Search results for: Hidden Markov random field model
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 9777

Search results for: Hidden Markov random field model

9597 Strong Law of Large Numbers for *- Mixing Sequence

Authors: Bainian Li, Kongsheng Zhang

Abstract:

Strong law of large numbers and complete convergence for sequences of *-mixing random variables are investigated. In particular, Teicher-s strong law of large numbers for independent random variables are generalized to the case of *-mixing random sequences and extended to independent and identically distributed Marcinkiewicz Law of large numbers for *-mixing.

Keywords: mixing squences, strong law of large numbers, martingale differences, Lacunary System

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1258
9596 Modified Fuzzy PID Control for Networked Control Systems with Random Delays

Authors: Yong-can Cao, Wei-dong Zhang

Abstract:

To deal with random delays in Networked Control System (NCS), Modified Fuzzy PID Controller is introduced in this paper to implement real-time control adaptively. Via adjusting the control signal dynamically, the system performance is improved. In this paper, the design process and the ultimate simulation results are represented. Finally, examples and corresponding comparisons prove the significance of this method.

Keywords: Fuzzy Control, Networked Control System, PID, Random Delays

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1524
9595 Mathematical Modeling on Capturing of Magnetic Nanoparticles in an Implant Assisted Channel for Magnetic Drug Targeting

Authors: Shashi Sharma, V. K. Katiyar, Uaday Singh

Abstract:

In IA-MDT, the magnetic implants are placed strategically at the target site to greatly and locally increase the magnetic force on MDCPs and help to attract and retain the MDCPs at the targeted region. In the present work, we develop a mathematical model to study the capturing of magnetic nanoparticles flowing within a fluid in an implant assisted cylindrical channel under magnetic field. A coil of ferromagnetic SS-430 has been implanted inside the cylindrical channel to enhance the capturing of magnetic nanoparticles under magnetic field. The dominant magnetic and drag forces, which significantly affect the capturing of nanoparticles, are incorporated in the model. It is observed through model results that capture efficiency increases as we increase the magnetic field from 0.1 to 0.5 T, respectively. The increase in capture efficiency by increase in magnetic field is because as the magnetic field increases, the magnetization force, which is attractive in nature and responsible to attract or capture the magnetic particles, increases and results the capturing of large number of magnetic particles due to high strength of attractive magnetic force.

Keywords: Capture efficiency, Implant assisted-Magnetic drug targeting (IA-MDT), Magnetic nanoparticles (MNPs).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1762
9594 Bandwidth, Area Efficient and Target Device Independent DDR SDRAM Controller

Authors: T. Mladenov, F. Mujahid, E. Jung, D. Har

Abstract:

The application of the synchronous dynamic random access memory (SDRAM) has gone beyond the scope of personal computers for quite a long time. It comes into hand whenever a big amount of low price and still high speed memory is needed. Most of the newly developed stand alone embedded devices in the field of image, video and sound processing take more and more use of it. The big amount of low price memory has its trade off – the speed. In order to take use of the full potential of the memory, an efficient controller is needed. Efficient stands for maximum random accesses to the memory both for reading and writing and less area after implementation. This paper proposes a target device independent DDR SDRAM pipelined controller and provides performance comparison with available solutions.

Keywords: DDR SDRAM, controller, effective implementation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1526
9593 Social Work Practice to Labour Welfare: A Proposed Model of Field Work Practicum and Role of Social Worker in India

Authors: Naeem Ahmed

Abstract:

Social work is a professional activity based on the approach of “helping people to help themselves” (Stroup). Social work education and practice both are based on humanitarian philosophy in which social workers try to increase the happiness of the society and to reduce the problems of society. Labour welfare is a specialised field of social work which especially focuses on welfare of organised and unorganised labour. In India labour is facing numerous problems in both organised and unorganised sectors because of ignorance, illiteracy, high rate of unemployment etc. In most of the Indian social work institutions we have this specialization with different names like Human Resource Management or Industrial Relation and Personnel Management or Industrial Relations and Labour Welfare or Industrial Social Work etc. Field work practice is integrated part of social work education curriculum in all specialised field. In India we have different field work practice models being followed in different institutions. The main objective of this paper is to prepare a universal field work practicum model in the field of labour welfare. This paper is exploratory in nature, researcher used personal experience and secondary data (model of field work practice in different institutions like Aligarh Muslim University, Pondicherry University, Central University of Karnataka, University of Lucknow, MJP Rohilkhand University Bareilly etc.) Researcher found that there is an immediate need to upgrade the curriculum or field work practice in this particular field, as more than 40 percent of total population engaged in either unorganised or organised sector (NSSO 2011-12) and they are not aware about their rights. In this way a social worker can play an important role in existing labour welfare facilities by making them aware.

Keywords: Fieldwork, labour welfare, organised labour, social work practice, unorganised labour.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2810
9592 Numerical Simulation of the Turbulent Flow over a Three-Dimensional Flat Roof

Authors: M. Raciti Castelli, A. Castelli, E. Benini

Abstract:

The flow field over a flat roof model building has been numerically investigated in order to determine threedimensional CFD guidelines for the calculation of the turbulent flow over a structure immersed in an atmospheric boundary layer. To this purpose, a complete validation campaign has been performed through a systematic comparison of numerical simulations with wind tunnel experimental data. Wind tunnel measurements and numerical predictions have been compared for five different vertical positions, respectively from the upstream leading edge to the downstream bottom edge of the analyzed model. Flow field characteristics in the neighborhood of the building model have been numerically investigated, allowing a quantification of the capabilities of the CFD code to predict the flow separation and the extension of the recirculation regions. The proposed calculations have allowed the development of a preliminary procedure to be used as guidance in selecting the appropriate grid configuration and corresponding turbulence model for the prediction of the flow field over a three-dimensional roof architecture dominated by flow separation.

Keywords: CFD, roof, building, wind

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1702
9591 A Semi-Implicit Phase Field Model for Droplet Evolution

Authors: M. H. Kazemi, D. Salac

Abstract:

A semi-implicit phase field method for droplet evolution is proposed. Using the phase field Cahn-Hilliard equation, we are able to track the interface in multiphase flow. The idea of a semi-implicit finite difference scheme is reviewed and employed to solve two nonlinear equations, including the Navier-Stokes and the Cahn-Hilliard equations. The use of a semi-implicit method allows us to have larger time steps compared to explicit schemes. The governing equations are coupled and then solved by a GMRES solver (generalized minimal residual method) using modified Gram-Schmidt orthogonalization. To show the validity of the method, we apply the method to the simulation of a rising droplet, a leaky dielectric drop and the coalescence of drops. The numerical solutions to the phase field model match well with existing solutions over a defined range of variables.

Keywords: Coalescence, leaky dielectric, numerical method, phase field, rising droplet, semi-implicit method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 851
9590 Simulation of Piezoelectric Laminated Smart Structure under Strong Electric Field

Authors: Shun-Qi Zhang, Shu-Yang Zhang, Min Chen

Abstract:

Applying strong electric field on piezoelectric actuators, on one hand very significant electroelastic material nonlinear effects will occur, on the other hand piezo plates and shells may undergo large displacements and rotations. In order to give a precise prediction of piezolaminated smart structures under large electric field, this paper develops a finite element (FE) model accounting for both electroelastic material nonlinearity and geometric nonlinearity with large rotations based on the first order shear deformation (FSOD) hypothesis. The proposed FE model is applied to analyze a piezolaminated semicircular shell structure.

