scholarly journals A Smoothing Interval Neural Network

2012 ◽  
Vol 2012 ◽  
pp. 1-25 ◽  
Author(s):  
Dakun Yang ◽  
Wei Wu
Keyword(s):  
Neural Network ◽  
Smooth Function ◽  
Numerical Experiments ◽  
Interval Data ◽  
Gradient Algorithm ◽  
Output Layer ◽  
Learning Procedure ◽  
The Absolute ◽  
Hidden Layer ◽  
Interval Neural Network

In many applications, it is natural to use interval data to describe various kinds of uncertainties. This paper is concerned with an interval neural network with a hidden layer. For the original interval neural network, it might cause oscillation in the learning procedure as indicated in our numerical experiments. In this paper, a smoothing interval neural network is proposed to prevent the weights oscillation during the learning procedure. Here, by smoothing we mean that, in a neighborhood of the origin, we replace the absolute values of the weights by a smooth function of the weights in the hidden layer and output layer. The convergence of a gradient algorithm for training the smoothing interval neural network is proved. Supporting numerical experiments are provided.

scholarly journals The effect of Kurtosis on the accuracy of artificial neural network predictive model

2018 ◽  
Vol 204 ◽  
pp. 02018
Author(s):  
Aisyah Larasati ◽  
Anik Dwiastutik ◽  
Darin Ramadhanti ◽  
Aal Mahardika
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Predictive Model ◽  
Predictive Models ◽  
Output Layer ◽  
Input Layer ◽  
Artificial Neural ◽  
Misclassification Rates ◽  
Hidden Layer ◽  
Program Data

This study aims to explore the effect of kurtosis level of the data in the output layer on the accuracy of artificial neural network predictive models. The artificial neural network predictive models are comprised of one node in the output layer and six nodes in the input layer. The number of hidden layer is automatically built by the program. Data are generated using simulation approach. The results show that the kurtosis level of the node in the output layer is significantly affect the accuracy of the artificial neural network predictive model. Platycurtic and leptocurtic data has significantly higher misclassification rates than mesocurtic data. However, the misclassification rates between platycurtic and leptocurtic is not significantly different. Thus, data distribution with kurtosis nearly to zero results in a better ANN predictive model.

Prediction Model of Flow-Induced Noise in Large-Scale Centrifugal Pumps Based on BP Neural Network

2017 ◽  
Author(s):  
Chang Guo ◽  
Ming Gao ◽  
Peixin Dong ◽  
Yuetao Shi ◽  
Fengzhong Sun
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Working Conditions ◽  
Bp Neural Network ◽  
Centrifugal Pumps ◽  
Output Layer ◽  
Sample Data ◽  
Input Layer ◽  
Flow Induced Noise ◽  
Hidden Layer

As one kind of serious environmental problems, flow-induced noise in centrifugal pumps pollutes the working circumstance and deteriorates the performance of pumps, meanwhile, it always changes drastically under various working conditions. Consequently, it is extremely significant to predict flow-induced noise of centrifugal pumps under various working conditions with a practical mathematical model. In this paper, a three-layer back propagation (BP) neural network model is established and the number of input, hidden and output layer node is set as 3, 6 and 1, respectively. To be specific, the flow rate, rotational speed and medium temperature are chosen as input layer, and the corresponding flow-induced noise evaluated by average of total sound pressure level (A_TSPL) as output layer. Furthermore, the tansig function is used to act as transfer function between the input layer and hidden layer, and the purelin function is used between hidden layer and output layer. The trainlm function based on Levenberg-Marquardt algorithm is selected as the training function. By using a large number of sample data, the training of the network model and prediction research are accomplished. The results indicate that good correlation is established among the sample data, and the predictive values show great consistence with simulation ones, of which the average relative error of A_TSPL in process of verification is 0.52%. The precision of the model can satisfy the requirement of relevant research and engineering application.

