Search results for: Large scale VLSI neural net

Authors: Silvina Caíno-Lores, Jesús Carretero

Abstract:

Large scale computing infrastructures have been widely developed with the core objective of providing a suitable platform for high-performance and high-throughput computing. These systems are designed to support resource-intensive and complex applications, which can be found in many scientific and industrial areas. Currently, large scale data-intensive applications are hindered by the high latencies that result from the access to vastly distributed data. Recent works have suggested that improving data locality is key to move towards exascale infrastructures efficiently, as solutions to this problem aim to reduce the bandwidth consumed in data transfers, and the overheads that arise from them. There are several techniques that attempt to move computations closer to the data. In this survey we analyse the different mechanisms that have been proposed to provide data locality for large scale high-performance and high-throughput systems. This survey intends to assist scientific computing community in understanding the various technical aspects and strategies that have been reported in recent literature regarding data locality. As a result, we present an overview of locality-oriented techniques, which are grouped in four main categories: application development, task scheduling, in-memory computing and storage platforms. Finally, the authors include a discussion on future research lines and synergies among the former techniques.

Keywords: Co-scheduling, data-centric, data-intensive, data locality, in-memory storage, large scale.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1461

Authors: Lili Wang, Meng Hu

Abstract:

In this paper, a class of recurrent neural networks (RNNs) with variable delays are studied on almost periodic time scales, some sufficient conditions are established for the existence and global exponential stability of the almost periodic solution. These results have important leading significance in designs and applications of RNNs. Finally, two examples and numerical simulations are presented to illustrate the feasibility and effectiveness of the results.

Keywords: Recurrent neural network, Almost periodic solution, Global exponential stability, Time scale.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1389

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 855

Authors: C. Hemasundara Rao, M. Madhavi Latha

Abstract:

Image compression can improve the performance of the digital systems by reducing time and cost in image storage and transmission without significant reduction of the image quality. Furthermore, the discrete cosine transform has emerged as the new state-of-the art standard for image compression. In this paper, a hybrid image compression technique based on reversible blockade transform coding is proposed. The technique, implemented over regions of interest (ROIs), is based on selection of the coefficients that belong to different transforms, depending on the coefficients is proposed. This method allows: (1) codification of multiple kernals at various degrees of interest, (2) arbitrary shaped spectrum,and (3) flexible adjustment of the compression quality of the image and the background. No standard modification for JPEG2000 decoder was required. The method was applied over different types of images. Results show a better performance for the selected regions, when image coding methods were employed for the whole set of images. We believe that this method is an excellent tool for future image compression research, mainly on images where image coding can be of interest, such as the medical imaging modalities and several multimedia applications. Finally VLSI implementation of proposed method is shown. It is also shown that the kernal of Hartley and Cosine transform gives the better performance than any other model.

Keywords: VLSI, Discrete Cosine Transform, JPEG, Hartleytransform, Radon Transform

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1807

Authors: Poramate Manoonpong, Frank Pasemann, Florentin Wörgötter

Abstract:

This paper describes reactive neural control used to generate phototaxis and obstacle avoidance behavior of walking machines. It utilizes discrete-time neurodynamics and consists of two main neural modules: neural preprocessing and modular neural control. The neural preprocessing network acts as a sensory fusion unit. It filters sensory noise and shapes sensory data to drive the corresponding reactive behavior. On the other hand, modular neural control based on a central pattern generator is applied for locomotion of walking machines. It coordinates leg movements and can generate omnidirectional walking. As a result, through a sensorimotor loop this reactive neural controller enables the machines to explore a dynamic environment by avoiding obstacles, turn toward a light source, and then stop near to it.

Keywords: Recurrent neural networks, Walking robots, Modular neural control, Phototaxis, Obstacle avoidance behavior.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1697

Authors: Chien-Hua Lee, Cheng-Yi Chen

Abstract:

The stability test problem for homogeneous large-scale perturbed bilinear time-delay systems subjected to constrained inputs is considered in this paper. Both nonlinear uncertainties and interval systems are discussed. By utilizing the Lyapunove equation approach associated with linear algebraic techniques, several delay-independent criteria are presented to guarantee the robust stability of the overall systems. The main feature of the presented results is that although the Lyapunov stability theorem is used, they do not involve any Lyapunov equation which may be unsolvable. Furthermore, it is seen the proposed schemes can be applied to solve the stability analysis problem of large-scale time-delay systems.