Keywords: Smart structures, piezolamintes, material nonlinearity, geometric nonlinearity, strong electric field.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1006
9589 Spatially Random Sampling for Retail Food Risk Factors Study

Authors: Guilan Huang

Abstract:

In 2013 and 2014, the U.S. Food and Drug Administration (FDA) collected data from selected fast food restaurants and full service restaurants for tracking changes in the occurrence of foodborne illness risk factors. This paper discussed how we customized spatial random sampling method by considering financial position and availability of FDA resources, and how we enriched restaurants data with location. Location information of restaurants provides opportunity for quantitatively determining random sampling within non-government units (e.g.: 240 kilometers around each data-collector). Spatial analysis also could optimize data-collectors’ work plans and resource allocation. Spatial analytic and processing platform helped us handling the spatial random sampling challenges. Our method fits in FDA’s ability to pinpoint features of foodservice establishments, and reduced both time and expense on data collection.

Keywords: Geospatial technology, restaurant, retail food risk factors study, spatial random sampling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1428
9588 Using Fractional Factorial Designs for Variable Importance in Random Forest Models

Authors: Ewa. M. Sztendur, Neil T. Diamond

Abstract:

Random Forests are a powerful classification technique, consisting of a collection of decision trees. One useful feature of Random Forests is the ability to determine the importance of each variable in predicting the outcome. This is done by permuting each variable and computing the change in prediction accuracy before and after the permutation. This variable importance calculation is similar to a one-factor-at a time experiment and therefore is inefficient. In this paper, we use a regular fractional factorial design to determine which variables to permute. Based on the results of the trials in the experiment, we calculate the individual importance of the variables, with improved precision over the standard method. The method is illustrated with a study of student attrition at Monash University.

Keywords: Random Forests, Variable Importance, Fractional Factorial Designs, Student Attrition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1967
9587 A Frequency Dependence of the Phase Field Model in Laminar Boundary Layer with Periodic Perturbations

Authors: Yasuo Obikane

Abstract:

The frequency dependence of the phase field model(PFM) is studied. A simple PFM is proposed, and is tested in a laminar boundary layer. The Blasius-s laminar boundary layer solution on a flat plate is used for the flow pattern, and several frequencies are imposed on the PFM, and the decay times of the interfaces are obtained. The computations were conducted for three cases: 1) no-flow, and 2) a half ball on the laminar boundary layer, 3) a line of mass sources in the laminar boundary layer. The computations show the decay time becomes shorter as the frequency goes larger, and also show that it is sensitive to both background disturbances and surface tension parameters. It is concluded that the proposed simple PFM can describe the properties of decay process, and could give the fundamentals for the decay of the interface in turbulent flows.

Keywords: Phase field model, two phase flows, Laminarboundary Layer

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1486
9586 Artificial Intelligence-Based Detection of Individuals Suffering from Vestibular Disorder

Authors: D. Hişam, S. İkizoğlu

Abstract:

Identifying the problem behind balance disorder is one of the most interesting topics in medical literature. This study has considerably enhanced the development of artificial intelligence (AI) algorithms applying multiple machine learning (ML) models to sensory data on gait collected from humans to classify between normal people and those suffering from Vestibular System (VS) problems. Although AI is widely utilized as a diagnostic tool in medicine, AI models have not been used to perform feature extraction and identify VS disorders through training on raw data. In this study, three ML models, the Random Forest Classifier (RF), Extreme Gradient Boosting (XGB), and K-Nearest Neighbor (KNN), have been trained to detect VS disorder, and the performance comparison of the algorithms has been made using accuracy, recall, precision, and f1-score. With an accuracy of 95.28 %, Random Forest (RF) Classifier was the most accurate model.

