Search results for: Complex valued neural network

Authors: Omer F. Cansiz, Said M. Easa

Abstract:

The purpose of this study is mainly to predict collision frequency on the horizontal tangents combined with vertical curves using artificial neural network methods. The proposed ANN models are compared with existing regression models. First, the variables that affect collision frequency were investigated. It was found that only the annual average daily traffic, section length, access density, the rate of vertical curvature, smaller curve radius before and after the tangent were statistically significant according to related combinations. Second, three statistical models (negative binomial, zero inflated Poisson and zero inflated negative binomial) were developed using the significant variables for three alignment combinations. Third, ANN models are developed by applying the same variables for each combination. The results clearly show that the ANN models have the lowest mean square error value than those of the statistical models. Similarly, the AIC values of the ANN models are smaller to those of the regression models for all the combinations. Consequently, the ANN models have better statistical performances than statistical models for estimating collision frequency. The ANN models presented in this paper are recommended for evaluating the safety impacts 3D alignment elements on horizontal tangents.

Keywords: Collision frequency, horizontal tangent, 3D two-lane highway, negative binomial, zero inflated Poisson, artificial neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1611

Authors: Mario Gonzalez, David Dominguez, Francisco B. Rodriguez

Abstract:

An attractor neural network on the small-world topology is studied. A learning pattern is presented to the network, then a stimulus carrying local information is applied to the neurons and the retrieval of block-like structure is investigated. A synaptic noise decreases the memory capability. The change of stability from local to global attractors is shown to depend on the long-range character of the network connectivity.

Keywords: Hebbian learning, image recognition, small world, spatial information.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1832

Authors: Gonzalo Rubio, Eusebio Valero, Sven Lanzan

Abstract:

The design of a modern aircraft is based on three pillars: theoretical results, experimental test and computational simulations. As a results of this, Computational Fluid Dynamic (CFD) solvers are widely used in the aeronautical field. These solvers require the correct selection of many parameters in order to obtain successful results. Besides, the computational time spent in the simulation depends on the proper choice of these parameters. In this paper we create an expert system capable of making an accurate prediction of the number of iterations and time required for the convergence of a computational fluid dynamic (CFD) solver. Artificial neural network (ANN) has been used to design the expert system. It is shown that the developed expert system is capable of making an accurate prediction the number of iterations and time required for the convergence of a CFD solver.

Keywords: Artificial Neural Network, Computational Fluid Dynamics, Optimization

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2923

Authors: H. Bonakdari, I. Ebtehaj

Abstract:

The prediction of scour depth around bridge piers is frequently considered in river engineering. One of the key aspects in efficient and optimum bridge structure design is considered to be scour depth estimation around bridge piers. In this study, scour depth around bridge piers is estimated using two methods, namely the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Artificial Neural Network (ANN). Therefore, the effective parameters in scour depth prediction are determined using the ANN and ANFIS methods via dimensional analysis, and subsequently, the parameters are predicted. In the current study, the methods’ performances are compared with the nonlinear regression (NLR) method. The results show that both methods presented in this study outperform existing methods. Moreover, using the ratio of pier length to flow depth, ratio of median diameter of particles to flow depth, ratio of pier width to flow depth, the Froude number and standard deviation of bed grain size parameters leads to optimal performance in scour depth estimation.

Keywords: Adaptive neuro-fuzzy inference system, ANFIS, artificial neural network, ANN, bridge pier, scour depth, nonlinear regression, NLR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 889

Authors: Kifah Tout, Nisrine Sinno, Mohamad Mikati

Abstract:

Many studies have focused on the nonlinear analysis of electroencephalography (EEG) mainly for the characterization of epileptic brain states. It is assumed that at least two states of the epileptic brain are possible: the interictal state characterized by a normal apparently random, steady-state EEG ongoing activity; and the ictal state that is characterized by paroxysmal occurrence of synchronous oscillations and is generally called in neurology, a seizure. The spatial and temporal dynamics of the epileptogenic process is still not clear completely especially the most challenging aspects of epileptology which is the anticipation of the seizure. Despite all the efforts we still don-t know how and when and why the seizure occurs. However actual studies bring strong evidence that the interictal-ictal state transition is not an abrupt phenomena. Findings also indicate that it is possible to detect a preseizure phase. Our approach is to use the neural network tool to detect interictal states and to predict from those states the upcoming seizure ( ictal state). Analysis of the EEG signal based on neural networks is used for the classification of EEG as either seizure or non-seizure. By applying prediction methods it will be possible to predict the upcoming seizure from non-seizure EEG. We will study the patients admitted to the epilepsy monitoring unit for the purpose of recording their seizures. Preictal, ictal, and post ictal EEG recordings are available on such patients for analysis The system will be induced by taking a body of samples then validate it using another. Distinct from the two first ones a third body of samples is taken to test the network for the achievement of optimum prediction. Several methods will be tried 'Backpropagation ANN' and 'RBF'.

