Using eigencolor normalization for illumination-invariant color object recognition

Color is one of salient features for color object recognition, however, the colors of object images sensitively depend on scene illumination. To overcome the lighting dependency problem, a color constancy or color normalization method has to be used. This paper presents a color image normalization method, called eigencolor normalization, which consists of two phases as follows. First, the compacting method, which was originally used for compensating the adverse effect due to shape distortion for 2-D planar objects, is exploited for 3-D color space to make the color distribution less correlated and more compact. Second, the compact color image is further normalized by rotating the histogram to align with the reference axis computed. Consequently, the object colors are transformed into a new color space, called eigencolor space, which reflects the inherent colors of the object and is more invariant to illumination changes. Experimental results show that our eigencolor normalization method is superior to other existing color constancy or color normalization schemes on achieving more accurate color object recognition.     

A neural network approach to decision alternative prioritization

A common decision problem faced by managers in organizations is that of decision alternative prioritization. There have been many proposed approaches to the problem where the decision maker constructs a pairwise comparison matrix of the alternatives under study. All existing ranking methods possess major shortcomings for the general problem. This paper illustrates the usefulness of a neural network model in such prioritization problems, which considers these shortcomings of previous methods. Use of the model is shown through the use of example ranking scenarios.     

A sequential Bayesian approach to color constancy using non-uniform filters

This paper introduces a non-uniform filter formulation into the Brainard and Freeman Bayesian color constancy technique. The formulation comprises sensor measurements taken through a non-uniform filter, of spatially-varying spectral sensitivity, placed on the camera lens. The main goal of this paper is twofold. First, it presents a framework in which sensor measurements obtained through a non-uniform filter can be sequentially incorporated into the Bayesian probabilistic formulation. Second, it shows that such additional measurements obtained reduce the effect of the prior in Bayesian color constancy. For the purposes of testing the proposed framework, we use a filter formulation of two portions of different spectral sensitivities. We show through experiments on real data that improvement in the parameter estimation can be obtained inexpensively by sequentially incorporating additional information obtained from the sensor through the different portions of a filter by Bayesian chaining. We also show that our approach outperforms previous approaches in the literature.     

White color tracking adjustment in television receivers using neural networks

This paper discusses the application of neural networks to the white tracking adjustment of television receivers during production. High quality levels of tracking for the color temperature 8000 K were obtained with four-layer (7-10-10-6) network. The network input set consists of brightness level, high and low luminance levels, and “x” and “y” coordinates on the chromaticity diagram for both high and low luminance. The network output set consists of recommended adjustments for brightness, red, green, and blue cutoffs, and green and blue gains. The network was trained using the back-propagation algorithm. The experimental study has shown that the application of neural networks has reduced the testing time which has led to an increase in production rate.     

Classifying inventory using an artificial neural network approach

This paper presents artificial neural networks (ANNs) for ABC classification of stock keeping units (SKUs) in a pharmaceutical company. Two learning methods were utilized in the ANNs, namely back propagation (BP) and genetic algorithms (GA). The reliability of the models was tested by comparing their classification ability with two data sets (a hold-out sample and an external data set). Furthermore, the ANN models were compared with the multiple discriminate analysis (MDA) technique. The results showed that both ANN models had higher predictive accuracy than MDA. The results also indicate that there was no significant difference between the two learning methods used to develop the ANN.     

Committees, collectives and individuals: Expert visual classification by neural network

It has been established that committee classifiers, in which the outputs of different, individual network classifiers are combined in various ways, can produce better accuracy than the best individual in the committee. We describe results showing that these advantages are obtained when neural networks are applied to a taxonomic problem in marine science: the classification of images of marine phytoplankton. Significant benefits were found when individual networks, trained on different classes of input, having comparable individual performances, were combined. Combining networks of very different accuracy did not improve performance when measured against the best single network, but nor was it reduced. An alternative architecture, which we term a collective machine, in which the different data types are combined in a single network, was found to have significantly better accuracy than the committee machine architectures. The performance gains and resilience to non-discriminatory types of data suggest the techniques have great utility in the development of general purpose, network classifiers.     

