Showing papers by "Mepco Schlenk Engineering College published in 2005"
TL;DR: In this article, support vector machine (SVM) was applied to extend the rating curves developed at three gauging stations in Washington, namely Chehalis River at Dryad and Morse Creek at Four Seasons Ranch and Bear Branch near Naselle.
Abstract: It is often necessary to have stage discharge curve extended (extrapolated) beyond the highest (and sometimes lowest) measured discharges, for river forecasting, flood control and water supply for agricultural/industrial uses. During the floods or high stages, the river may become inaccessible for discharge measurement. Rating curves are usually extended using log–log axes, which are reported to have a number of problems. This paper suggests the use of Support Vector Machine (SVM) in the extrapolation of rating curves, which works on the principle of linear regression on a higher dimensional feature space. SVM is applied to extend the rating curves developed at three gauging stations in Washington, namely Chehalis River at Dryad and Morse Creek at Four Seasons Ranch (for extension of high stages) and Bear Branch near Naselle (for extension of low stages). The results obtained are significantly better as compared with widely used logarithmic method and higher order polynomial fitting method. A comparison of SVM results with ANN (Artificial Neural Network) indicates that SVM is better suited for extrapolation.
81 citations
TL;DR: The proposed approach is implemented in Tryggevaelde Catchment (Denmark) for 1- and 3- lead days, using the Support Vector Machine (SVM), which yields promising results, particularly for high flows in a 3-lead day model.
Abstract: Prediction of high magnitude flows is of interest in many hydrological applications such as operation of flood control reservoirs, flood forecasting and gated spillways. Of the various types of existing streamflow prediction approaches, data driven models (such as ANN) are increasingly being preferred over the traditional conceptual models due to their simplicity, fast speed and ease of use. For models that consider only historical streamflow data, an attempt has been made to design a robust model over a wide range of streamflow magnitudes. The model inputs are the immediate past streamflow data which generally do not predict the typically high flows well, particularly for large lead times. In this study, the flow range is divided into three regions (low, medium and high flow regions) and the attributes are decided based on the underlying hydrological process of the flow region. A flow forecasting model is applied for each flow region, using only the historical streamflow data as input. The proposed approach is implemented in Tryggevaelde Catchment (Denmark) for 1- and 3-lead days, using the Support Vector Machine (SVM), which yields promising results, particularly for high flows in a 3-lead day model.
63 citations
TL;DR: A comparison that shows the higher recognition rate achieved with the newly proposed method for the set of 6720 samples collected from 105 different textures of Brodatz, Vistek, Indezine databases and some additional images collected from other resources of indexed and true color images is shown.
62 citations
TL;DR: In this paper, the effects of iron content and initial fractional density of the preforms on deformation behavior have been investigated thoroughly by using graphite as a lubricant and the power law relationship between fractional theoretical density (ρ f /ρ th ) and e (e z -e θ) has been established.
Abstract: Cold upsetting experiments were carried out on sintered Al-Fe preforms in order to evaluate their deformation characteristics. The effects of iron content and initial fractional density of the preforms on deformation behavior have been investigated thoroughly by using graphite as a lubricant. Cylindrical preforms with different initial theoretical density and aspect ratio (0.75) were prepared using a suitable die, a punch and a die bottom insert on a 1.0 MN capacity Universal testing machine. The preforms were well covered with dry fine silica sand and sintered in an electric muffle furnace at 550 ±10°C for a period of 1 h and then furnace cooled. Cold deformation experiments were carried out in several steps. Dimensions such as height, contact, and bulged diameters and densities were measured for each test. In general, each compact was subjected to an incremental compressive loading in steps of 0.005 MN until fine cracks appeared on its free surface. Analysis of the experimental data has shown that the power law relationship between fractional theoretical density (ρ f /ρ th ) and e (e z -e θ) has been established. This remained valid for 0-8% iron content and all initial preform densities. Further it was found that the preforms of higher iron content shows higher values of deformation properties like the axial stress and the Poisson's ratio than less/without iron preforms provided that the initial fractional density taken is kept constant.