Keywords: Vestibular disorder, machine learning, random forest classifier, k-nearest neighbor, extreme gradient boosting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 120
9585 Effect of Non Uniformity Factors and Assignment Factors on Errors in Charge Simulation Method with Point Charge Model

Authors: Gururaj S Punekar, N K Kishore Senior, H S Y Shastry

Abstract:

Charge Simulation Method (CSM) is one of the very widely used numerical field computation technique in High Voltage (HV) engineering. The high voltage fields of varying non uniformities are encountered in practice. CSM programs being case specific, the simulation accuracies heavily depend on the user (programmers) experience. Here is an effort to understand CSM errors and evolve some guidelines to setup accurate CSM models, relating non uniformities with assignment factors. The results are for the six-point-charge model of sphere-plane gap geometry. Using genetic algorithm (GA) as tool, optimum assignment factors at different non uniformity factors for this model have been evaluated and analyzed. It is shown that the symmetrically placed six-point-charge models can be good enough to set up CSM programs with potential errors less than 0.1% when the field non uniformity factor is greater than 2.64 (field utilization factor less than 52.76%).

Keywords: Assignment factor, Charge Simulation Method, High Voltage, Numerical field computation, Non uniformity factor, Simulation errors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2012
9584 Monotonicity of Dependence Concepts from Independent Random Vector into Dependent Random Vector

Authors: Guangpu Chen

Abstract:

When the failure function is monotone, some monotonic reliability methods are used to gratefully simplify and facilitate the reliability computations. However, these methods often work in a transformed iso-probabilistic space. To this end, a monotonic simulator or transformation is needed in order that the transformed failure function is still monotone. This note proves at first that the output distribution of failure function is invariant under the transformation. And then it presents some conditions under which the transformed function is still monotone in the newly obtained space. These concern the copulas and the dependence concepts. In many engineering applications, the Gaussian copulas are often used to approximate the real word copulas while the available information on the random variables is limited to the set of marginal distributions and the covariances. So this note catches an importance on the conditional monotonicity of the often used transformation from an independent random vector into a dependent random vector with Gaussian copulas.

Keywords: Monotonic, Rosenblatt, Nataf transformation, dependence concepts, completely positive matrices, Gaussiancopulas

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1184
9583 Behavior Model Mapping and Transformation using Model-Driven Architecture

Authors: Mohammed Abdalla Osman Mukhtar, Azween Abdullah, Alan Giffin Downe

Abstract:

Model mapping and transformation are important processes in high level system abstractions, and form the cornerstone of model-driven architecture (MDA) techniques. Considerable research in this field has devoted attention to static system abstraction, despite the fact that most systems are dynamic with high frequency changes in behavior. In this paper we provide an overview of work that has been done with regard to behavior model mapping and transformation, based on: (1) the completeness of the platform independent model (PIM); (2) semantics of behavioral models; (3) languages supporting behavior model transformation processes; and (4) an evaluation of model composition to effect the best approach to describing large systems with high complexity.

Keywords: MDA; PIM, PSM, QVT, Model Transformation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1718
9582 A Numerical Simulation of Arterial Mass Transport in Presence of Magnetic Field-Links to Atherosclerosis

Authors: H. Aminfar, M. Mohammadpourfard, K. Khajeh

Abstract:

This paper has focused on the most important parameters in the LSC uptake; inlet Re number and Sc number in the presence of non-uniform magnetic field. The magnetic field is arising from the thin wire with electric current placed vertically to the arterial blood vessel. According to the results of this study, applying magnetic field can be a treatment for atherosclerosis by reducing LSC along the vessel wall. Homogeneous porous layer as a arterial wall has been regarded. Blood flow has been considered laminar and incompressible containing Ferro fluid (blood and 4 % vol. Fe3O4) under steady state conditions. Numerical solution of governing equations was obtained by using the single-phase model and control volume technique for flow field.

Keywords: LDL Surface Concentration (LSC), Magnetic field, Computational fluid dynamics, Porous wall.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1544
9581 Using Data Clustering in Oral Medicine

Authors: Fahad Shahbaz Khan, Rao Muhammad Anwer, Olof Torgersson

Abstract:

The vast amount of information hidden in huge databases has created tremendous interests in the field of data mining. This paper examines the possibility of using data clustering techniques in oral medicine to identify functional relationships between different attributes and classification of similar patient examinations. Commonly used data clustering algorithms have been reviewed and as a result several interesting results have been gathered.

