Search results for: Recurrent Neural Networks

Authors: Asar Khan, Peter D. Widdop, Andrew J. Day, Aliaster S. Wood, Steve, R. Mounce, John Machell

Abstract:

This paper describes an automated event detection and location system for water distribution pipelines which is based upon low-cost sensor technology and signature analysis by an Artificial Neural Network (ANN). The development of a low cost failure sensor which measures the opacity or cloudiness of the local water flow has been designed, developed and validated, and an ANN based system is then described which uses time series data produced by sensors to construct an empirical model for time series prediction and classification of events. These two components have been installed, tested and verified in an experimental site in a UK water distribution system. Verification of the system has been achieved from a series of simulated burst trials which have provided real data sets. It is concluded that the system has potential in water distribution network management.

Keywords: Detection, leakage, neural networks, sensors, water distribution networks

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

Authors: Jacqueline R. T. Alipo-on, Francesca I. F. Escobar, Myles J. T. Tan, Hezerul Abdul Karim, Nouar AlDahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases which are considered as one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis on the ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heart beat types. The dataset used in this work is the synthetic MIT-Beth Israel Hospital (MIT-BIH) Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: Heartbeat classification, convolutional neural network, electrocardiogram signals, ECG signals, generative adversarial networks, long short-term memory, LSTM, ResNet-50.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 188

Authors: Hamza A. Ali, Waleed A. J. Rasheed

Abstract:

The use of neural networks for recognition application is generally constrained by their inherent parameters inflexibility after the training phase. This means no adaptation is accommodated for input variations that have any influence on the network parameters. Attempts were made in this work to design a neural network that includes an additional mechanism that adjusts the threshold values according to the input pattern variations. The new approach is based on splitting the whole network into two subnets; main traditional net and a supportive net. The first deals with the required output of trained patterns with predefined settings, while the second tolerates output generation dynamically with tuning capability for any newly applied input. This tuning comes in the form of an adjustment to the threshold values. Two levels of supportive net were studied; one implements an extended additional layer with adjustable neuronal threshold setting mechanism, while the second implements an auxiliary net with traditional architecture performs dynamic adjustment to the threshold value of the main net that is constructed in dual-layer architecture. Experiment results and analysis of the proposed designs have given quite satisfactory conducts. The supportive layer approach achieved over 90% recognition rate, while the multiple network technique shows more effective and acceptable level of recognition. However, this is achieved at the price of network complexity and computation time. Recognition generalization may be also improved by accommodating capabilities involving all the innate structures in conjugation with Intelligence abilities with the needs of further advanced learning phases.

Keywords: Classification, Recognition, Neural Networks, Pattern Recognition, Generalization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1627

Authors: A. Golmohammadi, B. Jahandideh

Abstract:

One of the determinants of a firm-s prosperity is the customers- perceived service quality and satisfaction. While service quality is wide in scope, and consists of various dimensions, there may be differences in the relative importance of these dimensions in affecting customers- overall satisfaction of service quality. Identifying the relative rank of different dimensions of service quality is very important in that it can help managers to find out which service dimensions have a greater effect on customers- overall satisfaction. Such an insight will consequently lead to more effective resource allocation which will finally end in higher levels of customer satisfaction. This issue – despite its criticality- has not received enough attention so far. Therefore, using a sample of 240 bank customers in Iran, an artificial neural network is developed to address this gap in the literature. As customers- evaluation of service quality is a subjective process, artificial neural networks –as a brain metaphor- may appear to have a potentiality to model such a complicated process. Proposing a neural network which is able to predict the customers- overall satisfaction of service quality with a promising level of accuracy is the first contribution of this study. In addition, prioritizing the service quality dimensions in affecting customers- overall satisfaction –by using sensitivity analysis of neural network- is the second important finding of this paper.

