A PVC Identification Method of ECG Signal Based on Improved BPNN

2015 ◽  
Vol 738-739 ◽  
pp. 578-581 ◽  
Author(s):  
Xiong Yang ◽  
Xin Yu Jin ◽  
Jian Feng Shen
Keyword(s):  
Adaptive Learning ◽  
Back Propagation ◽  
Premature Ventricular Contraction ◽  
Back Propagation Neural Network ◽  
Local Optimum ◽  
Ecg Signal ◽  
Training Time ◽  
Identification Methods ◽  
Treatment Of Arrhythmias ◽  
Aided Diagnosis

Computer-aided diagnosis of Premature Ventricular Contraction (PVC) plays an important role in timely detection and treatment of arrhythmias. Conventional identification methods based on back propagation neural network (BPNN) get problems of overlong training time and local optimum. This paper proposes an application of improved BPNN on PVC identification and the improvements of BPNN are based on self-adaptive learning rate and momentum in training. Denoising and feature extraction of ECG signal obtained from MIT-BIH arrhythmia database are processed first. A comparison between standard BPNN and improved BPNN shows that the latter gets less training time and better accuracy.

Construction of a deep sparse filtering network for rotating machinery fault diagnosis

2021 ◽  
pp. 095440702110148
Author(s):  
Chun Cheng ◽  
Wei Zou ◽  
Weiping Wang ◽  
Michael Pecht
Keyword(s):  
Fault Diagnosis ◽  
Back Propagation ◽  
Feature Learning ◽  
Back Propagation Neural Network ◽  
Rotating Machinery ◽  
Fine Tuning ◽  
Local Optimum ◽  
Back Propagation Algorithm ◽  
Intelligent Fault Diagnosis ◽  
Sparse Filtering

Deep neural networks (DNNs) have shown potential in intelligent fault diagnosis of rotating machinery. However, traditional DNNs such as the back-propagation neural network are highly sensitive to the initial weights and easily fall into the local optimum, which restricts the feature learning capability and diagnostic performance. To overcome the above problems, a deep sparse filtering network (DSFN) constructed by stacked sparse filtering is developed in this paper and applied to fault diagnosis. The developed DSFN is pre-trained by sparse filtering in an unsupervised way. The back-propagation algorithm is employed to optimize the DSFN after pre-training. Then, the DSFN-based intelligent fault diagnosis method is validated using two experiments. The results show that pre-training with sparse filtering and fine-tuning can help the DSFN search for the optimal network parameters, and the DSFN can learn discriminative features adaptively from rotating machinery datasets. Compared with classical methods, the developed diagnostic method can diagnose rotating machinery faults with higher accuracy using fewer training samples.

scholarly journals Computer Aided Diagnosis System To Distinguish Adhd From Similar Behavioral Disorders

2018 ◽  
Vol 11 (2) ◽  
pp. 1135-1141
Author(s):  
Siba Shankar Beriha
Keyword(s):  
Fractal Dimension ◽  
Behavioral Disorders ◽  
Research Work ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Computer Aided Diagnosis ◽  
Signal Features ◽  
Computer Aided ◽  
Anxiety Depression ◽  
Aided Diagnosis

ADHD is one of the most prevalent psychiatric disorder of childhood, characterized by inattention and distractibility, with or without accompanying hyperactivity. The main aim of this research work is to develop a Computer Aided Diagnosis (CAD) technique with minimal steps that can differentiate the ADHD children from the other similar children behavioral disorders such as anxiety, depression and conduct disorder based on the Electroencephalogram (EEG) signal features and symptoms. The proposed technique is based on soft computing and bio inspired computing algorithms. Four non-linear features are extracted from the EEG such as Higuchi fractal dimension, Katz fractal dimension, Sevick fractal dimension and Lyapunov exponent and 14 symptoms which are most important in differentiation are extracted by experts in the field of psychiatry. Particle Swarm Optimization (PSO) tuned Back Propagation Neural Network (BPNN) and PSO tuned Radial Basis Function (RBF) employed as a classifier. By investigating these integrated features, we obtained good classification accuracy. Simulation results suggest that the proposed technique offer high potential in the diagnosis of ADHD and may be a good preliminary assistant for psychiatrists in diagnosing high risk behavioral disorders of children.

