Mechanism for automated neural network based transport system with learning

A multilayer feedforward neural network with a modification to the standard backpropagation training of neural nets is considered. Information on the gradients of target outputs with respect to network inputs is used in this modification. This modified neural network is then applied for approximating design requirements of aerospace composite components, such as an aircraft engine guide vane and a satellite reflector assembly. This neural network functional approximator is then used with an optimization algorithm for determining the optimal parameters for component design requirements. The modified neural network provides for faster convergence of learning process and requires a smaller number of hidden layer nodes for convergence to similar training error levels. HE application of neural networks as universal approximators has been the focus of tremendous amount of activity in the past few years.16 Neural networks have been used for approximating and modeling both memoryless systems and dynamical systems with memory. This paper does not go into the various neural net architectures and training schemes, and the interested reader could refer to standard texts on this subject matter.1'2 This paper considers static neural networks (systems without memory) formed by interconnections without loops, called feedforward networks.2 In addition, this work considers a backpropagation learning scheme with adaptation of learning rate. There have been many additions to, or adaptations of, the basic backpropagation scheme, such as adaptive learning rate, learning with momentum, and the like,1'2 for improving convergence of the learning scheme, and these are not addressed in this paper. This paper explores a modification of the backpropagation learning scheme using information on the gradient of the target outputs with respect to the inputs of the network. The performance of the modified learning scheme is compared with that of the standard backpropagation learning scheme.2 A feedforward network with a single hidden layer trained with this modified learning scheme is applied in structural optimization problems. Figure 1 shows a feedforward net with a single hidden layer. The restriction to a single hidden layer is not a limitation of the modified learning scheme, and the new training scheme can be used on networks with multiple hidden layers also. The use of neural networks for structural response approximation has been reported by several authors.46 The primary reason for investigating such properties is to assess the applicability of trained neural networks for quick and accurate approximation of response functions during structural design optimization. Structural optimization, utilizing either gradient-based numerical search or genetic search algorithms, requires repeated function (response) evaluations during the search process. A single finite element analysis of large-scale structures requires a significant amount of computational time and resource and hence the need for robust approxima

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

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.

Remote sensing has served as an efficient method of gathering data about glaciers since its emergence. The recent advent of Geographic Information Systems (GIS) and Global Positioning Systems (GPS) has created an effective means by which the acquired data are analysed for the effective monitoring and mapping of temporal dynamics of glaciers. A large number of researchers have taken advantage of remote sensing, GIS and GPS in their studies of glaciers. These applications are comprehensively reviewed in this paper. This review shows that glacial features identifiable from aerial photographs and satellite imagery include spatial extent, transient snowline, equilibrium line elevation, accumulation and ablation zones, and differentiation of ice/snow. Digital image processing (e.g., image enhancement, spectral ratioing and automatic classification) improves the ease and accuracy of mapping these parameters. The traditional visible light/infrared remote sensing of two-dimensional glacier distribution has been extended to three-dimensional volume estimation and dynamic monitoring using radar imagery and GPS. Longitudinal variations in glacial extent have been detected from multi-temporal images in GIS. However, the detected variations have neither been explored nor modelled from environmental and topographic variables. GPS has been utilized independent of remote sensing and GIS to determine glacier ice velocity and to obtain information about glacier surfaces. Therefore, the potential afforded by the integration of nonconventional remote sensing (e.g., SAR interferometry) with GIS and GPS still remains to be realized in glaciology. The emergence of new satellite images will make remote sensing of glaciology more predictive, more global and towards longer terms.