Keywords: service quality, customer satisfaction, relative importance, artificial neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1643

Authors: Abdelhamid Louliej, Younes Jabrane

Abstract:

Satellites are becoming indispensable assets to fifth-generation (5G) new radio architecture, complementing wireless and terrestrial communication links. The combination of satellites and 5G architecture allows consumers to access all next-generation services anytime, anywhere, including scenarios, like traveling to remote areas (without coverage). Nevertheless, this solution faces several challenges, such as a significant propagation delay, Doppler frequency shift, and high Peak-to-Average Power Ratio (PAPR), causing signal distortion due to the non-linear saturation of the High-Power Amplifier (HPA). To compensate for HPA non-linearity in 5G satellite transmission, an efficient pre-distorter scheme using Neural Networks (NN) is proposed. To assess the proposed NN pre-distorter, two types of HPA were investigated: Travelling Wave Tube Amplifier (TWTA) and Solid-State Power Amplifier (SSPA). The results show that the NN pre-distorter design presents an Error Vector Magnitude (EVM) improvement by 95.26%. Normalized Mean Square Error (NMSE) and Adjacent Channel Power Ratio (ACPR) were reduced by -43,66 dB and 24.56 dBm, respectively. Moreover, the system suffers no degradation of the Bit Error Rate (BER) for TWTA and SSPA amplifiers.

Keywords: Satellites, 5G, Neural Networks, High-Power Amplifier, Travelling Wave Tube Amplifier, Solid-State Power Amplifier, EVM, NMSE, ACPR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 107

Authors: M. Mohagheghian, A. M. Ghaedi, A. Vafaei

Abstract:

An artificial neural network (ANN) model is presented for the prediction of kinematic viscosity of binary mixtures of poly (ethylene glycol) (PEG) in water as a function of temperature, number-average molecular weight and mass fraction. Kinematic viscosities data of aqueous solutions for PEG (0.55419×10-6 – 9.875×10-6 m2/s) were obtained from the literature for a wide range of temperatures (277.15 - 338.15 K), number-average molecular weight (200 -10000), and mass fraction (0.0 – 1.0). A three layer feed-forward artificial neural network was employed. This model predicts the kinematic viscosity with a mean square error (MSE) of 0.281 and the coefficient of determination (R2) of 0.983. The results show that the kinematic viscosity of binary mixture of PEG in water could be successfully predicted using an artificial neural network model.

Keywords: Artificial neural network, kinematic viscosity, poly ethylene glycol (PEG)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2530

Authors: Alexandre Boum, Salomon Madinatou

Abstract:

This paper aims at bringing a scientific contribution to the cardiac arrhythmia biomedical diagnosis systems; more precisely to the study of the amelioration of cardiac arrhythmia classification performance using artificial neural network, adaptive neuro-fuzzy and fuzzy inference systems classifiers. The purpose of this amelioration is to enable cardiologists to make reliable diagnosis through automatic cardiac arrhythmia analyzes and classifications based on high confidence classifiers. In this study, six classes of the most commonly encountered arrhythmias are considered: the Right Bundle Branch Block, the Left Bundle Branch Block, the Ventricular Extrasystole, the Auricular Extrasystole, the Atrial Fibrillation and the Normal Cardiac rate beat. From the electrocardiogram (ECG) extracted parameters, we constructed a matrix (360x360) serving as an input data sample for the classifiers based on neural networks and a matrix (1x6) for the classifier based on fuzzy logic. By varying three parameters (the quality of the neural network learning, the data size and the quality of the input parameters) the automatic classification permitted us to obtain the following performances: in terms of correct classification rate, 83.6% was obtained using the fuzzy logic based classifier, 99.7% using the neural network based classifier and 99.8% for the adaptive neuro-fuzzy based classifier. These results are based on signals containing at least 360 cardiac cycles. Based on the comparative analysis of the aforementioned three arrhythmia classifiers, the classifiers based on neural networks exhibit a better performance.

