Search results for: BP neural network model.

Authors: M. Yoneda

Abstract:

In this paper, a lateral walking design force per person is proposed and compared with Imperial College test results. Numerical simulations considering the proposed walking design force which is incorporated into the neural-oscillator model are carried out placing much emphasis on the synchronization (the lock-in phenomenon) for a pedestrian bridge model with the span length of 50 m. Numerical analyses are also conducted for an existing pedestrian suspension bridge. As compared with full scale measurements for this suspension bridge, it is confirmed that the analytical method based on the neural-oscillator model might be one of the useful ways to explain the synchronization (the lock-in phenomenon) of pedestrians being on the bridge.

Keywords: Pedestrian bridge, human-induced lateral vibration, neural-oscillator, full scale measurement, dynamic response analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 790

Authors: Chaudhuri Manoj Kumar Swain, Susmita Das

Abstract:

This paper explores a detailed procedure of predicting a path loss (PL) model and its application in estimating the coverage probability in a WiMAX network. For this a hybrid approach is followed in predicting an empirical PL model of a 2.65 GHz WiMAX network deployed in a suburban environment. Data collection, statistical analysis, and regression analysis are the phases of operations incorporated in this approach and the importance of each of these phases has been discussed properly. The procedure of collecting data such as received signal strength indicator (RSSI) through experimental set up is demonstrated. From the collected data set, empirical PL and RSSI models are predicted with regression technique. Furthermore, with the aid of the predicted PL model, essential parameters such as PL exponent as well as the coverage probability of the network are evaluated. This research work may assist in the process of deployment and optimisation of any cellular network significantly.

Keywords: WiMAX, RSSI, path loss, coverage probability, regression analysis.

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

Authors: Seyed Sadegh Naseralavi, Najmeh Bemani

Abstract:

In this paper, different concrete codes including America, New Zealand, Mexico, Italy, India, Canada, Hong Kong, Euro Code and Britain are compared with the Iranian concrete design code. First, by using Adaptive Neuro Fuzzy Inference System (ANFIS), the codes having the most correlation with the Iranian ninth issue of the national regulation are determined. Consequently, two anticipated methods are used for comparing the codes: Artificial Neural Network (ANN) and Multi-variable regression. The results show that ANN performs better. Predicting is done by using only tensile steel ratio and with ignoring the compression steel ratio.

Keywords: Concrete design code, anticipate method, artificial neural network, multi-variable regression, adaptive neuro fuzzy inference system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 817

Authors: Chee Peng Lim, Wei Yee Goh

Abstract:

In this paper, the application of multiple Elman neural networks to time series data regression problems is studied. An ensemble of Elman networks is formed by boosting to enhance the performance of the individual networks. A modified version of the AdaBoost algorithm is employed to integrate the predictions from multiple networks. Two benchmark time series data sets, i.e., the Sunspot and Box-Jenkins gas furnace problems, are used to assess the effectiveness of the proposed system. The simulation results reveal that an ensemble of boosted Elman networks can achieve a higher degree of generalization as well as performance than that of the individual networks. The results are compared with those from other learning systems, and implications of the performance are discussed.

Keywords: AdaBoost, Elman network, neural network ensemble, time series regression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1691

Authors: Pawalai Kraipeerapun, Chun Che Fung, Kok Wai Wong

Abstract:

This paper proposes a novel approach to the question of lithofacies classification based on an assessment of the uncertainty in the classification results. The proposed approach has multiple neural networks (NN), and interval neutrosophic sets (INS) are used to classify the input well log data into outputs of multiple classes of lithofacies. A pair of n-class neural networks are used to predict n-degree of truth memberships and n-degree of false memberships. Indeterminacy memberships or uncertainties in the predictions are estimated using a multidimensional interpolation method. These three memberships form the INS used to support the confidence in results of multiclass classification. Based on the experimental data, our approach improves the classification performance as compared to an existing technique applied only to the truth membership. In addition, our approach has the capability to provide a measure of uncertainty in the problem of multiclass classification.

Keywords: Multiclass classification, feed-forward backpropagation neural network, interval neutrosophic sets, uncertainty.