Keywords: Artificial neural network (ANN), automatic prediction, epileptic seizures analysis, genetic algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1514

Authors: Samia Salah, M’hamed Hadj Sadok, Abderrezak Guessoum

Abstract:

In this paper, we propose a new modular approach called neuroglial consisting of two neural networks slow and fast which emulates a biological reality recently discovered. The implementation is based on complex multi-time scale systems; validation is performed on the model of the asynchronous machine. We applied the geometric approach based on the Gerschgorin circles for the decoupling of fast and slow variables, and the method of singular perturbations for the development of reductions models.

This new architecture allows for smaller networks with less complexity and better performance in terms of mean square error and convergence than the single network model.

Keywords: Gerschgorin’s Circles, Neuroglial Network, Multi time scales systems, Singular perturbation method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1567

Authors: S. Zappacosta, C. Bove, M. Carmela Marinelli, P. di Lauro, K. Spasenovic, L. Ostano, G. Aiello, M. Pietrosanto

Abstract:

This paper proposes a neural network approach for assessing flood hazard mapping. The core of the model is a machine learning component fed by frequency ratios, namely statistical correlations between flood event occurrences and a selected number of topographic properties. The classification capability was compared with the flood hazard mapping River Basin Plans (Piani Assetto Idrogeologico, acronimed as PAI) designed by the Italian Institute for Environmental Research and Defence, ISPRA (Istituto Superiore per la Protezione e la Ricerca Ambientale), encoding four different increasing flood hazard levels. The study area of Piemonte, an Italian region, has been considered without loss of generality. The frequency ratios may be used as a standalone block to model the flood hazard mapping. Nevertheless, the mixture with a neural network improves the classification power of several percentage points, and may be proposed as a basic tool to model the flood hazard map in a wider scope.

Keywords: flood modeling, hazard map, neural networks, hydrogeological risk, flood risk assessment

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 663

Authors: Pavan K. Rallabandi, Kailash C. Patidar

Abstract:

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

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

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2848

Authors: Salim Ouchtati, Bedda Mouldi, Abderrazak Lachouri

Abstract:

In this paper we present an off line system for the recognition of the handwritten numeric chains. Our work is divided in two big parts. The first part is the realization of a recognition system of the isolated handwritten digits. In this case the study is based mainly on the evaluation of neural network performances, trained with the gradient back propagation algorithm. The used parameters to form the input vector of the neural network are extracted on the binary images of the digits by several methods: the distribution sequence, the Barr features and the centred moments of the different projections and profiles. The second part is the extension of our system for the reading of the handwritten numeric chains constituted of a variable number of digits. The vertical projection is used to segment the numeric chain at isolated digits and every digit (or segment) will be presented separately to the entry of the system achieved in the first part (recognition system of the isolated handwritten digits). The result of the recognition of the numeric chain will be displayed at the exit of the global system.

Keywords: Optical Characters Recognition, Neural networks, Barr features, Image processing, Pattern Recognition, Featuresextraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1402

Authors: Nicole Pearcy, Jonathan J. Crofts, Nadia Chuzhanova

Abstract:

In this paper, we employ a directed hypergraph model to investigate the extent to which environmental variability influences the set of available biochemical reactions within a living cell. Such an approach avoids the limitations of the usual complex network formalism by allowing for the multilateral relationships (i.e. connections involving more than two nodes) that naturally occur within many biological processes. More specifically, we extend the concept of network reciprocity to complex hyper-networks, thus enabling us to characterise a network in terms of the existence of mutual hyper-connections, which may be considered a proxy for metabolic network complexity. To demonstrate these ideas, we study 115 metabolic hyper-networks of bacteria, each of which can be classified into one of 6 increasingly varied habitats. In particular, we found that reciprocity increases significantly with increased environmental variability, supporting the view that organism adaptability leads to increased complexities in the resultant biochemical networks.

