An Effective Solution to Regression Problem by RBF Neuron Network

2015 ◽  
Vol 6 (4) ◽  
pp. 57-74 ◽  
Author(s):  
Dang Thi Thu Hien ◽  
Hoang Xuan Huan ◽  
Le Xuan Minh Hoang
Keyword(s):  
Regression Function ◽  
Training Data ◽  
Neuron Network ◽  
Open Problems ◽  
Regression Problem ◽  
Rbf Network ◽  
Network Training ◽  
Hidden Layer ◽  
Definition Of ◽  
Selection Of

Radial Basis Function (RBF) neuron network is being applied widely in multivariate function regression. However, selection of neuron number for hidden layer and definition of suitable centre in order to produce a good regression network are still open problems which have been researched by many people. This article proposes to apply grid equally space nodes as the centre of hidden layer. Then, the authors use k-nearest neighbour method to define the value of regression function at the center and an interpolation RBF network training algorithm with equally spaced nodes to train the network. The experiments show the outstanding efficiency of regression function when the training data has Gauss white noise.

A VISUALIZATION AND DESIGN TOOL (AVID) FOR DATA MINING WITH THE SELF-ORGANIZING FEATURE MAP

2000 ◽  
Vol 09 (03) ◽  
pp. 369-375
Author(s):  
SUSAN E. GEORGE
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Software Tool ◽  
Design Tool ◽  
The Self ◽  
Training Data ◽  
Feature Map ◽  
Network Training ◽  
Som Network ◽  
Selection Of

This paper presents a software tool called AVID (A VIsualization and Design) which is particularly useful for data mining with an artificial neural network known as the self-organising feature map (SOM). AVID supports network training in both the i) selection of network inputs and ii) visualisation of the trained SOM. Both these features are novel aids to SOM network training and are particularly important when consideration is given to using the SOM for data mining. Once trained the SOM produces a 2-dimensional topological ordering of the input training data and it is particularly useful for representing the relationships within multi-dimensional data. The main classes within the data can be identified from the output map. AVID is an important software tool which enables data mining with the SOM by the selection of network inputs and the subsequent visualisation of the classes within these input vectors.

scholarly journals Fault Diagnosis for Engine Based on Single-Stage Extreme Learning Machine

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
Fei Gao ◽  
Jiangang Lv
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Feature Space ◽  
Single Stage ◽  
Training Data ◽  
Learning Machine ◽  
Hidden Layer ◽  
Signal Processing Methods ◽  
Hidden Nodes ◽  
Selection Of

Single-Stage Extreme Learning Machine (SS-ELM) is presented to dispose of the mechanical fault diagnosis in this paper. Based on it, the traditional mapping type of extreme learning machine (ELM) has been changed and the eigenvectors extracted from signal processing methods are directly regarded as outputs of the network’s hidden layer. Then the uncertainty that training data transformed from the input space to the ELM feature space with the ELM mapping and problem of the selection of the hidden nodes are avoided effectively. The experiment results of diesel engine fault diagnosis show good performance of the SS-ELM algorithm.

scholarly journals Combination of SOM-RBF for drought code prediction using rainfall and air temperature data

2019 ◽  
Vol 8 (1) ◽  
pp. 64-68
Author(s):  
Dwi Marisa Midyanti
Keyword(s):  
Air Temperature ◽  
Temperature Data ◽  
Detection Accuracy ◽  
Rbf Network ◽  
Network Training ◽  
Learning Rates ◽  
Weight Value ◽  
Final Weight ◽  
Hidden Layer ◽  
Number Of Iterations

This study aims to predict Drought Code (DC) in Kabupaten Kubu Raya using a combination of SOM-RBF. The final weight value of SOM was used as a center on the RBF network. The input data variables are rainfall data and air temperature data for three days with three binary outputs to predict DC values. This study also observed the effect of the number of neurons, learning rates, and the number of iterations on the results of the SOM-RBF network training. The smallest MSE of training result from the SOM-RBF network was 0.159933 using 65 neurons in the hidden layer, learning rate 0.007, and epoch 45000. The detection accuracy of SOM-RBF was 91.34 % from 245 test data.

scholarly journals A Two-Stage Combining Classifier Model for the Development of Adaptive Dialog Systems

