Search results for: supervised neural network (perceptron).

Authors: Svitov David, Alyamkin Sergey

Abstract:

The usage of convolutional neural networks (CNNs) in conjunction with the margin-based softmax approach demonstrates the state-of-the-art performance for the face recognition problem. Recently, lightweight neural network models trained with the margin-based softmax have been introduced for the face identification task for edge devices. In this paper, we propose a distillation method for lightweight neural network architectures that outperforms other known methods for the face recognition task on LFW, AgeDB-30 and Megaface datasets. The idea of the proposed method is to use class centers from the teacher network for the student network. Then the student network is trained to get the same angles between the class centers and face embeddings predicted by the teacher network.

Keywords: ArcFace, distillation, face recognition, margin-based softmax.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 547

Authors: Nadia Hmad, Tony Allen

Abstract:

This paper presents an ESN-based Arabic phoneme recognition system trained with supervised, forced and combined supervised/forced supervised learning algorithms. Mel-Frequency Cepstrum Coefficients (MFCCs) and Linear Predictive Code (LPC) techniques are used and compared as the input feature extraction technique. The system is evaluated using 6 speakers from the King Abdulaziz Arabic Phonetics Database (KAPD) for Saudi Arabia dialectic and 34 speakers from the Center for Spoken Language Understanding (CSLU2002) database of speakers with different dialectics from 12 Arabic countries. Results for the KAPD and CSLU2002 Arabic databases show phoneme recognition performances of 72.31% and 38.20% respectively.

Keywords: Arabic phonemes recognition, echo state networks (ESNs), neural networks (NNs), supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2366

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 2141

Authors: M.Ghazvini, S. A. Monadjemi, N. Movahhedinia, K. Jamshidi

Abstract:

In this article, a method has been offered to classify normal and defective tiles using wavelet transform and artificial neural networks. The proposed algorithm calculates max and min medians as well as the standard deviation and average of detail images obtained from wavelet filters, then comes by feature vectors and attempts to classify the given tile using a Perceptron neural network with a single hidden layer. In this study along with the proposal of using median of optimum points as the basic feature and its comparison with the rest of the statistical features in the wavelet field, the relational advantages of Haar wavelet is investigated. This method has been experimented on a number of various tile designs and in average, it has been valid for over 90% of the cases. Amongst the other advantages, high speed and low calculating load are prominent.

Keywords: Defect detection, tile and ceramic quality inspection, wavelet transform, classification, neural networks, statistical features.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2307

Authors: Han Bing, Yin Zhenjie

Abstract:

In order to analyze the status of a diesel engine, as well as conduct fault prediction, a new prediction model based on a gray system is proposed in this paper, which takes advantage of the neural network and the genetic algorithm. The proposed GBPGA prediction model builds on the GM (1.5) model and uses a neural network, which is optimized by a genetic algorithm to construct the error compensator. We verify our proposed model on the diesel faulty simulation data and the experimental results show that GBPGA has the potential to employ fault prediction on diesel.

Keywords: Fault prediction, Neural network, GM (1.5), Genetic algorithm, GBPGA.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1249

Authors: Nahid Ardalani, Ahmadreza Khoogar, H. Roohi

Abstract:

In this paper we compare the response of linear and nonlinear neural network-based prediction schemes in prediction of received Signal-to-Interference Power Ratio (SIR) in Direct Sequence Code Division Multiple Access (DS/CDMA) systems. The nonlinear predictor is Multilayer Perceptron MLP and the linear predictor is an Adaptive Linear (Adaline) predictor. We solve the problem of complexity by using the Minimum Mean Squared Error (MMSE) principle to select the optimal predictors. The optimized Adaline predictor is compared to optimized MLP by employing noisy Rayleigh fading signals with 1.8 GHZ carrier frequency in an urban environment. The results show that the Adaline predictor can estimates SIR with the same error as MLP when the user has the velocity of 5 km/h and 60 km/h but by increasing the velocity up-to 120 km/h the mean squared error of MLP is two times more than Adaline predictor. This makes the Adaline predictor (with lower complexity) more suitable than MLP for closed-loop power control where efficient and accurate identification of the time-varying inverse dynamics of the multi path fading channel is required.