Keywords: homogeneous bilinear system, constrained input, time-delay, uncertainty, transient response, decay rate.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1584

Authors: K.Sedhuraman, S.Himavathi, A.Muthuramalingam

Abstract:

The performance of sensor-less controlled induction motor drive depends on the accuracy of the estimated speed. Conventional estimation techniques being mathematically complex require more execution time resulting in poor dynamic response. The nonlinear mapping capability and powerful learning algorithms of neural network provides a promising alternative for on-line speed estimation. The on-line speed estimator requires the NN model to be accurate, simpler in design, structurally compact and computationally less complex to ensure faster execution and effective control in real time implementation. This in turn to a large extent depends on the type of Neural Architecture. This paper investigates three types of neural architectures for on-line speed estimation and their performance is compared in terms of accuracy, structural compactness, computational complexity and execution time. The suitable neural architecture for on-line speed estimation is identified and the promising results obtained are presented.

Keywords: Sensorless IM drives, rotor speed estimators, artificial neural network, feed- forward architecture, single neuron cascaded architecture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1426

Authors: Henrik Prinzhorn, Peter Nyhuis, Johannes Wagner, Peter Burggräf, Torben Schmitz, Christina Reuter

Abstract:

Assembling large-scale products, such as airplanes, locomotives, or wind turbines, involves frequent process interruptions induced by e.g. delayed material deliveries or missing availability of resources. This leads to a negative impact on the logistical performance of a producer of xxl-products. In industrial practice, in case of interruptions, the identification, evaluation and eventually the selection of an alternative order of assembly activities (‘assembly alternative’) leads to an enormous challenge, especially if an optimized logistical decision should be reached. Therefore, in this paper, an innovative, optimization model for the identification of assembly alternatives that addresses the given problem is presented. It describes make-to-order, large-scale product assembly processes as a resource constrained project scheduling (RCPS) problem which follows given restrictions in practice. For the evaluation of the assembly alternative, a cost-based definition of the logistical objectives (delivery reliability, inventory, make-span and workload) is presented.

Keywords: Assembly scheduling, large-scale products, make-to-order, rescheduling, optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1416

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In recent years, fast neural networks for object/face detection have been introduced based on cross correlation in the frequency domain between the input matrix and the hidden weights of neural networks. In our previous papers [3,4], fast neural networks for certain code detection was introduced. It was proved in [10] that for fast neural networks to give the same correct results as conventional neural networks, both the weights of neural networks and the input matrix must be symmetric. This condition made those fast neural networks slower than conventional neural networks. Another symmetric form for the input matrix was introduced in [1-9] to speed up the operation of these fast neural networks. Here, corrections for the cross correlation equations (given in [13,15,16]) to compensate for the symmetry condition are presented. After these corrections, it is proved mathematically that the number of computation steps required for fast neural networks is less than that needed by classical neural networks. Furthermore, there is no need for converting the input data into symmetric form. Moreover, such new idea is applied to increase the speed of neural networks in case of processing complex values. Simulation results after these corrections using MATLAB confirm the theoretical computations.

Keywords: Fast Code/Data Detection, Neural Networks, Cross Correlation, real/complex values.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1601

Authors: S. Bouhouche, M. Lahreche, S. Ziani, J. Bast

Abstract:

Modern manufacturing facilities are large scale, highly complex, and operate with large number of variables under closed loop control. Early and accurate fault detection and diagnosis for these plants can minimise down time, increase the safety of plant operations, and reduce manufacturing costs. Fault detection and isolation is more complex particularly in the case of the faulty analog control systems. Analog control systems are not equipped with monitoring function where the process parameters are continually visualised. In this situation, It is very difficult to find the relationship between the fault importance and its consequences on the product failure. We consider in this paper an approach to fault detection and analysis of its effect on the production quality using an adaptive centring and scaling in the pickling process in cold rolling. The fault appeared on one of the power unit driving a rotary machine, this machine can not track a reference speed given by another machine. The length of metal loop is then in continuous oscillation, this affects the product quality. Using a computerised data acquisition system, the main machine parameters have been monitored. The fault has been detected and isolated on basis of analysis of monitored data. Normal and faulty situation have been obtained by an artificial neural network (ANN) model which is implemented to simulate the normal and faulty status of rotary machine. Correlation between the product quality defined by an index and the residual is used to quality classification.

Keywords: Modeling, fault detection and diagnosis, parameters estimation, neural networks, Fault Detection and Diagnosis (FDD), pickling process.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1552

Authors: Radouane Iqdour, Abdelouhab Zeroual

Abstract:

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

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

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1303

Authors: C. Pislaru, A. Shebani

Abstract:

This paper uses the radial basis function neural network (RBFNN) for system identification of nonlinear systems. Five nonlinear systems are used to examine the activity of RBFNN in system modeling of nonlinear systems; the five nonlinear systems are dual tank system, single tank system, DC motor system, and two academic models. The feed forward method is considered in this work for modelling the non-linear dynamic models, where the KMeans clustering algorithm used in this paper to select the centers of radial basis function network, because it is reliable, offers fast convergence and can handle large data sets. The least mean square method is used to adjust the weights to the output layer, and Euclidean distance method used to measure the width of the Gaussian function.

Keywords: System identification, Nonlinear system, Neural networks, RBF neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2831

Authors: Leong Lee, Jennifer Leopold, Julia Albath, Alton Coalter

Abstract:

As more people from non-technical backgrounds are becoming directly involved with large-scale ontology development, the focal point of ontology research has shifted from the more theoretical ontology issues to problems associated with the actual use of ontologies in real-world, large-scale collaborative applications. Recently the National Science Foundation funded a large collaborative ontology development project for which a new formal ontology model, the Ontology Abstract Machine (OAM), was developed to satisfy some unique functional and data representation requirements. This paper introduces the OAM model and the related algorithms that enable maintenance of an ontology that supports node-based user access. The successful software implementation of the OAM model and its subsequent acceptance by a large research community proves its validity and its real-world application value.

Keywords: Ontology, Abstract Machine, Ontology Editor, WebbasedOntology Management System.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1382

Authors: Young-Seok Choi

Abstract:

This work assesses the cortical and the sub-cortical neural activity recorded from rodents using entropy and mutual information based approaches to study how hypothermia affects neural activity. By applying the multi-scale entropy and Shannon entropy, we quantify the degree of the regularity embedded in the cortical and sub-cortical neurons and characterize the dependency of entropy of these regions on temperature. We study also the degree of the mutual information on thalamocortical pathway depending on temperature. The latter is most likely an indicator of coupling between these highly connected structures in response to temperature manipulation leading to arousal after global cerebral ischemia.

Keywords: Spiking activity, entropy, mutual information, temperature modulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1602

Authors: Tatjana Eitrich, Bruno Lang

Abstract:

This work deals with aspects of support vector learning for large-scale data mining tasks. Based on a decomposition algorithm that can be run in serial and parallel mode we introduce a data transformation that allows for the usage of an expensive generalized kernel without additional costs. In order to speed up the decomposition algorithm we analyze the problem of working set selection for large data sets and analyze the influence of the working set sizes onto the scalability of the parallel decomposition scheme. Our modifications and settings lead to improvement of support vector learning performance and thus allow using extensive parameter search methods to optimize classification accuracy.