2016 ◽  
Vol 26 (01) ◽  
pp. 1650002 ◽  
Author(s):  
David Griol ◽  
José Antonio Iglesias ◽  
Agapito Ledezma ◽  
Araceli Sanchis
Keyword(s):  
Training Data ◽  
System Response ◽  
Dialog Systems ◽  
Statistical Framework ◽  
Dialog System ◽  
Spoken Dialog System ◽  
Detailed Evaluation ◽  
History Of ◽  
Definition Of ◽  
Selection Of

This paper proposes a statistical framework to develop user-adapted spoken dialog systems. The proposed framework integrates two main models. The first model is used to predict the user’s intention during the dialog. The second model uses this prediction and the history of dialog up to the current moment to predict the next system response. This prediction is performed with an ensemble-based classifier trained for each of the tasks considered, so that a better selection of the next system can be attained weighting the outputs of these specialized classifiers. The codification of the information and the definition of data structures to store the data supplied by the user throughout the dialog makes the estimation of the models from the training data and practical domains manageable. We describe our proposal and its application and detailed evaluation in a practical spoken dialog system.

Selection and Preparation of Specific Tissue Regions For Tem Using Large Epoxy-Embedded Blocks

1973 ◽  
Vol 31 ◽  
pp. 324-325 ◽  
Author(s):  
P. M. Lowrie ◽  
W. S. Tyler
Keyword(s):  
Electron Microscopy ◽  
Anatomical Structures ◽  
Ultrastructural Studies ◽  
Transmission Electron ◽  
Microscopic Evaluation ◽  
Embedded Blocks ◽  
Specific Tissue ◽  
Definition Of ◽  
Areas Of Interest ◽  
Selection Of

The importance of examining stained 1 to 2μ plastic sections by light microscopy has long been recognized, both for increased definition of many histologic features and for selection of specimen samples to be used in ultrastructural studies. Selection of specimens with specific orien ation relative to anatomical structures becomes of critical importance in ultrastructural investigations of organs such as the lung. The uantity of blocks necessary to locate special areas of interest by random sampling is large, however, and the method is lacking in precision. Several methods have been described for selection of specific areas for electron microscopy using light microscopic evaluation of paraffin, epoxy-infiltrated, or epoxy-embedded large blocks from which thick sections were cut. Selected areas from these thick sections were subsequently removed and re-embedded or attached to blank precasted blocks and resectioned for transmission electron microscopy (TEM).

scholarly journals Hardware implementation of radial-basis neural networks with Gaussian activation functions on FPGA

2021 ◽  
Author(s):  
Volodymyr Shymkovych ◽  
Sergii Telenyk ◽  
Petro Kravets
Keyword(s):  
Neural Networks ◽  
Hardware Implementation ◽  
Gaussian Function ◽  
Activation Function ◽  
Rbf Neural Networks ◽  
Activation Functions ◽  
Rbf Network ◽  
Combination Scheme ◽  
Radial Basis ◽  
Hidden Layer

AbstractThis article introduces a method for realizing the Gaussian activation function of radial-basis (RBF) neural networks with their hardware implementation on field-programmable gaits area (FPGAs). The results of modeling of the Gaussian function on FPGA chips of different families have been presented. RBF neural networks of various topologies have been synthesized and investigated. The hardware component implemented by this algorithm is an RBF neural network with four neurons of the latent layer and one neuron with a sigmoid activation function on an FPGA using 16-bit numbers with a fixed point, which took 1193 logic matrix gate (LUTs—LookUpTable). Each hidden layer neuron of the RBF network is designed on an FPGA as a separate computing unit. The speed as a total delay of the combination scheme of the block RBF network was 101.579 ns. The implementation of the Gaussian activation functions of the hidden layer of the RBF network occupies 106 LUTs, and the speed of the Gaussian activation functions is 29.33 ns. The absolute error is ± 0.005. The Spartan 3 family of chips for modeling has been used to get these results. Modeling on chips of other series has been also introduced in the article. RBF neural networks of various topologies have been synthesized and investigated. Hardware implementation of RBF neural networks with such speed allows them to be used in real-time control systems for high-speed objects.

scholarly journals Promotion of Resilience in Migrants: A Systematic Review of Study and Psychosocial Intervention

