Search results for: Back propagation neural network

Authors: D. A. K. S. Gunaratna, N. D. Kodikara, H. L. Premaratne

Abstract:

Automatic currency note recognition invariably depends on the currency note characteristics of a particular country and the extraction of features directly affects the recognition ability. Sri Lanka has not been involved in any kind of research or implementation of this kind. The proposed system “SLCRec" comes up with a solution focusing on minimizing false rejection of notes. Sri Lankan currency notes undergo severe changes in image quality in usage. Hence a special linear transformation function is adapted to wipe out noise patterns from backgrounds without affecting the notes- characteristic images and re-appear images of interest. The transformation maps the original gray scale range into a smaller range of 0 to 125. Applying Edge detection after the transformation provided better robustness for noise and fair representation of edges for new and old damaged notes. A three layer back propagation neural network is presented with the number of edges detected in row order of the notes and classification is accepted in four classes of interest which are 100, 500, 1000 and 2000 rupee notes. The experiments showed good classification results and proved that the proposed methodology has the capability of separating classes properly in varying image conditions.

Keywords: Artificial intelligence, linear transformation and pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2833

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, capsule network, capacity optimization, character recognition, data augmentation; semantic segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 701

Authors: A. Bagheri Garmarudi, M. Khanmohammadi, N. Khoddami, K. Shabani

Abstract:

Determination of nano particle size is substantial since the nano particle size exerts a significant effect on various properties of nano materials. Accordingly, proposing non-destructive, accurate and rapid techniques for this aim is of high interest. There are some conventional techniques to investigate the morphology and grain size of nano particles such as scanning electron microscopy (SEM), atomic force microscopy (AFM) and X-ray diffractometry (XRD). Vibrational spectroscopy is utilized to characterize different compounds and applied for evaluation of the average particle size based on relationship between particle size and near infrared spectra [1,4] , but it has never been applied in quantitative morphological analysis of nano materials. So far, the potential application of nearinfrared (NIR) spectroscopy with its ability in rapid analysis of powdered materials with minimal sample preparation, has been suggested for particle size determination of powdered pharmaceuticals. The relationship between particle size and diffuse reflectance (DR) spectra in near infrared region has been applied to introduce a method for estimation of particle size. Back propagation artificial neural network (BP-ANN) as a nonlinear model was applied to estimate average particle size based on near infrared diffuse reflectance spectra. Thirty five different nano TiO2 samples with different particle size were analyzed by DR-FTNIR spectrometry and the obtained data were processed by BP- ANN.

Keywords: near infrared, particle size, chemometrics, neuralnetwork, nano structure.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1842

Authors: N. Klinpikul, P. Srichandr, N. Poolthong, N. Thavarungkul

Abstract:

Breastfeeding has been receiving much attention of late. Prolonged sitting for breastfeeding often results in back pain of the mothers. This paper reports the findings of a study on the effect of some factors, especially lumbar support, on back pain of breastfeeding mothers. The results showed that the use of lumbar support can reduce back pain of breastfeeding mothers significantly. Back pain was found to increase with breastfeeding time and the rate of increase was lower when lumbar supports were used. When lumbar support thickness was increased gradually from zero (no support) to 11 cm., the degree of low back pain decreased; rapidly at first, then slowly, and leveled off when the thickness reached 9 cm. Younger mothers were less prone to back pain than older mothers. The implications of the findings are discussed.

Keywords: back pain, breastfeeding, lumbar support

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1983

Authors: S. Farzi

Abstract:

Recently, a lot of attention has been devoted to advanced techniques of system modeling. PNN(polynomial neural network) is a GMDH-type algorithm (Group Method of Data Handling) which is one of the useful method for modeling nonlinear systems but PNN performance depends strongly on the number of input variables and the order of polynomial which are determined by trial and error. In this paper, we introduce GPNN (genetic polynomial neural network) to improve the performance of PNN. GPNN determines the number of input variables and the order of all neurons with GA (genetic algorithm). We use GA to search between all possible values for the number of input variables and the order of polynomial. GPNN performance is obtained by two nonlinear systems. the quadratic equation and the time series Dow Jones stock index are two case studies for obtaining the GPNN performance.

