GAP-RBF based NR image quality measurement for JPEG coded images

In this paper, we present a growing and pruning radial basis function based no-reference (NR) image quality model for JPEG-coded images. The quality of the images are estimated without referring to their original images. The features for predicting the perceived image quality are extracted by considering key human visual sensitivity factors such as edge amplitude, edge length, background activity and background luminance. Image quality estimation involves computation of functional relationship between HVS features and subjective test scores. Here, the problem of quality estimation is transformed to a function approximation problem and solved using GAP-RBF network. GAP-RBF network uses sequential learning algorithm to approximate the functional relationship. The computational complexity and memory requirement are less in GAP-RBF algorithm compared to other batch learning algorithms. Also, the GAP-RBF algorithm finds a compact image quality model and does not require retraining when the new image samples are presented. Experimental results prove that the GAP-RBF image quality model does emulate the mean opinion score (MOS). The subjective test results of the proposed metric are compared with JPEG no-reference image quality index as well as full-reference structural similarity image quality index and it is observed to outperform both.

Gas turbine diagnostics using a soft computing approach

A fuzzy system is developed using a linearized performance model of the gas turbine engine for performing gas turbine fault isolation from noisy measurements. By using a priori information about measurement uncertainties and through design variable linking, the design of the fuzzy system is posed as an optimization problem with low number of design variables which can be solved using the genetic algorithm in considerably low amount of computer time. The faults modeled are module faults in five modules: fan, low pressure compressor, high pressure compressor, high pressure turbine and low pressure turbine. The measurements used are deviations in exhaust gas temperature, low rotor speed, high rotor speed and fuel flow from a base line 'good engine'. The genetic fuzzy system (GFS) allows rapid development of the rule base if the fault signatures and measurement uncertainties change which happens for different engines and airlines. In addition, the genetic fuzzy system reduces the human effort needed in the trial and error process used to design the fuzzy system and makes the development of such a system easier and faster. A radial basis function neural network (RBFNN) is also used to preprocess the measurements before fault isolation. The RBFNN shows significant noise reduction and when combined with the GFS leads to a diagnostic system that is highly robust to the presence of noise in data. Showing the advantage of using a soft computing approach for gas turbine diagnostics.

Physics based basis function for vibration analysis of high speed rotating beams

The natural frequencies of continuous systems depend on the governing partial differential equation and can be numerically estimated using the finite element method. The accuracy and convergence of the finite element method depends on the choice of basis functions. A basis function will generally perform better if it is closely linked to the problem physics. The stiffness matrix is the same for either static or dynamic loading, hence the basis function can be chosen such that it satisfies the static part of the governing differential equation. However, in the case of a rotating beam, an exact closed form solution for the static part of the governing differential equation is not known. In this paper, we try to find an approximate solution for the static part of the governing differential equation for an uniform rotating beam. The error resulting from the approximation is minimized to generate relations between the constants assumed in the solution. This new function is used as a basis function which gives rise to shape functions which depend on position of the element in the beam, material, geometric properties and rotational speed of the beam. The results of finite element analysis with the new basis functions are verified with published literature for uniform and tapered rotating beams under different boundary conditions. Numerical results clearly show the advantage of the current approach at high rotation speeds with a reduction of 10 to 33% in the degrees of freedom required for convergence of the first five modes to four decimal places for an uniform rotating cantilever beam.

Machine recognition of printed Kannada text

This paper presents the design of a full fledged OCR system for printed Kannada text. The machine recognition of Kannada characters is difficult due to similarity in the shapes of different characters, script complexity and non-uniqueness in the representation of diacritics. The document image is subject to line segmentation, word segmentation and zone detection. From the zonal information, base characters, vowel modifiers and consonant conjucts are separated. Knowledge based approach is employed for recognizing the base characters. Various features are employed for recognising the characters. These include the coefficients of the Discrete Cosine Transform, Discrete Wavelet Transform and Karhunen-Louve Transform. These features are fed to different classifiers. Structural features are used in the subsequent levels to discriminate confused characters. Use of structural features, increases recognition rate from 93% to 98%. Apart from the classical pattern classification technique of nearest neighbour, Artificial Neural Network (ANN) based classifiers like Back Propogation and Radial Basis Function (RBF) Networks have also been studied. The ANN classifiers are trained in supervised mode using the transform features. Highest recognition rate of 99% is obtained with RBF using second level approximation coefficients of Haar wavelets as the features on presegmented base characters.