47 citations
16 Aug 2005
TL;DR: A method to accurately classify the heartbeat of ECG signals through the artificial neural networks (ANN) based on Heartbeat intervals, RR intervals and Spectral entropy of the ECG signal is proposed.
Abstract: Automatic detection and classification of cardiac arrhythmias from a limited number of ECG signals is of considerable importance in critical care or operating room patient monitoring. We propose a method to accurately classify the heartbeat of ECG signals through the artificial neural networks (ANN). Feature sets are based on Heartbeat intervals, RR intervals and Spectral entropy of the ECG signal. The ability of properly trained artificial neural networks to correctly classify and recognize patterns makes them particularly suitable for use in an expert system that aids in the interpretation of ECG signals. In the present work the ECG data is taken from standard MIT-BIH arrhythmia database. The proposed method is capable of distinguishing the normal beat and 9 different arrhythmias. The overall accuracy of classification of the proposed approach is 99.02%. The results of the analysis are found to be more accurate than the other existing methods. Detection and classification of cardiac signals is important for diagnosis of cardiac abnormalities and hence any automated processing of the ECG that assists this process would be of assistance and is the focus of this paper.
46 citations
11 Dec 2005
TL;DR: A computer aided diagnostic system for classifying diffused liver diseases from Computerized Tomography (CT) images using wavelet based texture analysis and neural network is presented.
Abstract: In this paper a computer aided diagnostic system for classifying diffused liver diseases from Computerized Tomography (CT) images using wavelet based texture analysis and neural network is presented. Liver is extracted from CT abdominal images using adaptive threshold and morphological processing. Orthogonal wavelet transform is applied on the liver to get horizontal, vertical and diagonal details. The statistical texture features like Mean, Standard deviation, Contrast, Entropy, Homogeneity and Angular second moment are extracted from these details and hence the eighteen features are used to train the Probabilistic neural network to classify the liver as fatty or cirrhosis. The proposed system is tested for 100 images. It produces an accuracy of 95%. The performance of the proposed system is also evaluated by calculating specificity, sensitivity, positive prediction value and negative prediction value. The performance measures of the above system are compared with the results evaluated by radiologists.
34 citations
TL;DR: A novel filtering method is proposed that combines the Stationary Wavelet Transform with a mean based smoothing operation, which adapts to variation in both signal and the noise, which yields significantly superior image quality and better Peak Signal to Noise Ratio (PSNR).
31 citations
16 Aug 2005
TL;DR: Features are derived from sub-bands of the ridgelet decomposition and are used for classification for a data set containing 20 texture images and Experimental results show that this approach allows to obtain a high degree of success in classification.
Abstract: Texture classification has long been an important research topic in image processing. Classification based on the wavelet transform has become very popular. Wavelets are very effective in representing objects with isolated point singularities, but failed to represent line singularities. Recently, a ridgelet transform which deals effectively with line singularities in 2-D is introduced. It allows representing edges and other singularities along lines in a more efficient way. In this paper, the issue of texture classification based on a ridgelet transform has been analyzed. Features are derived from sub-bands of the ridgelet decomposition and are used for classification for a data set containing 20 texture images. Experimental results show that this approach allows to obtain a high degree of success in classification.
29 citations
16 Aug 2005
TL;DR: An algorithm for classifying color textures using wavelet transform is described, which is useful for extracting texture features of images and is found to be satisfactory.
Abstract: Texture and color are two very important attributes in image analysis. While the color information describes the first order image properties, the texture generally describes second order property of surfaces and scenes, measured over image intensities. The need to include color aspect in texture analysis is being felt increasingly. The important aspect is, the way in which the chromatic information is involved in the formation and description of a texture. This paper describes an algorithm for classifying color textures using wavelet transform. Wavelet transform is useful for extracting texture features of images. A set of features are derived and color texture classification is done for different combination of the features and for different color models. The results obtained are found to be satisfactory.