Keywords: Complexity, hypergraphs, reciprocity, metabolism.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2411

Authors: Vidhu Mitha Goutham, Ruma Mukherjee

Abstract:

The low availability of well-trained, unlimited, dynamic-access models for specific languages makes it hard for corporate users to adopt quick translation techniques and incorporate them into product solutions. As translation tasks increasingly require a dynamic sequence learning curve; stable, cost-free opensource models are scarce. We survey and compare current translation techniques and propose a modified sequence to sequence model repurposed with attention techniques. Sequence learning using an encoder-decoder model is now paving the path for higher precision levels in translation. Using a Convolutional Neural Network (CNN) encoder and a Recurrent Neural Network (RNN) decoder background, we use Fairseq tools to produce an end-to-end bilingually trained Spanish-English machine translation model including source language detection. We acquire competitive results using a duo-lingo-corpus trained model to provide for prospective, ready-made plug-in use for compound sentences and document translations. Our model serves a decent system for large, organizational data translation needs. While acknowledging its shortcomings and future scope, it also identifies itself as a well-optimized deep neural network model and solution.

Keywords: Attention, encoder-decoder, Fairseq, Seq2Seq, Spanish, translation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 430

Authors: Zixin Liu, Shu Lü, Shouming Zhong, Mao Ye

Abstract:

The problem of exponential stability and periodicity for a class of cellular neural networks (DCNNs) with time-varying delays is investigated. By dividing the network state variables into subgroups according to the characters of the neural networks, some sufficient conditions for exponential stability and periodicity are derived via the methods of variation parameters and inequality techniques. These conditions are represented by some blocks of the interconnection matrices. Compared with some previous methods, the method used in this paper does not resort to any Lyapunov function, and the results derived in this paper improve and generalize some earlier criteria established in the literature cited therein. Two examples are discussed to illustrate the main results.

Keywords: Cellular neural networks, exponential stability, time varying delays, partitioned matrices, periodic solution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1490

Authors: R. B. Knudsen, O. T. Rasmussen, R. A. Alphinas

Abstract:

The reason for conducting this research is to develop an algorithm that is capable of classifying news articles from the automobile industry, according to the competitive actions that they entail, with the use of Text Mining (TM) methods. It is needed to test how to properly preprocess the data for this research by preparing pipelines which fits each algorithm the best. The pipelines are tested along with nine different classification algorithms in the realm of regression, support vector machines, and neural networks. Preliminary testing for identifying the optimal pipelines and algorithms resulted in the selection of two algorithms with two different pipelines. The two algorithms are Logistic Regression (LR) and Artificial Neural Network (ANN). These algorithms are optimized further, where several parameters of each algorithm are tested. The best result is achieved with the ANN. The final model yields an accuracy of 0.79, a precision of 0.80, a recall of 0.78, and an F1 score of 0.76. By removing three of the classes that created noise, the final algorithm is capable of reaching an accuracy of 94%.

Keywords: Artificial neural network, competitive dynamics, logistic regression, text classification, text mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 479

Authors: Gitanjali Devi, Kandarpa Kumar Sarma, Pranayee Datta, Anjana Kakoti Mahanta

Abstract:

Cosmic showers, from their places of origin in space, after entering earth generate secondary particles called Extensive Air Shower (EAS). Detection and analysis of EAS and similar High Energy Particle Showers involve a plethora of experimental setups with certain constraints for which soft-computational tools like Artificial Neural Network (ANN)s can be adopted. The optimality of ANN classifiers can be enhanced further by the use of Multiple Classifier System (MCS) and certain data - dimension reduction techniques. This work describes the performance of certain data dimension reduction techniques like Principal Component Analysis (PCA), Independent Component Analysis (ICA) and Self Organizing Map (SOM) approximators for application with an MCS formed using Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN) and Probabilistic Neural Network (PNN). The data inputs are obtained from an array of detectors placed in a circular arrangement resembling a practical detector grid which have a higher dimension and greater correlation among themselves. The PCA, ICA and SOM blocks reduce the correlation and generate a form suitable for real time practical applications for prediction of primary energy and location of EAS from density values captured using detectors in a circular grid.