The Sixth International Symposium on Neural Networks (ISNN 2009)

Neural networks have been proposed as nonlinear filters in a variety of applications that involve nonlinear processing of input signals; examples include blind signal separation, image registration, and blind deconvolution. The Global Positioning System (GPS) navigation equations are nonlinear (quadratic) in nature, and a direct closed form solution of the GPS navigation equations does not exist. This article presents a new approach to solving the GPS pseudorange equations using three-layer neural networks. A three-layer radial basis function (RBF) neural network is designed, which solves the non-linear GPS pseudorange equations directly as opposed to the linear least squares or extended Kalman filter approaches in traditional GPS receivers. For training the neural network, a carefully selected cost function is minimized using a variation of the classical conjugate gradient algorithm such that training time for the neural network is reasonable. Simulations have been performed at SiRF Technology Inc. that show stable behavior even under bad geometry conditions where the traditional recursive least squares and extended Kalman filter approaches show high sensitivity to measurement errors. Under good geometry conditions the neural network solution shows slightly improved noise performance compared to the expected performance of traditional leas squares solution. Simulations have been performed with additive white Gaussian noise and correlated noise models to evaluate the performance of the trained neural network. © 2000 John Wiley & Sons, Inc.

TAO-robust backpropagation learning algorithm

We propose‘harnessed Chaotic Activation Functions’ (HCAF) to compute final activation of a neural network. That is biologically plausible to connect with neuron. Multilayer feed-forward neural networks are trained with a supervised algorithm which is loosely connected with biological learning. Bio-inspired system development is recently a challenging topic in intelligent system design. We investigate whether HCAF can enable the learning to be faster. Validity of the proposed method is examined by performing simulations on challenging five real benchmark classification problems. The HCAF has been examined to 2-bit, Diabetes, Wine, Glass and Soybean problems. The algorithm is shown to work better than other AFs used independently in BP such as sigmoid(SIG), arctangent (ATAN), logarithmic (LOG), robust chaos in neural network (RCNN), and that of jointly such as fusion of activation function (FAF).

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 is the second part of a two-part discussion, in which we will provide an overview of the use of GIS and GPS in environmental analysis and enforcement. Geographic Information Systems (GIS) describes a system which manages, analyses and displays geographic information. Environmental applications include analysis of source, extent and transport of contaminants, nonpoint runoff modeling, flood control, and emergency response support. The ability to examine spatial relationships between environmental observations and other mapped and historical information, and to communicate these relationships to others, makes GIS valuable in environmental forensics. The US Environmental Protection Agency currently requires the inclusion of locational information with all other environmental data that is collected. Geographic Information Systems is a complex tool that requires careful planning and design to be successfully implemented. Choices in hardware, software and data development must be based on evaluation of project objectives, analytical requirements, data availability and data development considerations. Data sets must be evaluated and documented with metadata. The Global Positioning System (GPS) is a satellite-based system which provides highly accurate, three-dimensional position information anywhere on the earth's surface. Using portable radio receivers, field analysts can easily record the positions of spill sites, sampling locations and other environmental features. Spatial accuracy of GPS ranges from 20-30 m (single receiver) to 1-5 m (differential GPS) for navigation-grade instruments, and down to millimeter level accuracy for geodetic units. Global Position Systems can be used not only to capture spatial information into a GIS system, but also to evaluate and quantify the spatial accuracy of existing digital map data, and to provide control points for existing aerial photographs and other remotely-sensed data.

In present days, real time navigation depends on Kalman filter to fuse data from Global Positioning System (GPS) and Inertial Navigation System (INS). But there exist drawbacks like long design time, requirement of prior knowledge in fusing data from GPS and INS using Kalman Filter. In order to overcome the drawbacks of Kalman filter, GPS and INS integration are done using Artificial Neural Networks (ANN) like FFNNs. But still there exists certain drawbacks like less accuracy in FFNNs for GPS and INS data integration. Therefore, this paper introduces Higher Order Neural Networks (HONNs) approach for INS and GPS data integration to overcome the drawback. A higher order feed forward neural network architecture with optimum number of nodes is used. In the given architectures, the replacement of summation at each node by multiplication results in more powerful mapping, because of its capability of processing higher-order information from training data. Performance comparison of HONNs with FFNNs shows that the proposed architecture provides satisfactory results in terms of error rate and number of epochs. The HONNs like Multiplicative Neural Network (MNN) module and Sigma-Pi-ANN module and Traditional Feed Forward Neural Networks(FFNNs) like Radial Basis Function Neural Network (RBF) module and Back propagation Neural Network (BPN) module are trained to predict the INS position error and provide accurate position of the moving aircrafts. Sigma-Pi ANN is found to be the best in terms of accuracy, number of epochs and execution time among the two HONNs.