27 citations
TL;DR: Several operations on fuzzy graphs such as union, join, composition, Cartesian product, and others are discussed and their domination parameters are studied.
Abstract: In this paper we discuss several operations on fuzzy graphs such as union, join, composition, Cartesian product and study their domination parameters.
26 citations
TL;DR: An efficient and adaptive method of threshold estimation for removing impulse noise from images, based on Double Density Wavelet Transform, which yields significantly superior image quality and better Peak Signal-to-Noise Ratio (PSNR).
Abstract: This paper describes an efficient and adaptive method of threshold estimation for removing impulse noise from images, based on Double Density Wavelet Transform (DDWT). The performance of image de-noising algorithms using wavelet transforms can be improved significantly by fixing an optimum threshold value, based on the analysis of the statistical parameters of subband coefficients. In this proposed method, the choice of the threshold estimation is carried out by analyzing the statistical parameters of the wavelet subband coefficients like standard deviation, arithmetic mean and geometrical mean. Here the noisy image is first decomposed into many levels to obtain different frequency bands using DDWT. Then soft thresholding method is used to remove the noisy coefficients, by fixing the optimum threshold value by the proposed method. Experimental results on several test images by using the proposed method show that, the proposed method yields significantly superior image quality and better Peak Signal-to-Noise Ratio (PSNR). Some comparisons with the best available results will be given in order to illustrate the effectiveness of the proposed algorithm.
16 Aug 2005
TL;DR: The use and implementation of fuzzy C means clustering and genetic algorithm (GA) for an automatic segmentation of white matter, gray matter (GM), cerebro spinal fluid (CSF), the extra cranial regions and the presence of tumor regions are discussed.
Abstract: In medical image visualization and analysis, segmentation is an indispensable step in the processing of images. MR has become a particularly useful medical diagnostic tool for cases involving soft tissues, such as in brain imaging. The aim of our research is to develop an effective algorithm for the segmentation of the MRI images. This paper discusses the use and implementation of fuzzy C means clustering and genetic algorithm (GA) for an automatic segmentation of white matter (WM), gray matter (GM), cerebro spinal fluid (CSF), the extra cranial regions and the presence of tumor regions. The results were analyzed and compared with the reference "gold standard" obtained from radiologists.
TL;DR: A new meta-heuristic evolutionary algorithm, named a memetic algorithm, for solving single machine total weighted tardiness scheduling problems is presented and performs better than the heuristics like earliest due date and modified due date.
Abstract: A new meta-heuristic evolutionary algorithm, named a memetic algorithm, for solving single machine total weighted tardiness scheduling problems is presented in this paper. Scheduling problems are proved to be NP-hard (Non-deterministic polynomial-time hard) types of problems and they are not easily or exactly solved for larger sizes. Therefore, application of the meta-heuristic technique to solve such NP hard problems is pursued by many researchers. The memetic algorithm is a marriage between population-based global searches with local improvement for each individual. The algorithm is tested with benchmark problems available in the OR (operations research) library. The results of the proposed algorithm are compared with the best available results and were found to be nearer to optimal. The memetic algorithm performs better than the heuristics like earliest due date and modified due date.
TL;DR: An intensive search evolutionary algorithm is proposed to solve single machine total weighted tardiness scheduling problems and it is observed that the proposed evolutionary algorithm provides better results than others.
Abstract: In this paper, an intensive search evolutionary algorithm is proposed to solve single machine total weighted tardiness scheduling problems. A specialised locally improved random swap mutation operator and an ordered crossover operator are used for evolution. The proposed algorithm starts with a pair of sequences: one generated by a greedy heuristic, namely, a backward phase heuristic acts as one parent, and a randomly generated sequence acts as the other. A computational experiment is conducted by applying the mutation operator on the backward phase sequence and the proposed algorithm with the same number of generations as the termination criteria. A total of 125 benchmark instances for sizes 40, 50 and 100 available in the OR library are solved and the results are compared with the available best-known results. It is observed that the proposed evolutionary algorithm provides better results than others .