Keywords: EAS, Shower, Core, ANN, Location.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1574

Authors: Norbik Bashah, Idris Bharanidharan Shanmugam, Abdul Manan Ahmed

Abstract:

Intrusion Detection Systems are increasingly a key part of systems defense. Various approaches to Intrusion Detection are currently being used, but they are relatively ineffective. Artificial Intelligence plays a driving role in security services. This paper proposes a dynamic model Intelligent Intrusion Detection System, based on specific AI approach for intrusion detection. The techniques that are being investigated includes neural networks and fuzzy logic with network profiling, that uses simple data mining techniques to process the network data. The proposed system is a hybrid system that combines anomaly, misuse and host based detection. Simple Fuzzy rules allow us to construct if-then rules that reflect common ways of describing security attacks. For host based intrusion detection we use neural-networks along with self organizing maps. Suspicious intrusions can be traced back to its original source path and any traffic from that particular source will be redirected back to them in future. Both network traffic and system audit data are used as inputs for both.

Keywords: Intrusion Detection, Network Security, Data mining, Fuzzy Logic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2099

Authors: Yongxin Yuan

Abstract:

The problem of updating damped gyroscopic systems using measured modal data can be mathematically formulated as following two problems. Problem I: Given Ma ∈ Rn×n, Λ = diag{λ1, ··· , λp} ∈ Cp×p, X = [x1, ··· , xp] ∈ Cn×p, where p<n and both Λ and X are closed under complex conjugation in the sense that λ2j = λ¯2j−1 ∈ C, x2j = ¯x2j−1 ∈ Cn for j = 1, ··· , l, and λk ∈ R, xk ∈ Rn for k = 2l + 1, ··· , p, find real-valued symmetric matrices D,K and a real-valued skew-symmetric matrix G (that is, GT = −G) such that MaXΛ2 + (D + G)XΛ + KX = 0. Problem II: Given real-valued symmetric matrices Da, Ka ∈ Rn×n and a real-valued skew-symmetric matrix Ga, find (D, ˆ G, ˆ Kˆ ) ∈ SE such that Dˆ −Da2+Gˆ−Ga2+Kˆ −Ka2 = min(D,G,K)∈SE (D− Da2 + G − Ga2 + K − Ka2), where SE is the solution set of Problem I and · is the Frobenius norm. This paper presents an iterative algorithm to solve Problem I and Problem II. By using the proposed iterative method, a solution of Problem I can be obtained within finite iteration steps in the absence of roundoff errors, and the minimum Frobenius norm solution of Problem I can be obtained by choosing a special kind of initial matrices. Moreover, the optimal approximation solution (D, ˆ G, ˆ Kˆ ) of Problem II can be obtained by finding the minimum Frobenius norm solution of a changed Problem I. A numerical example shows that the introduced iterative algorithm is quite efficient.

Keywords: Model updating, iterative algorithm, gyroscopic system, partially prescribed spectral data, optimal approximation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1414

Authors: F. Caliskan

Abstract:

This paper presents a Neural Network (NN) identification of icing parameters in an A340 aircraft and a reconfiguration technique to keep the A/C performance close to the performance prior to icing. Five aircraft parameters are assumed to be considerably affected by icing. The off-line training for identifying the clear and iced dynamics is based on the Levenberg-Marquard Backpropagation algorithm. The icing parameters are located in the system matrix. The physical locations of the icing are assumed at the right and left wings. The reconfiguration is based on the technique known as the control mixer approach or pseudo inverse technique. This technique generates the new control input vector such that the A/C dynamics is not much affected by icing. In the simulations, the longitudinal and lateral dynamics of an Airbus A340 aircraft model are considered, and the stability derivatives affected by icing are identified. The simulation results show the successful NN identification of the icing parameters and the reconfigured flight dynamics having the similar performance before the icing. In other words, the destabilizing icing affect is compensated.

Keywords: Aircraft Icing, Stability Derivatives, Neural NetworkIdentification, Reconfiguration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1670

Authors: Hanaa T. El-Madany, Faten H. Fahmy, Ninet M. A. El-Rahman, Hassen T. Dorrah

Abstract:

Advancements in the field of artificial intelligence (AI) made during this decade have forever changed the way we look at automating spacecraft subsystems including the electrical power system. AI have been used to solve complicated practical problems in various areas and are becoming more and more popular nowadays. In this paper, a mathematical modeling and MATLAB–SIMULINK model for the different components of the spacecraft power system is presented. Also, a control system, which includes either the Neural Network Controller (NNC) or the Fuzzy Logic Controller (FLC) is developed for achieving the coordination between the components of spacecraft power system as well as control the energy flows. The performance of the spacecraft power system is evaluated by comparing two control systems using the NNC and the FLC.