Keywords: Power control, neural networks, DS/CDMA mobilecommunication systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2457

Authors: V Krishnaveni, S Jayaraman, A Gunasekaran, K Ramadoss

Abstract:

The ElectroEncephaloGram (EEG) is useful for clinical diagnosis and biomedical research. EEG signals often contain strong ElectroOculoGram (EOG) artifacts produced by eye movements and eye blinks especially in EEG recorded from frontal channels. These artifacts obscure the underlying brain activity, making its visual or automated inspection difficult. The goal of ocular artifact removal is to remove ocular artifacts from the recorded EEG, leaving the underlying background signals due to brain activity. In recent times, Independent Component Analysis (ICA) algorithms have demonstrated superior potential in obtaining the least dependent source components. In this paper, the independent components are obtained by using the JADE algorithm (best separating algorithm) and are classified into either artifact component or neural component. Neural Network is used for the classification of the obtained independent components. Neural Network requires input features that exactly represent the true character of the input signals so that the neural network could classify the signals based on those key characters that differentiate between various signals. In this work, Auto Regressive (AR) coefficients are used as the input features for classification. Two neural network approaches are used to learn classification rules from EEG data. First, a Polynomial Neural Network (PNN) trained by GMDH (Group Method of Data Handling) algorithm is used and secondly, feed-forward neural network classifier trained by a standard back-propagation algorithm is used for classification and the results show that JADE-FNN performs better than JADEPNN.

Keywords: Auto Regressive (AR) Coefficients, Feed Forward Neural Network (FNN), Joint Approximation Diagonalisation of Eigen matrices (JADE) Algorithm, Polynomial Neural Network (PNN).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1826

Authors: Safaa R. Amer

Abstract:

Missing data yields many analysis challenges. In case of complex survey design, in addition to dealing with missing data, researchers need to account for the sampling design to achieve useful inferences. Methods for incorporating sampling weights in neural network imputation were investigated to account for complex survey designs. An estimate of variance to account for the imputation uncertainty as well as the sampling design using neural networks will be provided. A simulation study was conducted to compare estimation results based on complete case analysis, multiple imputation using a Markov Chain Monte Carlo, and neural network imputation. Furthermore, a public-use dataset was used as an example to illustrate neural networks imputation under a complex survey design

Keywords: Complex survey, estimate, imputation, neural networks, variance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1929

Authors: Bing Yu , Xingshi He

Abstract:

In this paper, Differential Evolution (DE) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, DE achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.

Keywords: differential evolution, neural network, Rbf function

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1997

Authors: M. Khouil, N. Saber, M. Mestari

Abstract:

In this paper, a different architecture of a collision detection neural network (DCNN) is developed. This network, which has been particularly reviewed, has enabled us to solve with a new approach the problem of collision detection between two convex polyhedra in a fixed time (O (1) time). We used two types of neurons, linear and threshold logic, which simplified the actual implementation of all the networks proposed. The study of the collision detection is divided into two sections, the collision between a point and a polyhedron and then the collision between two convex polyhedra. The aim of this research is to determine through the AMAXNET network a mini maximum point in a fixed time, which allows us to detect the presence of a potential collision.

Keywords: Collision identification, fixed time, convex polyhedra, neural network, AMAXNET.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1773

Authors: H.Mohammadi Majd, M.Jalali Azizpour , Foad Saadi

Abstract:

In this paper back-propagation artificial neural network (BPANN) 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 1504

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, relativeimportance, artificial neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2103

Authors: Fengxia Zheng, Shouming Zhong

Abstract:

ANNARIMA that combines both autoregressive integrated moving average (ARIMA) model and artificial neural network (ANN) model is a valuable tool for modeling and forecasting nonlinear time series, yet the over-fitting problem is more likely to occur in neural network models. This paper provides a hybrid methodology that combines both radial basis function (RBF) neural network and auto regression (AR) model based on binomial smoothing (BS) technique which is efficient in data processing, which is called BSRBFAR. This method is examined by using the data of Canadian Lynx data. Empirical results indicate that the over-fitting problem can be eased using RBF neural network based on binomial smoothing which is called BS-RBF, and the hybrid model–BS-RBFAR can be an effective way to improve forecasting accuracy achieved by BSRBF used separately.

Keywords: Binomial smoothing (BS), hybrid, Canadian Lynx data, forecasting accuracy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3610

Authors: Rahib Abiyev, Vasif H. Abiyev, C. Ardil

Abstract:

In this paper the development of neural network based fuzzy inference system for electricity consumption prediction is considered. The electricity consumption depends on number of factors, such as number of customers, seasons, type-s of customers, number of plants, etc. It is nonlinear process and can be described by chaotic time-series. The structure and algorithms of neuro-fuzzy system for predicting future values of electricity consumption is described. To determine the unknown coefficients of the system, the supervised learning algorithm is used. As a result of learning, the rules of neuro-fuzzy system are formed. The developed system is applied for predicting future values of electricity consumption of Northern Cyprus. The simulation of neuro-fuzzy system has been performed.