TL;DR: In this article, an experimental set up for the measurement of velocities and attenuation for the propagation of ultrasonic waves in solids using through transmission technique at different temperatures is presented.
TL;DR: In this article, optical transmittance measurements have been made on thin films of CdxSn1−xSe, with x = 0, 0.3, 0.75 and 1 for various thicknesses.
Abstract: Polycrystalline CdxSn1−xSe material is synthesized by melt growth technique for various x values and thin films are prepared by vacuum evaporation technique. Optical transmittance measurements have been made on thin films of CdxSn1−xSe, with x = 0 , 0.3 , 0.75 and 1 for various thicknesses. The studies reveal that these thin films have a direct allowed band gap energy and the indirect band gap energy is improbable. The band gap energy increases with decrease in thickness in all the compositions and it is attributed to the quantum size effect.
TL;DR: In this article, the effect of γ-irradiation on the acoustical properties of xZnO·2xPbO·(1-3x)B2O3 glasses has been studied.
Abstract: The effect of γ-irradiation on the acoustical properties of xZnO·2xPbO·(1–3x)B2O3 glasses has been studied. Ultrasonic velocity and attenuation measurements have been made before and after γ-irradiation at room temperature in the frequency range 2.25–10 MHz. From the measured density and ultrasonic velocity data, the elastic moduli, Poisson's ratio and other parameters have been obtained. Changes in the acoustical properties are explained in terms of radiation-induced structural defects and the influence of PbO/ZnO in the glass network structure. (© 2005 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim)
16 Aug 2005
TL;DR: Two types of wavelet based schemes to improve the spectral efficiency (SE) of a digital communication system are presented and it is shown that wavelets obey Nyquist pulse shaping conditions.
Abstract: In this paper, two types of wavelet based schemes to improve the spectral efficiency (SE) of a digital communication system are presented. First one is wavelet based pulse shaping and the other is wavelet based digital modulation called wavelet shift keying (WSK). In pulse shaping scheme, orthonormal wavelets and their translates are used as base band shaping pulses. To improve spectral efficiency and coding gain, dyadic expansions and their translates are used for signaling. Since wavelets have zero average value, they can be transmitted using single side-band (SSB) transmission. By comparing with raised-cosine (RC) signaling, this wavelet approach offers more data rate at the same bandwidth. RC systems offers only 0.83 b/S/Hz for low pass transmission where as transmission using the first two dyadics offers 1.12 b/S/Hz. More over, it is shown that wavelets obey Nyquist pulse shaping conditions. Using a dyadic expansion to support a channel code there is a coding gain over the RC system, with essentially no bandwidth penalty. In modulation scheme, the user data stream is transformed into sequence of scaled mother wavelets to indicate which version of the mother wavelet is transmitted. This modulation offers more spectral efficiency as number of users increases keeping the power efficiency as constant.
TL;DR: A closed form solution to determine the AQL indexed single sampling plan using an artificial neural network (ANN) is described, where feed-forward neural networks with sigmoid neural function are trained by a back propagation algorithm for normal, tightened, and reduced inspections.
Abstract: Tabled sampling schemes such as MIL-STD-105D offer limited flexibility to quality control engineers in designing sampling plans to meet specific needs. We describe a closed form solution to determine the AQL indexed single sampling plan using an artificial neural network (ANN). To determine the sample size and the acceptance number, feed-forward neural networks with sigmoid neural function are trained by a back propagation algorithm for normal, tightened, and reduced inspections. From these trained ANNs, the relevant weight and bias values are obtained. The closed form solutions to determine the sampling plans are obtained using these values. Numerical examples are provided for using these closed form solutions to determine sampling plans for normal, tightened, and reduced inspections. The proposed method does not involve table look-ups or complex calculations. Sampling plan can be determined by using this method, for any required acceptable quality level and lot size. Suggestions are provided to...
