Search results for: RBF neural network modelling

Authors: Inam Shamsher, Zaheer Ahmad, Jehanzeb Khan Orakzai, Awais Adnan

Abstract:

This paper deals with an Optical Character Recognition system for printed Urdu, a popular Pakistani/Indian script and is the third largest understandable language in the world, especially in the subcontinent but fewer efforts are made to make it understandable to computers. Lot of work has been done in the field of literature and Islamic studies in Urdu, which has to be computerized. In the proposed system individual characters are recognized using our own proposed method/ algorithms. The feature detection methods are simple and robust. Supervised learning is used to train the feed forward neural network. A prototype of the system has been tested on printed Urdu characters and currently achieves 98.3% character level accuracy on average .Although the system is script/ language independent but we have designed it for Urdu characters only.

Keywords: Algorithm, Feed Forward Neural Networks, Supervised learning, Pattern Matching.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2981

Authors: H. Shayeghi, H. A. Shayanfar, G. Azimi

Abstract:

Short-Term Load Forecasting (STLF) plays an important role for the economic and secure operation of power systems. In this paper, Continuous Genetic Algorithm (CGA) is employed to evolve the optimum large neural networks structure and connecting weights for one-day ahead electric load forecasting problem. This study describes the process of developing three layer feed-forward large neural networks for load forecasting and then presents a heuristic search algorithm for performing an important task of this process, i.e. optimal networks structure design. The proposed method is applied to STLF of the local utility. Data are clustered due to the differences in their characteristics. Special days are extracted from the normal training sets and handled separately. In this way, a solution is provided for all load types, including working days and weekends and special days. We find good performance for the large neural networks. The proposed methodology gives lower percent errors all the time. Thus, it can be applied to automatically design an optimal load forecaster based on historical data.

Keywords: Feed-forward Large Neural Network, Short-TermLoad Forecasting, Continuous Genetic Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1796

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 1451

Authors: Guojian Cheng, Tianshi Liu, Jiaxin Han, Zheng Wang

Abstract:

The competitive learning is an adaptive process in which the neurons in a neural network gradually become sensitive to different input pattern clusters. The basic idea behind the Kohonen-s Self-Organizing Feature Maps (SOFM) is competitive learning. SOFM can generate mappings from high-dimensional signal spaces to lower dimensional topological structures. The main features of this kind of mappings are topology preserving, feature mappings and probability distribution approximation of input patterns. To overcome some limitations of SOFM, e.g., a fixed number of neural units and a topology of fixed dimensionality, Growing Self-Organizing Neural Network (GSONN) can be used. GSONN can change its topological structure during learning. It grows by learning and shrinks by forgetting. To speed up the training and convergence, a new variant of GSONN, twin growing cell structures (TGCS) is presented here. This paper first gives an introduction to competitive learning, SOFM and its variants. Then, we discuss some GSONN with fixed dimensionality, which include growing cell structures, its variants and the author-s model: TGCS. It is ended with some testing results comparison and conclusions.

Keywords: Artificial neural networks, Competitive learning, Growing cell structures, Self-organizing feature maps.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1511

Authors: John Kabuba, Antoine Mulaba-Bafubiandi, Kim Battle

Abstract:

This paper presents a critical study about the application of Neural Networks to ion-exchange process. Ionexchange is a complex non-linear process involving many factors influencing the ions uptake mechanisms from the pregnant solution. The following step includes the elution. Published data presents empirical isotherm equations with definite shortcomings resulting in unreliable predictions. Although Neural Network simulation technique encounters a number of disadvantages including its “black box", and a limited ability to explicitly identify possible causal relationships, it has the advantage to implicitly handle complex nonlinear relationships between dependent and independent variables. In the present paper, the Neural Network model based on the back-propagation algorithm Levenberg-Marquardt was developed using a three layer approach with a tangent sigmoid transfer function (tansig) at hidden layer with 11 neurons and linear transfer function (purelin) at out layer. The above mentioned approach has been used to test the effectiveness in simulating ion exchange processes. The modeling results showed that there is an excellent agreement between the experimental data and the predicted values of copper ions removed from aqueous solutions.

