Search results for: Number of neurons in the hidden layer.

Authors: Ehsan Amid, Sina Rezaei Aghdam

Abstract:

In this paper, a novel method for recognition of musical instruments in a polyphonic music is presented by using an embedded hidden Markov model (EHMM). EHMM is a doubly embedded HMM structure where each state of the external HMM is an independent HMM. The classification is accomplished for two different internal HMM structures where GMMs are used as likelihood estimators for the internal HMMs. The results are compared to those achieved by an artificial neural network with two hidden layers. Appropriate classification accuracies were achieved both for solo instrument performance and instrument combinations which demonstrates that the new approach outperforms the similar classification methods by means of the dynamic of the signal.

Keywords: hidden Markov model (HMM), embedded hidden Markov models (EHMM), MFCC, musical instrument.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1846

Authors: Said M. Easa, Ahmed Shaker

Abstract:

The hidden-point bar method is useful in many surveying applications. The method involves determining the coordinates of a hidden point as a function of horizontal and vertical angles measured to three fixed points on the bar. Using these measurements, the procedure involves calculating the slant angles, the distances from the station to the fixed points, the coordinates of the fixed points, and then the coordinates of the hidden point. The propagation of the measurement errors in this complex process has not been fully investigated in the literature. This paper evaluates the effect of the bar geometry on the position accuracy of the hidden point which depends on the measurement errors of the horizontal and vertical angles. The results are used to establish some guidelines regarding the inclination angle of the bar and the location of the observed points that provide the best accuracy.

Keywords: Hidden point, accuracy, error propagation, surveying, evaluation, simulation, geometry.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1679

Authors: Nam Lethanh, Bryan T. Adey

Abstract:

In this paper, the potential use of an exponential hidden Markov model to model a hidden pavement deterioration process, i.e. one that is not directly measurable, is investigated. It is assumed that the evolution of the physical condition, which is the hidden process, and the evolution of the values of pavement distress indicators, can be adequately described using discrete condition states and modeled as a Markov processes. It is also assumed that condition data can be collected by visual inspections over time and represented continuously using an exponential distribution. The advantage of using such a model in decision making process is illustrated through an empirical study using real world data.

Keywords: Deterioration modeling, Exponential distribution, Hidden Markov model, Pavement management

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2260

Authors: Zhanli Zhang, Wei Chen, Xin Jiang, Lili Ma, Shaoting Tang, Zhiming Zheng

Abstract:

A new class of percolation model in complex networks, in which nodes are characterized by hidden variables reflecting the properties of nodes and the occupied probability of each link is determined by the hidden variables of the end nodes, is studied in this paper. By the mean field theory, the analytical expressions for the phase of percolation transition is deduced. It is determined by the distribution of the hidden variables for the nodes and the occupied probability between pairs of them. Moreover, the analytical expressions obtained are checked by means of numerical simulations on a particular model. Besides, the general model can be applied to describe and control practical diffusion models, such as disease diffusion model, scientists cooperation networks, and so on.

Keywords: complex networks, percolation transition, hidden variable, occupied probability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1564

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in VerilogHDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: Auto-encoder, Behavior model simulation, Digital hardware design, Pre-route simulation, Unsupervised feature learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2646

Authors: N. A. Salim, M. M. Othman, I. Musirin, M. S. Serwan

Abstract:

Protection system hidden failures have been identified as one of the main causes of system cascading collapse resulting to power system instability. In this paper, a systematic approach is presented in order to identify the probability of a system cascading collapse by taking into consideration the effect of protection system hidden failure. This includes the accurate calculation of the probability of hidden failure as it will provide significant impinge on the findings of the probability of system cascading collapse. The probability of a system cascading collapse is then used to identify the initial tripping of sensitive transmission lines which will contribute to a critical system cascading collapse. Based on the results obtained from this study, it is important to decide on the accurate value of the hidden failure probability as it will affect the probability of a system cascading collapse.