A genetic algorithm-based artificial neural network model for the optimization of machining processes

Artificial intelligent tools like genetic algorithm, artificial neural network (ANN) and fuzzy logic are found to be extremely useful in modeling reliable processes in the field of computer integrated manufacturing (for example, selecting optimal parameters during process planning, design and implementing the adaptive control systems). When knowledge about the relationship among the various parameters of manufacturing are found to be lacking, ANNs are used as process models, because they can handle strong nonlinearities, a large number of parameters and missing information. When the dependencies between parameters become noninvertible, the input and output configurations used in ANN strongly influence the accuracy. However, running of a neural network is found to be time consuming. If genetic algorithm-based ANNs are used to construct models, it can provide more accurate results in less time. This article proposes a genetic algorithm-based ANN model for the turning process in manufacturing Industry. This model is found to be a time-saving model that satisfies all the accuracy requirements.     

Constructing neural network sediment estimation models using a data-driven algorithm

Artificial neural network (ANN) models are designed for suspended sediment estimation using statistical pre-processing of the data. Statistical properties such as cross-, auto- and partial auto-correlation of the data series are used for identifying a unique input vector to the ANN that best represents the sediment estimation process for a basin. The methodology is evaluated using the flow and sediment data from the stations Quebrada Blanca and Rio Valenciano in USA. The result of the study indicates that the statistical pre-processing of the data could significantly reduce the effort and computational time required in developing an ANN model. Three ANN training algorithms are also compared with each other for the selected input vector.     

A hybrid multi-objective approach based on the genetic algorithm and neural network to design an incremental cellular manufacturing system

One important issue related to the implementation of cellular manufacturing systems (CMSs) is to decide whether to convert an existing job shop into a CMS comprehensively in a single run, or in stages incrementally by forming cells one after the other, taking the advantage of the experiences of implementation. This paper presents a new multi-objective nonlinear programming model in a dynamic environment. Furthermore, a novel hybrid multi-objective approach based on the genetic algorithm and artificial neural network is proposed to solve the presented model. From the computational analyses, the proposed algorithm is found much more efficient than the fast non-dominated sorting genetic algorithm (NSGA-II) in generating Pareto optimal fronts.     

Temperature analysis of Coherent Anti-Stokes Raman spectra using a neural network approach

A neural network trained with clustered data has been applied to the extraction of temperature from vibrational Coherent Anti-Stokes Raman (CARS) spectra of nitrogen. CARS is a non-intrusive thermometry technique applied in practical combustors in industry. The advantages of clustering of training data over training with unprocessed calculated spectra is described. The method is applied to CARS data from an isothermal furnace and a liquid kerosene fuelled aeroengine combustor sector rig. Resulting temperatures have been compared with values extracted from the data using conventional least squares fitting and, where possible, mean temperatures measured by pyrometer and blackbody cavity probe. The main advantage of the neural network method is speed, with the potential for online temperature extraction at the spectral acquisition rate of 10 Hz using standard PC hardware.     

A novel neural network method for shortest path tree computation

Shortest path tree (SPT) computation is a critical issue in many real world problems, such as routing in networks. It is also a constrained optimization problem, which has been studied by many authors in recent years. Typically, it is solved by heuristic algorithms, such as the famous Dijkstra's algorithm, which can quickly provide a good solution in most instances. However, with the scale of problem increasing, these methods are inefficient and may consume a considerable amount of CPU time. Neural networks, which are massively parallel models, can solve this question easily. This paper presents an efficient modified continued pulse coupled neural network (MCPCNN) model for SPT computation in a large scale instance. The proposed model is topologically organized with only local lateral connections among neurons. The start neuron fires first, and then the firing event spreads out through the lateral connections among the neurons, like the propagation of a wave. Each neuron records its parent, that is, the neighbor which caused it to fire. It proves that the generated wave in the network spreads outward with travel times proportional to the connection weight between neurons. Thus, the generated path is always the global optimal shortest path from the source to all destinations. The proposed model is also applied to generate SPTs for a real given graph step by step. The effectiveness and efficiency of the proposed approach is demonstrated through simulation and comparison studies.     

