Application of InP Neural Network to ECG BeatClassification

Ölmez, Tamer; Dokur, Zümray

doi:10.1007/s00521-003-0351-6

Cited by 10 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial Neural Networks (ANN) and fuzzy-based techniques were also employed to exploit their natural ability in pattern recognition task for successful classification of ECG beats [1,2].…”

Section: Fig 1 Schematic Of Ecg Signalmentioning

confidence: 99%

“…Many artificial intelligent techniques such as maximum likelihood, artificial neural networks [2], and support vector machines [3] have been used successfully for ECG beat classification. These methods based on supervised learning learn from the samples of training data and map new data instances based on the information extracted from the annotated training data (targets) [4].…”

Section: Fig 1 Schematic Of Ecg Signalmentioning

confidence: 99%

“…They are often affected by noise. The acquisition of the signal requires their amplification and further processing in order to suppress noise to highest extent [2,7]. Further ECG signal analysis is realized based on these recordings for which the noise due to power-line interferences, EMG artifacts from muscles, motion artifacts from the subject and electrodes has been suppressed.…”

Section: Pre-processing and Ecg Beat Detectionmentioning

confidence: 99%

See 2 more Smart Citations

ECG Beats Extraction and Classification Using Radial Basis Function Neural Networks

Belkheiri

Douidi

Belkheiri

2013

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

This paper aims the design of an ECG diagnosis system that helps physicians in the interpretation of ECG signals. This system preprocesses and extracts the ECG beats of an ECG record and some feature extraction techniques are invoked to get a feature vector that represents the main characteristics of the ECG wave. After that a well trained RBF artificial neural network is used as a classifier for four different ECG heart conditions selected from MIT-BIH arrhythmia database. The ECG samples were processed and normalized to produce a set of reduced feature vectors. The results of sensitivity, specificity accuracy and recognition rate of the system are analyzed to find the best RBF neural network for ECG classification. Different ECG feature vectors composed of averaged amplitude values, DCT coefficients, DFT coefficients, and wavelet coefficients were used as inputs to the neural network. Among different feature sets, it was found that an RBF which has one layer and the feature vector 61 inputs, and 20 neurons possessed the best performance with highest recognition rate of 95 % for four cardiac conditions.

show abstract

Section: Fig 1 Schematic Of Ecg Signalmentioning

confidence: 99%

Section: Fig 1 Schematic Of Ecg Signalmentioning

confidence: 99%

Section: Pre-processing and Ecg Beat Detectionmentioning

confidence: 99%

See 1 more Smart Citation

ECG Beats Extraction and Classification Using Radial Basis Function Neural Networks

Belkheiri

Douidi

Belkheiri

2013

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…Various methods have been considered to achieve this objective. The most common approaches that have been widely attempted to reduce the dimensionality of high-dimensional data like spectra, signals or images are the wavelet transform (WT) and principal component analysis (PCA) [6][7][8][9]. They are often utilized in conjunction with neural networks to form a kind of hybrid structure [10] to solve highdimensional data classification problems and image analysis problems.…”

Section: Introductionmentioning

confidence: 99%

Intelligent methods for solving inverse problems of backscattering spectra with noise: a comparison between neural networks and simulated annealing

Guo

Verma

et al. 2008

Neural Comput & Applic

View full text Add to dashboard Cite

This paper investigates two different intelligent techniques-the neural network (NN) method and the simulated annealing (SA) algorithm for solving the inverse problem of Rutherford backscattering (RBS) with noisy data. The RBS inverse problem is to determine the sample structure information from measured spectra, which can be defined as either a function approximation or a non-linear optimization problem. Early studies emphasized on numerical methods and empirical fitting. In this work, we have applied intelligent techniques and compared their performance and effectiveness for spectral data analysis by solving the inverse problem. Since each RBS spectrum may contain up to 512 data points, principal component analysis is used to make the feature extraction so as to ease the complexity of constructing the network. The innovative aspects of our work include introducing dimensionality reduction and noise modeling. Experiments on RBS spectra from SiGe thin films on a silicon substrate show that the SA is more accurate but the NN is faster, though both methods produce satisfactory results. Both methods are resilient to 10% Poisson noise in the input. These new findings indicate that in RBS data analysis the NN approach should be preferred when fast processing is required; whereas the SA method becomes the first choice should the analysis accuracy be targeted.

show abstract

“…Olmez and Dokur [42] developed a neural network-based method for the classification of heart sounds, and a hybrid network trained by genetic algorithms for the classification of electrocardiogram (ECG) beats [43].…”

Section: Signal and Image Analysis And Interpretationmentioning

confidence: 99%