Keywords: Critical system cascading collapse, hidden failure, probability of cascading collapse, sensitive transmission lines.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1745

Authors: Parvinder S. Sandhu, Sandeep Khimta, Kiranpreet Kaur

Abstract:

The prediction of Software quality during development life cycle of software project helps the development organization to make efficient use of available resource to produce the product of highest quality. “Whether a module is faulty or not" approach can be used to predict quality of a software module. There are numbers of software quality prediction models described in the literature based upon genetic algorithms, artificial neural network and other data mining algorithms. One of the promising aspects for quality prediction is based on clustering techniques. Most quality prediction models that are based on clustering techniques make use of K-means, Mixture-of-Guassians, Self-Organizing Map, Neural Gas and fuzzy K-means algorithm for prediction. In all these techniques a predefined structure is required that is number of neurons or clusters should be known before we start clustering process. But in case of Growing Neural Gas there is no need of predetermining the quantity of neurons and the topology of the structure to be used and it starts with a minimal neurons structure that is incremented during training until it reaches a maximum number user defined limits for clusters. Hence, in this work we have used Growing Neural Gas as underlying cluster algorithm that produces the initial set of labeled cluster from training data set and thereafter this set of clusters is used to predict the quality of test data set of software modules. The best testing results shows 80% accuracy in evaluating the quality of software modules. Hence, the proposed technique can be used by programmers in evaluating the quality of modules during software development.

Keywords: Growing Neural Gas, data clustering, fault prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1819

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In this paper, an approach to reduce the computation steps required by fast neural networksfor the searching process is presented. The principle ofdivide and conquer strategy is applied through imagedecomposition. Each image is divided into small in sizesub-images and then each one is tested separately usinga fast neural network. The operation of fast neuralnetworks based on applying cross correlation in thefrequency domain between the input image and theweights of the hidden neurons. Compared toconventional and fast neural networks, experimentalresults show that a speed up ratio is achieved whenapplying this technique to locate human facesautomatically in cluttered scenes. Furthermore, fasterface detection is obtained by using parallel processingtechniques to test the resulting sub-images at the sametime using the same number of fast neural networks. Incontrast to using only fast neural networks, the speed upratio is increased with the size of the input image whenusing fast neural networks and image decomposition.

Keywords: Fast Neural Networks, 2D-FFT, CrossCorrelation, Image decomposition, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2127

Authors: Md. Ashikur Rahman Khan, M. M. Rahman, K. Kadirgama, M.A. Maleque, Rosli A. Bakar

Abstract:

Conventionally the selection of parameters depends intensely on the operator-s experience or conservative technological data provided by the EDM equipment manufacturers that assign inconsistent machining performance. The parameter settings given by the manufacturers are only relevant with common steel grades. A single parameter change influences the process in a complex way. Hence, the present research proposes artificial neural network (ANN) models for the prediction of surface roughness on first commenced Ti-15-3 alloy in electrical discharge machining (EDM) process. The proposed models use peak current, pulse on time, pulse off time and servo voltage as input parameters. Multilayer perceptron (MLP) with three hidden layer feedforward networks are applied. An assessment is carried out with the models of distinct hidden layer. Training of the models is performed with data from an extensive series of experiments utilizing copper electrode as positive polarity. The predictions based on the above developed models have been verified with another set of experiments and are found to be in good agreement with the experimental results. Beside this they can be exercised as precious tools for the process planning for EDM.

Keywords: Ti-15l-3, surface roughness, copper, positive polarity, multi-layered perceptron.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1853

Authors: Samit Ari, Goutam Saha

Abstract:

Artificial Neural Network (ANN) has been extensively used for classification of heart sounds for its discriminative training ability and easy implementation. However, it suffers from overparameterization if the number of nodes is not chosen properly. In such cases, when the dataset has redundancy within it, ANN is trained along with this redundant information that results in poor validation. Also a larger network means more computational expense resulting more hardware and time related cost. Therefore, an optimum design of neural network is needed towards real-time detection of pathological patterns, if any from heart sound signal. The aims of this work are to (i) select a set of input features that are effective for identification of heart sound signals and (ii) make certain optimum selection of nodes in the hidden layer for a more effective ANN structure. Here, we present an optimization technique that involves Singular Value Decomposition (SVD) and QR factorization with column pivoting (QRcp) methodology to optimize empirically chosen over-parameterized ANN structure. Input nodes present in ANN structure is optimized by SVD followed by QRcp while only SVD is required to prune undesirable hidden nodes. The result is presented for classifying 12 common pathological cases and normal heart sound.