Keywords: Adaptive neuro-fuzzy, artificial neural network, cardiac arrythmias, fuzzy inference systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 708

Authors: H.Mohammadi Majd, M.Jalali Azizpour

Abstract:

In this paper back-propagation artificial neural network (BPANN )with Levenberg–Marquardt algorithm is employed to predict the deformation of the upsetting process. To prepare a training set for BPANN, some finite element simulations were carried out. The input data for the artificial neural network are a set of parameters generated randomly (aspect ratio d/h, material properties, temperature and coefficient of friction). The output data are the coefficient of polynomial that fitted on barreling curves. Neural network was trained using barreling curves generated by finite element simulations of the upsetting and the corresponding material parameters. This technique was tested for three different specimens and can be successfully employed to predict the deformation of the upsetting process

Keywords: Back-propagation artificial neural network(BPANN), prediction, upsetting

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1789

Authors: E. Sobhani-Tehrani, K. Khorasani, N. Meskin

Abstract:

This paper presents a novel integrated hybrid approach for fault diagnosis (FD) of nonlinear systems. Unlike most FD techniques, the proposed solution simultaneously accomplishes fault detection, isolation, and identification (FDII) within a unified diagnostic module. At the core of this solution is a bank of adaptive neural parameter estimators (NPE) associated with a set of singleparameter fault models. The NPEs continuously estimate unknown fault parameters (FP) that are indicators of faults in the system. Two NPE structures including series-parallel and parallel are developed with their exclusive set of desirable attributes. The parallel scheme is extremely robust to measurement noise and possesses a simpler, yet more solid, fault isolation logic. On the contrary, the series-parallel scheme displays short FD delays and is robust to closed-loop system transients due to changes in control commands. Finally, a fault tolerant observer (FTO) is designed to extend the capability of the NPEs to systems with partial-state measurement.

Keywords: Hybrid fault diagnosis, Dynamic neural networks, Nonlinear systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2221

Authors: Balimu Mwiya, Mundia Muya, Chabota Kaliba, Peter Mukalula

Abstract:

Factors affecting construction unit cost vary depending on a country’s political, economic, social and technological inclinations. Factors affecting construction costs have been studied from various perspectives. Analysis of cost factors requires an appreciation of a country’s practices. Identified cost factors provide an indication of a country’s construction economic strata. The purpose of this paper is to identify the essential factors that affect unit cost estimation and their breakdown using artificial neural networks. Twenty five (25) identified cost factors in road construction were subjected to a questionnaire survey and employing SPSS factor analysis the factors were reduced to eight. The 8 factors were analysed using neural network (NN) to determine the proportionate breakdown of the cost factors in a given construction unit rate. NN predicted that political environment accounted 44% of the unit rate followed by contractor capacity at 22% and financial delays, project feasibility and overhead & profit each at 11%. Project location, material availability and corruption perception index had minimal impact on the unit cost from the training data provided. Quantified cost factors can be incorporated in unit cost estimation models (UCEM) to produce more accurate estimates. This can create improvements in the cost estimation of infrastructure projects and establish a benchmark standard to assist the process of alignment of work practises and training of new staff, permitting the on-going development of best practises in cost estimation to become more effective.

Keywords: Construction cost factors, neural networks, roadworks, Zambian Construction Industry.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3824

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 1725

Authors: Wajdi Bellil, Chokri Ben Amar, Adel M. Alimi

Abstract:

An application of Beta wavelet networks to synthesize pass-high and pass-low wavelet filters is investigated in this work. A Beta wavelet network is constructed using a parametric function called Beta function in order to resolve some nonlinear approximation problem. We combine the filter design theory with wavelet network approximation to synthesize perfect filter reconstruction. The order filter is given by the number of neurons in the hidden layer of the neural network. In this paper we use only the first derivative of Beta function to illustrate the proposed design procedures and exhibit its performance.

Keywords: Beta wavelets, Wavenet, multiresolution analysis, perfect filter reconstruction, salient point detect, repeatability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1664

Authors: Brian A. Smith, Ronald W. McClendon, Gerrit Hoogenboom

Abstract:

The mitigation of crop loss due to damaging freezes requires accurate air temperature prediction models. An improved model for temperature prediction in Georgia was developed by including information on seasonality and modifying parameters of an existing artificial neural network model. Alternative models were compared by instantiating and training multiple networks for each model. The inclusion of up to 24 hours of prior weather information and inputs reflecting the day of year were among improvements that reduced average four-hour prediction error by 0.18°C compared to the prior model. Results strongly suggest model developers should instantiate and train multiple networks with different initial weights to establish appropriate model parameters.