Rapid Method for Prediction of Escherichia coli Numbers Using an Electronic Sensor Array and an Artificial Neural Network

2004 ◽  
Vol 67 (8) ◽  
pp. 1604-1609 ◽  
Author(s):  
UBONRATANA SIRIPATRAWAN ◽  
JOHN E. LINZ ◽  
BRUCE R. HARTE
Keyword(s):  
Neural Network ◽  
Escherichia Coli ◽  
Artificial Neural Network ◽  
Transfer Function ◽  
Sensor Array ◽  
E Coli ◽  
Output Layer ◽  
Electronic Sensor ◽  
Artificial Neural ◽  
Hidden Layer

An electronic sensor array with 12 nonspecific metal oxide sensors was evaluated for its ability to monitor volatile compounds in super broth alone and in super broth inoculated with Escherichia coli (ATCC 25922) at 37°C for 2 to 12 h. Using discriminant function analysis, it was possible to differentiate super broth alone from that containing E. coli when cell numbers were 105 CFU or more. There was a good agreement between the volatile profiles from the electronic sensor array and a gas chromatography–mass spectrometer method. The potential to predict the number of E. coli and the concentration of specific metabolic compounds was investigated using an artificial neural network (ANN). The artificial neural network was composed of an input layer, one hidden layer, and an output layer, with a hyperbolic tangent sigmoidal transfer function in the hidden layer and a linear transfer function in the output layer. Good prediction was found as measured by a regression coefficient (R2 = 0.999) between actual and predicted data.

Neural Network Modeling for Family Welfare Classification

Tech-E ◽  
2018 ◽  
Vol 1 (2) ◽  
pp. 26
Author(s):  
Sri Redjeki
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Network Modeling ◽  
Gradient Algorithm ◽  
Neural Network Modeling ◽  
Family Welfare ◽  
Gradient Descent Algorithm ◽  
Artificial Neural ◽  
Input Variables ◽  
Hidden Layer

Welfare in general can be defined as the level of a person's ability to meet their basic needs in the form of clothing, food, boards, education, and health. Welfare can be assessed in terms of family welfare. This study aims to perform analysis of artificial neural network modeling backpropagation method. The model will compare the optimization algorithm of artificial neural network results. The data used are 251 data of pre prosperous family in Banguntapan District, Bantul Regency. There are 16 input variables with 14 variables from BPS and 2 additional variables. There is one variable that has constant data so that this variable is not used in artificial neural network model analysis. There is a hidden layer with a number of dynamic neurons. Output layer there are 4 neurons which is the family welfare category. Data is processed using Matlab and SPSS. The system results show that the best accuracy for training is 68% of the Scale Conjugate Gradient algorithm while for best test results it is 68.8% of the Gradient Descent algorithm.

Training Pi-Sigma Network by Online Gradient Algorithm with Penalty for Small Weight Update

2007 ◽  
Vol 19 (12) ◽  
pp. 3356-3368 ◽  
Author(s):  
Yan Xiong ◽  
Wei Wu ◽  
Xidai Kang ◽  
Chao Zhang
Keyword(s):  
Neural Networks ◽  
Numerical Experiments ◽  
Error Function ◽  
Feedforward Neural Networks ◽  
Gradient Algorithm ◽  
Training Method ◽  
Penalty Term ◽  
Slow Convergence ◽  
Output Layer ◽  
Adaptive Penalty

A pi-sigma network is a class of feedforward neural networks with product units in the output layer. An online gradient algorithm is the simplest and most often used training method for feedforward neural networks. But there arises a problem when the online gradient algorithm is used for pi-sigma networks in that the update increment of the weights may become very small, especially early in training, resulting in a very slow convergence. To overcome this difficulty, we introduce an adaptive penalty term into the error function, so as to increase the magnitude of the update increment of the weights when it is too small. This strategy brings about faster convergence as shown by the numerical experiments carried out in this letter.

scholarly journals Konstruksi Model Matematika Pola Curah Hujan Menggunakan Artificial Neural Network (ANN) dengan Metode Backpropagation

2018 ◽  
Vol 1 (1) ◽  
pp. 10
Author(s):  
Habibi Ratu Perwira Negara ◽  
Irzani Irzani ◽  
Ripai Ripai
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Rainfall Pattern ◽  
Output Layer ◽  
South Central ◽  
Southern Central ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
The Mathematical Model