Keywords: Oral Medicine, Cluto, Data Clustering, Data Mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1948
9580 Optimizing the Probabilistic Neural Network Training Algorithm for Multi-Class Identification

Authors: Abdelhadi Lotfi, Abdelkader Benyettou

Abstract:

In this work, a training algorithm for probabilistic neural networks (PNN) is presented. The algorithm addresses one of the major drawbacks of PNN, which is the size of the hidden layer in the network. By using a cross-validation training algorithm, the number of hidden neurons is shrunk to a smaller number consisting of the most representative samples of the training set. This is done without affecting the overall architecture of the network. Performance of the network is compared against performance of standard PNN for different databases from the UCI database repository. Results show an important gain in network size and performance.

Keywords: Classification, probabilistic neural networks, network optimization, pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1185
9579 An Alternative Method for Generating Almost Infinite Sequence of Gaussian Variables

Authors: Nyah C. Temaneh, F. A. Phiri, E. Ruhunga

Abstract:

Most of the well known methods for generating Gaussian variables require at least one standard uniform distributed value, for each Gaussian variable generated. The length of the random number generator therefore, limits the number of independent Gaussian distributed variables that can be generated meanwhile the statistical solution of complex systems requires a large number of random numbers for their statistical analysis. We propose an alternative simple method of generating almost infinite number of Gaussian distributed variables using a limited number of standard uniform distributed random numbers.

Keywords: Gaussian variable, statistical analysis, simulation ofCommunication Network, Random numbers.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1447
9578 Engine Power Effects on Support Interference

Authors: B.J.C. Horsten, L.L.M. Veldhuis

Abstract:

Renewed interest in propeller propulsion on aircraft configurations combined with higher propeller loads lead to the question how the effects of the propulsion on model support disturbances should be accounted for. In this paper, the determination of engine power effects on support interference of sting-mounted models is demonstrated by a measurement on a four-engine turboprop aircraft. CFD results on a more generic model are presented in order to clarify the possible mechanism behind engine power effects on support interference. The engine slipstream induces a local change in angle of sideslip at the model sting thereby influencing the sting near-field and far-field effects. Whether or not the net result of these changes in the disturbance pattern leads to a significant engine power effect depends on the configuration of the wind tunnel model and the test setup.

Keywords: CFD, engine power effects, measurements, support interference.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1453
9577 Measurement and Analysis of Temperature Effects on Box Girders of Continuous Rigid Frame Bridges

Authors: Bugao Wang, Weifeng Wang, Xianwei Zeng

Abstract:

Researches on the general rules of temperature field changing and their effects on the bridge in construction are necessary. This paper investigated the rules of temperature field changing and its effects on bridge using onsite measurement and computational analysis. Guanyinsha Bridge was used as a case study in this research. The temperature field was simulated in analyses. The effects of certain boundary conditions such as sun radiance, wind speed, and model parameters such as heat factor and specific heat on temperature field are investigated. Recommended values for these parameters are proposed. The simulated temperature field matches the measured observations with high accuracy. At the same time, the stresses and deflections of the bridge computed with the simulated temperature field matches measured values too. As a conclusion, the temperature effect analysis of reinforced concrete box girder can be conducted directly based on the reliable weather data of the concerned area.

Keywords: continuous rigid frame bridge, temperature effectanalysis, temperature field, temperature field simulation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2542
9576 A New Approach to Feedback Shift Registers

Authors: Myat Su Mon Win

Abstract:

The pseudorandom number generators based on linear feedback shift registers (LFSRs), are very quick, easy and secure in the implementation of hardware and software. Thus they are very popular and widely used. But LFSRs lead to fairly easy cryptanalysis due to their completely linearity properties. In this paper, we propose a stochastic generator, which is called Random Feedback Shift Register (RFSR), using stochastic transformation (Random block) with one-way and non-linearity properties.