Keywords: Spacecraft, Neural network, Fuzzy logic control, Photovoltaic array.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1919

Authors: A. M. N. El-Khoja, A. F. Ashour, J. Abdalhmid, X. Dai, A. Khan

Abstract:

In recent years, waste tyre problem is considered as one of the most crucial environmental pollution problems facing the world. Thus, reusing waste rubber crumb from recycled tyres to develop highly damping concrete is technically feasible and a viable alternative to landfill or incineration. The utilization of waste rubber in concrete generally enhances the ductility, toughness, thermal insulation, and impact resistance. However, the mechanical properties decrease with the amount of rubber used in concrete. The aim of this paper is to develop artificial neural network (ANN) models to predict the compressive strength of rubberised concrete (RuC). A trained and tested ANN was developed using a comprehensive database collected from different sources in the literature. The ANN model developed used 5 input parameters that include: coarse aggregate (CA), fine aggregate (FA), w/c ratio, fine rubber (Fr), and coarse rubber (Cr), whereas the ANN outputs were the corresponding compressive strengths. A parametric study was also conducted to study the trend of various RuC constituents on the compressive strength of RuC.

Keywords: Rubberized concrete, compressive strength, artificial neural network, prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 870

Authors: Gelareh Mohammadi, Parisa Shoushtari, Behnam Molaee Ardekani, Mohammad B. Shamsollahi

Abstract:

A direct connection between ElectroEncephaloGram (EEG) and the genetic information of individuals has been investigated by neurophysiologists and psychiatrists since 1960-s; and it opens a new research area in the science. This paper focuses on the person identification based on feature extracted from the EEG which can show a direct connection between EEG and the genetic information of subjects. In this work the full EO EEG signal of healthy individuals are estimated by an autoregressive (AR) model and the AR parameters are extracted as features. Here for feature vector constitution, two methods have been proposed; in the first method the extracted parameters of each channel are used as a feature vector in the classification step which employs a competitive neural network and in the second method a combination of different channel parameters are used as a feature vector. Correct classification scores at the range of 80% to 100% reveal the potential of our approach for person classification/identification and are in agreement to the previous researches showing evidence that the EEG signal carries genetic information. The novelty of this work is in the combination of AR parameters and the network type (competitive network) that we have used. A comparison between the first and the second approach imply preference of the second one.

Keywords: Person Identification, Autoregressive Model, EEG, Neural Network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1713

Authors: Dariush Jafari, S. Mostafa Nowee

Abstract:

In this study a ternary system containing sodium chloride as solute, water as primary solvent and ethanol as the antisolvent was considered to investigate the application of artificial neural network (ANN) in prediction of sodium solubility in the mixture of water as the solvent and ethanol as the antisolvent. The system was previously studied using by Extended UNIQUAC model by the authors of this study. The comparison between the results of the two models shows an excellent agreement between them (R2=0.99), and also approves the capability of ANN to predict the thermodynamic behavior of ternary electrolyte systems which are difficult to model.

Keywords: Thermodynamic modeling, ANN, solubility, ternary electrolyte system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2124

Authors: Kejun Zhuang, Zhaohui Wen

Abstract:

In this paper, a tri–neuron network model with time delay is investigated. By using the Bendixson-s criterion for high– dimensional ordinary differential equations and global Hopf bifurcation theory for functional differential equations, sufficient conditions for existence of periodic solutions when the time delay is sufficiently large are established.

Keywords: Delay, global Hopf bifurcation, neural network, periodicsolutions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1449

Authors: Lin Cheng, Zijiang Yang

Abstract:

Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specification. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and node are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.