2021 ◽  
Author(s):  
Maria Ciaramella ◽  
Nadia Monacelli ◽  
Livia Concetta Eugenia Cocimano
Keyword(s):  
Systematic Review ◽  
Psychosocial Intervention ◽  
Life Experiences ◽  
Psychosocial Interventions ◽  
Migrant Population ◽  
Methodological Choices ◽  
Research Questions ◽  
Definition Of ◽  
Selection Of

AbstractThis systematic review aimed to contribute to a better and more focused understanding of the link between the concept of resilience and psychosocial interventions in the migrant population. The research questions concerned the type of population involved, definition of resilience, methodological choices and which intervention programmes were targeted at migrants. In the 90 articles included, an heterogeneity in defining resilience or not well specified definition resulted. Different migratory experiences were not adequately considered in the selection of participants. Few resilience interventions on migrants were resulted. A lack of procedure’s descriptions that keep in account specific migrants’ life-experiences and efficacy’s measures were highlighted.

scholarly journals A Geometric Perspective on Information Plane Analysis

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 711
Author(s):  
Mina Basirat ◽  
Bernhard C. Geiger ◽  
Peter M. Roth
Keyword(s):  
Neural Network ◽  
Mutual Information ◽  
Geometric Interpretation ◽  
Neural Network Training ◽  
Neural Network Learning ◽  
Network Learning ◽  
Plane Analysis ◽  
Network Training ◽  
Hidden Layer ◽  
The Impact

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

scholarly journals Designing Strong Privacy Metrics Suites Using Evolutionary Optimization

2021 ◽  
Vol 24 (2) ◽  
pp. 1-35
Author(s):  
Isabel Wagner ◽  
Iryna Yevseyeva
Keyword(s):  
Optimization Problem ◽  
Evolutionary Optimization ◽  
Multiple Objectives ◽  
Shared Value ◽  
Vehicular Communications ◽  
Open Problems ◽  
Value Range ◽  
Genomic Privacy ◽  
Metaheuristic Optimization Algorithms ◽  
Selection Of

The ability to measure privacy accurately and consistently is key in the development of new privacy protections. However, recent studies have uncovered weaknesses in existing privacy metrics, as well as weaknesses caused by the use of only a single privacy metric. Metrics suites, or combinations of privacy metrics, are a promising mechanism to alleviate these weaknesses, if we can solve two open problems: which metrics should be combined and how. In this article, we tackle the first problem, i.e., the selection of metrics for strong metrics suites, by formulating it as a knapsack optimization problem with both single and multiple objectives. Because solving this problem exactly is difficult due to the large number of combinations and many qualities/objectives that need to be evaluated for each metrics suite, we apply 16 existing evolutionary and metaheuristic optimization algorithms. We solve the optimization problem for three privacy application domains: genomic privacy, graph privacy, and vehicular communications privacy. We find that the resulting metrics suites have better properties, i.e., higher monotonicity, diversity, evenness, and shared value range, than previously proposed metrics suites.

scholarly journals Coronary Centerline Extraction from CCTA Using 3D-UNet

2021 ◽  
Vol 13 (4) ◽  
pp. 101
Author(s):  
Alexandru Dorobanțiu ◽  
Valentin Ogrean ◽  
Remus Brad
Keyword(s):  
Computed Tomography ◽  
Cardiac Computed Tomography ◽  
Three Dimensional ◽  
Class Imbalance ◽  
Training Data ◽  
Cardiac Computed Tomography Angiography ◽  
Centerline Extraction ◽  
Network Training ◽  
Dimensional Reconstruction ◽  
Coronary Centerline

The mesh-type coronary model, obtained from three-dimensional reconstruction using the sequence of images produced by computed tomography (CT), can be used to obtain useful diagnostic information, such as extracting the projection of the lumen (planar development along an artery). In this paper, we have focused on automated coronary centerline extraction from cardiac computed tomography angiography (CCTA) proposing a 3D version of U-Net architecture, trained with a novel loss function and with augmented patches. We have obtained promising results for accuracy (between 90–95%) and overlap (between 90–94%) with various network training configurations on the data from the Rotterdam Coronary Artery Centerline Extraction benchmark. We have also demonstrated the ability of the proposed network to learn despite the huge class imbalance and sparse annotation present in the training data.

Sign in / Sign up

Export Citation Format

Share Document