16 Aug 2005
TL;DR: This paper analyses the performance of texture classification techniques using (i) multi resolution Markov random field (MRMRF) features and a combination of wavelet statistical features (WSFs) and wavelet co-occurrence features (WCFs) with two different texture datasets.
Abstract: Texture analysis plays an important role in many tasks, ranging from remote sensing to medical imaging and query by content in large image data bases. The main difficulty of texture analysis in the past was the lack of adequate tools to characterize different scales of textures effectively. The development in multi-resolution analysis such as Gabor and wavelet transform help to overcome this difficulty. This paper analyses the performance of texture classification techniques using (i) multi resolution Markov random field (MRMRF) features and (ii) a combination of wavelet statistical features (WSFs) and wavelet co-occurrence features (WCFs) with two different texture datasets.
TL;DR: An effective method has been proposed for texture segmentation, which incorporates the best features of filter bank and statistical approaches, and has been successfully tested for various textures from Brodatz texture collection.
Abstract: In this work, an effective method has been proposed for texture segmentation, which incorporates the best features of filter bank and statistical approaches. This technique combines the features of Gabor wavelets (filter based) and General Moments (statistical) approaches. The method has been successfully tested for various textures from Brodatz texture collection. The relative performance of this method against the conventional approaches has been analyzed using Fisher Criterion.
16 Aug 2005
TL;DR: A novel approach for segmentation of color textured images using dual tree complex wavelet transform (DTCWT), which emphasizes on the feature representation by labeling each pixel independently using fuzzy clustering.
Abstract: In this paper, we have proposed a novel approach for segmentation of color textured images using dual tree complex wavelet transform (DTCWT). The choice of DTCWT is proven for its attractive properties such as shift invariance, good directional selectivity, limited redundancy and efficient computation. The image is first decomposed into 16 sub bands by applying one level DTCWT in a separable manner without down sampling. Texture features are extracted from these sub bands by estimating in each sub band, the local energy around each pixel over a small neighborhood. To offer dimensionality reduction in feature space, a decisive criterion called mutual information is used to remove irrelevant or redundant features. Having obtained the feature images, we emphasize on the feature representation by labeling each pixel independently using fuzzy clustering. The segmentation results have demonstrated the effectiveness of the proposed method.
16 Aug 2005
TL;DR: Embedded lossless Wavelet based coder with hybrid bit scanning is used for ECG signal coding and Experimental results show that this algorithm outperforms than other coders such as Djohn, EZW, SPIHT, LJPEG etc in terms of coding efficiency.
Abstract: Wavelets have emerged as powerful tools for signal coding. In this paper embedded lossless Wavelet based coder with hybrid bit scanning is used for ECG signal coding. Experimental results show that this algorithm outperforms than other coders such as Djohn, EZW, SPIHT, LJPEG etc exits in the literature in terms of coding efficiency by successive partitioned the wavelet coefficients in the space frequency domain and sent them using hybrid bit scanning. Since no zero tree exists this coder is significantly more efficient in compression, simple in implementation and in computation than the previously proposed coders. This algorithm is tested for thirty seven different records from MIT-BIH arrhythmia database and obtained an average percent root mean square difference as around 0.0502% to 3.5399% for an average compression ratio of 1.5:1 to 25.1429:1 and for an average bit rate of 2552.7bps to 254.5 bps. A compression ratio of 8.0688:1 is achieved for MIT-BIH arrhythmia database record 117 with a percent mean square difference as 0.5183% and bit rate as 909.8 bps using Bior6.8 wavelet. All clinical information is preserved after compression and this makes the algorithm an attractive choice for use in portable heart monitoring systems.