Keywords: Linear Feedback Shift Register, Non Linearity, R_Block, Random Feedback Shift Register

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1783
9575 Dynamic Variation in Nano-Scale CMOS SRAM Cells Due to LF/RTS Noise and Threshold Voltage

Authors: M. Fadlallah, G. Ghibaudo, C. G. Theodorou

Abstract:

The dynamic variation in memory devices such as the Static Random Access Memory can give errors in read or write operations. In this paper, the effect of low-frequency and random telegraph noise on the dynamic variation of one SRAM cell is detailed. The effect on circuit noise, speed, and length of time of processing is examined, using the Supply Read Retention Voltage and the Read Static Noise Margin. New test run methods are also developed. The obtained results simulation shows the importance of noise caused by dynamic variation, and the impact of Random Telegraph noise on SRAM variability is examined by evaluating the statistical distributions of Random Telegraph noise amplitude in the pull-up, pull-down. The threshold voltage mismatch between neighboring cell transistors due to intrinsic fluctuations typically contributes to larger reductions in static noise margin. Also the contribution of each of the SRAM transistor to total dynamic variation has been identified.

Keywords: Low-frequency noise, Random Telegraph Noise, Dynamic Variation, SRRV.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 681
9574 Application of BP Neural Network Model in Sports Aerobics Performance Evaluation

Authors: Shuhe Shao

Abstract:

This article provides partial evaluation index and its standard of sports aerobics, including the following 12 indexes: health vitality, coordination, flexibility, accuracy, pace, endurance, elasticity, self-confidence, form, control, uniformity and musicality. The three-layer BP artificial neural network model including input layer, hidden layer and output layer is established. The result shows that the model can well reflect the non-linear relationship between the performance of 12 indexes and the overall performance. The predicted value of each sample is very close to the true value, with a relative error fluctuating around of 5%, and the network training is successful. It shows that BP network has high prediction accuracy and good generalization capacity if being applied in sports aerobics performance evaluation after effective training.

Keywords: BP neural network, sports aerobics, performance, evaluation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1594
9573 Data Oriented Modeling of Uniform Random Variable: Applied Approach

Authors: Ahmad Habibizad Navin, Mehdi Naghian Fesharaki, Mirkamal Mirnia, Mohamad Teshnelab, Ehsan Shahamatnia

Abstract:

In this paper we introduce new data oriented modeling of uniform random variable well-matched with computing systems. Due to this conformity with current computers structure, this modeling will be efficiently used in statistical inference.

Keywords: Uniform random variable, Data oriented modeling, Statistical inference, Prodigraph, Statistically complete tree, Uniformdigital probability digraph, Uniform n-complete probability tree.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1600
9572 Application of Feed-Forward Neural Networks Autoregressive Models in Gross Domestic Product Prediction

Authors: Ε. Giovanis

Abstract:

In this paper we present an autoregressive model with neural networks modeling and standard error backpropagation algorithm training optimization in order to predict the gross domestic product (GDP) growth rate of four countries. Specifically we propose a kind of weighted regression, which can be used for econometric purposes, where the initial inputs are multiplied by the neural networks final optimum weights from input-hidden layer after the training process. The forecasts are compared with those of the ordinary autoregressive model and we conclude that the proposed regression-s forecasting results outperform significant those of autoregressive model in the out-of-sample period. The idea behind this approach is to propose a parametric regression with weighted variables in order to test for the statistical significance and the magnitude of the estimated autoregressive coefficients and simultaneously to estimate the forecasts.

Keywords: Autoregressive model, Error back-propagation Feed-Forward neural networks, , Gross Domestic Product

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1400
9571 Application of Feed-Forward Neural Networks Autoregressive Models with Genetic Algorithm in Gross Domestic Product Prediction

Authors: E. Giovanis

Abstract:

In this paper we present a Feed-Foward Neural Networks Autoregressive (FFNN-AR) model with genetic algorithms training optimization in order to predict the gross domestic product growth of six countries. Specifically we propose a kind of weighted regression, which can be used for econometric purposes, where the initial inputs are multiplied by the neural networks final optimum weights from input-hidden layer of the training process. The forecasts are compared with those of the ordinary autoregressive model and we conclude that the proposed regression-s forecasting results outperform significant those of autoregressive model. Moreover this technique can be used in Autoregressive-Moving Average models, with and without exogenous inputs, as also the training process with genetics algorithms optimization can be replaced by the error back-propagation algorithm.

