Search results for: random PWM algorithm.
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 3927

Search results for: random PWM algorithm.

1557 A Network Traffic Prediction Algorithm Based On Data Mining Technique

Authors: D. Prangchumpol

Abstract:

This paper is a description approach to predict incoming and outgoing data rate in network system by using association rule discover, which is one of the data mining techniques. Information of incoming and outgoing data in each times and network bandwidth are network performance parameters, which needed to solve in the traffic problem. Since congestion and data loss are important network problems. The result of this technique can predicted future network traffic. In addition, this research is useful for network routing selection and network performance improvement.

Keywords: Traffic prediction, association rule, data mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3669
1556 On the Strong Solutions of the Nonlinear Viscous Rotating Stratified Fluid

Authors: A. Giniatoulline

Abstract:

A nonlinear model of the mathematical fluid dynamics which describes the motion of an incompressible viscous rotating fluid in a homogeneous gravitational field is considered. The model is a generalization of the known Navier-Stokes system with the addition of the Coriolis parameter and the equations for changeable density. An explicit algorithm for the solution is constructed, and the proof of the existence and uniqueness theorems for the strong solution of the nonlinear problem is given. For the linear case, the localization and the structure of the spectrum of inner waves are also investigated.

Keywords: Galerkin method, Navier-Stokes equations, nonlinear partial differential equations, Sobolev spaces, stratified fluid.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1431
1555 On a New Inverse Polynomial Numerical Scheme for the Solution of Initial Value Problems in Ordinary Differential Equations

Authors: R. B. Ogunrinde

Abstract:

This paper presents the development, analysis and implementation of an inverse polynomial numerical method which is well suitable for solving initial value problems in first order ordinary differential equations with applications to sample problems. We also present some basic concepts and fundamental theories which are vital to the analysis of the scheme. We analyzed the consistency, convergence, and stability properties of the scheme. Numerical experiments were carried out and the results compared with the theoretical or exact solution and the algorithm was later coded using MATLAB programming language.

Keywords: Differential equations, Numerical, Initial value problem, Polynomials.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1772
1554 Grid Artifacts Suppression in Computed Radiographic Images

Authors: Igor Belykh

Abstract:

Anti-scatter grids used in radiographic imaging for the contrast enhancement leave specific artifacts. Those artifacts may be visible or may cause Moiré effect when digital image is resized on a diagnostic monitor. In this paper we propose an automated grid artifactsdetection and suppression algorithm which is still an actual problem. Grid artifacts detection is based on statistical approach in spatial domain. Grid artifacts suppression is based on Kaiser bandstop filter transfer function design and application avoiding ringing artifacts. Experimental results are discussed and concluded with description of advantages over existing approaches.

Keywords: Computed radiography, grid artifacts, image filtering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4292
1553 Evolved Strokes in Non Photo–Realistic Rendering

Authors: Ashkan Izadi, Vic Ciesielski

Abstract:

We describe a work with an evolutionary computing algorithm for non photo–realistic rendering of a target image. The renderings are produced by genetic programming. We have used two different types of strokes: “empty triangle" and “filled triangle" in color level. We compare both empty and filled triangular strokes to find which one generates more aesthetic pleasing images. We found the filled triangular strokes have better fitness and generate more aesthetic images than empty triangular strokes.

Keywords: Artificial intelligence, Evolutionary programming, Geneticprogramming, Non photo–realistic rendering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1931
1552 Seismic Base Shear Force Depending on Building Fundamental Period and Site Conditions: Deterministic Formulation and Probabilistic Analysis

Authors: S. Dorbani, M. Badaoui, D. Benouar

Abstract:

The aim of this paper is to investigate the effect of the building fundamental period of reinforced concrete buildings of (6, 9, and 12-storey), with different floor plans: Symmetric, mono-symmetric, and unsymmetric. These structures are erected at different epicentral distances. Using the Boumerdes, Algeria (2003) earthquake data, we focused primarily on the establishment of the deterministic formulation linking the base shear force to two parameters: The first one is the fundamental period that represents the numerical fingerprint of the structure, and the second one is the epicentral distance used to represent the impact of the earthquake on this force. In a second step, with a view to highlight the effect of uncertainty in these parameters on the analyzed response, these parameters are modeled as random variables with a log-normal distribution. The variability of the coefficients of variation of the chosen uncertain parameters, on the statistics on the seismic base shear force, showed that the effect of uncertainty on fundamental period on this force statistics is low compared to the epicentral distance uncertainty influence.

Keywords: Base shear force, fundamental period, epicentral distance, uncertainty, lognormal variable, statistics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1301
1551 Replacing MOSFETs with Single Electron Transistors (SET) to Reduce Power Consumption of an Inverter Circuit

Authors: Ahmed Shariful Alam, Abu Hena M. Mustafa Kamal, M. Abdul Rahman, M. Nasmus Sakib Khan Shabbir, Atiqul Islam

Abstract:

According to the rules of quantum mechanics there is a non-vanishing probability of for an electron to tunnel through a thin insulating barrier or a thin capacitor which is not possible according to the laws of classical physics. Tunneling of electron through a thin insulating barrier or tunnel junction is a random event and the magnitude of current flowing due to the tunneling of electron is very low. As the current flowing through a Single Electron Transistor (SET) is the result of electron tunneling through tunnel junctions of its source and drain the supply voltage requirement is also very low. As a result, the power consumption across a Single Electron Transistor is ultra-low in comparison to that of a MOSFET. In this paper simulations have been done with PSPICE for an inverter built with both SETs and MOSFETs. 35mV supply voltage was used for a SET built inverter circuit and the supply voltage used for a CMOS inverter was 3.5V.

Keywords: ITRS, enhancement type MOSFET, island, DC analysis, transient analysis, power consumption, background charge co-tunneling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1803
1550 Modeling of Blood Flow Velocity into the Main Artery via Left Ventricle of Heart during Steady Condition

Authors: Mohd Azrul Hisham Mohd Adib, Nur Hazreen Mohd Hasni

Abstract:

A three-dimensional and pulsatile blood flow in the left ventricle of heart model has been studied numerically. The geometry was derived from a simple approximation of the left ventricle model and the numerical simulations were obtained using a formulation of the Navier-Stokes equations. In this study, simulation was used to investigate the pattern of flow velocity in 3D model of heart with consider the left ventricle based on critical parameter of blood under steady condition. Our results demonstrate that flow velocity focused from mitral valve channel and continuous linearly to left ventricle wall but this skewness progresses into outside wall in atrium through aortic valve with random distribution that is irregular due to force subtract from ventricle wall during cardiac cycle. The findings are the prediction of the behavior of the blood flow velocity pattern in steady flow condition which can assist the medical practitioners in their decision on the patients- treatments.

Keywords: Mitral Valve, Aortic Valve, Cardiac Cycle, Leaflet, Biomechanics, Left Ventricle

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2137
1549 Characterization of Pure Nickel Coatings Fabricated under Pulse Current Conditions

Authors: M. Sajjadnejad, H. Omidvar, M. Javanbakht, A. Mozafari

Abstract:

Pure nickel coatings have been successfully electrodeposited on copper substrates by the pulse plating technique. The influence of current density, duty cycle and pulse frequency on the surface morphology, crystal orientation, and microhardness was determined. It was found that the crystallite size of the deposit increases with increasing current density and duty cycle. The crystal orientation progressively changed from a random texture at 1 A/dm2 to (200) texture at 10 A/dm2. Increasing pulse frequency resulted in increased texture coefficient and peak intensity of (111) reflection. An increase in duty cycle resulted in considerable increase in texture coefficient and peak intensity of (311) reflection. Coatings obtained at high current densities and duty cycle present a mixed morphology of small and large grains. Maximum microhardness of 193 Hv was achieved at 4 A/dm2, 10 Hz and duty cycle of 50%. Nickel coatings with (200) texture are ductile while (111) texture improves the microhardness of the coatings.