Estimating VaR in crude oil market: A novel multi-scale non-linear ensemble approach incorporating wavelet analysis and neural network

Facing the complicated non-linear nature of risk evolutions, current risk measurement approaches offer insufficient explanatory power and limited performance. Thus this paper proposes wavelet decomposed non-linear ensemble value at risk (WDNEVaR), a novel semi-parametric paradigm, incorporating both, wavelet analysis and artificial neural network technique to further improve the modeling accuracy and reliability. Wavelet analysis is utilized to capture the multi-scale data characteristics across scales while artificial neural network technique is utilized to reduce estimation biases following non-linear ensemble algorithms. Experiment results in three major markets suggest that the proposed WDNEVaR is superior to more traditional approaches as it provides value at risk (VaR) estimates at higher reliability and accuracy.     

A novel model by evolving partially connected neural network for stock price trend forecasting

This paper proposes a novel model by evolving partially connected neural networks (EPCNNs) to predict the stock price trend using technical indicators as inputs. The proposed architecture has provided some new features different from the features of artificial neural networks: (1) connection between neurons is random; (2) there can be more than one hidden layer; (3) evolutionary algorithm is employed to improve the learning algorithm and training weights. In order to improve the expressive ability of neural networks, EPCNN utilizes random connection between neurons and more hidden layers to learn the knowledge stored within the historic time series data. The genetically evolved weights mitigate the well-known limitations of gradient descent algorithm. In addition, the activation function is defined using sin(x) function instead of sigmoid function. Three experiments were conducted which are explained as follows. In the first experiment, we compared the predicted value of the trained EPCNN model with the actual value to evaluate the prediction accuracy of the model. Second experiment studied the over fitting problem which occurred in neural network training by taking different number of neurons and layers. The third experiment compared the performance of the proposed EPCNN model with other models like BPN, TSK fuzzy system, multiple regression analysis and showed that EPCNN can provide a very accurate prediction of the stock price index for most of the data. Therefore, it is a very promising tool in forecasting of the financial time series data.     

Optimum design of structures by an improved genetic algorithm using neural networks

Optimum design of large-scale structures by standard genetic algorithm (GA) makes the computational burden of the process very high. To reduce the computational cost of standard GA, two different strategies are used. The first strategy is by modifying the standard GA, called virtual sub-population method (VSP). The second strategy is by using artificial neural networks for approximating the structural analysis. In this study, radial basis function (RBF), counter propagation (CP) and generalized regression (GR) neural networks are used. Using neural networks within the framework of VSP creates a robust tool for optimum design of structures.     

Face detection in complicated backgrounds and different illumination conditions by using YCbCr color space and neural network

This investigation develops an efficient face detection scheme that can detect multiple faces in color images with complex environments and different illumination levels. The proposed scheme comprises two stages. The first stage adopts color and triangle-based segmentation to search potential face regions. The second stage involves face verification using a multilayer feedforward neural network. The system can handle various sizes of faces, different illumination conditions, diverse pose and changeable expression. In particular, the scheme significantly increases the execution speed of the face detection algorithm in the case of complex backgrounds. Results of this study demonstrate that the proposed method performs better than previous methods in terms of speed and ability to handle different illumination conditions.     

Edge detection using a neural network

Artificial neural networks have been shown to perform well in many image processing applications such as coding, pattern recognition and texture segmentation. In a typical multi-layer model of this class, neurons in each layer are linked by synaptic weights to a receptive field region in the layer below it. The input image itself is linked to the lowest layer. We propose here a two stage encoder-detector network for edge detection. The single layer encoder stage, trained in a competitive mode, compresses data from an input receptive field and drives a back-propagation-trained detector network whose two outputs represent components of an edge vector. Experimental results show that for the case of step edges in noisy images, the performance of the neural edge detector is comparable to that of the Canny detector.     