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

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 2416

Authors: M. Sedighizadeh, A. Rezazadeh

Abstract:

A self tuning PID control strategy using reinforcement learning is proposed in this paper to deal with the control of wind energy conversion systems (WECS). Actor-Critic learning is used to tune PID parameters in an adaptive way by taking advantage of the model-free and on-line learning properties of reinforcement learning effectively. In order to reduce the demand of storage space and to improve the learning efficiency, a single RBF neural network is used to approximate the policy function of Actor and the value function of Critic simultaneously. The inputs of RBF network are the system error, as well as the first and the second-order differences of error. The Actor can realize the mapping from the system state to PID parameters, while the Critic evaluates the outputs of the Actor and produces TD error. Based on TD error performance index and gradient descent method, the updating rules of RBF kernel function and network weights were given. Simulation results show that the proposed controller is efficient for WECS and it is perfectly adaptable and strongly robust, which is better than that of a conventional PID controller.

Keywords: Wind energy conversion systems, reinforcementlearning; Actor-Critic learning; adaptive PID control; RBF network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4942

Authors: Nassib Abdallah, Pierre Chauvet, Abd El Salam Hajjar, Bassam Daya

Abstract:

In this paper, we propose an optimized brain computer interface (BCI) system for unspoken speech recognition, based on the fact that the constructions of unspoken words rely strongly on the Wernicke area, situated in the temporal lobe. Our BCI system has four modules: (i) the EEG Acquisition module based on a non-invasive headset with 14 electrodes; (ii) the Preprocessing module to remove noise and artifacts, using the Common Average Reference method; (iii) the Features Extraction module, using Wavelet Packet Transform (WPT); (iv) the Classification module based on a one-hidden layer artificial neural network. The present study consists of comparing the recognition accuracy of 5 Arabic words, when using all the headset electrodes or only the 4 electrodes situated near the Wernicke area, as well as the selection effect of the subbands produced by the WPT module. After applying the articial neural network on the produced database, we obtain, on the test dataset, an accuracy of 83.4% with all the electrodes and all the subbands of 8 levels of the WPT decomposition. However, by using only the 4 electrodes near Wernicke Area and the 6 middle subbands of the WPT, we obtain a high reduction of the dataset size, equal to approximately 19% of the total dataset, with 67.5% of accuracy rate. This reduction appears particularly important to improve the design of a low cost and simple to use BCI, trained for several words.

Keywords: Brain-computer interface, speech recognition, electroencephalography EEG, Wernicke area, artificial neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 919

Authors: Rohan Putatunda, Aryya Gangopadhyay

Abstract:

Acoustic sensors, if embedded in smart street lights, can help in capturing the activities (car honking, sirens, events, traffic, etc.) in cities. Needless to say, the acoustic data from such scenarios are complex due to multiple audio streams originating from different events, and when decomposed to independent signals, the amount of retrieved data volume is small in quantity which is inadequate to train deep neural networks. So, in this paper, we address the two challenges: a) separating the mixed signals, and b) developing an efficient acoustic classifier under data paucity. So, to address these challenges, we propose an architecture with supervised deep learning, where the initial captured mixed acoustics data are analyzed with Fast Fourier Transformation (FFT), followed by filtering the noise from the signal, and then decomposed to independent signals by fast independent component analysis (Fast ICA). To address the challenge of data paucity, we propose a multi feature-based deep neural network with high performance that is reflected in our experiments when compared to the conventional convolutional neural network (CNN) and multi-layer perceptron (MLP).

Keywords: FFT, ICA, vehicle classification, multi-feature DNN, CNN, MLP.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 432

Authors: Hema C. R., Paulraj M. P., S. Yaacob, A. H. Adom, R. Nagarajan

Abstract:

Motor imagery classification provides an important basis for designing Brain Machine Interfaces [BMI]. A BMI captures and decodes brain EEG signals and transforms human thought into actions. The ability of an individual to control his EEG through imaginary mental tasks enables him to control devices through the BMI. This paper presents a method to design a four state BMI using EEG signals recorded from the C3 and C4 locations. Principle features extracted through principle component analysis of the segmented EEG are analyzed using two novel classification algorithms using Elman recurrent neural network and functional link neural network. Performance of both classifiers is evaluated using a particle swarm optimization training algorithm; results are also compared with the conventional back propagation training algorithm. EEG motor imagery recorded from two subjects is used in the offline analysis. From overall classification performance it is observed that the BP algorithm has higher average classification of 93.5%, while the PSO algorithm has better training time and maximum classification. The proposed methods promises to provide a useful alternative general procedure for motor imagery classification

Keywords: Motor Imagery, Brain Machine Interfaces, Neural Networks, Particle Swarm Optimization, EEG signal processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2456

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

Abstract:

Cosmic showers, during the transit through space, produce sub - products as a result of interactions with the intergalactic or interstellar medium which after entering earth generate secondary particles called Extensive Air Shower (EAS). Detection and analysis of High Energy Particle Showers involve a plethora of theoretical and experimental works with a host of constraints resulting in inaccuracies in measurements. Therefore, there exist a necessity to develop a readily available system based on soft-computational approaches which can be used for EAS analysis. This is due to the fact that soft computational tools such as Artificial Neural Network (ANN)s can be trained as classifiers to adapt and learn the surrounding variations. But single classifiers fail to reach optimality of decision making in many situations for which Multiple Classifier System (MCS) are preferred to enhance the ability of the system to make decisions adjusting to finer variations. This work describes the formation of an MCS using Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN) and Probabilistic Neural Network (PNN) with data inputs from correlation mapping Self Organizing Map (SOM) blocks and the output optimized by another SOM. The results show that the setup can be adopted 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 1302

Authors: Parvinder S. Sandhu, Harpreet Kaur, Amanpreet Singh

Abstract:

Automatic reusability appraisal is helpful in evaluating the quality of developed or developing reusable software components and in identification of reusable components from existing legacy systems; that can save cost of developing the software from scratch. But the issue of how to identify reusable components from existing systems has remained relatively unexplored. In this research work, structural attributes of software components are explored using software metrics and quality of the software is inferred by different Neural Network based approaches, taking the metric values as input. The calculated reusability value enables to identify a good quality code automatically. It is found that the reusability value determined is close to the manual analysis used to be performed by the programmers or repository managers. So, the developed system can be used to enhance the productivity and quality of software development.

Keywords: Neural Network, Software Reusability, Software Metric, Accuracy, MAE, RMSE.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2081

Authors: R.V Pawar, P.P.Kajave, S.N.Mali

Abstract:

The speech signal conveys information about the identity of the speaker. The area of speaker identification is concerned with extracting the identity of the person speaking the utterance. As speech interaction with computers becomes more pervasive in activities such as the telephone, financial transactions and information retrieval from speech databases, the utility of automatically identifying a speaker is based solely on vocal characteristic. This paper emphasizes on text dependent speaker identification, which deals with detecting a particular speaker from a known population. The system prompts the user to provide speech utterance. System identifies the user by comparing the codebook of speech utterance with those of the stored in the database and lists, which contain the most likely speakers, could have given that speech utterance. The speech signal is recorded for N speakers further the features are extracted. Feature extraction is done by means of LPC coefficients, calculating AMDF, and DFT. The neural network is trained by applying these features as input parameters. The features are stored in templates for further comparison. The features for the speaker who has to be identified are extracted and compared with the stored templates using Back Propogation Algorithm. Here, the trained network corresponds to the output; the input is the extracted features of the speaker to be identified. The network does the weight adjustment and the best match is found to identify the speaker. The number of epochs required to get the target decides the network performance.

Keywords: Average Mean Distance function, Backpropogation, Linear Predictive Coding, MultilayeredPerceptron,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1893

Authors: N. Nim-on, A. Oonsivilai

Abstract:

In this paper, the application of GRNN in modeling of SOFC fuel cells were studied. The parameters are of interested as voltage and power value and the current changes are investigated. In addition, the comparison between GRNN neural network application and conventional method was made. The error value showed the superlative results.