Keywords: Current density, Duty cycle, Microstructure, Nickel, Pulse frequency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2246
1548 Swarm Navigation in a Complex Environment

Authors: Jai Raj, Jito Vanualailai, Bibhya Sharma, Shonal Singh

Abstract:

This paper proposes a solution to the motion planning and control problem of car-like mobile robots which is required to move safely to a designated target in a priori known workspace cluttered with swarm of boids exhibiting collective emergent behaviors. A generalized algorithm for target convergence and swarm avoidance is proposed that will work for any number of swarms. The control laws proposed in this paper also ensures practical stability of the system. The effectiveness of the proposed control laws are demonstrated via computer simulations of an emergent behavior.

Keywords: Swarm, practical stability, motion planning, emergent.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1396
1547 Neuro-Fuzzy Algorithm for a Biped Robotic System

Authors: Hataitep Wongsuwarn, Djitt Laowattana

Abstract:

This paper summaries basic principles and concepts of intelligent controls, implemented in humanoid robotics as well as recent algorithms being devised for advanced control of humanoid robots. Secondly, this paper presents a new approach neuro-fuzzy system. We have included some simulating results from our computational intelligence technique that will be applied to our humanoid robot. Subsequently, we determine a relationship between joint trajectories and located forces on robot-s foot through a proposed neuro-fuzzy technique.

Keywords: Biped Robot, Computational Intelligence, Static and Dynamic Walking, Gait Synthesis, Neuro-Fuzzy System.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2556
1546 Evolutionary Computing Approach for the Solution of Initial value Problems in Ordinary Differential Equations

Authors: A. Junaid, M. A. Z. Raja, I. M. Qureshi

Abstract:

An evolutionary computing technique for solving initial value problems in Ordinary Differential Equations is proposed in this paper. Neural network is used as a universal approximator while the adaptive parameters of neural networks are optimized by genetic algorithm. The solution is achieved on the continuous grid of time instead of discrete as in other numerical techniques. The comparison is carried out with classical numerical techniques and the solution is found with a uniform accuracy of MSE ≈ 10-9 .

Keywords: Neural networks, Unsupervised learning, Evolutionary computing, Numerical methods, Fitness evaluation function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1780
1545 Methodology for the Multi-Objective Analysis of Data Sets in Freight Delivery

Authors: Dale Dzemydiene, Aurelija Burinskiene, Arunas Miliauskas, Kristina Ciziuniene

Abstract:

Data flow and the purpose of reporting the data are different and dependent on business needs. Different parameters are reported and transferred regularly during freight delivery. This business practices form the dataset constructed for each time point and contain all required information for freight moving decisions. As a significant amount of these data is used for various purposes, an integrating methodological approach must be developed to respond to the indicated problem. The proposed methodology contains several steps: (1) collecting context data sets and data validation; (2) multi-objective analysis for optimizing freight transfer services. For data validation, the study involves Grubbs outliers analysis, particularly for data cleaning and the identification of statistical significance of data reporting event cases. The Grubbs test is often used as it measures one external value at a time exceeding the boundaries of standard normal distribution. In the study area, the test was not widely applied by authors, except when the Grubbs test for outlier detection was used to identify outsiders in fuel consumption data. In the study, the authors applied the method with a confidence level of 99%. For the multi-objective analysis, the authors would like to select the forms of construction of the genetic algorithms, which have more possibilities to extract the best solution. For freight delivery management, the schemas of genetic algorithms' structure are used as a more effective technique. Due to that, the adaptable genetic algorithm is applied for the description of choosing process of the effective transportation corridor. In this study, the multi-objective genetic algorithm methods are used to optimize the data evaluation and select the appropriate transport corridor. The authors suggest a methodology for the multi-objective analysis, which evaluates collected context data sets and uses this evaluation to determine a delivery corridor for freight transfer service in the multi-modal transportation network. In the multi-objective analysis, authors include safety components, the number of accidents a year, and freight delivery time in the multi-modal transportation network. The proposed methodology has practical value in the management of multi-modal transportation processes.