Aproximação fisionômica pericial através de função de base radial hermitiana

A aproximação fisionômica é o método que busca, a partir do crânio, simular a fotografia de um indivíduo quando em vida. Deve ser empregada como último recurso, na busca de desaparecidos, quando não houver possibilidade de aplicação de um método válido de identificação. O objetivo deste estudo foi obter a aproximação fisionômica, a partir de um crânio seco e de tomografia computadorizada multislice de indivíduos vivos, através da função de base radial hermitiana (FBRH). Constituiu-se também em avaliar o resultado da mesma quanto ao reconhecimento. Na primeira etapa do estudo, foi utilizada a imagem escaneada de um crânio seco, de origem desconhecida, com o intuito de avaliar se a quantidade de pontos obtidos seria suficiente para aplicação da FBRH e consequente reconstrução da superfície facial. Na segunda fase, foram utilizadas três tomografias de indivíduos vivos, para análise da semelhança alcançada entre a face escaneada e as aproximações faciais. Nesta etapa, foi aplicada uma associação de diferentes metodologias já publicadas, para reconstrução de uma mesma região da face, a partir de um mesmo crânio. Na última etapa, foram simuladas situações de reconhecimento com familiares e amigos dos indivíduos doadores das tomografias. Observou-se que a metodologia de FBRH pode ser empregada em aproximação fisionômica. Houve reconhecimento positivo nos três sujeitos estudados, sendo que, em dois deles, os resultados foram ainda mais significativos. Desta forma, conclui-se que a metodologia é rápida, objetiva e proporciona o reconhecimento. Esta permite a criação de múltiplas versões de aproximações fisionômicas a partir do mesmo crânio, o que amplia as possibilidades de reconhecimento. Observou-se ainda que a técnica não exige habilidade artística do profissional.

Double synaptic weight neuron theory and its application

In this paper, a novel mathematical model of neuron-Double Synaptic Weight Neuron (DSWN)(l) is presented. The DSWN can simulate many kinds of neuron architectures, including Radial-Basis-Function (RBF), Hyper Sausage and Hyper Ellipsoid models, etc. Moreover, this new model has been implemented in the new CASSANN-II neurocomputer that can be used to form various types of neural networks with multiple mathematical models of neurons. The flexibility of the DSWN has also been described in constructing neural networks. Based on the theory of Biomimetic Pattern Recognition (BPR) and high-dimensional space covering, a recognition system of omni directionally oriented rigid objects on the horizontal surface and a face recognition system had been implemented on CASSANN-II neurocomputer. In these two special cases, the result showed DSWN neural network had great potential in pattern recognition.

Discussion on the basic mathematical models of neurons - Double synaptic weight neuron in general-purpose neurocomputer, theory and application

Based on the introduction of the traditional mathematical models of neurons in general-purpose neurocomputer, a novel all-purpose mathematical model-Double synaptic weight neuron (DSWN) is presented, which can simulate all kinds of neuron architectures, including Radial-Basis-Function (RBF) and Back-propagation (BP) models, etc. At the same time, this new model is realized using hardware and implemented in the new CASSANN-II neurocomputer that can be used to form various types of neural networks with multiple mathematical models of neurons. In this paper, the flexibility of the new model has also been described in constructing neural networks and based on the theory of Biomimetic pattern recognition (BPR) and high-dimensional space covering, a recognition system of omni directionally oriented rigid objects on the horizontal surface and a face recognition system had been implemented on CASSANN-H neurocomputer. The result showed DSWN neural network has great potential in pattern recognition.

Modeling and optimization of semiconductor manufacturing process with neural networks

A neural network-based process model is proposed to optimize the semiconductor manufacturing process. Being different from some works in several research groups which developed neural network-based models to predict process quality with a set of process variables of only single manufacturing step, we applied this model to wafer fabrication parameters control and wafer lot yield optimization. The original data are collected from a wafer fabrication line, including technological parameters and wafer test results. The wafer lot yield is taken as the optimization target. Learning from historical technological records and wafer test results, the model can predict the wafer yield. To eliminate the "bad" or noisy samples from the sample set, an experimental method was used to determine the number of hidden units so that both good learning ability and prediction capability can be obtained.

Cancer classification based on direction-basis-function neural networks

Automatic molecular classification of cancer based on DNA microarray has many advantages over conventional classification based on morphological appearance of the tumor. Using artificial neural networks is a general approach for automatic classification. In this paper, Direction-Basis-Function neuron and Priority-Ordered algorithm are applied to neural networks. And the leukemia gene expression dataset is used as an example to testify the classifier. The result of our method is compared to that of SVM. It shows that our method makes a better performance than SVM.

Construction of Robot Intra-modal and Inter-modal Coordination Skills by Developmental Learning

Q. Meng and M. H. Lee, 'Construction of Robot Intra-modal and Inter-modal Coordination Skills by Developmental Learning', Journal of Intelligent and Robotic Systems, 48(1), pp 97-114, 2007.

Power system parameters forecasting using Hilbert-Huang transform and machine learning

A novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective data using the Hilbert-Huang transform and machine learning algorithms. The random forests and gradient boosting trees learning techniques were examined. The decision tree techniques were used to rank the importance of variables employed in the forecasting models. The Mean Decrease Gini index is employed as an impurity function. The resulting hybrid forecasting models employ the radial basis function neural network and support vector regression. A part from introduction and references the paper is organized as follows. The second section presents the background and the review of several approaches for short-term forecasting of power system parameters. In the third section a hybrid machine learningbased algorithm using Hilbert-Huang transform is developed for short-term forecasting of power system parameters. Fourth section describes the decision tree learning algorithms used for the issue of variables importance. Finally in section six the experimental results in the following electric power problems are presented: active power flow forecasting, electricity price forecasting and for the wind speed and direction forecasting.