A neural networks approach to minority game

The minority game (MG) comes from the so-called “El Farol bar” problem by W.B. Arthur. The underlying idea is competition for limited resources and it can be applied to different fields such as: stock markets, alternative roads between two locations and in general problems in which the players in the “minority” win. Players in this game use a window of the global history for making their decisions, we propose a neural networks approach with learning algorithms in order to determine players strategies. We use three different algorithms to generate the sequence of minority decisions and consider the prediction power of a neural network that uses the Hebbian algorithm. The case of sequences randomly generated is also studied. Research supported by Local Project 2004–2006 (EX 40%) Università di Foggia. A. Sfrecola is a researcher financially supported by Dipartimento di Scienze Economiche, Matematiche e Statistiche, Università degli Studi di Foggia, Foggia, Italy.     

Fault diagnosis on bottle filling plant using genetic-based neural network

Timely detection of the pneumatic system problems is important in industry. Many techniques have been employed to solve this problem. In this paper, Genetic Algorithm (GA) based optimal configuration of neural networks is proposed for fault diagnostic of bottle filling systems. Back-propagation is used for neural networks algorithm. The back-propagation algorithm had six inputs and one output. A fitness function was designed to the minimize execution time of ANN model by keeping the number of hidden layer(s) and nodes as low as possible while the mean square error of estimated output error is minimized. The designed GA–ANN combination and the graphical user interface (GUI) eliminate the trial and error process for selection of the fastest and most accurate configuration. The performance of the proposed system was evaluated by using experimental data collected at a pneumatic work cell which attach caps to the bottles. The sensory data was collected at normal operating conditions and a series of faults were imposed to the system such as missing bottle, attaching nonworking bottle caps at two different cylinders, two air pressure problems (insufficient and low air), and not filling water. The study demonstrated the convenience, accuracy and speed of the proposed GA–NN environment. It may also be used for training for selection of ANN configurations at various applications.     

A neural network based multi-classifier system for gene identification in DNA sequences

The paper presents a neural network based multi-classifier system for the identification of Escherichia coli promoter sequences in strings of DNA. As each gene in DNA is preceded by a promoter sequence, the successful location of an E. coli promoter leads to the identification of the corresponding E. coli gene in the DNA sequence. A set of 324 known E. coli promoters and a set of 429 known non-promoter sequences were encoded using four different encoding methods. The encoded sequences were then used to train four different neural networks. The classification results of the four individual neural networks were then combined through an aggregation function, which used a variation of the logarithmic opinion pool method. The weights of this function were determined by a genetic algorithm. The multi-classifier system was then tested on 159 known promoter sequences and 171 non-promoter sequences not contained in the training set. The results obtained through this study proved that the same data set, when presented to neural networks in different forms, can provide slightly varying results. It also proves that when different opinions of more classifiers on the same input data are integrated within a multi-classifier system, we can obtain results that are better than the individual performances of the neural networks. The performances of our multi-classifier system outperform the results of other prediction systems for E. coli promoters developed so far.

Prediction of indoor temperature and relative humidity using neural network models: model comparison

The use of neural networks grows great popularity in various building applications such as prediction of indoor temperature, heating load and ventilation rate. But few papers detail indoor relative humidity prediction which is an important indicator of indoor air quality, service life and energy efficiency of buildings. In this paper, the design of indoor temperature and relative humidity predictive neural networks in our test house was developed. The test house presented complicated physical features which are difficult to simulate with physical models. The work presented in this paper aimed to show the suitability of neural networks to perform predictions. Nonlinear AutoRegressive with eXternal input (NNARX) model and genetic algorithm were employed to construct networks and were detailed. The comparison between the two methods was also made. Applicability of some important mathematical validation criteria to practical reality was examined. Satisfactory results with correlation coefficients 0.998 and 0.997 for indoor temperature and relative humidity were obtained in the testing stage.