Keywords: Autoregressive model, Feed-Forward neuralnetworks, Genetic Algorithms, Gross Domestic Product

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1644
9570 Implementation of an Associative Memory Using a Restricted Hopfield Network

Authors: Tet H. Yeap

Abstract:

An analog restricted Hopfield Network is presented in this paper. It consists of two layers of nodes, visible and hidden nodes, connected by directional weighted paths forming a bipartite graph with no intralayer connection. An energy or Lyapunov function was derived to show that the proposed network will converge to stable states. By introducing hidden nodes, the proposed network can be trained to store patterns and has increased memory capacity. Training to be an associative memory, simulation results show that the associative memory performs better than a classical Hopfield network by being able to perform better memory recall when the input is noisy.

Keywords: Associative memory, Hopfield network, Lyapunov function, Restricted Hopfield network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 450
9569 A High Bitrate Information Hiding Algorithm for Video in Video

Authors: Wang Shou-Dao, Xiao Chuang-Bai, Lin Yu

Abstract:

In high bitrate information hiding techniques, 1 bit is embedded within each 4 x 4 Discrete Cosine Transform (DCT) coefficient block by means of vector quantization, then the hidden bit can be effectively extracted in terminal end. In this paper high bitrate information hiding algorithms are summarized, and the scheme of video in video is implemented. Experimental result shows that the host video which is embedded numerous auxiliary information have little visually quality decline. Peak Signal to Noise Ratio (PSNR)Y of host video only degrades 0.22dB in average, while the hidden information has a high percentage of survives and keeps a high robustness in H.264/AVC compression, the average Bit Error Rate(BER) of hiding information is 0.015%.

Keywords: Information Hiding, Embed, Quantification, Extract

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1864
9568 Experimental and Theoretical Investigation of Rough Rice Drying in Infrared-assisted Hot Air Dryer Using Artificial Neural Network

Authors: D. Zare, H. Naderi, A. A. Jafari

Abstract:

Drying characteristics of rough rice (variety of lenjan) with an initial moisture content of 25% dry basis (db) was studied in a hot air dryer assisted by infrared heating. Three arrival air temperatures (30, 40 and 500C) and four infrared radiation intensities (0, 0.2 , 0.4 and 0.6 W/cm2) and three arrival air speeds (0.1, 0.15 and 0.2 m.s-1) were studied. Bending strength of brown rice kernel, percentage of cracked kernels and time of drying were measured and evaluated. The results showed that increasing the drying arrival air temperature and radiation intensity of infrared resulted decrease in drying time. High bending strength and low percentage of cracked kernel was obtained when paddy was dried by hot air assisted infrared dryer. Between this factors and their interactive effect were a significant difference (p<0.01). An intensity level of 0.2 W/cm2 was found to be optimum for radiation drying. Furthermore, in the present study, the application of Artificial Neural Network (ANN) for predicting the moisture content during drying (output parameter for ANN modeling) was investigated. Infrared Radiation intensity, drying air temperature, arrival air speed and drying time were considered as input parameters for the model. An ANN model with two hidden layers with 8 and 14 neurons were selected for studying the influence of transfer functions and training algorithms. The results revealed that a network with the Tansig (hyperbolic tangent sigmoid) transfer function and trainlm (Levenberg-Marquardt) back propagation algorithm made the most accurate predictions for the paddy drying system. Mean square error (MSE) was calculated and found that the random errors were within and acceptable range of ±5% with coefficient of determination (R2) of 99%.

Keywords: Rough rice, Infrared-hot air, Artificial Neural Network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1800