Keywords: SOFC, GRNN, Fuel cells.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2100

Authors: N. M. Nawi, M. R. Ransing, R. S. Ransing

Abstract:

The conjugate gradient optimization algorithm usually used for nonlinear least squares is presented and is combined with the modified back propagation algorithm yielding a new fast training multilayer perceptron (MLP) algorithm (CGFR/AG). The approaches presented in the paper consist of three steps: (1) Modification on standard back propagation algorithm by introducing gain variation term of the activation function, (2) Calculating the gradient descent on error with respect to the weights and gains values and (3) the determination of the new search direction by exploiting the information calculated by gradient descent in step (2) as well as the previous search direction. The proposed method improved the training efficiency of back propagation algorithm by adaptively modifying the initial search direction. Performance of the proposed method is demonstrated by comparing to the conjugate gradient algorithm from neural network toolbox for the chosen benchmark. The results show that the number of iterations required by the proposed method to converge is less than 20% of what is required by the standard conjugate gradient and neural network toolbox algorithm.

Keywords: Back-propagation, activation function, conjugategradient, search direction, gain variation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2838

Authors: C. Temaneh Nyah

Abstract:

The analysis of electromagnetic environment using deterministic mathematical models is characterized by the impossibility of analyzing a large number of interacting network stations with a priori unknown parameters, and this is characteristic, for example, of mobile wireless communication networks. One of the tasks of the tools used in designing, planning and optimization of mobile wireless network is to carry out simulation of electromagnetic environment based on mathematical modelling methods, including computer experiment, and to estimate its effect on radio communication devices. This paper proposes the development of a statistical model of electromagnetic environment of a mobile wireless communication network by describing the parameters and factors affecting it including the propagation channel and their statistical models.

Keywords: Electromagnetic Environment, Statistical model, Wireless communication network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1918

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Here, a new idea to speed up the operation of complex valued time delay neural networks is presented. The whole data are collected together in a long vector and then tested as a one input pattern. The proposed fast complex valued time delay neural networks uses cross correlation in the frequency domain between the tested data and the input weights of neural networks. It is proved mathematically that the number of computation steps required for the presented fast complex valued time delay neural networks is less than that needed by classical time delay neural networks. Simulation results using MATLAB confirm the theoretical computations.

Keywords: Fast Complex Valued Time Delay Neural Networks, Cross Correlation, Frequency Domain

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

Authors: Afaf Alharbi, Qianni Zhang

Abstract:

The identification of malignant tissue in histopathological slides holds significant importance in both clinical settings and pathology research. This paper presents a methodology aimed at automatically categorizing cancerous tissue through the utilization of a multiple instance learning framework. This framework is specifically developed to acquire knowledge of the Bernoulli distribution of the bag label probability by employing neural networks. Furthermore, we put forward a neural network-based permutation-invariant aggregation operator, equivalent to attention mechanisms, which is applied to the multi-instance learning network. Through empirical evaluation on an openly available colon cancer histopathology dataset, we provide evidence that our approach surpasses various conventional deep learning methods.

Keywords: Attention Multiple Instance Learning, Multiple Instance Learning, transfer learning, histopathological slides, cancer tissue classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 226

Authors: S. Loumi, H. Merrad, F. Alilat, B. Sansal

Abstract:

In this article, we propose a methodology for the characterization of the suspended matter along Algiers-s bay. An approach by multi layers perceptron (MLP) with training by back propagation of the gradient optimized by the algorithm of Levenberg Marquardt (LM) is used. The accent was put on the choice of the components of the base of training where a comparative study made for four methods: Random and three alternatives of classification by K-Means. The samples are taken from suspended matter image, obtained by analytical model based on polynomial regression by taking account of in situ measurements. The mask which selects the zone of interest (water in our case) was carried out by using a multi spectral classification by ISODATA algorithm. To improve the result of classification, a cleaning of this mask was carried out using the tools of mathematical morphology. The results of this study presented in the forms of curves, tables and of images show the founded good of our methodology.

Keywords: Classification K-means, mathematical morphology, neural network MLP, remote sensing, suspended particulate matter

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

Authors: Mengzhuo Luo, Shouming Zhong

Abstract:

This paper investigates the problem of exponential stability for a class of uncertain discrete-time stochastic neural network with time-varying delays. By constructing a suitable Lyapunov-Krasovskii functional, combining the stochastic stability theory, the free-weighting matrix method, a delay-dependent exponential stability criteria is obtained in term of LMIs. Compared with some previous results, the new conditions obtain in this paper are less conservative. Finally, two numerical examples are exploited to show the usefulness of the results derived.