N-MyristoylG-PseAAC: Sequence-based Prediction of N-Myristoyl Glycine Sites in Proteins by Integration of PseAAC and Statistical Moments

2019 ◽  
Vol 16 (3) ◽  
pp. 226-234 ◽  
Author(s):  
Sher Afzal Khan ◽  
Yaser Daanial Khan ◽  
Shakeel Ahmad ◽  
Khalid H. Allehaibi
Keyword(s):  
Adaptive Learning ◽  
Protein Modification ◽  
Cross Validation ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Statistical Moments ◽  
Covalent Attachment ◽  
Related Proteins ◽  
Self Consistency ◽  
Fold Cross Validation

N-Myristoylation, an irreversible protein modification, occurs by the covalent attachment of myristate with the N-terminal glycine of the eukaryotic and viral proteins, and is associated with a variety of pathogens and disease-related proteins. Identification of myristoylation sites through experimental mechanisms can be costly, labour associated and time-consuming. Due to the association of N-myristoylation with various diseases, its timely prediction can help in diagnosing and controlling the associated fatal diseases. Herein, we present a method named N-MyristoylG-PseAAC in which we have incorporated PseAAC with statistical moments for the prediction of N-Myristoyl Glycine (NMG) sites. A benchmark dataset of 893 positive and 1093 negative samples was collected and used in this study. For feature vector, various position and composition relative features along with the statistical moments were calculated. Later on, a back propagation neural network was trained using feature vectors and scaled conjugate gradient descent with adaptive learning was used as an optimizer. Selfconsistency testing and 10-fold cross-validation were performed to evaluate the performance of N-MyristoylG-PseAAC, by using accuracy metrics. For self-consistency testing, 99.80% Acc, 99.78% Sp, 99.81% Sn and 0.99 MCC were observed, whereas, for 10-fold cross validation, 97.18% Acc, 98.54% Sp, 96.07% Sn and 0.94 MCC were observed. Thus, it was found that the proposed predictor can help in predicting the myristoylation sites in an efficient and accurate way.

Neural Network-Based Geometry Classification for Navigation Satellite Selection

2003 ◽  
Vol 56 (2) ◽  
pp. 291-304 ◽  
Author(s):  
Dah-Jing Jwo ◽  
Chien-Cheng Lai
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Probabilistic Neural Network ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Classification Performance ◽  
Navigation Satellite ◽  
Training Time ◽  
Fast Learning ◽  
Satellite Geometry

The neural networks (NN)-based geometry classification for good or acceptable navigation satellite subset selection is presented. The approach is based on classifying the values of satellite Geometry Dilution of Precision (GDOP) utilizing the classification-type NNs. Unlike some of the NNs that approximate the function, such as the back-propagation neural network (BPNN), the NNs here are employed as classifiers. Although BPNN can also be employed as a classifier, it takes a long training time. Two other methods that feature a fast learning speed will be implemented, including Optimal Interpolative (OI) Net and Probabilistic Neural Network (PNN). Simulation results from these three neural networks are presented. The classification performance and computational expense of neural network-based GDOP classification are explored.

scholarly journals Incremental Approach of Neural Network in Back Propagation Algorithms for Web Data Mining

2017 ◽  
Vol 6 (2) ◽  
pp. 74
Author(s):  
A. P. Tawdar ◽  
M. S. Bewoor ◽  
S. H. Patil
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Text Categorization ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Classification Task ◽  
Text Documents ◽  
Training Time ◽  
Text Document ◽  
Content Mining

Text Classification is also called as Text Categorization (TC), is the task of classifying a set of text documents automatically into different categories from a predefined set. If a text document relates to exactly one of the categories, then it is called as single-label classification task; otherwise, it is called as multi-label classification task. For Information Retrieval (IR) and Machine Learning (ML), TC uses several tools and has received much attention in the last decades. In this paper, first classifies the text documents using MLP based machine learning approach (BPP) and then return the most relevant documents. And also describes a proposed back propagation neural network classifier that performs cross validation for original Neural Network. In order to optimize the classification accuracy, training time. Proposed web content mining methodology in the exploration with the aid of BPP. The main objective of this investigation is web document extraction and utilizing different grouping algorithm. This work extricates the data from the web URL.