Keywords: Multi-objective decision support, analysis, data validation, freight delivery, multi-modal transportation, genetic programming methods.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 484
1544 Issues in Travel Demand Forecasting

Authors: Huey-Kuo Chen

Abstract:

Travel demand forecasting including four travel choices, i.e., trip generation, trip distribution, modal split and traffic assignment constructs the core of transportation planning. In its current application, travel demand forecasting has associated with three important issues, i.e., interface inconsistencies among four travel choices, inefficiency of commonly used solution algorithms, and undesirable multiple path solutions. In this paper, each of the three issues is extensively elaborated. An ideal unified framework for the combined model consisting of the four travel choices and variable demand functions is also suggested. Then, a few remarks are provided in the end of the paper

Keywords: Travel choices, B algorithm, entropy maximization, dynamic traffic assignment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2357
1543 Optimizing the Design of Radial/Axial PMSM and SRM used for Powered Wheel-Chairs

Authors: D. Fodorean, D.C. Popa, F. Jurca, M. Ruba

Abstract:

the paper presents the optimization results for several electrical machines dedicated for powered electric wheel-chairs. The optimization, using the Hook-Jeeves algorithm, was employed based on a design approach which takes into consideration the road conditions. Also, through numerical simulations (based on finite element method), the analytical approach was validated. The optimization approach gave satisfactory results and the best suited variant was chosen for the motorization of the wheel-chair.

Keywords: electrical machines, numerical validation, optimization, electric wheel chair.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2072
1542 The Evaluation of the Performance of Different Filtering Approaches in Tracking Problem and the Effect of Noise Variance

Authors: Mohammad Javad Mollakazemi, Farhad Asadi, Aref Ghafouri

Abstract:

Performance of different filtering approaches depends on modeling of dynamical system and algorithm structure. For modeling and smoothing the data the evaluation of posterior distribution in different filtering approach should be chosen carefully. In this paper different filtering approaches like filter KALMAN, EKF, UKF, EKS and smoother RTS is simulated in some trajectory tracking of path and accuracy and limitation of these approaches are explained. Then probability of model with different filters is compered and finally the effect of the noise variance to estimation is described with simulations results.

Keywords: Gaussian approximation, KALMAN smoother, Parameter estimation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1775
1541 Analysis of Self Excited Induction Generator using Particle Swarm Optimization

Authors: Hassan E. A. Ibrahim, Mohamed F. Serag

Abstract:

In this paper, Novel method, Particle Swarm Optimization (PSO) algorithm, based technique is proposed to estimate and analyze the steady state performance of self-excited induction generator (SEIG). In this novel method the tedious job of deriving the complex coefficients of a polynomial equation and solving it, as in previous methods, is not required. By comparing the simulation results obtained by the proposed method with those obtained by the well known mathematical methods, a good agreement between these results is obtained. The comparison validates the effectiveness of the proposed technique.

Keywords: Evolution theory, MATLAB, optimization, PSO, SEIG.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2464
1540 PI Control for Second Order Delay System with Tuning Parameter Optimization

Authors: R. Farkh, K. Laabidi, M. Ksouri

Abstract:

In this paper, we consider the control of time delay system by Proportional-Integral (PI) controller. By Using the Hermite- Biehler theorem, which is applicable to quasi-polynomials, we seek a stability region of the controller for first order delay systems. The essence of this work resides in the extension of this approach to second order delay system, in the determination of its stability region and the computation of the PI optimum parameters. We have used the genetic algorithms to lead the complexity of the optimization problem.