Abstrak: Penelitian ini bertujuan untuk menentukan model pola curah hujan menggunakan Artificial Neural Network (ANN) dengan metode Backpropagatiaon. Sampel dalam penelitian ini adalah 5 pos pencataan hujan di daerah Lombok Tengah bagian Selatan dan 2 pos pencatatan hujan di  daerah Lombok Timur bagian Selatan. Data penelitian berupa data setengah bulanan yang dicatat dari tahun 1973 sampai tahun 2010 untuk daerah Lombok Tengah bagian Selatan dan data dari tahun 1974 sampai tahun 2010 untuk daerah Lombok Timur bagian Selatan. Metode penilitian dilakukan dengan melakukan pembelajaran data curah hujan menggunakan 5 arsitektur yang berbeda. Pembelajaran dilakukan untuk menemukan arsitektur terbaik. Arsitektur untuk daerah Lombok Tengah bagian Selatan adalah 120 layer inputan, 240 layer hidden 1, 12 layer hidden 2, dan 1 layer output. Sedangkan arsitektur untuk daerah Lombok Timur bagian Selatan adalah 363 layer inputan, 54 layer hidden 1, 24 layer hidden 2, dan 1 layer output. Model matematika pola curah hujan yang diperoleh adalah .Abstract:  This study aims to determine the model of rainfall pattern using Artificial Neural Network (ANN) with Backpropagatiaon method. The sample in this research is 5 rainfall checkpoint in South Central Lombok and 2 post recording of rain in South East of Lombok. The research data are semi-monthly data recorded from 1973 to 2010 for the southern part of Central Lombok and data from 1974 to 2010 for the southern part of Lombok Timur. Methods of research conducted by conducting rainfall data learning using 5 different architectures. Learning is done to find the best architecture. The architecture for the Southern Central Lombok area is 120 layers of input, 240 hidden layers 1, 12 hidden layers 2, and 1 output layer. While the architecture for the southern part of East Lombok is 363 layers inputan, 54 hidden layer 1, 24 hidden layer 2, and 1 output layer. The mathematical model of the obtained rainfall pattern is .

scholarly journals IMPLEMENTASI JARINGAN SYARAF TIRUAN BACKPROPAGATION DENGAN ALGORITMA CONJUGATE GRADIENT UNTUK KLASIFIKASI KONDISI RUMAH (Studi Kasus di Kabupaten Cilacap Tahun 2018)

2020 ◽  
Vol 9 (1) ◽  
pp. 41-49
Author(s):  
Johanes Roisa Prabowo ◽  
Rukun Santoso ◽  
Hasbi Yasin
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Conjugate Gradient ◽  
Training Data ◽  
Gradient Algorithm ◽  
Output Layer ◽  
Average Accuracy ◽  
Testing Data ◽  
Artificial Neural ◽  
Hidden Layer

House is one aspect of the welfare of society that must be met, because house is the main need for human life besides clothing and food. The condition of the house as a good shelter can be known from the structure and facilities of buildings. This research aims to analyze the classification of house conditions is livable or not livable. The method used is artificial neural networks (ANN). ANN is a system information processing that has characteristics similar to biological neural networks. In this research the optimization method used is the conjugate gradient algorithm. The data used are data of Survei Sosial Ekonomi Nasional (Susenas) March 2018 Kor Keterangan Perumahan for Cilacap Regency. The data is divided into training data and testing data with the proportion that gives the highest average accuracy is 90% for training data and 10% for testing data. The best architecture obtained a model consisting of 8 neurons in input layer, 10 neurons in hidden layer and 1 neuron in output layer. The activation function used are bipolar sigmoid in the hidden layer and binary sigmoid in the output layer. The results of the analysis showed that ANN works very well for classification on house conditions in Cilacap Regency with an average accuracy of 98.96% at the training stage and 97.58% at the testing stage.Keywords: House, Classification, Artificial Neural Networks, Conjugate Gradient

scholarly journals Live to learn: learning rules-based artificial neural network

2021 ◽  
Vol 21 (1) ◽  
pp. 558
Author(s):  
Aseel Shakir I. Hilaiwah ◽  
Hanan Abed Alwally Abed Allah ◽  
Basim Akhudir Abbas ◽  
Tole Sutikno
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Ann Model ◽  
Output Layer ◽  
Ann Models ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Intelligent Model ◽  
Human Nervous System