A New Hybrid Method for Parameter Optimization of SVR

2018 ◽  
Vol 22 (2) ◽  
pp. 271-279 ◽  
Author(s):  
Jiang Xie ◽  
Taifeng Sun ◽  
Jieyu Zhang ◽  
Wu Zhang ◽  
◽  
...  
Keyword(s):  
Parameter Optimization ◽  
Hybrid Method ◽  
Scatter Search ◽  
Back Propagation ◽  
Optimization Methods ◽  
Optimization Method ◽  
Back Propagation Neural Network ◽  
Support Vector ◽  
Local Optimum ◽  
Improvement Method

The performance of Support Vector Regression (SVR) depends heavily on its parameters, but some optimization methods based on Grid Search (GS) or evolutionary algorithms still have several issues that must be addressed. This paper proposes a new hybrid method (PSO-SS) that combines Particle Swarm Optimization (PSO) and Scatter Search (SS) to optimize the parameters of the SVR. In PSO-SS, to improve the search capability of PSO and reduce the likelihood of the PSO becoming trapped in the local optimum, the initial PSO population is generated by the diversification generation method and the improvement method of SS, and the velocity updating formula of PSO is improved by adding diversity information. On the StatLib and UCI datasets, our experiments show that the PSO-SS method is an effective parameter optimization method compared with other methods. In addition, an SVR model with its parameters optimized by PSO-SS (PSO-SS-SVR) is used to predict the grain size of aluminum alloys. The experimental results show that the PSO-SS-SVR method outperforms Back Propagation Neural Network (BPNN), PSO-SVR and the empirical model.

scholarly journals FPGA Based Design of Artificial Neural Processor Used for Wireless Sensor Network

2019 ◽  
Vol 7 (1) ◽  
pp. 200-222
Author(s):  
Azzad Bader Saeed ◽  
Sabah Abdul-Hassan Gitaffa
Keyword(s):  
Mean Square Error ◽  
Adaptive Learning ◽  
Gradient Descent ◽  
High Speed ◽  
Intelligent System ◽  
Back Propagation ◽  
Optimization Method ◽  
Back Propagation Neural Network ◽  
Mean Square ◽  
Powerful Learning

In this paper,  a simulation of  artificial intelligent system has been designed for processing  the incoming data of  sensor  units and then presenting proper decision. The Back-propagation Neural Network BPNN has been used as the proposed  intelligent system for this work, whereas the BPNN is considered as a trained network in conjunction with an optimization method for changing the weights and biases of the overall network. The main two features of the  BPNN are: high speed processing, and producing  lowest Mean-Square-Error MSE ( cost function ) in few iterations. The proposed BPNN has used the linear activation functions 'Satlins' and 'Satline' for the hidden and output layer respectively, and has used the training function 'Traingda' ( which is gradient descent with adaptive learning rate)  as a powerful learning method. It is worth to mention, that no previous research used these three functions together for such analysis. The MATLAB software package has been used for  designing and testing the proposed system. An optimal result has been obtained in this work, where the value of  Mean-Square-Error has reached to zero   in 87 epochs, and the real and desired outputs have been fitted. In fact, there is  no previous work has reached to this optimal result.  The proposed BPNN has been implemented in FPGA, which is fast, and low power tool.

A New Automatic Modulation Classifier Using Swarm Intelligence-Trained Neural Network

2013 ◽  
Vol 734-737 ◽  
pp. 2871-2874
Author(s):  
Li Cheng ◽  
Jin Liu
Keyword(s):  
Neural Network ◽  
Swarm Intelligence ◽  
Adaptive Learning ◽  
Fault Tolerant ◽  
Back Propagation ◽  
Intermediate Step ◽  
Modulation Classification ◽  
Training Time ◽  
Identification Rate ◽  
Modulation Type

Monitoring modulation type of the detected signal is the most important intermediate step between signal detection and demodulation. The back propagation neural network (BPNN) was widely used in constructing modulated signal classifier in the field of automatic modulation classification (AMC). There are many visible features in the back propagation (BP) algorithm including adaptive learning, the ability of fault tolerant, etc. However, this algorithm has two main disadvantages, such as the slow convergence speed and easily falling into the local minimum. This paper presents a novel modulation classifier using BPNN trained with swarm intelligence algorithms (SIA), for the sake of overcoming these deficiencies. The initial weights and thresholds of BP neural network were optimized by SIA. As the SIA has an excellent global search property, this classifier can consume less training time and improve the automatic modulation type identification rate.

Sign in / Sign up

Export Citation Format

Share Document