Keywords: ANN, Classification of heart diseases, murmurs, optimization, Phonocardiogram, QRcp, SVD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2014

Authors: Ali Keshavarzi, Fereydoon Sarmadian

Abstract:

Investigation of soil properties like Cation Exchange Capacity (CEC) plays important roles in study of environmental reaserches as the spatial and temporal variability of this property have been led to development of indirect methods in estimation of this soil characteristic. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from more readily available soil data. 70 soil samples were collected from different horizons of 15 soil profiles located in the Ziaran region, Qazvin province, Iran. Then, multivariate regression and neural network model (feedforward back propagation network) were employed to develop a pedotransfer function for predicting soil parameter using easily measurable characteristics of clay and organic carbon. The performance of the multivariate regression and neural network model was evaluated using a test data set. In order to evaluate the models, root mean square error (RMSE) was used. The value of RMSE and R2 derived by ANN model for CEC were 0.47 and 0.94 respectively, while these parameters for multivariate regression model were 0.65 and 0.88 respectively. Results showed that artificial neural network with seven neurons in hidden layer had better performance in predicting soil cation exchange capacity than multivariate regression.

Keywords: Easily measurable characteristics, Feed-forwardback propagation, Pedotransfer functions, CEC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2172

Authors: Terrence Chen, Thomas S. Huang

Abstract:

In this paper, we present the region based hidden Markov random field model (RBHMRF), which encodes the characteristics of different brain regions into a probabilistic framework for brain MR image segmentation. The recently proposed TV+L1 model is used for region extraction. By utilizing different spatial characteristics in different brain regions, the RMHMRF model performs beyond the current state-of-the-art method, the hidden Markov random field model (HMRF), which uses identical spatial information throughout the whole brain. Experiments on both real and synthetic 3D MR images show that the segmentation result of the proposed method has higher accuracy compared to existing algorithms.

Keywords: Finite Gaussian mixture model, Hidden Markov random field model, image segmentation, MRI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2054

Authors: A. Mirzaaghazadeh, H. Motameni, M. Karshenas, H. Nematzadeh

Abstract:

Learning the gradient of neuron's activity function like the weight of links causes a new specification which is flexibility. In flexible neural networks because of supervising and controlling the operation of neurons, all the burden of the learning is not dedicated to the weight of links, therefore in each period of learning of each neuron, in fact the gradient of their activity function, cooperate in order to achieve the goal of learning thus the number of learning will be decreased considerably. Furthermore, learning neurons parameters immunes them against changing in their inputs and factors which cause such changing. Likewise initial selecting of weights, type of activity function, selecting the initial gradient of activity function and selecting a fixed amount which is multiplied by gradient of error to calculate the weight changes and gradient of activity function, has a direct affect in convergence of network for learning.

Keywords: Back propagation, Flexible, Gradient, Learning, Neural network, Pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1448

Authors: Ainon Syazana Ab. Hamid, Seripah Awang Kechil, Ahmad Sukri Abd. Aziz

Abstract:

The Marangoni convective instability in a horizontal fluid layer with the insoluble surfactant and nondeformable free surface is investigated. The surface tension at the free surface is linearly dependent on the temperature and concentration gradients. At the bottom surface, the temperature conditions of uniform temperature and uniform heat flux are considered. By linear stability theory, the exact analytical solutions for the steady Marangoni convection are derived and the marginal curves are plotted. The effects of surfactant or elasticity number, Lewis number and Biot number on the marginal Marangoni instability are assessed. The surfactant concentration gradients and the heat transfer mechanism at the free surface have stabilizing effects while the Lewis number destabilizes fluid system. The fluid system with uniform temperature condition at the bottom boundary is more stable than the fluid layer that is subjected to uniform heat flux at the bottom boundary.