Keywords: Genetic algorithm, Hermit-Biehler theorem, optimization, PI controller, second order delay system, stability region.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1775
1539 Modeling of Crude Oil Blending via Discrete-Time Neural Networks

Authors: Xiaoou Li, Wen Yu

Abstract:

Crude oil blending is an important unit operation in petroleum refining industry. A good model for the blending system is beneficial for supervision operation, prediction of the export petroleum quality and realizing model-based optimal control. Since the blending cannot follow the ideal mixing rule in practice, we propose a static neural network to approximate the blending properties. By the dead-zone approach, we propose a new robust learning algorithm and give theoretical analysis. Real data of crude oil blending is applied to illustrate the neuro modeling approach.

Keywords: Neural networks, modeling, stability, crude oil.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2263
1538 A Numerical Method to Evaluate the Elastoplastic Material Properties of Fiber Reinforced Composite

Authors: M. Palizvan, M. H. Sadr, M. T. Abadi

Abstract:

The representative volume element (RVE) plays a central role in the mechanics of random heterogeneous materials with a view to predicting their effective properties. In this paper, a computational homogenization methodology, developed to determine effective linear elastic properties of composite materials, is extended to predict the effective nonlinear elastoplastic response of long fiber reinforced composite. Finite element simulations of volumes of different sizes and fiber volume fractures are performed for calculation of the overall response RVE. The dependencies of the overall stress-strain curves on the number of fibers inside the RVE are studied in the 2D cases. Volume averaged stress-strain responses are generated from RVEs and compared with the finite element calculations available in the literature at moderate and high fiber volume fractions. For these materials, the existence of an RVE is demonstrated for the sizes of RVE corresponding to 10–100 times the diameter of the fibers. In addition, the response of small size RVE is found anisotropic, whereas the average of all large ones leads to recover the isotropic material properties.

Keywords: Homogenization, periodic boundary condition, elastoplastic properties, RVE.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 860
1537 Predicting Effective Permeability of Nanodielectric Composites Bonded by Soft Magnetic Nanoparticles

Authors: A. Thabet, M. Repetto

Abstract:

Dielectric materials play an important role in broad applications, such as electrical and electromagnetic applications. This research studied the prediction of effective permeability of composite and nanocomposite dielectric materials based on theoretical analysis to specify the effects of embedded magnetic inclusions in enhancing magnetic properties of dielectrics. Effective permeability of Plastics and Glass nanodielectrics have been predicted with adding various types and percentages of magnetic nano-particles (Fe, Ni-Cu, Ni-Fe, MgZn_Ferrite, NiZn_Ferrite) for formulating new nanodielectric magnetic industrial materials. Soft nanoparticles powders that have been used in new nanodielectrics often possess the structure of a particle size in the range of micrometer- to nano-sized grains and magnetic isotropy, e.g., a random distribution of magnetic easy axes of the nanograins. It has been succeeded for enhancing characteristics of new nanodielectric magnetic industrial materials. The results have shown a significant effect of inclusions distribution on the effective permeability of nanodielectric magnetic composites, and so, explained the effect of magnetic inclusions types and their concentration on the effective permeability of nanodielectric magnetic materials.

Keywords: Nanoparticles, Nanodielectrics, Nanocomposites, Effective Permeability, Magnetic Properties.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2760
1536 The Multi-Layered Perceptrons Neural Networks for the Prediction of Daily Solar Radiation

Authors: Radouane Iqdour, Abdelouhab Zeroual

Abstract:

The Multi-Layered Perceptron (MLP) Neural networks have been very successful in a number of signal processing applications. In this work we have studied the possibilities and the met difficulties in the application of the MLP neural networks for the prediction of daily solar radiation data. We have used the Polack-Ribière algorithm for training the neural networks. A comparison, in term of the statistical indicators, with a linear model most used in literature, is also performed, and the obtained results show that the neural networks are more efficient and gave the best results.