Keywords: Time-series forecasting, weather modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1866

Authors: Romisaa Ali

Abstract:

The Policy Gradient approach is a subset of the Deep Reinforcement Learning (DRL) combines Deep Neural Networks (DNN) with Reinforcement Learning (RL). This approach finds the optimal policy of robot movement, based on the experience it gains from interaction with its environment. Unlike previous policy gradient algorithms, which were unable to handle the two types of error variance and bias introduced by the DNN model due to over- or underestimation, this algorithm is capable of handling both types of error variance and bias. This article will discuss the state-of-the-art SOTA policy gradient technique, trust region policy optimization (TRPO), by applying this method in various environments compared to another policy gradient method, the Proximal Policy Optimization (PPO), to explain their robust optimization, using this SOTA to gather experience data during various training phases after observing the impact of hyper-parameters on neural network performance.

Keywords: Deep neural networks, deep reinforcement learning, Proximal Policy Optimization, state-of-the-art, trust region policy optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 183

Authors: S. Anna Durai, E. Anna Saro

Abstract:

Image Compression using Artificial Neural Networks is a topic where research is being carried out in various directions towards achieving a generalized and economical network. Feedforward Networks using Back propagation Algorithm adopting the method of steepest descent for error minimization is popular and widely adopted and is directly applied to image compression. Various research works are directed towards achieving quick convergence of the network without loss of quality of the restored image. In general the images used for compression are of different types like dark image, high intensity image etc. When these images are compressed using Back-propagation Network, it takes longer time to converge. The reason for this is, the given image may contain a number of distinct gray levels with narrow difference with their neighborhood pixels. If the gray levels of the pixels in an image and their neighbors are mapped in such a way that the difference in the gray levels of the neighbors with the pixel is minimum, then compression ratio as well as the convergence of the network can be improved. To achieve this, a Cumulative distribution function is estimated for the image and it is used to map the image pixels. When the mapped image pixels are used, the Back-propagation Neural Network yields high compression ratio as well as it converges quickly.

Keywords: Back-propagation Neural Network, Cumulative Distribution Function, Correlation, Convergence.

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

Authors: Abiodun M. Aibinu, Momoh J. E. Salami, Amir A. Shafie, Athaur Rahman Najeeb

Abstract:

Autoregressive Moving average (ARMA) is a parametric based method of signal representation. It is suitable for problems in which the signal can be modeled by explicit known source functions with a few adjustable parameters. Various methods have been suggested for the coefficients determination among which are Prony, Pade, Autocorrelation, Covariance and most recently, the use of Artificial Neural Network technique. In this paper, the method of using Artificial Neural network (ANN) technique is compared with some known and widely acceptable techniques. The comparisons is entirely based on the value of the coefficients obtained. Result obtained shows that the use of ANN also gives accurate in computing the coefficients of an ARMA system.

Keywords: Autoregressive moving average, coefficients, back propagation, model parameters, neural network, weight.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2290

Authors: Rana Yousef, Khalil el Hindi

Abstract:

The behavior of Radial Basis Function (RBF) Networks greatly depends on how the center points of the basis functions are selected. In this work we investigate the use of instance reduction techniques, originally developed to reduce the storage requirements of instance based learners, for this purpose. Five Instance-Based Reduction Techniques were used to determine the set of center points, and RBF networks were trained using these sets of centers. The performance of the RBF networks is studied in terms of classification accuracy and training time. The results obtained were compared with two Radial Basis Function Networks: RBF networks that use all instances of the training set as center points (RBF-ALL) and Probabilistic Neural Networks (PNN). The former achieves high classification accuracies and the latter requires smaller training time. Results showed that RBF networks trained using sets of centers located by noise-filtering techniques (ALLKNN and ENN) rather than pure reduction techniques produce the best results in terms of classification accuracy. The results show that these networks require smaller training time than that of RBF-ALL and higher classification accuracy than that of PNN. Thus, using ALLKNN and ENN to select center points gives better combination of classification accuracy and training time. Our experiments also show that using the reduced sets to train the networks is beneficial especially in the presence of noise in the original training sets.