Artificial neural networks in modelling osmotic dehydration of foods

Artificial neural network (ANN) models for water loss (WL) and solid gain (SG) were evaluated as potential alternative to multiple linear regression (MLR) for osmotic dehydration of apple, banana and potato. The radial basis function (RBF) network with a Gaussian function was used in this study. The RBF employed the orthogonal least square learning method. When predictions of experimental data from MLR and ANN were compared, an agreement was found for ANN models than MLR models for SG than WL. The regression coefficient for determination (R2) for SG in MLR models was 0.31, and for ANN was 0.91. The R2 in MLR for WL was 0.89, whereas ANN was 0.84.Osmotic dehydration experiments found that the amount of WL and SG occurred in the following descending order: Golden Delicious apple > Cox apple > potato > banana. The effect of temperature and concentration of osmotic solution on WL and SG of the plant materials followed a descending order as: 55 > 40 > 32.2C and 70 > 60 > 50 > 40%, respectively.

Analysis of classification accuracy for pre-filtered multichannel remote sensing data

Noise is one of the main factors degrading the quality of original multichannel remote sensing data and its presence influences classification efficiency, object detection, etc. Thus, pre-filtering is often used to remove noise and improve the solving of final tasks of multichannel remote sensing. Recent studies indicate that a classical model of additive noise is not adequate enough for images formed by modern multichannel sensors operating in visible and infrared bands. However, this fact is often ignored by researchers designing noise removal methods and algorithms. Because of this, we focus on the classification of multichannel remote sensing images in the case of signal-dependent noise present in component images. Three approaches to filtering of multichannel images for the considered noise model are analysed, all based on discrete cosine transform in blocks. The study is carried out not only in terms of conventional efficiency metrics used in filtering (MSE) but also in terms of multichannel data classification accuracy (probability of correct classification, confusion matrix). The proposed classification system combines the pre-processing stage where a DCT-based filter processes the blocks of the multichannel remote sensing image and the classification stage. Two modern classifiers are employed, radial basis function neural network and support vector machines. Simulations are carried out for three-channel image of Landsat TM sensor. Different cases of learning are considered: using noise-free samples of the test multichannel image, the noisy multichannel image and the pre-filtered one. It is shown that the use of the pre-filtered image for training produces better classification in comparison to the case of learning for the noisy image. It is demonstrated that the best results for both groups of quantitative criteria are provided if a proposed 3D discrete cosine transform filter equipped by variance stabilizing transform is applied. The classification results obtained for data pre-filtered in different ways are in agreement for both considered classifiers. Comparison of classifier performance is carried out as well. The radial basis neural network classifier is less sensitive to noise in original images, but after pre-filtering the performance of both classifiers is approximately the same.

A novel continuous forward algorithm for RBF neural modelling

A continuous forward algorithm (CFA) is proposed for nonlinear modelling and identification using radial basis function (RBF) neural networks. The problem considered here is simultaneous network construction and parameter optimization, well-known to be a mixed integer hard one. The proposed algorithm performs these two tasks within an integrated analytic framework, and offers two important advantages. First, the model performance can be significantly improved through continuous parameter optimization. Secondly, the neural representation can be built without generating and storing all candidate regressors, leading to significantly reduced memory usage and computational complexity. Computational complexity analysis and simulation results confirm the effectiveness.

PLS modelling and fault detection on the Tennessee Eastman benchmark

This paper describes the application of multivariate regression techniques to the Tennessee Eastman benchmark process for modelling and fault detection. Two methods are applied : linear partial least squares, and a nonlinear variant of this procedure using a radial basis function inner relation. The performance of the RBF networks is enhanced through the use of a recently developed training algorithm which uses quasi-Newton optimization to ensure an efficient and parsimonious network; details of this algorithm can be found in this paper. The PLS and PLS/RBF methods are then used to create on-line inferential models of delayed process measurements. As these measurements relate to the final product composition, these models suggest that on-line statistical quality control analysis should be possible for this plant. The generation of `soft sensors' for these measurements has the further effect of introducing a redundant element into the system, redundancy which can then be used to generate a fault detection and isolation scheme for these sensors. This is achieved by arranging the sensors and models in a manner comparable to the dedicated estimator scheme of Clarke et al. 1975, IEEE Trans. Pero. Elect. Sys., AES-14R, 465-473. The effectiveness of this scheme is demonstrated on a series of simulated sensor and process faults, with full detection and isolation shown to be possible for sensor malfunctions, and detection feasible in the case of process faults. Suggestions for enhancing the diagnostic capacity in the latter case are covered towards the end of the paper.