Keywords: GMDH, GPNN, GA, PNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2094

Authors: M. Khajezadeh, M. Saied Fallah Niasar, S. Ali Asli, D. Davani Davari, M. Godarzi, Y. Asgari

Abstract:

This study aims to explore the joint application of both Boston and Ansoff matrices in the operational development of the product. We conduct deep analysis, by utilizing the Artificial Neural Network, to predict the position of the product in the market while the company is interested in increasing its share. The data are gathered from two industries, called hygiene and detergent. In doing so, the effort is being made by investigating the behavior of top player companies and, recommend strategic orientations. In conclusion, this combination analysis is appropriate for operational development; as well, it plays an important role in providing the position of the product in the market for both hygiene and detergent industries. More importantly, it will elaborate on the company’s strategies to increase its market share related to a combination of the Boston Consulting Group (BCG) Matrix and Ansoff Matrix.

Keywords: Artificial neural network, portfolio analysis, BCG matrix, Ansoff matrix.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1956

Authors: Farouk Cherif

Abstract:

This paper is concerned with the existence and unique¬ness of pseudo-almost periodic solutions to the chaotic delayed neural networks (t)= —Dx(t) ± A f (x (t)) B f (x (t — r)) C f (x(p))dp J (t) . t-o Under some suitable assumptions on A, B, C, D, J and f, the existence and uniqueness of a pseudo-almost periodic solution to equation above is obtained. The results of this paper are new and they complement previously known results.

Keywords: Chaotic neural network, Hamiltonian systems, Pseudo almost periodic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1310

Authors: Jia Xin Low, Keng Wah Choo

Abstract:

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Keywords: Convolutional neural network, discrete wavelet transform, deep learning, heart sound classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1146

Authors: Ashish Payal, C. S. Rai, B. V. R. Reddy

Abstract:

With the increasing use and application of Wireless Sensor Networks (WSN), need has arisen to explore them in more effective and efficient manner. An important area which can bring efficiency to WSNs is the localization process, which refers to the estimation of the position of wireless sensor nodes in an ad hoc network setting, in reference to a coordinate system that may be internal or external to the network. In this paper, we have done comparison and analysed Sigmoidal Feedforward Artificial Neural Networks (SFFANNs) and Radial Basis Function (RBF) networks for developing localization framework in WSNs. The presented work utilizes the Received Signal Strength Indicator (RSSI), measured by static node on 100 x 100 m² grid from three anchor nodes. The comprehensive evaluation of these approaches is done using MATLAB software. The simulation results effectively demonstrate that FFANNs based sensor motes will show better localization accuracy as compared to RBF.

Keywords: Localization, wireless sensor networks, artificial neural network, radial basis function, multi-layer perceptron, backpropagation, RSSI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1523

Authors: A. Sina, A. Aeenmehr, H. Mohamadian

Abstract:

Optimization and control of reactive power distribution in the power systems leads to the better operation of the reactive power resources. Reactive power control reduces considerably the power losses and effective loads and improves the power factor of the power systems. Another important reason of the reactive power control is improving the voltage profile of the power system. In this paper, voltage and reactive power control using Neural Network techniques have been applied to the 33 shines- Tehran Electric Company. In this suggested ANN, the voltages of PQ shines have been considered as the input of the ANN. Also, the generators voltages, tap transformers and shunt compensators have been considered as the output of ANN. Results of this techniques have been compared with the Linear Programming. Minimization of the transmission line power losses has been considered as the objective function of the linear programming technique. The comparison of the results of the ANN technique with the LP shows that the ANN technique improves the precision and reduces the computation time. ANN technique also has a simple structure and this causes to use the operator experience.

Keywords: voltage control, linear programming, artificial neural network, power systems

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1760

Authors: Kesari Verma, Aniruddha S. Thoke, Pritam Singh

Abstract:

Automatic face detection is a complex problem in image processing. Many methods exist to solve this problem such as template matching, Fisher Linear Discriminate, Neural Networks, SVM, and MRC. Success has been achieved with each method to varying degrees and complexities. In proposed algorithm we used upright, frontal faces for single gray scale images with decent resolution and under good lighting condition. In the field of face recognition technique the single face is matched with single face from the training dataset. The author proposed a neural network based face detection algorithm from the photographs as well as if any test data appears it check from the online scanned training dataset. Experimental result shows that the algorithm detected up to 95% accuracy for any image.

Keywords: Face Detection, Face Recognition, NN Approach, PCA Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2301

Authors: Marque Adrien, Delahaye Daniel, Marechal Pierre, Berry Isabelle

Abstract:

Wind direction and uncertainty are crucial in aircraft or unmanned aerial vehicle trajectories. By computing wind covariance matrices on each spatial grid point, these spatial grids can be defined as images with symmetric positive definite matrix elements. A data pre-processing step, a specific convolution, a specific max-pooling, and specific flatten layers are implemented to process such images. Then, the neural network is applied to spatial grids, whose elements are wind covariance matrices, to solve classification problems related to the feasibility of unmanned aerial vehicles based on wind direction and wind uncertainty.