Keywords: Radial basis function networks, Instance-based reduction, PNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1687

Authors: Pingping Lin, Xudong Luo, Yifan Fan

Abstract:

Sentiment analysis is a very active research topic. Every day, Facebook, Twitter, Weibo, and other social media, as well as significant e-commerce websites, generate a massive amount of comments, which can be used to analyse peoples opinions or emotions. The existing methods for sentiment analysis are based mainly on sentiment dictionaries, machine learning, and deep learning. The first two kinds of methods rely on heavily sentiment dictionaries or large amounts of labelled data. The third one overcomes these two problems. So, in this paper, we focus on the third one. Specifically, we survey various sentiment analysis methods based on convolutional neural network, recurrent neural network, long short-term memory, deep neural network, deep belief network, and memory network. We compare their futures, advantages, and disadvantages. Also, we point out the main problems of these methods, which may be worthy of careful studies in the future. Finally, we also examine the application of deep learning in multimodal sentiment analysis and aspect-level sentiment analysis.

Keywords: Natural language processing, sentiment analysis, document analysis, multimodal sentiment analysis, deep learning.

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

Authors: Mona Lisa M. Oliveira, Nara A. Policarpo, Ana Luiza B. P. Barros, Carla A. Silva

Abstract:

Selective catalytic reduction systems for nitrogen oxides reduction by ammonia has been the chosen technology by most of diesel vehicle (i.e. bus and truck) manufacturers in Brazil, as also in Europe. Furthermore, at some conditions, over-stoichiometric ammonia availability is also needed that increases the NH₃ slips even more. Ammonia (NH₃) by this vehicle exhaust aftertreatment system provides a maximum efficiency of NOx removal if a significant amount of NH₃ is stored on its catalyst surface. In the other words, the practice shows that slightly less than 100% of the NOx conversion is usually targeted, so that the aqueous urea solution hydrolyzes to NH₃ via other species formation, under relatively low temperatures. This paper presents a model based on neural networks integrated with a road vehicle simulator that allows to estimate NH₃-slip emission factors for different driving conditions and patterns. The proposed model generates high NH₃slips which are not also limited in Brazil, but more efforts needed to be made to elucidate the contribution of vehicle-emitted NH₃ to the urban atmosphere.

Keywords: Ammonia slip, neural-network, vehicles emissions, SCR-NOx.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1040

Authors: Nestor A. Garcia Fragoso, Tetyana Baydyk, Ernst Kussul

Abstract:

This article contains information from our investigation in the field of voice recognition. For this purpose, we created a voice database that contains different phrases in two languages, English and Spanish, for men and women. As a classifier, the LIRA (Limited Receptive Area) grayscale neural classifier was selected. The LIRA grayscale neural classifier was developed for image recognition tasks and demonstrated good results. Therefore, we decided to develop a recognition system using this classifier for voice recognition. From a specific set of speakers, we can recognize the speaker’s voice. For this purpose, the system uses spectrograms of the voice signals as input to the system, extracts the characteristics and identifies the speaker. The results are described and analyzed in this article. The classifier can be used for speaker identification in security system or smart buildings for different types of intelligent devices.

Keywords: Extreme learning, LIRA neural classifier, speaker identification, voice recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 764

Authors: Dima Stopel, Zvi Boger, Robert Moskovitch, Yuval Shahar, Yuval Elovici

Abstract:

Computer worm detection is commonly performed by antivirus software tools that rely on prior explicit knowledge of the worm-s code (detection based on code signatures). We present an approach for detection of the presence of computer worms based on Artificial Neural Networks (ANN) using the computer's behavioral measures. Identification of significant features, which describe the activity of a worm within a host, is commonly acquired from security experts. We suggest acquiring these features by applying feature selection methods. We compare three different feature selection techniques for the dimensionality reduction and identification of the most prominent features to capture efficiently the computer behavior in the context of worm activity. Additionally, we explore three different temporal representation techniques for the most prominent features. In order to evaluate the different techniques, several computers were infected with five different worms and 323 different features of the infected computers were measured. We evaluated each technique by preprocessing the dataset according to each one and training the ANN model with the preprocessed data. We then evaluated the ability of the model to detect the presence of a new computer worm, in particular, during heavy user activity on the infected computers.