Keywords: Support Vector Machines, Shared Memory Parallel Computing, Large Data

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1554

Authors: Mohammad Reza Ghasemi, Amin Ghorbani

Abstract:

The main goal of the present work is to decrease the computational burden for optimum design of steel frames with frequency constraints using a new type of neural networks called Wavelet Neural Network. It is contested to train a suitable neural network for frequency approximation work as the analysis program. The combination of wavelet theory and Neural Networks (NN) has lead to the development of wavelet neural networks. Wavelet neural networks are feed-forward networks using wavelet as activation function. Wavelets are mathematical functions within suitable inner parameters, which help them to approximate arbitrary functions. WNN was used to predict the frequency of the structures. In WNN a RAtional function with Second order Poles (RASP) wavelet was used as a transfer function. It is shown that the convergence speed was faster than other neural networks. Also comparisons of WNN with the embedded Artificial Neural Network (ANN) and with approximate techniques and also with analytical solutions are available in the literature.

Keywords: Weight Minimization, Frequency Constraints, Steel Frames, ANN, WNN, RASP Function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1712

Authors: Mangesh R. Phate, V. H. Tatwawadi

Abstract:

This paper is intended to develop an artificial neural network (ANN) based model of material removal rate (MRR) in the turning of ferrous and nonferrous material in a Indian small-scale industry. MRR of the formulated model was proved with the testing data and artificial neural network (ANN) model was developed for the analysis and prediction of the relationship between inputs and output parameters during the turning of ferrous and nonferrous materials. The input parameters of this model are operator, work-piece, cutting process, cutting tool, machine and the environment.

The ANN model consists of a three layered feedforward back propagation neural network. The network is trained with pairs of independent/dependent datasets generated when machining ferrous and nonferrous material. A very good performance of the neural network, in terms of contract with experimental data, was achieved. The model may be used for the testing and forecast of the complex relationship between dependent and the independent parameters in turning operations.

Keywords: Field data based model, Artificial neural network, Simulation, Convectional Turning, Material removal rate.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1945

Authors: Farhad Asadi, S. Hossein Sadati

Abstract:

This paper presents a prediction performance of feedforward Multilayer Perceptron (MLP) and Echo State Networks (ESN) trained with extended Kalman filter. Feedforward neural networks and ESN are powerful neural networks which can track and predict nonlinear signals. However, their tracking performance depends on the specific signals or data sets, having the risk of instability accompanied by large error. In this study we explore this process by applying different network size and leaking rate for prediction of nonlinear or chaotic signals in MLP neural networks. Major problems of ESN training such as the problem of initialization of the network and improvement in the prediction performance are tackled. The influence of coefficient of activation function in the hidden layer and other key parameters are investigated by simulation results. Extended Kalman filter is employed in order to improve the sequential and regulation learning rate of the feedforward neural networks. This training approach has vital features in the training of the network when signals have chaotic or non-stationary sequential pattern. Minimization of the variance in each step of the computation and hence smoothing of tracking were obtained by examining the results, indicating satisfactory tracking characteristics for certain conditions. In addition, simulation results confirmed satisfactory performance of both of the two neural networks with modified parameterization in tracking of the nonlinear signals.

Keywords: Feedforward neural networks, nonlinear signal prediction, echo state neural networks approach, leaking rates, capacity of neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 727

Authors: Yuanyuan Chai, Limin Jia, Zundong Zhang

Abstract:

Hybrid algorithm is the hot issue in Computational Intelligence (CI) study. From in-depth discussion on Simulation Mechanism Based (SMB) classification method and composite patterns, this paper presents the Mamdani model based Adaptive Neural Fuzzy Inference System (M-ANFIS) and weight updating formula in consideration with qualitative representation of inference consequent parts in fuzzy neural networks. M-ANFIS model adopts Mamdani fuzzy inference system which has advantages in consequent part. Experiment results of applying M-ANFIS to evaluate traffic Level of service show that M-ANFIS, as a new hybrid algorithm in computational intelligence, has great advantages in non-linear modeling, membership functions in consequent parts, scale of training data and amount of adjusted parameters.