<span>An extensive review of the artificial neural network (ANN) is presented in this paper. Previous studies review the artificial neural network (ANN) based on the approaches (algorithms) used or based on the types of the artificial neural network (ANN). The presented paper reviews the ANN based on the goal of the ANN (methods, and layers), which become the main objective of this paper. As a famous artificial intelligent model, ANN mimics the human nervous system in handling the information transmited by different nodes (also known as neurons) in this model. These nodes are stacked in layers and work collectively to bring about solution to complex problems. Numerous structures exist for ANN and each of these structures is designed to addressa a specific task. Basically, the ANN architecture is comprised of 3 different layers wherein the first layer rpresents the input layer that consist of several input nodes that represent the input parameterfor the model. The hidden layer is te second layer and consists of a hidden layer of neurons. The neurons in this layer are directly connected to the neurons in the output layer. The third layer is the output layer which is the models’ response layer. The output layer neurons have the activation functions for the calculation of the ANN final output. The connection between the nodes in the ANN model is mediated by synaptic weights. This paper is a comprehensive study of ANN models and their layers.</span>

scholarly journals PENDETEKSIAN DERAU CITRA SECARA OTOMATIS MENGGUNAKAN TEKNIK JARINGAN SYARAF TIRUAN

2009 ◽  
Vol 1 (2) ◽  
pp. 73-86
Author(s):  
Julsam Julsam
Keyword(s):  
Neural Network ◽  
Back Propagation ◽  
Convolution Operation ◽  
Output Layer ◽  
Output Neuron ◽  
Input Layer ◽  
Image Blurring ◽  
Hidden Layer ◽  
Propagation Technique ◽  
Blurring Effect

This research is application of neural network technique to optimize convolution operation using mask 3x3 to omit the image blurring effect. This neural network consists of three layers.  They are input layer (9 neuron inputs), output layer (1 output neuron) and hidden layer. Each layer is applied to 3, 5 and 7 neuron using back propagation technique. The result shows the using five neurons to hidden layer give the highest value of sound pixel recognizing (76.47%)

scholarly journals PATTERN RECOGNITION AKSARA LAMPUNG MENGGUNAKAN ALGORITMA NEURAL NETWORK

2021 ◽  
Vol 9 (2) ◽  
pp. 116-121
Author(s):  
Nopiyanto . ◽  
Rahmadi Rahmadi
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Error Rate ◽  
Output Layer ◽  
Input Layer ◽  
Hidden Layer

Indonesia merupakan Negara yang terdiri dari berbagai macam suku dan budaya, Indonesia juga memiliki berbagai macam bahasa daerah, salah satunya merupakan bahasa Lampung. Bahasa Lampung merupakan bahasa asli suku lampung, didalam bahasa lampung terdapat aksara yaitu aksara lampung. Aksara lampung memiliki 20 kepala bahasa dan 12 tanda baca. Pada penelitian ini dilakukan analisa pengenalan tulisan berdasarkan perubahan iterasi dengan menggunakan metode neural network. Neural network merupakan jaringan saraf yang terdiri dari unit dasar yang seperti analog dengan neuron, neural network dibagi berdasarkan 3 layer yaitu input layer, hidden layer dan output layer. Dimana setiap node pada masing-masing layer memiliki suatu error rate, yang akan digunakan untuk proses training. Pada penelitian ini akan menggunakan bahasa pemograman python. Percobaan untuk induk surat akan menggunakan 20 huruf aksara lampung dengan masing-masing huruf terdapat 10 pengujian citra, dan percobaan untuk anak surat akan menggunakan 12 huruf anak aksara lampung dengan masing-masing huruf terdapat 10 pengujian citra, sehingga total keseluruhan dataset mejadi 320 citra. Hasil yang diperoleh dari proses pemeriksaan masing-masing adalah 75%, untuk induk surat dengan sebaran 135 citra terdeteksi benar dan 45 citra tidak terdeteksi dengan benar. Untuk anak surat 81 citra terdeteksi dengan benar dan 27 citra tidak terdeteksi dengan benar.

Sign in / Sign up

Export Citation Format

Share Document