Keywords: Copper, ion-exchange process, neural networks, simulation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1593

Authors: Derjew Ayele Ejigu, Houde Song, Xiaojing Liu

Abstract:

This work presents the particle swarm optimization trained neural network (PSO-NN) supervisory proportional integral derivative (PID) control method to monitor the pressurized water reactor (PWR) core power for safe operation. The proposed control approach is implemented on the transfer function of the PWR core, which is computed from the state-space model. The PWR core state-space model is designed from the neutronics, thermal-hydraulics, and reactivity models using perturbation around the equilibrium value. The proposed control approach computes the control rod speed to maneuver the core power to track the reference in a closed-loop scheme. The particle swarm optimization (PSO) algorithm is used to train the neural network (NN) and to tune the PID simultaneously. The controller performance is examined using integral absolute error, integral time absolute error, integral square error, and integral time square error functions, and the stability of the system is analyzed by using the Bode diagram. The simulation results indicated that the controller shows satisfactory performance to control and track the load power effectively and smoothly as compared to the PSO-PID control technique. This study will give benefit to design a supervisory controller for nuclear engineering research fields for control application.

Keywords: machine learning, neural network, pressurized water reactor, supervisory controller

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 448

Authors: Jun Seok Kim, Cheong-Sool Park, Jun-Geol Baek, Sung-Shick Kim

Abstract:

Control chart pattern recognition is one of the most important tools to identify the process state in statistical process control. The abnormal process state could be classified by the recognition of unnatural patterns that arise from assignable causes. In this study, a wavelet based neural network approach is proposed for the recognition of control chart patterns that have various characteristics. The procedure of proposed control chart pattern recognizer comprises three stages. First, multi-resolution wavelet analysis is used to generate time-shape and time-frequency coefficients that have detail information about the patterns. Second, distance based features are extracted by a bi-directional Kohonen network to make reduced and robust information. Third, a back-propagation network classifier is trained by these features. The accuracy of the proposed method is shown by the performance evaluation with numerical results.

Keywords: Control chart pattern recognition, Multi-resolution wavelet analysis, Bi-directional Kohonen network, Back-propagation network, Feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2435

Authors: Ozlem Faydasicok, Sabri Arik

Abstract:

This paper derives some new sufficient conditions for the stability of a class of neutral-type neural networks with discrete time delays by employing a suitable Lyapunov functional. The obtained conditions can be easily verified as they can be expressed in terms of the network parameters only. It is shown that the results presented in this paper for neutral-type delayed neural networks establish a new set of stability criteria, and therefore can be considered as the alternative results to the previously published literature results. A numerical example is also given to demonstrate the applicability of our proposed stability criterion.

Keywords: Stability Analysis, Neutral-Type Neural Networks, Time Delay Systems, Lyapunov Functionals.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1603

Authors: Yahya H. Zweiri

Abstract:

The back-propagation algorithm calculates the weight changes of an artificial neural network, and a two-term algorithm with a dynamically optimal learning rate and a momentum factor is commonly used. Recently the addition of an extra term, called a proportional factor (PF), to the two-term BP algorithm was proposed. The third term increases the speed of the BP algorithm. However, the PF term also reduces the convergence of the BP algorithm, and optimization approaches for evaluating the learning parameters are required to facilitate the application of the three terms BP algorithm. This paper considers the optimization of the new back-propagation algorithm by using derivative information. A family of approaches exploiting the derivatives with respect to the learning rate, momentum factor and proportional factor is presented. These autonomously compute the derivatives in the weight space, by using information gathered from the forward and backward procedures. The three-term BP algorithm and the optimization approaches are evaluated using the benchmark XOR problem.

Keywords: Neural Networks, Backpropagation, Optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1505

Authors: Bhim Kumar Dahal

Abstract:

Transportation network development in the developing country is in rapid pace. The majority of the network belongs to railway and expressway which passes through diverse topography, landform and geological conditions despite the avoidance principle during route selection. Construction of such networks demand many low to high embankment which required improvement in the foundation soil. This paper is mainly focused on the various advanced ground improvement techniques used to improve the soft soil, modelling approach and its predictability for embankments construction. The ground improvement techniques can be broadly classified in to three groups i.e. densification group, drainage and consolidation group and reinforcement group which are discussed with some case studies.  Various methods were used in modelling of the embankments from simple 1-dimensional to complex 3-dimensional model using variety of constitutive models. However, the reliability of the predictions is not found systematically improved with the level of sophistication.  And sometimes the predictions are deviated more than 60% to the monitored value besides using same level of erudition. This deviation is found mainly due to the selection of constitutive model, assumptions made during different stages, deviation in the selection of model parameters and simplification during physical modelling of the ground condition. This deviation can be reduced by using optimization process, optimization tools and sensitivity analysis of the model parameters which will guide to select the appropriate model parameters.

