a single hidden layer and Recurrent Neural Network (RNN) as possible alternatives to existing Genetic Algorithm (GA) based Minimum Bit Error Rate (MBER) MUD. Further, these techniques offer low complexity. Extensive simulation based performance study is carried out to prove the efficiency of the proposed techniques. Better performance of FNN with hidden layer and RNN compared to FNN without hidden layer is clearly observed in rank deficient MIMO scenario, where number of users exceeds the number of receiving antennas. The Bit Error Rate (BER) and complexity analysis of the proposed neural MUD schemes are close to optimal ML and show improvement over the previous implemented technique.

Single-hidden-layer feed-forward quantum neural network based on Grover learning

TAO-robust backpropagation learning algorithm

Flash floods can demolish infrastructure and property within seconds as they are very sudden. Flash floods are the main cause of the casualties and loss of properties. Existing natural disaster prediction algorithms contains false alarms. Indefinite techniques have been applied to overcome this leading issue in many countries. A competent flood management system must have the potential and tendency to identify the flash floods and atmospheric and climatic changes on early basis with less false alarm rate. Techniques which have been designed for the flash flood investigation may be categorized into following types a. Sensors based direct measurement b. Radar images c. Satellite based X-band images. The proposed research consisted of Artificial intelligence-based decision making for multi-modal sensing (direct measurement from multi-resolution sensors). A combination of sensors like Passive infrared (PIR), water level sensor, ultrasonic sensor, temperature sensor, pressure and altimeter sensors have been integrated on a single device to investigate the flash floods. The use of most suitable pair of measurement sensors can substantially enhance the advantage of more accuracy and reliability compared to a single sensor. In recent trends Particle swarm optimization is very popular for solving stochastic global optimization problems. The data was trained and processed by modified multi-layer feed forward neural network optimized by particle swarm optimization algorithm. Hybrid Modified Particle swarm optimization has been combined with feed forward neural network for the vigorous investigation of flash floods with less false alarm rate. Simulated results showed that the proposed research algorithm Modified multi-layer feed forward neural network optimized by Particle swarm optimization for multi-modal sensing performed very well in terms of evaluation parameters compared to other existing strategies with minimum false alarm ratio. Moreover, modified multi-layer feed forward neural network optimized by article swarm optimization algorithm results have been compared with the cuckoo search, modified cuckoo search, particle swarm optimization and Multi-layer perceptron neural network configurations for the validation purpose.

This study aims to establish the fundamental concepts of multiple linear regression models involving qualitative predictor variables and to validate their associations using a Multilayer Feed Forward (MLFF) neural network. A simple guide is introduced to separate qualitative variables based on the number of classes, ensuring they meet the assumptions of multiple linear regression. The approach provides a basic and practical template for integrating qualitative predictors into applied linear models. Validation is carried out using the sum of square error and relative error obtained from the MLFF neural network. The low error values produced by the MLFF model highlight the effectiveness and superiority of the proposed methodology.

This article proposes the use of a feedforward neural network (FNN) to select the starting point for the first iteration in well-known iterative location estimation algorithms, with the research objective of finding the minimum size of a neural network that allows iterative position estimation algorithms to converge in an example positioning network. The selected algorithms for iterative position estimation, the structure of the neural network and how the FNN is used in 2D and 3D position estimation process are presented. The most important results of the work are the parameters of various FNN network structures that resulted in a 100% probability of convergence of iterative position estimation algorithms in the exemplary TDoA positioning network, as well as the average and maximum number of iterations, which can give a general idea about the effectiveness of using neural networks to support the position estimation process. In all simulated scenarios, simple networks with a single hidden layer containing a dozen non-linear neurons turned out to be sufficient to solve the convergence problem.

To develop and evaluate a model for obstructive sleep apnea (OSA) detection using an artificial neural network (ANN) based on the combined features of body mass index (BMI), electrocardiogram (ECG), and pulse oxygen saturation (SpO2). Polysomnography (PSG) data for 148 patients withOSA and 33 unaffected individuals were included. A multi-layer feed-forward neural network (FNN) was used based on the features obtained from ECG, SpO2, and BMI. The receiver operating characteristic (ROC) curve and the metrics of accuracy, sensitivity, and specificity were used to evaluate the performance of the overall classification. Some other machine learning methods including linear discriminant, linear Support Vector Machine (SVM), Complex Tree, RUSBoosted Trees, and Logistic Regression were also used to compare their performance with the FNN. The accuracy, sensitivity, and specificity of the proposed multi-layer FNN were 97.8%, 98.6%, and 93.9%, respectively, and the area under the ROC curve was 97.0%. Compared with the other machine learning methods mentioned above, the FNN achieved the highest performance. The satisfactory performance of the proposed FNN model for OSA detection indicated that it is reliable to screen potential patients withOSA using the combined channels of ECG and SpO2 and also taking into account BMI. This strategy might be a viable alternative method for OSA diagnosis.