Keywords: Fuzzy neural networks, Mamdani fuzzy inference, M-ANFIS

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5211

Authors: Zulhadi Zakaria, Nor Ashidi Mat Isa, Shahrel A. Suandi

Abstract:

This paper reports the study results on neural network training algorithm of numerical optimization techniques multiface detection in static images. The training algorithms involved are scale gradient conjugate backpropagation, conjugate gradient backpropagation with Polak-Riebre updates, conjugate gradient backpropagation with Fletcher-Reeves updates, one secant backpropagation and resilent backpropagation. The final result of each training algorithms for multiface detection application will also be discussed and compared.

Keywords: training algorithm, multiface, static image, neural network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2553

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 1406

Authors: S. M. Anowarul Haque, Md. Asiful Islam

Abstract:

Electrical load forecasting is considered to be one of the most indispensable parts of a modern-day electrical power system. To ensure a reliable and efficient supply of electric energy, special emphasis should have been put on the predictive feature of electricity supply. Artificial Neural Network-based approaches have emerged to be a significant area of interest for electric load forecasting research. This paper proposed an Artificial Neural Network model based on the particle swarm optimization algorithm for improved electric load forecasting for Mymensingh, Bangladesh. The forecasting model is developed and simulated on the MATLAB environment with a large number of training datasets. The model is trained based on eight input parameters including historical load and weather data. The predicted load data are then compared with an available dataset for validation. The proposed neural network model is proved to be more reliable in terms of day-wise load forecasting for Mymensingh, Bangladesh.

Keywords: Load forecasting, artificial neural network, particle swarm optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 647

Authors: Nameer N. EL-Emam

Abstract:

In this paper, we construct and implement a new Steganography algorithm based on learning system to hide a large amount of information into color BMP image. We have used adaptive image filtering and adaptive non-uniform image segmentation with bits replacement on the appropriate pixels. These pixels are selected randomly rather than sequentially by using new concept defined by main cases with sub cases for each byte in one pixel. According to the steps of design, we have been concluded 16 main cases with their sub cases that covere all aspects of the input information into color bitmap image. High security layers have been proposed through four layers of security to make it difficult to break the encryption of the input information and confuse steganalysis too. Learning system has been introduces at the fourth layer of security through neural network. This layer is used to increase the difficulties of the statistical attacks. Our results against statistical and visual attacks are discussed before and after using the learning system and we make comparison with the previous Steganography algorithm. We show that our algorithm can embed efficiently a large amount of information that has been reached to 75% of the image size (replace 18 bits for each pixel as a maximum) with high quality of the output.

Keywords: Adaptive image segmentation, hiding with high capacity, hiding with high security, neural networks, Steganography.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1959

Authors: Emad Amar, Tawfik Khattab, Fatma Zada

Abstract:

Predicting earthquakes is an important issue in the study of geography. Accurate prediction of earthquakes can help people to take effective measures to minimize the loss of personal and economic damage, such as large casualties, destruction of buildings and broken of traffic, occurred within a few seconds. United States Geological Survey (USGS) science organization provides reliable scientific information about Earthquake Existed throughout history & the Preliminary database from the National Center Earthquake Information (NEIC) show some useful factors to predict an earthquake in a seismic area like Aleutian Arc in the U.S. state of Alaska. The main advantage of this prediction method that it does not require any assumption, it makes prediction according to the future evolution of the object's time series. The article compares between simulation data result from trained BP and RBF neural network versus actual output result from the system calculations. Therefore, this article focuses on analysis of data relating to real earthquakes. Evaluation results show better accuracy and higher speed by using radial basis functions (RBF) neural network.

Keywords: BP neural network, Prediction, RBF neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3190

Authors: K.-J. You, H.J. Lee, Y. Lang, C. Im, C.S. Koh, H.-C. Shin

Abstract:

This paper presents a novel method for inferring the odor based on neural activities observed from rats- main olfactory bulbs. Multi-channel extra-cellular single unit recordings were done by micro-wire electrodes (tungsten, 50μm, 32 channels) implanted in the mitral/tufted cell layers of the main olfactory bulb of anesthetized rats to obtain neural responses to various odors. Neural response as a key feature was measured by substraction of neural firing rate before stimulus from after. For odor inference, we have developed a decoding method based on the maximum likelihood (ML) estimation. The results have shown that the average decoding accuracy is about 100.0%, 96.0%, 84.0%, and 100.0% with four rats, respectively. This work has profound implications for a novel brain-machine interface system for odor inference.