Keywords: Embankment, ground improvement, modelling, model prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 907

Authors: Isao Taguchi, Yasuo Sugai

Abstract:

This paper proposes an efficient learning method for the layered neural networks based on the selection of training data and input characteristics of an output layer unit. Comparing to recent neural networks; pulse neural networks, quantum neuro computation, etc, the multilayer network is widely used due to its simple structure. When learning objects are complicated, the problems, such as unsuccessful learning or a significant time required in learning, remain unsolved. Focusing on the input data during the learning stage, we undertook an experiment to identify the data that makes large errors and interferes with the learning process. Our method devides the learning process into several stages. In general, input characteristics to an output layer unit show oscillation during learning process for complicated problems. The multi-stage learning method proposes by the authors for the function approximation problems of classifying learning data in a phased manner, focusing on their learnabilities prior to learning in the multi layered neural network, and demonstrates validity of the multi-stage learning method. Specifically, this paper verifies by computer experiments that both of learning accuracy and learning time are improved of the BP method as a learning rule of the multi-stage learning method. In learning, oscillatory phenomena of a learning curve serve an important role in learning performance. The authors also discuss the occurrence mechanisms of oscillatory phenomena in learning. Furthermore, the authors discuss the reasons that errors of some data remain large value even after learning, observing behaviors during learning.

Keywords: data selection, function approximation problem, multistage leaning, neural network, voluntary oscillation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1395

Authors: Ruibiao J. Guo, Brad Cain, Pierre Meunier

Abstract:

The Integrated Performance Modelling Environment (IPME) is a powerful simulation engine for task simulation and performance analysis. However, it has no high level cognition such as memory and reasoning for complex simulation. This article introduces a knowledge representation and reasoning scheme that can accommodate uncertainty in simulations of military personnel with IPME. This approach demonstrates how advanced reasoning models that support similarity-based associative process, rule-based abstract process, multiple reasoning methods and real-time interaction can be integrated with conventional task network modelling to provide greater functionality and flexibility when modelling operator performance.

Keywords: Computer-Generated Forces, Human Behaviour Representation, IPME, Modelling and Simulation, Uncertainty Reasoning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2079

Authors: H. Shayeghi, H. A. Shayanfar, G. Azimi

Abstract:

The quality of short term load forecasting can improve the efficiency of planning and operation of electric utilities. Artificial Neural Networks (ANNs) are employed for nonlinear short term load forecasting owing to their powerful nonlinear mapping capabilities. At present, there is no systematic methodology for optimal design and training of an artificial neural network. One has often to resort to the trial and error approach. This paper describes the process of developing three layer feed-forward large neural networks for short-term load forecasting and then presents a heuristic search algorithm for performing an important task of this process, i.e. optimal networks structure design. Particle Swarm Optimization (PSO) is used to develop the optimum large neural network structure and connecting weights for one-day ahead electric load forecasting problem. PSO is a novel random optimization method based on swarm intelligence, which has more powerful ability of global optimization. Employing PSO algorithms on the design and training of ANNs allows the ANN architecture and parameters to be easily optimized. The proposed method is applied to STLF of the local utility. Data are clustered due to the differences in their characteristics. Special days are extracted from the normal training sets and handled separately. In this way, a solution is provided for all load types, including working days and weekends and special days. The experimental results show that the proposed method optimized by PSO can quicken the learning speed of the network and improve the forecasting precision compared with the conventional Back Propagation (BP) method. Moreover, it is not only simple to calculate, but also practical and effective. Also, it provides a greater degree of accuracy in many cases and gives lower percent errors all the time for STLF problem compared to BP method. Thus, it can be applied to automatically design an optimal load forecaster based on historical data.