Keywords: Artificial Neural Networks, Feature Selection, Temporal Analysis, Worm Detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1728

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: Artificial Intelligence, machine learning, deep learning, convolutional neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1257

Authors: Z. Zainuddin, N. Mahat, Y. Abu Hassan

Abstract:

Since the presentation of the backpropagation algorithm, a vast variety of improvements of the technique for training a feed forward neural networks have been proposed. This article focuses on two classes of acceleration techniques, one is known as Local Adaptive Techniques that are based on weightspecific only, such as the temporal behavior of the partial derivative of the current weight. The other, known as Dynamic Adaptation Methods, which dynamically adapts the momentum factors, α, and learning rate, η, with respect to the iteration number or gradient. Some of most popular learning algorithms are described. These techniques have been implemented and tested on several problems and measured in terms of gradient and error function evaluation, and percentage of success. Numerical evidence shows that these techniques improve the convergence of the Backpropagation algorithm.

Keywords: Backpropagation, Dynamic Adaptation Methods, Local Adaptive Techniques, Neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2171

Authors: Seyed Ali Sadat Noori, Elham Sahebi Bazaz

Abstract:

Topological changes in mobile ad hoc networks frequently render routing paths unusable. Such recurrent path failures have detrimental effects on quality of service. A suitable technique for eliminating this problem is to use multiple backup paths between the source and the destination in the network. This paper proposes an effective and efficient protocol for backup and disjoint path set in ad hoc wireless network. This protocol converges to a highly reliable path set very fast with no message exchange overhead. The paths selection according to this algorithm is beneficial for mobile ad hoc networks, since it produce a set of backup paths with more high reliability. Simulation experiments are conducted to evaluate the performance of our algorithm in terms of route numbers in the path set and its reliability. In order to acquire link reliability estimates, we use link expiration time (LET) between two nodes.

Keywords: Wireless Ad Hoc Networks, Reliability, Routing, Disjoint Path

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1682

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: Mohamed Abdallah, Mostafa Warith, Roberto Narbaitz, Emil Petriu, Kevin Kennedy

Abstract:

Heterogeneity of solid waste characteristics as well as the complex processes taking place within the landfill ecosystem motivated the implementation of soft computing methodologies such as artificial neural networks (ANN), fuzzy logic (FL), and their combination. The present work uses a hybrid ANN-FL model that employs knowledge-based FL to describe the process qualitatively and implements the learning algorithm of ANN to optimize model parameters. The model was developed to simulate and predict the landfill gas production at a given time based on operational parameters. The experimental data used were compiled from lab-scale experiment that involved various operating scenarios. The developed model was validated and statistically analyzed using F-test, linear regression between actual and predicted data, and mean squared error measures. Overall, the simulated landfill gas production rates demonstrated reasonable agreement with actual data. The discussion focused on the effect of the size of training datasets and number of training epochs.

Keywords: Adaptive neural fuzzy inference system (ANFIS), gas production, landfill

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2415

Authors: D. Singh, R. Yousefi, M. Boroushaki

Abstract:

Intelligent deep-drawing is an instrumental research field in sheet metal forming. A set of 28 different experimental data have been employed in this paper, investigating the roles of die radius, punch radius, friction coefficients and drawing ratios for axisymmetric workpieces deep drawing. This paper focuses an evolutionary neural network, specifically, error back propagation in collaboration with genetic algorithm. The neural network encompasses a number of different functional nodes defined through the established principles. The input parameters, i.e., punch radii, die radii, friction coefficients and drawing ratios are set to the network; thereafter, the material outputs at two critical points are accurately calculated. The output of the network is used to establish the best parameters leading to the most uniform thickness in the product via the genetic algorithm. This research achieved satisfactory results based on demonstration of neural networks.