Keywords: program synthesis, flow chart, specification, graph recognition, CNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 767

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 1195

Authors: Sozon H. Papavlasopoulos, Marios S. Poulos, George D. Bokos, Angelos M. Evangelou

Abstract:

In this study, the problem of discriminating between interictal epileptic and non- epileptic pathological EEG cases, which present episodic loss of consciousness, investigated. We verify the accuracy of the feature extraction method of autocross-correlated coefficients which extracted and studied in previous study. For this purpose we used in one hand a suitable constructed artificial supervised LVQ1 neural network and in other a cross-correlation technique. To enforce the above verification we used a statistical procedure which based on a chi- square control. The classification and the statistical results showed that the proposed feature extraction is a significant accurate method for diagnostic discrimination cases between interictal and non-interictal EEG events and specifically the classification procedure showed that the LVQ neural method is superior than the cross-correlation one.

Keywords: Cross-Correlation Methods, Diagnostic Test, Interictal Epileptic, LVQ1 neural network, Auto-Cross-Correlation Methods, chi-square test.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1492

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 1301

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 1826

Authors: U. Bottigli, D.Cascio, F. Fauci, B. Golosio, R. Magro, G.L. Masala, P. Oliva, G. Raso, S.Stumbo

Abstract:

Purpose of this work is the development of an automatic classification system which could be useful for radiologists in the investigation of breast cancer. The software has been designed in the framework of the MAGIC-5 collaboration. In the automatic classification system the suspicious regions with high probability to include a lesion are extracted from the image as regions of interest (ROIs). Each ROI is characterized by some features based on morphological lesion differences. Some classifiers as a Feed Forward Neural Network, a K-Nearest Neighbours and a Support Vector Machine are used to distinguish the pathological records from the healthy ones. The results obtained in terms of sensitivity (percentage of pathological ROIs correctly classified) and specificity (percentage of non-pathological ROIs correctly classified) will be presented through the Receive Operating Characteristic curve (ROC). In particular the best performances are 88% ± 1 of area under ROC curve obtained with the Feed Forward Neural Network.

Keywords: Neural Networks, K-Nearest Neighbours, SupportVector Machine, Computer Aided Diagnosis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1348

Authors: Nonlapun Meenil, Pisitpong Intarapong, Thitima Wongsheree, Pranchalee Samanpiboon

Abstract:

In Thailand, once pineapples are harvested, they must be classified into two classes based on their sweetness: sweet and unsweet. This paper has studied and developed the assessment of internal quality of pineapples using a low-cost compact spectroscopy sensor according to the spectroscopy approach and Neural Network (NN). During the experiments, Batavia pineapples were utilized, generating 100 samples. The extracted pineapple juice of each sample was used to determine the Soluble Solid Content (SSC) labeling into sweet and unsweet classes. In terms of experimental equipment, the sensor cover was specifically designed to install the sensor and light source to read the reflectance at a five mm depth from pineapple flesh. By using a spectroscopy sensor, data on visible and near-infrared reflectance (Vis-NIR) were collected. The NN was used to classify the pineapple classes. Before the classification step, the preprocessing methods, which are class balancing, data shuffling, and standardization, were applied. The 510 nm and 900 nm reflectance values of the middle parts of pineapples were used as features of the NN. With the sequential model and ReLU activation function, 100% accuracy of the training set and 76.67% accuracy of the test set were achieved. According to the abovementioned information, using a low-cost compact spectroscopy sensor has achieved favorable results in classifying the sweetness of the two classes of pineapples.

Keywords: Spectroscopy, soluble solid content, pineapple, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 50

Authors: Wullapa Wongsinlatam

Abstract:

Back propagation algorithm (BP) is a widely used technique in artificial neural network and has been used as a tool for solving the time series problems, such as decreasing training time, maximizing the ability to fall into local minima, and optimizing sensitivity of the initial weights and bias. This paper proposes an improvement of a BP technique which is called IM-COH algorithm (IM-COH). By combining IM-COH algorithm with cuckoo search algorithm (CS), the result is cuckoo search improved control output hidden layer algorithm (CS-IM-COH). This new algorithm has a better ability in optimizing sensitivity of the initial weights and bias than the original BP algorithm. In this research, the algorithm of CS-IM-COH is compared with the original BP, the IM-COH, and the original BP with CS (CS-BP). Furthermore, the selected benchmarks, four time series samples, are shown in this research for illustration. The research shows that the CS-IM-COH algorithm give the best forecasting results compared with the selected samples.

Keywords: Artificial neural networks, back propagation algorithm, time series, local minima problem, metaheuristic optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1051