Keywords: Wind direction, uncertainty level, Unmanned Aerial Vehicle, convolution neural network, SPD matrices.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 28

Authors: Foad Nazari, Seyed Mahmood Hosseini, Mohammad Hossein Abolbashari, Mohammad Hassan Abolbashari

Abstract:

The present study is concerned with the optimal design of functionally graded plates using particle swarm optimization (PSO) algorithm. In this study, meshless local Petrov-Galerkin (MLPG) method is employed to obtain the functionally graded (FG) plate’s natural frequencies. Effects of two parameters including thickness to height ratio and volume fraction index on the natural frequencies and total mass of plate are studied by using the MLPG results. Then the first natural frequency of the plate, for different conditions where MLPG data are not available, is predicted by an artificial neural network (ANN) approach which is trained by back-error propagation (BEP) technique. The ANN results show that the predicted data are in good agreement with the actual one. To maximize the first natural frequency and minimize the mass of FG plate simultaneously, the weighted sum optimization approach and PSO algorithm are used. However, the proposed optimization process of this study can provide the designers of FG plates with useful data.

Keywords: Optimal design, natural frequency, FG plate, hybrid meshless method, MLPG method, ANN approach, particle swarm optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1433

Authors: Petia Georgieva, Sebastião Feyo de Azevedo

Abstract:

This paper is focused on issues of nonlinear dynamic process modeling and model-based predictive control of a fed-batch sugar crystallization process applying the concept of artificial neural networks as computational tools. The control objective is to force the operation into following optimal supersaturation trajectory. It is achieved by manipulating the feed flow rate of sugar liquor/syrup, considered as the control input. A feed forward neural network (FFNN) model of the process is first built as part of the controller structure to predict the process response over a specified (prediction) horizon. The predictions are supplied to an optimization procedure to determine the values of the control action over a specified (control) horizon that minimizes a predefined performance index. The control task is rather challenging due to the strong nonlinearity of the process dynamics and variations in the crystallization kinetics. However, the simulation results demonstrated smooth behavior of the control actions and satisfactory reference tracking.

Keywords: Feed forward neural network, process modelling, model predictive control, crystallization process.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1875

Authors: Mohammad Namazi, Mohammad Sadeghzadeh Maharluie

Abstract:

Predicting earnings management is vital for the capital market participants, financial analysts and managers. The aim of this research is attempting to respond to this query: Is there a significant difference between the regression model and neural networks’ models in predicting earnings management, and which one leads to a superior prediction of it? In approaching this question, a Linear Regression (LR) model was compared with two neural networks including Multi-Layer Perceptron (MLP), and Generalized Regression Neural Network (GRNN). The population of this study includes 94 listed companies in Tehran Stock Exchange (TSE) market from 2003 to 2011. After the results of all models were acquired, ANOVA was exerted to test the hypotheses. In general, the summary of statistical results showed that the precision of GRNN did not exhibit a significant difference in comparison with MLP. In addition, the mean square error of the MLP and GRNN showed a significant difference with the multi variable LR model. These findings support the notion of nonlinear behavior of the earnings management. Therefore, it is more appropriate for capital market participants to analyze earnings management based upon neural networks techniques, and not to adopt linear regression models.

Keywords: Earnings management, generalized regression neural networks, linear regression, multi-layer perceptron, Tehran stock exchange.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2104

Authors: Marcio Leal, Marta Villamil

Abstract:

Computacional recognition of sign languages aims to allow a greater social and digital inclusion of deaf people through interpretation of their language by computer. This article presents a model of recognition of two of global parameters from sign languages; hand configurations and hand movements. Hand motion is captured through an infrared technology and its joints are built into a virtual three-dimensional space. A Multilayer Perceptron Neural Network (MLP) was used to classify hand configurations and Dynamic Time Warping (DWT) recognizes hand motion. Beyond of the method of sign recognition, we provide a dataset of hand configurations and motion capture built with help of fluent professionals in sign languages. Despite this technology can be used to translate any sign from any signs dictionary, Brazilian Sign Language (Libras) was used as case study. Finally, the model presented in this paper achieved a recognition rate of 80.4%.