Keywords: biomedical signal processing, neural engineering, olfactory, neural decoding, BMI

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1582

Authors: Rui Antunes, Fernando V. Coito

Abstract:

This article presents the development of a neural network cognitive model for the classification and detection of different frequency signals. The basic structure of the implemented neural network was inspired on the perception process that humans generally make in order to visually distinguish between high and low frequency signals. It is based on the dynamic neural network concept, with delays. A special two-layer feedforward neural net structure was successfully implemented, trained and validated, to achieve minimum target error. Training confirmed that this neural net structure descents and converges to a human perception classification solution, even when far away from the target.

Keywords: Neural Networks, Signal Classification, Adaptative Filters, Cognitive Neuroscience

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1634

Authors: Nasrin Bakhshizadeh, Ashkan Forootan

Abstract:

A major problem that affects the quality control of polymer in the industrial polymerization is the lack of suitable on-line measurement tools to evaluate the properties of the polymer such as melt and density indices. Controlling the polymerization in ordinary method is performed manually by taking samples, measuring the quality of polymer in the lab and registry of results. This method is highly time consuming and leads to producing large number of incompatible products. An online application for estimating melt index and density proposed in this study is a neural network based on the input-output data of the polyethylene production plant. Temperature, the level of reactors' bed, the intensity of ethylene mass flow, hydrogen and butene-1, the molar concentration of ethylene, hydrogen and butene-1 are used for the process to establish the neural model. The neural network is taught based on the actual operational data and back-propagation and Levenberg-Marquart techniques. The simulated results indicate that the neural network process model established with three layers (one hidden layer) for forecasting the density and the four layers for the melt index is able to successfully predict those quality properties.

Keywords: Polyethylene, polymerization, density, melt index, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 653

Authors: Thomas Behan, Zaiyi Liao, Lian Zhao, Chunting Yang

Abstract:

In this paper, low end Digital Signal Processors (DSPs) are applied to accelerate integer neural networks. The use of DSPs to accelerate neural networks has been a topic of study for some time, and has demonstrated significant performance improvements. Recently, work has been done on integer only neural networks, which greatly reduces hardware requirements, and thus allows for cheaper hardware implementation. DSPs with Arithmetic Logic Units (ALUs) that support floating or fixed point arithmetic are generally more expensive than their integer only counterparts due to increased circuit complexity. However if the need for floating or fixed point math operation can be removed, then simpler, lower cost DSPs can be used. To achieve this, an integer only neural network is created in this paper, which is then accelerated by using DSP instructions to improve performance.

Keywords: Digital Signal Processor (DSP), Integer Neural Network(INN), Low Cost Neural Network, Integer Neural Network DSPImplementation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1766

Authors: Roland Pusch, Richard Weston

Abstract:

The scale dependence of the strength of virtually homogeneous rock is usually considered to be insignificant but the spectrum of discontinuities plays a very important role for the strength of differently sized rock elements and also controls the rock creep strain. Large-scale load tests comprised recording of the creep strain rate that was found to be strongly retarded and negligible for stresses lower than about 1/3 of the failure load. For higher stresses creep took place according to a log time law representing secondary creep that ultimately changed to tertiary creep and failure.

Keywords: Impact of scale, rock strength.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1683

Authors: Hanan Mahmoud Ezzat Mahmoud, Alaa Abd El Fatah Hefnawy

Abstract:

In this paper, we present a system for content-based retrieval of large database of classified satellite images, based on user's relevance feedback (RF).Through our proposed system, we divide each satellite image scene into small subimages, which stored in the database. The modified radial basis functions neural network has important role in clustering the subimages of database according to the Euclidean distance between the query feature vector and the other subimages feature vectors. The advantage of using RF technique in such queries is demonstrated by analyzing the database retrieval results.

Keywords: content-based image retrieval, large database of image, RBF neural net, relevance feedback

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