Keywords: Delay-dependent stability, Neural networks, Time varying delay, Linear matrix inequality (LMI).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1927

Authors: Wei Lu

Abstract:

With the development of information technology in China, network consumption is becoming more and more popular. As a special group, college students have a high degree of education and distinct opinions and personalities. In the future, the key groups of network consumption have gradually become the focus groups of network consumption. Studying college students’ online consumption behavior has important theoretical significance and practical value. Based on the Stimulus-Organism-Response (SOR) driving model and the structural equation model, this paper establishes the influencing factors model of College students’ online consumption behavior, evaluates and amends the model by using SPSS and AMOS software, analyses and determines the positive factors of marketing college students’ consumption, and provides an effective basis for guiding and promoting college student consumption.

Keywords: College students, online consumption, stimulus-organism-response driving model, structural equation model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 594

Authors: Marina Velikova, Hennie Daniels, Ad Feelders

Abstract:

In many applications, it is a priori known that the target function should satisfy certain constraints imposed by, for example, economic theory or a human-decision maker. Here we consider partially monotone problems, where the target variable depends monotonically on some of the predictor variables but not all. We propose an approach to build partially monotone models based on the convolution of monotone neural networks and kernel functions. The results from simulations and a real case study on house pricing show that our approach has significantly better performance than partially monotone linear models. Furthermore, the incorporation of partial monotonicity constraints not only leads to models that are in accordance with the decision maker's expertise, but also reduces considerably the model variance in comparison to standard neural networks with weight decay.

Keywords: Mixture models, monotone neural networks, partially monotone models, partially monotone problems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1621

Authors: Khalid Salhi, El Miloud Jaara, Mohammed Talibi Alaoui

Abstract:

In this paper, we present a neural approach for unsupervised natural color-texture image segmentation, which is based on both Kohonen maps and mathematical morphology, using a combination of the texture and the image color information of the image, namely, the fractal features based on fractal dimension are selected to present the information texture, and the color features presented in RGB color space. These features are then used to train the network Kohonen, which will be represented by the underlying probability density function, the segmentation of this map is made by morphological watershed transformation. The performance of our color-texture segmentation approach is compared first, to color-based methods or texture-based methods only, and then to k-means method.

Keywords: Segmentation, color-texture, neural networks, fractal, watershed.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1374

Authors: P. Pongsumpun

Abstract:

A new strain of Type A influenza virus can cause the transmission of H1N1 virus. This virus can spread between the people by coughing and sneezing. Because the people are always movement, so this virus can be easily spread. In this study, we construct the dynamical network model of H1N1 virus by separating the human into five groups; susceptible, exposed, infectious, quarantine and recovered groups. The movement of people between houses (local level) is considered. The behaviors of solutions to our dynamical model are shown for the different parameters.

Keywords: Dynamical network, H1N1virus, local level, simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1547

Authors: Mihails Kulikovs, Ernests Petersons

Abstract:

Network management techniques have long been of interest to the networking research community. The queue size plays a critical role for the network performance. The adequate size of the queue maintains Quality of Service (QoS) requirements within limited network capacity for as many users as possible. The appropriate estimation of the queuing model parameters is crucial for both initial size estimation and during the process of resource allocation. The accurate resource allocation model for the management system increases the network utilization. The present paper demonstrates the results of empirical observation of memory allocation for packet-based services.