Keywords: Deep-drawing, Neural network, Genetic algorithm, Sheet metal forming.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2202

Authors: El Mahdi Barrah, Said Safi, Abdessamad Malaoui

Abstract:

In this paper, we present an algorithm for reconstruction from incomplete 2D scans for tifinagh characters. This algorithm is based on using correlation between the lost block and its neighbors. This system proposed contains three main parts: pre-processing, features extraction and recognition. In the first step, we construct a database of tifinagh characters. In the second step, we will apply “shape analysis algorithm”. In classification part, we will use Neural Network. The simulation results demonstrate that the proposed method give good results.

Keywords: Tifinagh character recognition, Neural networks, Local cost computation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1286

Authors: A. M. Pashayev, D. D. Askerov, C. Ardil, R. A. Sadiqov, P. S. Abdullayev

Abstract:

Researches show that probability-statistical methods application, especially at the early stage of the aviation Gas Turbine Engine (GTE) technical condition diagnosing, when the flight information has property of the fuzzy, limitation and uncertainty is unfounded. Hence the efficiency of application of new technology Soft Computing at these diagnosing stages with the using of the Fuzzy Logic and Neural Networks methods is considered. According to the purpose of this problem training with high accuracy of fuzzy multiple linear and non-linear models (fuzzy regression equations) which received on the statistical fuzzy data basis is made. For GTE technical condition more adequate model making dynamics of skewness and kurtosis coefficients- changes are analysed. Researches of skewness and kurtosis coefficients values- changes show that, distributions of GTE work parameters have fuzzy character. Hence consideration of fuzzy skewness and kurtosis coefficients is expedient. Investigation of the basic characteristics changes- dynamics of GTE work parameters allows drawing conclusion on necessity of the Fuzzy Statistical Analysis at preliminary identification of the engines' technical condition. Researches of correlation coefficients values- changes shows also on their fuzzy character. Therefore for models choice the application of the Fuzzy Correlation Analysis results is offered. At the information sufficiency is offered to use recurrent algorithm of aviation GTE technical condition identification (Hard Computing technology is used) on measurements of input and output parameters of the multiple linear and non-linear generalised models at presence of noise measured (the new recursive Least Squares Method (LSM)). The developed GTE condition monitoring system provides stageby- stage estimation of engine technical conditions. As application of the given technique the estimation of the new operating aviation engine technical condition was made.

Keywords: aviation gas turbine engine, technical condition, fuzzy logic, neural networks, fuzzy statistics

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1570

Authors: Vipul M. Patel, Hemantkumar B. Mehta

Abstract:

Technological innovations in electronic world demand novel, compact, simple in design, less costly and effective heat transfer devices. Closed Loop Pulsating Heat Pipe (CLPHP) is a passive phase change heat transfer device and has potential to transfer heat quickly and efficiently from source to sink. Thermal performance of a CLPHP is governed by various parameters such as number of U-turns, orientations, input heat, working fluids and filling ratio. The present paper is an attempt to predict the thermal performance of a CLPHP using Artificial Neural Network (ANN). Filling ratio and heat input are considered as input parameters while thermal resistance is set as target parameter. Types of neural networks considered in the present paper are radial basis, generalized regression, linear layer, cascade forward back propagation, feed forward back propagation; feed forward distributed time delay, layer recurrent and Elman back propagation. Linear, logistic sigmoid, tangent sigmoid and Radial Basis Gaussian Function are used as transfer functions. Prediction accuracy is measured based on the experimental data reported by the researchers in open literature as a function of Mean Absolute Relative Deviation (MARD). The prediction of a generalized regression ANN model with spread constant of 4.8 is found in agreement with the experimental data for MARD in the range of ±1.81%.

Keywords: ANN models, CLPHP, filling ratio, generalized regression, spread constant.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1184