Training set parallelism and network based parallelism are two popular paradigms for parallelizing a feedforward (artificial) neural network. Training set parallelism is particularly suited to feedforward neural networks with backpropagation learning where the size of the training set is large in relation to the size of the network. This paper analyzes training set parallelism for feedforward neural networks when implemented on a transputer array configured in a pipelined ring topology. Theoretical expressions for the time per epoch (iteration) and optimal size of a processor network are derived when the training set is equally distributed among the processing nodes. These show that the speed up is a function of the number of patterns per processor, communication overhead per epoch and the total number of processors in the topology. Further analysis of how to optimally distribute the training set on a given processor network when the number of patterns in the training set is not an integer multiple of the number of processors, is also carried out. It is shown that optimal allocation of patterns in such cases is a mixed integer programming problem. Using this analysis it is found that equal distribution of training patterns among the processors is not the optimal way to allocate the patterns even when the training set is an integer multiple of the number of processors. Extension of the analysis to processor networks comprising processors of different speeds is also carried out. Experimental results from a T805 transputer array are presented to verify all the theoretical results.

Pulsed Nd:YAG laser has high intensity and high quality beam characteristics, which can be used to produce micro-grooves and micro-turning surface on advanced engineering ceramics. The present research attempts to develop mathematical models by using response surface methodology approach for correlating the machining process parameters and the process responses during laser micro-turning of aluminum oxide (Al2O3) ceramics. The process parameters such as laser average power, pulse frequency, workpiece rotating speed, assist air pressure and Y feed rate were varied during experimentation. The rotatable central composite design experimental planning has been used to design the experimentation. The performance measures considered are surface roughness (Ra) and micro-turning depth deviation. Multi-objective optimization has been carried out for achieving the desired surface roughness as well as minimum depth deviation during laser micro-turning operation. Further, an artificial neural network (ANN) model has been developed to predict the process criteria. Levenberg-Marquadt training algorithm is used for multilayer feed forward backpropagation neural network. The developed ANN model has 5-10-2 feed forward network. There are 5 neurons in the input layer, 10 neurons in the hidden layer and 2 neurons in the output layers corresponding to two output responses, respectively. The developed ANN model has been validated using data obtained by conducting additional set of experiments. It was found that the developed ANN model can predict the process criteria more accurately than response surface methodology (RSM) based developed models.

We have developed a computerized scheme that can aid in the radiologists diagnosis in the detection and classification of coronary artery diseases in 201T1 myocardial SPECT (single photon emission computed tomography) bull’s-eye images by use of artificial neural networks. The multi-layer feed-forward neural networks used with a back-propagation algorithm have 41–256 input units (pattern: compressed images), 50 or 100 units in a single hidden layer, and eight output units (diagnosis: one normal and seven different types of abnormalities). The neural networks consisting of two major networks for “EXTENT” and “SEVERITY” images were trained using pairs of training input data (bull’s-eye image) and desired output data (“correct” diagnosis). The results show that the recognition performance of our neural-network-based system is comparable to that of two year experienced radiologists. Our study suggests that the neural network approach is useful for the computer-aided diagnosis of coronary artery diseases in myocardial SPECT bull’s-eye images.

We have developed a bi-directional neural network as a massively parallel computing architecture for the design of semiconductor devices and circuits. We call this operation reverse modeling since the neural network trained to model a circuit is used in a reverse direction. A feedforward neural network can be used to model the behavior of a system. It can quickly predict the system response of given input parameters. We have extended the applications of neural networks beyond their traditional roles of black box models. Our approach begins with a neural network trained to model the response of the circuit to design parameters. The reverse modeling is then carried out by applying a modified backpropagation learning rule to the trained network. This changes the multi-layer, feedforward neural network from a uni-directional model into a bi-directional model. In the forward direction, the neural network model predicts the circuit property from given design parameters. In the reverse direction, design parameters are synthesized from desired circuit properties. We have demonstrated this reverse modeling approach by designing an RF amplifier. A neural network was trained to model the relations between the matching circuit elements of the amplifier and its output characteristics (output power and power gain). The result model has an average error of 1.7%. The trained model was then used to synthesize matching circuits for 10 sets of desired output characteristics. The neural network synthesized circuits were simulated using LIBRA to verify their performance. The simulated circuit performance was, in average, within 2.6% of the desired characteristics.

Application of artificial neural networks (ANNs) to forecast the hourly loads of an electrical power system is examined in this chapter. Two types of ANN’s, i.e., the Kohonen’s self-organising feature maps and the feedforward multilayer neural networks, are employed for load forecasting. Kohonen’s self-organising feature map, which is a kind of ANN with unsupervised learning scheme, is first used to identify those days with similar hourly load patterns. These days with similar load patterns are said to be of the same day type. The load pattern of the day under study is obtained by averaging the load patterns of several days in the past which are of the same day type as the given day. After the hourly load pattern has been reached, a multilayer feedforward neural network is designed to predict daily peak load and valley load. Once the peak load and valley load and the hourly load pattern are available, the desired hourly loads can be readily computed. The effectiveness of the proposed neural network is demonstrated by the short-term load forecasting of Taiwan power system.

Summary form only given. An analytic method for constructing polynomial functions by multi layer feedforward neural networks has been developed. Because the polynomials consist of multiplication operations and linear weighted summations, if the multiplier can be constructed by a neural network, any polynomial function can be represented by a neural network (a single unit already has the function of weighted summation). An attempt has been made to construct a neural network module with one hidden layer that works as a multiplier. It was shown that the multiplier can be approximated by a neural network with four hidden units, with arbitrary accuracy on a bounded closed set. >