Keywords: Analytical solutions, Marangoni Instability, Nondeformable free surface, Surfactant.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1793

Authors: Long Jye Sheu

Abstract:

This paper presents a linear stability analysis of natural convection in a horizontal layer of a viscoelastic nanofluid. The Oldroyd B model was utilized to describe the rheological behavior of a viscoelastic nanofluid. The model used for the nanofluid incorporated the effects of Brownian motion and thermophoresis. The onset criterion for stationary and oscillatory convection was derived analytically. The effects of the Deborah number, retardation parameters, concentration Rayleigh number, Prandtl number, and Lewis number on the stability of the system were investigated. Results indicated that there was competition among the processes of thermophoresis, Brownian diffusion, and viscoelasticity which caused oscillatory rather than stationary convection to occur. Oscillatory instability is possible with both bottom- and top-heavy nanoparticle distributions. Regimes of stationary and oscillatory convection for various parameters were derived and are discussed in detail.

Keywords: instability, viscoelastic, nanofluids, oscillatory, Brownian, thermophoresis

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2745

Authors: N. Bachok, N. L. Aleng, N. M. Arifin, A. Ishak, N. Senu

Abstract:

The problem of laminar fluid flow which results from the shrinking of a permeable surface in a nanofluid has been investigated numerically. The model used for the nanofluid incorporates the effects of Brownian motion and thermophoresis. A similarity solution is presented which depends on the mass suction parameter S, Prandtl number Pr, Lewis number Le, Brownian motion number Nb and thermophoresis number Nt. It was found that the reduced Nusselt number is decreasing function of each dimensionless number.

Keywords: Boundary layer, Nanofluid, Shrinking sheet, Brownian motion, Thermophoresis, Similarity solution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2755

Authors: Ami Nomura, Ken Imanishi, Yukinori Taniguchi, Etsuko Ueda, Tadahiro Wada, Shinichi Enoki

Abstract:

Recently, there have been a lot of earthquakes in Japan. It is necessary to promote seismic isolation devices for buildings. The devices have been hardly diffused in attached houses, because the devices are very expensive. We should develop a low-cost seismic isolation device for detached houses. We suggested a new seismic isolation device which uses a two-layer circular tube as a unit. If hysteresis is produced in the two-layer circular tube under lateral compression load, we think that the two-layer circular tube can have energy absorbing capacity. It is necessary to contact the outer layer and the inner layer to produce hysteresis. We have previously reported how the inner layer comes in contact with the outer layer from a perspective of analysis used mechanics of materials. We have clarified that the inner layer comes in contact with the outer layer under a lateral compression load. In this paper, we explored contact area between the outer layer and the inner layer under a lateral compression load by using FEA. We think that changing the inner layer’s thickness is effective in increase the contact area. In order to change the inner layer’s thickness, we changed the shape of the inner layer. As a result, the contact area changes depending on the inner layer’s thickness. Additionally, we experimented to check whether hysteresis occurs in fact. As a consequence, we can reveal hysteresis in the two-layer circular tube under the condition.

Keywords: Contact area, energy absorbing capacity, hysteresis, seismic isolation device.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1948

Authors: Zöhre Kara Kayikci, Günther Palm

Abstract:

A word recognition architecture based on a network of neural associative memories and hidden Markov models has been developed. The input stream, composed of subword-units like wordinternal triphones consisting of diphones and triphones, is provided to the network of neural associative memories by hidden Markov models. The word recognition network derives words from this input stream. The architecture has the ability to handle ambiguities on subword-unit level and is also able to add new words to the vocabulary during performance. The architecture is implemented to perform the word recognition task in a language processing system for understanding simple command sentences like “bot show apple".