Keywords: Fuzzy logic, neural network, neuro-fuzzy system, neuro-fuzzy prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1942

Authors: F. Rasi Maezabadi, M. Masdari, M. R. Soltani

Abstract:

Series of experimental tests were conducted on a section of a 660 kW wind turbine blade to measure the pressure distribution of this model oscillating in plunging motion. In order to minimize the amount of data required to predict aerodynamic loads of the airfoil, a General Regression Neural Network, GRNN, was trained using the measured experimental data. The network once proved to be accurate enough, was used to predict the flow behavior of the airfoil for the desired conditions. Results showed that with using a few of the acquired data, the trained neural network was able to predict accurate results with minimal errors when compared with the corresponding measured values. Therefore with employing this trained network the aerodynamic coefficients of the plunging airfoil, are predicted accurately at different oscillation frequencies, amplitudes, and angles of attack; hence reducing the cost of tests while achieving acceptable accuracy.

Keywords: Airfoil, experimental, GRNN, Neural Network, Plunging.

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

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 1474

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 2785

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 1594

Authors: K.Mala, V.Sadasivam, S.Alagappan

Abstract:

Advances in clinical medical imaging have brought about the routine production of vast numbers of medical images that need to be analyzed. As a result an enormous amount of computer vision research effort has been targeted at achieving automated medical image analysis. Computed Tomography (CT) is highly accurate for diagnosing liver tumors. This study aimed to evaluate the potential role of the wavelet and the neural network in the differential diagnosis of liver tumors in CT images. The tumors considered in this study are hepatocellular carcinoma, cholangio carcinoma, hemangeoma and hepatoadenoma. Each suspicious tumor region was automatically extracted from the CT abdominal images and the textural information obtained was used to train the Probabilistic Neural Network (PNN) to classify the tumors. Results obtained were evaluated with the help of radiologists. The system differentiates the tumor with relatively high accuracy and is therefore clinically useful.

Keywords: Fuzzy c means clustering, texture analysis, probabilistic neural network, LVQ neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2928

Authors: R. Amandi, A. Shahbazi, A. Mohebi, M. Bazargan, Y. Jaberi, P. Emadi, A. Valizade

Abstract:

The application of Neural Network for disease diagnosis has made great progress and is widely used by physicians. An Electrocardiogram carries vital information about heart activity and physicians use this signal for cardiac disease diagnosis which was the great motivation towards our study. In our work, tachycardia features obtained are used for the training and testing of a Neural Network. In this study we are using Fuzzy Probabilistic Neural Networks as an automatic technique for ECG signal analysis. As every real signal recorded by the equipment can have different artifacts, we needed to do some preprocessing steps before feeding it to our system. Wavelet transform is used for extracting the morphological parameters of the ECG signal. The outcome of the approach for the variety of arrhythmias shows the represented approach is superior than prior presented algorithms with an average accuracy of about %95 for more than 7 tachy arrhythmias.

Keywords: Fuzzy Logic, Probabilistic Neural Network, Tachycardia, Wavelet Transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2230

Authors: Ahmad Forouzantabar, Babak Gholami, Mohammad Azadi

Abstract:

An adaptive neural network controller for autonomous underwater vehicles (AUVs) is presented in this paper. The AUV model is highly nonlinear because of many factors, such as hydrodynamic drag, damping, and lift forces, Coriolis and centripetal forces, gravity and buoyancy forces, as well as forces from thruster. In this regards, a nonlinear neural network is used to approximate the nonlinear uncertainties of AUV dynamics, thus overcoming some limitations of conventional controllers and ensure good performance. The uniform ultimate boundedness of AUV tracking errors and the stability of the proposed control system are guaranteed based on Lyapunov theory. Numerical simulation studies for motion control of an AUV are performed to demonstrate the effectiveness of the proposed controller.

Keywords: Autonomous Underwater Vehicle (AUV), Neural Network Controller, Composite Adaptation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2468

Authors: Suk-Hyun Yu, Heeyong Kwon

Abstract:

Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.

Keywords: AI, air quality prediction, neural networks, pattern recognition, PM-10.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 783

Authors: Osama Elsarrar, Marjorie Darrah, Richard Devin

Abstract:

This paper discusses the idea of capturing an expert’s knowledge in the form of human understandable rules and then inserting these rules into a dynamic cell structure (DCS) neural network. The DCS is a form of self-organizing map that can be used for many purposes, including classification and prediction. This particular neural network is considered to be a topology preserving network that starts with no pre-structure, but assumes a structure once trained. The DCS has been used in mission and safety-critical applications, including adaptive flight control and health-monitoring in aerial vehicles. The approach is to insert expert knowledge into the DCS before training. Rules are translated into a pre-structure and then training data are presented. This idea has been demonstrated using the well-known Iris data set and it has been shown that inserting the pre-structure results in better accuracy with the same training.