Keywords: Large Neural Network, Short-Term Load Forecasting, Particle Swarm Optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2188

Authors: Tienfuan Kerh, Hsienchang Lu, Rob Saunders

Abstract:

Shoreline erosion problems caused by global warming and sea level rising may result in losing of land areas, so it should be examined regularly to reduce possible negative impacts. Initially in this study, three sets of survey images obtained from the years of 1990, 2001, and 2010, respectively, are digitalized by using graphical software to establish the spatial coordinates of six major beaches around the island of Taiwan. Then, by overlaying the known multi-period images, the change of shoreline can be observed from their distribution of coordinates. In addition, the neural network approximation is used to develop a model for predicting shoreline variation in the years of 2015 and 2020. The comparison results show that there is no significant change of total sandy area for all beaches in the three different periods. However, the prediction results show that two beaches may exhibit an increasing of total sandy areas under a statistical 95% confidence interval. The proposed method adopted in this study may be applicable to other shorelines of interest around the world.

Keywords: Digitalized shoreline coordinates, survey image overlaying, neural network approximation, total beach sandy areas.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1939

Authors: M.R. Mustafa, M.H. Isa, R.B. Rezaur

Abstract:

Prediction of highly non linear behavior of suspended sediment flow in rivers has prime importance in the field of water resources engineering. In this study the predictive performance of two Artificial Neural Networks (ANNs) namely, the Radial Basis Function (RBF) Network and the Multi Layer Feed Forward (MLFF) Network have been compared. Time series data of daily suspended sediment discharge and water discharge at Pari River was used for training and testing the networks. A number of statistical parameters i.e. root mean square error (RMSE), mean absolute error (MAE), coefficient of efficiency (CE) and coefficient of determination (R2) were used for performance evaluation of the models. Both the models produced satisfactory results and showed a good agreement between the predicted and observed data. The RBF network model provided slightly better results than the MLFF network model in predicting suspended sediment discharge.

Keywords: ANN, discharge, modeling, prediction, suspendedsediment,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1689

Authors: B. A. Gobin, R. K. Subramanian

Abstract:

Knowledge modelling, a main activity for the development of Knowledge Based Systems, have no set standards and are mostly done in an ad hoc way. There is a lack of support for the transition from abstract level to implementation. In this paper, a methodology for the development of the knowledge model, which is inspired by both Software and Knowledge Engineering, is proposed. Use of UML which is the de-facto standard for modelling in the software engineering arena is explored for knowledge modelling. The methodology proposed, is used to develop a knowledge model of a knowledge based system for recommending suitable hotels for tourists visiting Mauritius.

Keywords: Domain Modelling, Knowledge Based Systems, Knowledge Modelling, UML.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3721

Authors: H. Kiani, S. Moradi, B. Soltani Soulgani, S. Mousavian

Abstract:

Desalting/dehydration plants (DDP) are often installed in crude oil production units in order to remove water-soluble salts from an oil stream. In order to optimize this process, desalting unit should be modeled. In this research, artificial neural network is used to model efficiency of desalting unit as a function of input parameter. The result of this research shows that the mentioned model has good agreement with experimental data.

Keywords: Desalting unit, Crude oil, Neural Networks, Simulation, Recovery, Separation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4204

Authors: Mahdieh Khalilinezhad, Silvana Dellepiane, Gianni Vernazza

Abstract:

The aim of this work is to build a model based on tissue characterization that is able to discriminate pathological and non-pathological regions from three-phasic CT images. With our research and based on a feature selection in different phases, we are trying to design a neural network system with an optimal neuron number in a hidden layer. Our approach consists of three steps: feature selection, feature reduction, and classification. For each region of interest (ROI), 6 distinct sets of texture features are extracted such as: first order histogram parameters, absolute gradient, run-length matrix, co-occurrence matrix, autoregressive model, and wavelet, for a total of 270 texture features. When analyzing more phases, we show that the injection of liquid cause changes to the high relevant features in each region. Our results demonstrate that for detecting HCC tumor phase 3 is the best one in most of the features that we apply to the classification algorithm. The percentage of detection between pathology and healthy classes, according to our method, relates to first order histogram parameters with accuracy of 85% in phase 1, 95% in phase 2, and 95% in phase 3.

Keywords: Feature selection, Multi-phasic liver images, Neural network, Texture analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2498

Authors: Dilip Kumar S.M, Vijaya Kumar B.P.

Abstract:

The decisions made by admission control algorithms are based on the availability of network resources viz. bandwidth, energy, memory buffers, etc., without degrading the Quality-of-Service (QoS) requirement of applications that are admitted. In this paper, we present an energy-aware admission control (EAAC) scheme which provides admission control for flows in an ad hoc network based on the knowledge of the present and future residual energy of the intermediate nodes along the routing path. The aim of EAAC is to quantify the energy that the new flow will consume so that it can be decided whether the future residual energy of the nodes along the routing path can satisfy the energy requirement. In other words, this energy-aware routing admits a new flow iff any node in the routing path does not run out of its energy during the transmission of packets. The future residual energy of a node is predicted using the Multi-layer Neural Network (MNN) model. Simulation results shows that the proposed scheme increases the network lifetime. Also the performance of the MNN model is presented.