Keywords: Hebbian learning, hidden Markov models, neuralassociative memories, word recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1470

Authors: Fereydoon Sarmadian, Ali Keshavarzi

Abstract:

Study of soil properties like field capacity (F.C.) and permanent wilting point (P.W.P.) play important roles in study of soil moisture retention curve. Although these parameters can be measured directly, their measurement is difficult and expensive. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from more readily available soil data. In this investigation, 70 soil samples were collected from different horizons of 15 soil profiles located in the Ziaran region, Qazvin province, Iran. The data set was divided into two subsets for calibration (80%) and testing (20%) of the models and their normality were tested by Kolmogorov-Smirnov method. Both multivariate regression and artificial neural network (ANN) techniques were employed to develop the appropriate PTFs for predicting soil parameters using easily measurable characteristics of clay, silt, O.C, S.P, B.D and CaCO3. The performance of the multivariate regression and ANN models was evaluated using an independent test data set. In order to evaluate the models, root mean square error (RMSE) and R2 were used. The comparison of RSME for two mentioned models showed that the ANN model gives better estimates of F.C and P.W.P than the multivariate regression model. The value of RMSE and R2 derived by ANN model for F.C and P.W.P were (2.35, 0.77) and (2.83, 0.72), respectively. The corresponding values for multivariate regression model were (4.46, 0.68) and (5.21, 0.64), respectively. Results showed that ANN with five neurons in hidden layer had better performance in predicting soil properties than multivariate regression.

Keywords: Artificial neural network, Field capacity, Permanentwilting point, Pedotransfer functions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1772

Authors: Khaing Win Mar, Thinn Thu Naing

Abstract:

Nowadays, precipitation prediction is required for proper planning and management of water resources. Prediction with neural network models has received increasing interest in various research and application domains. However, it is difficult to determine the best neural network architecture for prediction since it is not immediately obvious how many input or hidden nodes are used in the model. In this paper, neural network model is used as a forecasting tool. The major aim is to evaluate a suitable neural network model for monthly precipitation mapping of Myanmar. Using 3-layerd neural network models, 100 cases are tested by changing the number of input and hidden nodes from 1 to 10 nodes, respectively, and only one outputnode used. The optimum model with the suitable number of nodes is selected in accordance with the minimum forecast error. In measuring network performance using Root Mean Square Error (RMSE), experimental results significantly show that 3 inputs-10 hiddens-1 output architecture model gives the best prediction result for monthly precipitation in Myanmar.

Keywords: Precipitation prediction, monthly precipitation, neural network models, Myanmar.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1700

Authors: Hsin-Chang Yang, Chung-Hong Lee, Kuo-Lung Ke

Abstract:

The self-organizing map (SOM) model is a well-known neural network model with wide spread of applications. The main characteristics of SOM are two-fold, namely dimension reduction and topology preservation. Using SOM, a high-dimensional data space will be mapped to some low-dimensional space. Meanwhile, the topological relations among data will be preserved. With such characteristics, the SOM was usually applied on data clustering and visualization tasks. However, the SOM has main disadvantage of the need to know the number and structure of neurons prior to training, which are difficult to be determined. Several schemes have been proposed to tackle such deficiency. Examples are growing/expandable SOM, hierarchical SOM, and growing hierarchical SOM. These schemes could dynamically expand the map, even generate hierarchical maps, during training. Encouraging results were reported. Basically, these schemes adapt the size and structure of the map according to the distribution of training data. That is, they are data-driven or dataoriented SOM schemes. In this work, a topic-oriented SOM scheme which is suitable for document clustering and organization will be developed. The proposed SOM will automatically adapt the number as well as the structure of the map according to identified topics. Unlike other data-oriented SOMs, our approach expands the map and generates the hierarchies both according to the topics and their characteristics of the neurons. The preliminary experiments give promising result and demonstrate the plausibility of the method.