Keywords: Sign language recognition, computer vision, infrared, artificial neural network, dynamic time warping.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 878

Authors: Gizelle K. Vianna, Gabriel V. Cunha, Gustavo S. Oliveira

Abstract:

Foliage diseases in plants can cause a reduction in both quality and quantity of agricultural production. Intelligent detection of plant diseases is an essential research topic as it may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. This work investigates ways to recognize the late blight disease from the analysis of tomato digital images, collected directly from the field. A pair of multilayer perceptron neural network analyzes the digital images, using data from both RGB and HSL color models, and classifies each image pixel. One neural network is responsible for the identification of healthy regions of the tomato leaf, while the other identifies the injured regions. The outputs of both networks are combined to generate the final classification of each pixel from the image and the pixel classes are used to repaint the original tomato images by using a color representation that highlights the injuries on the plant. The new images will have only green, red or black pixels, if they came from healthy or injured portions of the leaf, or from the background of the image, respectively. The system presented an accuracy of 97% in detection and estimation of the level of damage on the tomato leaves caused by late blight.

Keywords: Artificial neural networks, digital image processing, pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2552

Authors: Morteza Raki, Abolghasem Zabihollah, Omid Askari

Abstract:

Cantilever beam is a simplified sample of a lot of mechanical components used in a wide range of applications, including many industries such as gas turbine blade. Due to the nature of the operating conditions, beams are subject to variety of damages especially crack propagates. Crack propagation may lead to catastrophic failure during operation. Therefore, online detection of crack presence and its propagation is very important and may reduce possible significant cost of the whole system failure. This paper aims to investigate the effect of cracks presence and crack propagation on one end fixed beam`s vibration. A finite element model will be developed for the blade in which the modal response of the structure with and without crack will be studied. 

Keywords: Blade, crack propagation, health monitoring, modal analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2003

Authors: Pierre Abou-Haila, Richard Hall, Mark Dawes

Abstract:

Instead of representing individual cognition only, population cognition is represented using artificial neural networks whilst maintaining individuality. This population network trains continuously, simulating adaptation. An implementation of two coexisting populations is compared to the Lotka-Volterra model of predator-prey interaction. Applications include multi-agent systems such as artificial life or computer games.

Keywords: Collective unconsciousness, neural networks, adaptation, predator-prey simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1825

Authors: S. Makal, L. Ozyilmaz, S. Palavaroglu

Abstract:

Gene, principal unit of inheritance, is an ordered sequence of nucleotides. The genes of eukaryotic organisms include alternating segments of exons and introns. The region of Deoxyribonucleic acid (DNA) within a gene containing instructions for coding a protein is called exon. On the other hand, non-coding regions called introns are another part of DNA that regulates gene expression by removing from the messenger Ribonucleic acid (RNA) in a splicing process. This paper proposes to determine splice junctions that are exon-intron boundaries by analyzing DNA sequences. A splice junction can be either exon-intron (EI) or intron exon (IE). Because of the popularity and compatibility of the artificial neural network (ANN) in genetic fields; various ANN models are applied in this research. Multi-layer Perceptron (MLP), Radial Basis Function (RBF) and Generalized Regression Neural Networks (GRNN) are used to analyze and detect the splice junctions of gene sequences. 10-fold cross validation is used to demonstrate the accuracy of networks. The real performances of these networks are found by applying Receiver Operating Characteristic (ROC) analysis.

Keywords: Gene, neural networks, ROC analysis, splice junctions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1658

Authors: Chi-Fang Huang, Yun-Shiow Chen, Yun-Kung Chung

Abstract:

In the past decade, artificial neural networks (ANNs) have been regarded as an instrument for problem-solving and decision-making; indeed, they have already done with a substantial efficiency and effectiveness improvement in industries and businesses. In this paper, the Back-Propagation neural Networks (BPNs) will be modulated to demonstrate the performance of the collaborative forecasting (CF) function of a Collaborative Planning, Forecasting and Replenishment (CPFR®) system. CPFR functions the balance between the sufficient product supply and the necessary customer demand in a Supply and Demand Chain (SDC). Several classical standard BPN will be grouped, collaborated and exploited for the easy implementation of the proposed modular ANN framework based on the topology of a SDC. Each individual BPN is applied as a modular tool to perform the task of forecasting SKUs (Stock-Keeping Units) levels that are managed and supervised at a POS (point of sale), a wholesaler, and a manufacturer in an SDC. The proposed modular BPN-based CF system will be exemplified and experimentally verified using lots of datasets of the simulated SDC. The experimental results showed that a complex CF problem can be divided into a group of simpler sub-problems based on the single independent trading partners distributed over SDC, and its SKU forecasting accuracy was satisfied when the system forecasted values compared to the original simulated SDC data. The primary task of implementing an autonomous CF involves the study of supervised ANN learning methodology which aims at making “knowledgeable" decision for the best SKU sales plan and stocks management.