Keywords: Ad hoc networks, admission control, energy-aware routing, Quality-of-Service, future residual energy, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1613

Authors: Velappa Ganapathy, Kok Leong Liew

Abstract:

Advancement in Artificial Intelligence has lead to the developments of various “smart" devices. Character recognition device is one of such smart devices that acquire partial human intelligence with the ability to capture and recognize various characters in different languages. Firstly multiscale neural training with modifications in the input training vectors is adopted in this paper to acquire its advantage in training higher resolution character images. Secondly selective thresholding using minimum distance technique is proposed to be used to increase the level of accuracy of character recognition. A simulator program (a GUI) is designed in such a way that the characters can be located on any spot on the blank paper in which the characters are written. The results show that such methods with moderate level of training epochs can produce accuracies of at least 85% and more for handwritten upper case English characters and numerals.

Keywords: Character recognition, multiscale, backpropagation, neural network, minimum distance technique.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1874

Authors: Doraid Dalalah

Abstract:

A topologically oriented neural network is very efficient for real-time path planning for a mobile robot in changing environments. When using a recurrent neural network for this purpose and with the combination of the partial differential equation of heat transfer and the distributed potential concept of the network, the problem of obstacle avoidance of trajectory planning for a moving robot can be efficiently solved. The related dimensional network represents the state variables and the topology of the robot's working space. In this paper two approaches to problem solution are proposed. The first approach relies on the potential distribution of attraction distributed around the moving target, acting as a unique local extreme in the net, with the gradient of the state variables directing the current flow toward the source of the potential heat. The second approach considers two attractive and repulsive potential sources to decrease the time of potential distribution. Computer simulations have been carried out to interrogate the performance of the proposed approaches.

Keywords: Mobile robot, Path Planning, Mesh, Potential field.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1898

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 1473

Authors: Shamsuddin Ahmed, M. G. M. Khan, Biman Prasad, Avlin Prasad

Abstract:

The focus of this paper is to construct daily time series exchange rate forecast models of Samoan Tala/USD and Tala/AUD during the year 2008 to 2012 with neural network The performance of the models was measured by using varies error functions such as Root Square mean error (RSME), Mean absolute error (MAE), and Mean absolute percentage error (MAPE). Our empirical findings suggest that AR (1) model is an effective tool to forecast the Tala/USD and Tala/AUD.

Keywords: Neural Network Forecasting Model, Autoregressive time series, Exchange rate, Tala/AUD, winters model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2383

Authors: Gopu Sreenivasulu, Bimlesh Kumar, Achanta Ramakrishna Rao

Abstract:

To define or predict incipient motion in an alluvial channel, most of the investigators use a standard or modified form of Shields- diagram. Shields- diagram does give a process to determine the incipient motion parameters but an iterative one. To design properly (without iteration), one should have another equation for resistance. Absence of a universal resistance equation also magnifies the difficulties in defining the model. Neural network technique, which is particularly useful in modeling a complex processes, is presented as a tool complimentary to modeling incipient motion. Present work develops a neural network model employing the RBF network to predict the average velocity u and water depth y based on the experimental data on incipient condition. Based on the model, design curves have been presented for the field application.

Keywords: Incipient motion, Prediction error, Radial-Basisfunction, Sediment transport, Shields' diagram.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1445

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: Deep learning, field programmable gate array, FPGA, hardware acceleration, convolutional neural networks, CNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 829

Authors: M. R. Mustafa, M. H. Isa, R. B. Rezaur

Abstract:

The use of artificial neural network (ANN) modeling for prediction and forecasting variables in water resources engineering are being increasing rapidly. Infrastructural applications of ANN in terms of selection of inputs, architecture of networks, training algorithms, and selection of training parameters in different types of neural networks used in water resources engineering have been reported. ANN modeling conducted for water resources engineering variables (river sediment and discharge) published in high impact journals since 2002 to 2011 have been examined and presented in this review. ANN is a vigorous technique to develop immense relationship between the input and output variables, and able to extract complex behavior between the water resources variables such as river sediment and discharge. It can produce robust prediction results for many of the water resources engineering problems by appropriate learning from a set of examples. It is important to have a good understanding of the input and output variables from a statistical analysis of the data before network modeling, which can facilitate to design an efficient network. An appropriate training based ANN model is able to adopt the physical understanding between the variables and may generate more effective results than conventional prediction techniques.