Keywords: Daily solar radiation, Prediction, MLP neural networks, linear model

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1328
1535 Rural Women’s Skill Acquisition in the Processing of Locust Bean in Ipokia Local Government Area of Ogun State, Nigeria

Authors: A. A. Adekunle, A. M. Omoare, W. O. Oyediran

Abstract:

This study was carried out to assess rural women’s skill acquisition in the processing of locust bean in Ipokia Local Government Area of Ogun State, Nigeria. Simple random sampling technique was used to select 90 women locust bean processors for this study. Data were analyzed with descriptive statistics and Pearson Product Moment Correlation. The result showed that the mean age of respondents was 40.72 years. Most (70.00%) of the respondents were married. The mean processing experience was 8.63 years. 93.30% of the respondents relied on information from fellow locust beans processors and friends. All (100%) the respondents did not acquire improved processing skill through trainings and workshops. It can be concluded that the rural women’s skill acquisition on modernized processing techniques was generally low. It is hereby recommend that the rural women processors should be trained by extension service providers through series of workshops and seminars on improved processing techniques.

Keywords: Locust bean, processing, skill acquisition, rural women.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2818
1534 Hearing Aids Maintenance Training for Hearing-Impaired Preschool Children with the Help of Motion Graphic Tools

Authors: M. Mokhtarzadeh, M. Taheri Qomi, M. Nikafrooz, A. Atashafrooz

Abstract:

The purpose of the present study was to investigate the effectiveness of using motion graphics as a learning medium on training hearing aids maintenance skills to hearing-impaired children. The statistical population of this study consisted of all children with hearing loss in Ahvaz city, at age 4 to 7 years old. As the sample, 60, whom were selected by multistage random sampling, were randomly assigned to two groups; experimental (30 children) and control (30 children) groups. The research method was experimental and the design was pretest-posttest with the control group. The intervention consisted of a 2-minute motion graphics clip to train hearing aids maintenance skills. Data were collected using a 9-question researcher-made questionnaire. The data were analyzed by using one-way analysis of covariance. Results showed that the training of hearing aids maintenance skills with motion graphics was significantly effective for those children. The results of this study can be used by educators, teachers, professionals, and parents to train children with disabilities or normal students.

Keywords: Hearing-impaired children, hearing aids, hearing aids maintenance skill, and motion graphics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 575
1533 Transformation of Course Timetablinng Problem to RCPSP

Authors: M. Ahmad, M. Gourgand, C. Caux

Abstract:

The Resource-Constrained Project Scheduling Problem (RCPSP) is concerned with single-item or small batch production where limited resources have to be allocated to dependent activities over time. Over the past few decades, a lot of work has been made with the use of optimal solution procedures for this basic problem type and its extensions. Brucker and Knust[1] discuss, how timetabling problems can be modeled as a RCPSP. Authors discuss high school timetabling and university course timetabling problem as an example. We have formulated two mathematical formulations of course timetabling problem in a new way which are the prototype of single-mode RCPSP. Our focus is to show, how course timetabling problem can be transformed into RCPSP. We solve this transformation model with genetic algorithm.

Keywords: Course Timetabling, Integer programming, Combinatorial optimizations

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2016
1532 Face Recognition using Radial Basis Function Network based on LDA

Authors: Byung-Joo Oh

Abstract:

This paper describes a method to improve the robustness of a face recognition system based on the combination of two compensating classifiers. The face images are preprocessed by the appearance-based statistical approaches such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). LDA features of the face image are taken as the input of the Radial Basis Function Network (RBFN). The proposed approach has been tested on the ORL database. The experimental results show that the LDA+RBFN algorithm has achieved a recognition rate of 93.5%

Keywords: Face recognition, linear discriminant analysis, radial basis function network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2122
1531 Statistical Analysis of Stresses in Rigid Pavement