Keywords: Self-organizing map, topic identification, learning algorithm, text clustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1980

Authors: Elyas Akbari, Jafar Hasani, Newsha Dehestani, Mohammad Khaleghi, Alireza Moradi

Abstract:

The aim of the present study was to assess the effect of emotional experience induction in the mirror neurons systems (MNS) activity with regard to the spectrum of depressive symptoms. For this purpose, at first stage, 449 students of Kharazmi University of Tehran were selected randomly and completed the second version of the Beck Depression Inventory (BDI-II). Then, 36 students with standard Z-score equal or above +1.5 and equal or equal or below -1.5 were selected to construct two groups of high and low spectrum of depressive symptoms. In the next stage, the basic activity of MNS was recorded (mu wave) before presenting the positive and negative emotional video clips by Electroencephalography (EEG) technique. The findings related to emotion induction (neutral, negative and positive emotion) demonstrated that the activity of recorded mirror neuron areas had a significant difference between the depressive and non-depressive groups. These findings suggest that probably processing of negative emotions in depressive individuals is due to the idea that the mirror neurons in motor cortex matched up the activity of cognitive regions with the person’s schema. Considering the results of the present study, it could be said that the MNS provides a substrate where emotional disorders can be studied and evaluated.

Keywords: Emotional experiences, mirror neurons, depressive symptoms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1126

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: Convolutional Neural Network, Deep Learning, Deep Learning Based FER, Facial Emotion Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1305

Authors: Bhed Bahadur Bista, Danda B. Rawat

Abstract:

In this paper, we investigate multihop polling and data gathering schemes in layered sensor networks in order to extend the life time of the networks. A network consists of three layers. The lowest layer contains sensors. The middle layer contains so called super nodes with higher computational power, energy supply and longer transmission range than sensor nodes. The top layer contains a sink node. A node in each layer controls a number of nodes in lower layer by polling mechanism to gather data. We will present four types of data gathering schemes: intermediate nodes do not queue data packet, queue single packet, queue multiple packets and aggregate data, to see which data gathering scheme is more energy efficient for multihop polling in layered sensor networks.

Keywords: layered sensor network, polling, data gatheringschemes.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1522

Authors: Abdul Rahman Mohd Kasim, Mohd Ariff Admon, Sharidan Shafie

Abstract:

The present paper considers the steady free convection boundary layer flow of a viscoelastics fluid with constant temperature in the presence of heat generation. The boundary layer equations are an order higher than those for the Newtonian (viscous) fluid and the adherence boundary conditions are insufficient to determine the solution of these equations completely. The governing boundary layer equations are first transformed into non-dimensional form by using special dimensionless group. Computations are performed numerically by using Keller-box method by augmenting an extra boundary condition at infinity and the results are displayed graphically to illustrate the influence of viscoelastic K, heat generation γ , and Prandtl Number, Pr parameters on the velocity and temperature profiles. The results of the surface shear stress in terms of the local skin friction and the surface rate of heat transfer in terms of the local Nusselt number for a selection of the heat generation parameterγ (=0.0, 0.2, 0.5, 0.8, 1.0) are obtained and presented in both tabular and graphical formats. Without effect of the internal heat generation inside the fluid domain for which we take γ = 0.0, the present numerical results show an excellent agreement with previous publication.

Keywords: Free Convection, Boundary Layer, CircularCylinder, Viscoelastic Fluid, Heat Generation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1870

Authors: A.R.M. Kasim, N.F. Mohammad, Aurangzaib, S. Sharidan

Abstract:

The present paper considers the steady free convection boundary layer flow of a viscoelastic fluid on solid sphere with Newtonian heating. The boundary layer equations are an order higher than those for the Newtonian (viscous) fluid and the adherence boundary conditions are insufficient to determine the solution of these equations completely. Thus, the augmentation an extra boundary condition is needed to perform the numerical computational. The governing boundary layer equations are first transformed into non-dimensional form by using special dimensionless group and then solved by using an implicit finite difference scheme. The results are displayed graphically to illustrate the influence of viscoelastic K and Prandtl Number Pr parameters on skin friction, heat transfer, velocity profiles and temperature profiles. Present results are compared with the published papers and are found to concur very well.