Keywords: ANN, discharge, modeling, prediction, sediment,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5607

Authors: Si Mon Kueh, Tom J. Kazmierski

Abstract:

There are about 1% of the world population suffering from the hidden disability known as epilepsy and major developing countries are not fully equipped to counter this problem. In order to reduce the inconvenience and danger of epilepsy, different methods have been researched by using a artificial neural network (ANN) classification to distinguish epileptic waveforms from normal brain waveforms. This paper outlines the aim of achieving massive ANN parallelization through a dedicated hardware using bit-serial processing. The design of this bit-serial Neural Processing Element (NPE) is presented which implements the functionality of a complete neuron using variable accuracy. The proposed design has been tested taking into consideration non-idealities of a hardware ANN. The NPE consists of a bit-serial multiplier which uses only 16 logic elements on an Altera Cyclone IV FPGA and a bit-serial ALU as well as a look-up table. Arrays of NPEs can be driven by a single controller which executes the neural processing algorithm. In conclusion, the proposed compact NPE design allows the construction of complex hardware ANNs that can be implemented in a portable equipment that suits the needs of a single epileptic patient in his or her daily activities to predict the occurrences of impending tonic conic seizures.

Keywords: Artificial Neural Networks, bit-serial neural processor, FPGA, Neural Processing Element.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1532

Authors: Saeid Fazli, Hadis Askarifar, Maryam Sheikh Shoaie

Abstract:

Human identification at a distance has recently gained growing interest from computer vision researchers. Gait recognition aims essentially to address this problem by identifying people based on the way they walk [1]. Gait recognition has 3 steps. The first step is preprocessing, the second step is feature extraction and the third one is classification. This paper focuses on the classification step that is essential to increase the CCR (Correct Classification Rate). Multilayer Perceptron (MLP) is used in this work. Neural Networks imitate the human brain to perform intelligent tasks [3].They can represent complicated relationships between input and output and acquire knowledge about these relationships directly from the data [2]. In this paper we apply MLP NN for 11 views in our database and compare the CCR values for these views. Experiments are performed with the NLPR databases, and the effectiveness of the proposed method for gait recognition is demonstrated.

Keywords: Human motion analysis, biometrics, gait recognition, principal component analysis, MLP neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2071

Authors: Shan-Jen Cheng, Te-Jen Chang, Kuang-Hsiung Tan, Shou-Ling Kuo

Abstract:

Polymer Electrolyte Membrane Fuel Cell (PEMFC) is such a time-vary nonlinear dynamic system. The traditional linear modeling approach is hard to estimate structure correctly of PEMFC system. From this reason, this paper presents a nonlinear modeling of the PEMFC using Neural Network Auto-regressive model with eXogenous inputs (NNARX) approach. The multilayer perception (MLP) network is applied to evaluate the structure of the NNARX model of PEMFC. The validity and accuracy of NNARX model are tested by one step ahead relating output voltage to input current from measured experimental of PEMFC. The results show that the obtained nonlinear NNARX model can efficiently approximate the dynamic mode of the PEMFC and model output and system measured output consistently.

Keywords: PEMFC, neural network, nonlinear identification, NNARX.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2159

Authors: Sonia Manhas, Parvinder S. Sandhu, Vinay Chopra, Nirvair Neeru

Abstract:

The cost of developing the software from scratch can be saved by identifying and extracting the reusable components from already developed and existing software systems or legacy systems [6]. But the issue of how to identify reusable components from existing systems has remained relatively unexplored. We have used metric based approach for characterizing a software module. In this present work, the metrics McCabe-s Cyclometric Complexity Measure for Complexity measurement, Regularity Metric, Halstead Software Science Indicator for Volume indication, Reuse Frequency metric and Coupling Metric values of the software component are used as input attributes to the different types of Neural Network system and reusability of the software component is calculated. The results are recorded in terms of Accuracy, Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).

Keywords: Software reusability, Neural Networks, MAE, RMSE, Accuracy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1830