Keywords: CPFR, artificial neural networks, global logistics, supply and demand chain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1993

Authors: Ali Reza Tahavvor, Saeed Hosseini, Nazli Jowkar, Afshin Karimzadeh Fard

Abstract:

Experimental & numeral study of temperature distribution during milling process, is important in milling quality and tools life aspects. In the present study the milling cross-section temperature is determined by using Artificial Neural Networks (ANN) according to the temperature of certain points of the work piece and the point specifications and the milling rotational speed of the blade. In the present work, at first three-dimensional model of the work piece is provided and then by using the Computational Heat Transfer (CHT) simulations, temperature in different nods of the work piece are specified in steady-state conditions. Results obtained from CHT are used for training and testing the ANN approach. Using reverse engineering and setting the desired x, y, z and the milling rotational speed of the blade as input data to the network, the milling surface temperature determined by neural network is presented as output data. The desired points temperature for different milling blade rotational speed are obtained experimentally and by extrapolation method for the milling surface temperature is obtained and a comparison is performed among the soft programming ANN, CHT results and experimental data and it is observed that ANN soft programming code can be used more efficiently to determine the temperature in a milling process.

Keywords: Milling process, rotational speed, Artificial Neural Networks, temperature.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2332

Authors: Nermine Ahmed Hendy, Hania Farag

Abstract:

Emotion recognition is an important research field that finds lots of applications nowadays. This work emphasizes on recognizing different emotions from speech signal. The extracted features are related to statistics of pitch, formants, and energy contours, as well as spectral, perceptual and temporal features, jitter, and shimmer. The Artificial Neural Networks (ANN) was chosen as the classifier. Working on finding a robust and fast ANN classifier suitable for different real life application is our concern. Several experiments were carried out on different ANN to investigate the different factors that impact the classification success rate. Using a database containing 7 different emotions, it will be shown that with a proper and careful adjustment of features format, training data sorting, number of features selected and even the ANN type and architecture used, a success rate of 85% or even more can be achieved without increasing the system complicity and the computation time

Keywords: Classification, emotion recognition, features extraction, feature selection, neural network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4698

Authors: Javed Ahmed, M. N. Jafri, J. Ahmad, Muhammad I. Khan

Abstract:

Real-time object tracking is a problem which involves extraction of critical information from complex and uncertain imagedata. In this paper, we present a comprehensive methodology to design an artificial neural network (ANN) for a real-time object tracking application. The object, which is tracked for the purpose of demonstration, is a specific airplane. However, the proposed ANN can be trained to track any other object of interest. The ANN has been simulated and tested on the training and testing datasets, as well as on a real-time streaming video. The tracking error is analyzed with post-regression analysis tool, which finds the correlation among the calculated coordinates and the correct coordinates of the object in the image. The encouraging results from the computer simulation and analysis show that the proposed ANN architecture is a good candidate solution to a real-time object tracking problem.

Keywords: Image processing, machine vision, neural networks, real-time object tracking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3508

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean   Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: Air quality prediction, deep learning algorithms, time series forecasting, look-back window.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1167

Authors: Oktay Nusratov, Ramin Rzaev, Aydin Goyushov

Abstract:

Fuzzy inference method based approach to the forming of modular intellectual system of assessment the quality of communication services is proposed. Developed under this approach the basic fuzzy estimation model takes into account the recommendations of the International Telecommunication Union in respect of the operation of packet switching networks based on IPprotocol. To implement the main features and functions of the fuzzy control system of quality telecommunication services it is used multilayer feedforward neural network.

Keywords: Quality of communication, IP-telephony, Fuzzy set, Fuzzy implication, Neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2347

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 1830

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 3035

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 1542

Authors: András Barta, István Vajk

Abstract:

In pattern recognition applications the low level segmentation and the high level object recognition are generally considered as two separate steps. The paper presents a method that bridges the gap between the low and the high level object recognition. It is based on a Bayesian network representation and network propagation algorithm. At the low level it uses hierarchical structure of quadratic spline wavelet image bases. The method is demonstrated for a simple circuit diagram component identification problem.

Keywords: Object recognition, Bayesian network, Wavelets, Document processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1485