Keywords: boundary layer flow, Newtonian heating, sphere, viscoelastic fluid.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2361

Authors: N. A. Salim, M. M. Othman, I. Musirin, M. S. Serwan

Abstract:

Hidden failure in a protection system has been recognized as one of the main reasons which may cause to a power system instability leading to a system cascading collapse. This paper presents a computationally systematic approach used to obtain the estimated average probability of a system cascading collapse by considering the effect of probability hidden failure in a protection system. The estimated average probability of a system cascading collapse is then used to determine the severe loading condition contributing to the higher risk of critical system cascading collapse. This information is essential to the system utility since it will assist the operator to determine the highest point of increased system loading condition prior to the event of critical system cascading collapse.

Keywords: Critical system cascading collapse, protection system hidden failure, severe loading condition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1451

Authors: G. Sarojamma, K. Vendabai

Abstract:

An analysis is carried out to investigate the effect of magnetic field and heat source on the steady boundary layer flow and heat transfer of a Casson nanofluid over a vertical cylinder stretching exponentially along its radial direction. Using a similarity transformation, the governing mathematical equations, with the boundary conditions are reduced to a system of coupled, non –linear ordinary differential equations. The resulting system is solved numerically by the fourth order Runge – Kutta scheme with shooting technique. The influence of various physical parameters such as Reynolds number, Prandtl number, magnetic field, Brownian motion parameter, thermophoresis parameter, Lewis number and the natural convection parameter are presented graphically and discussed for non – dimensional velocity, temperature and nanoparticle volume fraction. Numerical data for the skin – friction coefficient, local Nusselt number and the local Sherwood number have been tabulated for various parametric conditions. It is found that the local Nusselt number is a decreasing function of Brownian motion parameter Nb and the thermophoresis parameter Nt.

Keywords: Casson nanofluid, Boundary layer flow, Internal heat generation/absorption, Exponentially stretching cylinder, Heat transfer, Brownian motion, Thermophoresis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2768

Authors: Reham A. El-mayet, Hesham M. El-Badawy, Salwa H. Elramly

Abstract:

New generation mobile communication networks have the ability of supporting triple play. In order that, Orthogonal Frequency Division Multiplexing (OFDM) access techniques have been chosen to enlarge the system ability for high data rates networks. Many of cross-layer modeling and optimization schemes for Quality of Service (QoS) and capacity of downlink multiuser OFDM system were proposed. In this paper, the Maximum Weighted Capacity (MWC) based resource allocation at the Physical (PHY) layer is used. This resource allocation scheme provides a much better QoS than the previous resource allocation schemes, while maintaining the highest or nearly highest capacity and costing similar complexity. In addition, the Delay Satisfaction (DS) scheduling at the Medium Access Control (MAC) layer, which allows more than one connection to be served in each slot is used. This scheduling technique is more efficient than conventional scheduling to investigate both of the number of users as well as the number of subcarriers against system capacity. The system will be optimized for different operational environments: the outdoor deployment scenarios as well as the indoor deployment scenarios are investigated and also for different channel models. In addition, effective capacity approach [1] is used not only for providing QoS for different mobile users, but also to increase the total wireless network's throughput.

Keywords: Cross-layer, effective capacity, LTE, OFDM, QoS, resource allocation, wireless networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1752

Authors: Pavan K. Rallabandi, Kailash C. Patidar

Abstract:

In this paper, we present an optimization technique or a learning algorithm using the hybrid architecture by combining the most popular sequence recognition models such as Recurrent Neural Networks (RNNs) and Hidden Markov models (HMMs). In order to improve the sequence/pattern recognition/classification performance by applying a hybrid/neural symbolic approach, a gradient descent learning algorithm is developed using the Real Time Recurrent Learning of Recurrent Neural Network for processing the knowledge represented in trained Hidden Markov Models. The developed hybrid algorithm is implemented on automata theory as a sample test beds and the performance of the designed algorithm is demonstrated and evaluated on learning the deterministic finite state automata.

Keywords: Hybrid systems, Hidden Markov Models, Recurrent neural networks, Deterministic finite state automata.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2834