Keywords: Queuing System, Packet Loss Probability, Measurement-Based Admission Control (MBAC), Performanceevaluation, Quality of Service (QoS).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1774

Authors: Muhammad Marsudi, Dzuraidah Abdul Wahab, Che Hassan Che Haron

Abstract:

Modeling of a manufacturing system enables one to identify the effects of key design parameters on the system performance and as a result to make correct decision. This paper proposes a manufacturing system modeling approach using a spreadsheet model based on queuing network theory, in which a static capacity planning model and stochastic queuing model are integrated. The model was used to improve the existing system utilization in relation to product design. The model incorporates few parameters such as utilization, cycle time, throughput, and batch size. The study also showed that the validity of developed model is good enough to apply and the maximum value of relative error is 10%, far below the limit value 32%. Therefore, the model developed in this study is a valuable alternative model in evaluating a manufacturing system

Keywords: Manufacturing system, product design, spreadsheet model, utilization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1920

Authors: Apoorva Vinod, Archana Mathur, Snehanshu Saha

Abstract:

Though there exists a plethora of Activation Functions (AFs) used in single and multiple hidden layer Neural Networks (NN), their behavior always raised curiosity, whether used in combination or singly. The popular AFs – Sigmoid, ReLU, and Tanh – have performed prominently well for shallow and deep architectures. Most of the time, AFs are used singly in multi-layered NN, and, to the best of our knowledge, their performance is never studied and analyzed deeply when used in combination. In this manuscript, we experiment on multi-layered NN architecture (both on shallow and deep architectures; Convolutional NN and VGG16) and investigate how well the network responds to using two different AFs (Sigmoid-Tanh, Tanh-ReLU, ReLU-Sigmoid) used alternately against a traditional, single (Sigmoid-Sigmoid, Tanh-Tanh, ReLU-ReLU) combination. Our results show that on using two different AFs, the network achieves better accuracy, substantially lower loss, and faster convergence on 4 computer vision (CV) and 15 Non-CV (NCV) datasets. When using different AFs, not only was the accuracy greater by 6-7%, but we also accomplished convergence twice as fast. We present a case study to investigate the probability of networks suffering vanishing and exploding gradients when using two different AFs. Additionally, we theoretically showed that a composition of two or more AFs satisfies Universal Approximation Theorem (UAT).

Keywords: Activation Function, Universal Approximation function, Neural Networks, convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 154

Authors: Mansoureh Naderipour, Susan Bastani, Mohammad Fazel Zarandi

Abstract:

Predicting links that may occur in the future and missing links in social networks is an attractive problem in social network analysis. Granular computing can help us to model the relationships between human-based system and social sciences in this field. In this paper, we present a model based on granular computing approach and Type-2 fuzzy logic to predict links regarding nodes’ activity and the relationship between two nodes. Our model is tested on collaboration networks. It is found that the accuracy of prediction is significantly higher than the Type-1 fuzzy and crisp approach.

Keywords: Social Network, link prediction, granular computing, Type-2 fuzzy sets.

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

Authors: Ahmed Abdolkhalig

Abstract:

This paper examines many mathematical methods for molding the hourly price forward curve (HPFC); the model will be constructed by numerous regression methods, like polynomial regression, radial basic function neural networks & a furrier series. Examination the models goodness of fit will be done by means of statistical & graphical tools. The criteria for choosing the model will depend on minimize the Root Mean Squared Error (RMSE), using the correlation analysis approach for the regression analysis the optimal model will be distinct, which are robust against model misspecification. Learning & supervision technique employed to determine the form of the optimal parameters corresponding to each measure of overall loss. By using all the numerical methods that mentioned previously; the explicit expressions for the optimal model derived and the optimal designs will be implemented.

Keywords: Forward curve, furrier series, regression, radial basic function neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4231

Authors: Hemashree Bordoloi, Kandarpa Kumar Sarma

Abstract:

Rotation or tilt present in an image capture by digital means can be detected and corrected using Artificial Neural Network (ANN) for application with a Face Recognition System (FRS). Principal Component Analysis (PCA) features of faces at different angles are used to train an ANN which detects the rotation for an input image and corrected using a set of operations implemented using another system based on ANN. The work also deals with the recognition of human faces with features from the foreheads, eyes, nose and mouths as decision support entities of the system configured using a Generalized Feed Forward Artificial Neural Network (GFFANN). These features are combined to provide a reinforced decision for verification of a person-s identity despite illumination variations. The complete system performing facial image rotation detection, correction and recognition using re-enforced decision support provides a success rate in the higher 90s.

Keywords: Rotation, Face, Recognition, ANN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2062