Keywords: Neural network, rule extraction, rule insertion, self-organizing map.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 450

Authors: John Kabuba, Antoine Mulaba-Bafubiandi

Abstract:

The elution process for the removal of Co and Cu from clinoptilolite as an ion-exchanger was investigated using three parameters: bed volume, pH and contact time. The present paper study has shown quantitatively that acid concentration has a significant effect on the elution process. The favorable eluant concentration was found to be 2 M HCl and 2 M H2SO4, respectively. The multi-component equilibrium relationship in the process can be very complex, and perhaps ill-defined. In such circumstances, it is preferable to use a non-parametric technique such as Neural Network to represent such an equilibrium relationship.

Keywords: Clinoptilolite, elution, modeling, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1380

Authors: Ceren Kaya, Okan Erkaymaz, Orhan Ayar, Mahmut Özer

Abstract:

Diabetes Mellitus (Diabetes) is a disease based on insulin hormone disorders and causes high blood glucose. Clinical findings determine that diabetes can be diagnosed by electrophysiological signals obtained from the vital organs. 'Diabetic Retinopathy' is one of the most common eye diseases resulting on diabetes and it is the leading cause of vision loss due to structural alteration of the retinal layer vessels. In this study, features of horizontal and vertical Video-Oculography (VOG) signals have been used to classify non-proliferative and proliferative diabetic retinopathy disease. Twenty-five features are acquired by using discrete wavelet transform with VOG signals which are taken from 21 subjects. Two models, based on multi-layer perceptron and radial basis function, are recommended in the diagnosis of Diabetic Retinopathy. The proposed models also can detect level of the disease. We show comparative classification performance of the proposed models. Our results show that proposed the RBF model (100%) results in better classification performance than the MLP model (94%).

Keywords: Diabetic retinopathy, discrete wavelet transform, multi-layer perceptron, radial basis function, video-oculography.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1293

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: Distillation, machine learning, neural networks, quantization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 679

Authors: Nahla Ibraheem Jabbar, Monica Mehrotra

Abstract:

This paper used a fuzzy kohonen neural network for medical image segmentation. Image segmentation plays a important role in the many of medical imaging applications by automating or facilitating the diagnostic. The paper analyses the tumor by extraction of the features of (area, entropy, means and standard deviation).These measurements gives a description for a tumor.

Keywords: FCM, features extraction, medical image processing, neural network, segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2065

Authors: Sheng-Hong Pong, Herng-Yu Huang, Yi-Ju Lee, Shih-Hsuan Chiu

Abstract:

In this paper, a neural network technique is applied to real-time classifying media while a projectile is penetrating through them. A laboratory-scaled penetrating setup was built for the experiment. Features used as the network inputs were extracted from the acceleration of penetrator. 6000 set of features from a single penetration with known media and status were used to train the neural network. The trained system was tested on 30 different penetration experiments. The system produced an accuracy of 100% on the training data set. And, their precision could be 99% for the test data from 30 tests.

Keywords: back-propagation, identification, neural network, penetration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1237

Authors: H.Mohammadi Majd, M.Jalali Azizpour, A.V. Hoseini

Abstract:

In this paper back-propagation artificial neural network (BPANN) is employed to predict the limiting drawing ratio (LDR) of the deep drawing process. To prepare a training set for BPANN, some finite element simulations were carried out. die and punch radius, die arc radius, friction coefficient, thickness, yield strength of sheet and strain hardening exponent were used as the input data and the LDR as the specified output used in the training of neural network. As a result of the specified parameters, the program will be able to estimate the LDR for any new given condition. Comparing FEM and BPANN results, an acceptable correlation was found.

Keywords: Back-propagation artificial neural network(BPANN), deep drawing, prediction, limiting drawing ratio (LDR).

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

Authors: O. O. Obe, V. Balanica, E. Neagoe

Abstract:

The effects of hypertension are often lethal thus its early detection and prevention is very important for everybody. In this paper, a neural network (NN) model was developed and trained based on a dataset of hypertension causative parameters in order to forecast the likelihood of occurrence of hypertension in patients. Our research goal was to analyze the potential of the presented NN to predict, for a period of time, the risk of hypertension or the risk of developing this disease for patients that are or not currently hypertensive. The results of the analysis for a given patient can support doctors in taking pro-active measures for averting the occurrence of hypertension such as recommendations regarding the patient behavior in order to lower his hypertension risk. Moreover, the paper envisages a set of three example scenarios in order to determine the age when the patient becomes hypertensive, i.e. determine the threshold for hypertensive age, to analyze what happens if the threshold hypertensive age is set to a certain age and the weight of the patient if being varied, and, to set the ideal weight for the patient and analyze what happens with the threshold of hypertensive age.

Keywords: Neural Network, hypertension, data set, training set, supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1620