Learning polynomial networks for classification of clinical electroencephalograms

@article{Schetinin2006LearningPN,
  title={Learning polynomial networks for classification of clinical electroencephalograms},
  author={Vitaly Schetinin and Joachim Schult},
  journal={Soft Computing},
  year={2006},
  volume={10},
  pages={397-403}
}
We describe a polynomial network technique developed for learning to classify clinical electroencephalograms (EEGs) presented by noisy features. Using an evolutionary strategy implemented within group method of data handling, we learn classification models which are comprehensively described by sets of short-term polynomials. The polynomial models were learnt to classify the EEGs recorded from Alzheimer and healthy patients and recognize the EEG artifacts. Comparing the performances of our… 

Feature Extraction with GMDH-Type Neural Networks for EEG-Based Person Identification

The proposed GMDH method can learn new features from multi-electrode EEG data, which are capable to improve the accuracy of biometric identification, and has correctly identified all the subjects and provided a statistically significant improvement of the identification accuracy.

hYBriD conVoluTional-mulTilaYer percepTron arTificial neural neTWorK for person recogniTion BY high gamma eeg feaTures

A hybrid Convolutional-Multilayer Perceptron Neural Network (CNN-MLP) architecture is proposed to be used to learn high gamma EEG features for person recognition.

Prognosis of automated sleep staging based on two-layer ensemble learning stacking model using single-channel EEG signal

The main objective of this study is to propose a high-effective and high-accuracy based multiple sleep staging classification model based on single-channel electroencephalogram (EEG) signals using machine learning (ML) model.

Transfer Learning in GMDH-Type Neural Networks

The ability of transfer learning for a face recognition problem by using Group Method of Data Handling (GMDH) type of Deep Neural Networks, which shows that the transfer learning of a GMDH-type neural network has reduced the training time by 31% on a face Recognition benchmark.

A review and experimental study on the application of classifiers and evolutionary algorithms in EEG-based brain–machine interface systems

A general survey on the base and the combinatorial classification methods for EEG signals as well as their optimization methods through the evolutionary algorithms for BMI-based systems in which EEG signals are used.

Computer-Aided Segmentation and Estimation of Indices in Brain CT Scans

This paper presents a novel technique for segmentation of significant anatomical landmarks using artificial neural networks and estimation of various ratios and indices performed on brain CT scans, efficient and robust in detecting and measuring sizes of anatomical structures on noncontrast CT scans.

Fault Diagnosis of Centrifugal Pump Using Symptom Parameters in Frequency Domain

A fuzzy neural network called “partially-linearized neural network” is proposed, by which the fault types of machinery can be quickly and effectively distinguished on the basis of the possibility grades of symptom parameters.

Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis

The ability of machine learning methods to design a radiology test of Osteoarthritis at early stage when the number of patients’ cases is small is explored and it is concluded that the designed model for early diagnostic of OA will provide more accurate radiology tests, although new study is required when a large number of cases will be available.

Extraction of Texture Features from X-Ray Images: Case of Osteoarthritis Detection

A new approach to extracting the texture features which are represented on the basis of Zernike orthogonal polynomials for osteoarthritis detection in X-ray images is described using a deep learning paradigm known as group method of data handling.

References

SHOWING 1-10 OF 23 REFERENCES

The combined technique for detection of artifacts in clinical electroencephalograms of sleeping newborns

A new method combining the polynomial neural network and decision tree techniques in order to derive comprehensible classification rules from clinical electroencephalograms recorded from sleeping newborns is described.

EEG signal classification with different signal representations

A study comparing four representations of EEG signals and their classification by a two-layer neural network with sigmoid activation functions, gaining a 100-fold decrease in training time over a Sun Sparc10 for a large number of hidden units.

An Assessment System of Dementia of Alzheimer Type Using Artificial Neural Networks

An assessment system of dementia of Alzheimer type (DAT) from electroencephalogram (EEG) was investigated and artificial neural networks models found useful in order to distinguish DAT patients and quantify the severity of DAT from EEG.

Independent Component Analysis of Electroencephalographic Data

First results of applying the ICA algorithm to EEG and event-related potential (ERP) data collected during a sustained auditory detection task show that ICA training is insensitive to different random seeds and ICA may be used to segregate obvious artifactual EEG components from other sources.

A spectral method for removing eye movement artifacts from the EEG.

Removing electroencephalographic artifacts by blind source separation.

The results on EEG data collected from normal and autistic subjects show that ICA can effectively detect, separate, and remove contamination from a wide variety of artifactual sources in EEG records with results comparing favorably with those obtained using regression and PCA methods.

Muscle artifacts in the sleep EEG: Automated detection and effect on all‐night EEG power spectra

It is concluded that elimination of short‐lasting muscle artifacts reduces the confound between cortical and myogenic activity and is important in interpreting quantitative EEG data.