Authors: Aleš Florian, Lenka Ševelová, Rudolf Hela

Abstract:

Complex statistical analysis of stresses in concrete slab of the real type of rigid pavement is performed. The computational model of the pavement is designed as a spatial (3D) model, is based on a nonlinear variant of the finite element method that respects the structural nonlinearity, enables to model different arrangement of joints, and the entire model can be loaded by the thermal load. Interaction of adjacent slabs in joints and contact of the slab and the subsequent layer are modeled with help of special contact elements. Four concrete slabs separated by transverse and longitudinal joints and the additional subgrade layers and soil to the depth of about 3m are modeled. The thickness of individual layers, physical and mechanical properties of materials, characteristics of joints, and the temperature of the upper and lower surface of slabs are supposed to be random variables. The modern simulation technique Updated Latin Hypercube Sampling with 20 simulations is used for statistical analysis. As results, the estimates of basic statistics of the principal stresses s1 and s3 in 53 points on the upper and lower surface of the slabs are obtained.

Keywords: concrete, FEM, pavement, simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1575
1530 Accuracy of Divergence Measures for Detection of Abrupt Changes

Authors: P. Bergl

Abstract:

Numerous divergence measures (spectral distance, cepstral distance, difference of the cepstral coefficients, Kullback-Leibler divergence, distance given by the General Likelihood Ratio, distance defined by the Recursive Bayesian Changepoint Detector and the Mahalanobis measure) are compared in this study. The measures are used for detection of abrupt spectral changes in synthetic AR signals via the sliding window algorithm. Two experiments are performed; the first is focused on detection of single boundary while the second concentrates on detection of a couple of boundaries. Accuracy of detection is judged for each method; the measures are compared according to results of both experiments.

Keywords: Abrupt changes detection, autoregressive model, divergence measure.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1449
1529 A Model for Test Case Selection in the Software-Development Life Cycle

Authors: Adtha Lawanna

Abstract:

Software maintenance is one of the essential processes of Software-Development Life Cycle. The main philosophies of retaining software concern the improvement of errors, the revision of codes, the inhibition of future errors, and the development in piece and capacity. While the adjustment has been employing, the software structure has to be retested to an upsurge a level of assurance that it will be prepared due to the requirements. According to this state, the test cases must be considered for challenging the revised modules and the whole software. A concept of resolving this problem is ongoing by regression test selection such as the retest-all selections, random/ad-hoc selection and the safe regression test selection. Particularly, the traditional techniques concern a mapping between the test cases in a test suite and the lines of code it executes. However, there are not only the lines of code as one of the requirements that can affect the size of test suite but including the number of functions and faulty versions. Therefore, a model for test case selection is developed to cover those three requirements by the integral technique which can produce the smaller size of the test cases when compared with the traditional regression selection techniques.

Keywords: Software maintenance, regression test selection, test case.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1697
1528 A Model for Test Case Selection in the Software-Development Life Cycle

Authors: Adtha Lawanna

Abstract:

Software maintenance is one of the essential processes of Software-Development Life Cycle. The main philosophies of retaining software concern the improvement of errors, the revision of codes, the inhibition of future errors, and the development in piece and capacity. While the adjustment has been employing, the software structure has to be retested to an upsurge a level of assurance that it will be prepared due to the requirements. According to this state, the test cases must be considered for challenging the revised modules and the whole software. A concept of resolving this problem is ongoing by regression test selection such as the retest-all selections, random/ad-hoc selection and the safe regression test selection. Particularly, the traditional techniques concern a mapping between the test cases in a test suite and the lines of code it executes. However, there are not only the lines of code as one of the requirements that can affect the size of test suite but including the number of functions and faulty versions. Therefore, a model for test case selection is developed to cover those three requirements by the integral technique which can produce the smaller size of the test cases when compared with the traditional regression selection techniques.

Keywords: Software maintenance, regression test selection, test case.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1599