This paper presents an application of multilayer feedforward neural network (MFNN) as a differential protection for synchronous generators. Two MFNN are designed, trained, and tested in this paper. The first one has two outputs which detect the internal and external fault state. The other neural network has four outputs to classify the faulty phases. The proposed neural fault detector and classifier were trained using various sets of data available from a selected synchronous model and simulating different fault scenarios (fault type, fault location, fault resistance and fault inception angle). The results show very good behavior of the MFNN and it was more reliable and accurate than conventional methods. It shows that MFNN offer the possibility to be used for on line synchronous generator protection and give satisfactory results.

In order to improve the information management of the modern digital agriculture, combined several modern digital agriculture technologies, namely wireless sensor network (WSN), global positioning system (GPS), geographic information system (GIS) and general packet radio service (GPRS), and applied them to the information collection and intelligent control process of the modern digital agriculture. Combining the advantage of the local multi-channel information collection and the low-power wireless transmission of WSN, the stable and low cost long-distance communication and data transmission ability of GPRS, the high-precision positioning technology of the DGPS positioning and the large-scale field information layer-management technology of GIS, such a hybrid technology combination is applied to the large-scale field information and intelligent management. In this study, wireless sensor network routing nodes are disposed in the sub-area of field. These nodes have GPS receiver modules and the electric control mechanism, and are relative positioned by GPS. They can real-time monitor the field information and control the equipment for the field application. When the GPS position information and other collected field information are measured, the information can be remotely transmitted to PC by GPRS. Then PC can upload the information to the GIS management software. All the field information can be classified into different layers in GIS and shown on the GIS map based on their GPS position. Moreover, we have developed remote control software based on GIS. It can send the control commands through GPRS to the nodes which have control modules; and then we can real-time manage and control the field application. In conclusion, the unattended automatic wireless intelligent technology for the field information collection and control can effectively utilize hardware resources, improve the field information intelligent management and reduce the information and intelligent cost.

Collection of Municipal Solid Waste (MSW) is important in every waste management program. Communal container collection systems appear most prevalent in many developing countries. However, this collection system is associated with problems such as overflow of waste containers, ground dumping at collection sites, and open/indiscriminate dumping at unauthorized places. The spatial distribution of these activities present potential contamination challenges to water resources. Spatial information on Municipal Solid Waste Collection/Dump Sites (MSWCS) is essential for Municipal Solid Waste Management (MSWM) decision-making, including siting and collection route planning, and dumps cleanup. Integration of Geographic Information Systems (GIS) and Global Positioning Systems (GPS) present a platform to capture, map, and analyze spatial MSWM issues. This study applied GIS and GPS technologies to map MSWCS in Wa town, Ghana. Wa Municipality waste collection system efficiency was analyzed based on spatial availability of communal containers. A GIS model was developed and used to analyze proximity of MSWCS to boreholes drinking water sources. A pollution risk map was also developed to analyze the potential impact of indiscriminate dumps on hand-dug wells and surface water in Wa. The results reveal poor management in a significant number (about 67%) of MSWCS sites. Fifteen percent of mechanized boreholes failed the minimum proximity requirement (≥100 m) of the model. This study findings illustrate that MSWM in developing countries may be improved using GIS and GPS technologies. The approach used for Wa could be replicated in other towns in Ghana and other developing nations with similar MSWM problems to enhance policy and management decision-making.