Wyniki wyszukiwania - BazTech

1

Automated detection of Parkinson's disease using minimum average maximum tree and singular value decomposition method with vowels

Tuncer Turker, Dogan Sengul, Acharya Udyavara Rajendra

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

211--220

EN

In this study, a novel method to automatically detect Parkinson's disease (PD) using vowels is proposed. A combination of minimum average maximum (MAMa) tree and singular value decomposition (SVD) are used to extract the salient features from the voice signals. A novel feature signal is constructed from 3 levels of MAMa tree in the preprocessing phase. The SVD operator is applied to the constructed signal for feature extraction. Then 50 most distinctive features are selected using relief feature selection technique. Finally, k nearest neighborhood (KNN) with 10-fold cross validation is used for the classification. We have achieved the highest classification accuracy rate of 92.46% using vowels with KNN classifier. The dataset used consists of 3 vowels for each person. To obtain individual results, post processing step is performed and best result of 96.83% is obtained with KNN classifier. The proposed method is ready to be tested with huge database and can aid the neurologists in the diagnosis of PD using vowels.

2

Generalized Stockwell transform and SVD-based epileptic seizure detection in EEG using random forest

Zhang T., Chen W., Li M.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 3

519--534

EN

Purpose: Visual inspection of electroencephalogram (EEG) records by neurologist is the main diagnostic method of epilepsy but it is particularly time-consuming and expensive. Hence, it is of great significance to develop automatic seizure detection technique. Methods: In this work, a seizure detection approach, synthesizing generalized Stockwell transform (GST), singular value decomposition (SVD) and random forest, was proposed. Utilizing GST, the raw EEG was transformed into a time–frequency matrix, then the global and local singular values were extracted by SVD from the holistic and partitioned matrices of GST, respectively. Subsequently, four local parameters were calculated from each vector of local singular values. Finally, the global singular value vectors and local parameters were respectively fed into two random forest classifiers for classification, and the final category of a testing EEG was voted based on sub-labels obtained from the trained classifiers. Results: Four most common but challenging classification tasks of Bonn EEG database were investigated. The highest accuracies of 99.12%, 99.63%, 99.03% and 98.62% were achieved using our presented technique, respectively. Conclusions: Our proposed technique is comparable or superior to other up-to-date methods. The presented method is promising and able to handle with kinds of epileptic seizure detection tasks with satisfactory accuracy.

3

Robust aperiodic-disturbance rejection in an uncertain modified repetitive-control system

Zhou L., She J., Li C., Pan C.

International Journal of Applied Mathematics and Computer Science

|

2016

|

Vol. 26, no. 2

285--295

EN

This paper concerns the problem of designing an EID-based robust output-feedback modified repetitive-control system (ROFMRCS) that provides satisfactory aperiodic-disturbance rejection performance for a class of plants with time-varying structured uncertainties. An equivalent-input-disturbance (EID) estimator is added to the ROFMRCS that estimates the influences of all types of disturbances and compensates them. A continuous-discrete two-dimensional model is built to describe the EID-based ROFMRCS that accurately presents the features of repetitive control, thereby enabling the control and learning actions to be preferentially adjusted. A robust stability condition for the closed-loop system is given in terms of a linear matrix inequality. It yields the parameters of the repetitive controller, the output-feedback controller, and the EID-estimator. Finally, a numerical example demonstrates the validity of the method.

4

Singular spectrum analysis as a smoothing method of load variability

Cempel C., Tabaszewski M.

Diagnostyka

|

2010

|

nr 4(56)

3-8

EN

Application of SVD to fault extraction from the machine symptom observation matrix (SOM) seems to be validated enough, especially by data taken from many real diagnostic cases. However, frequently we have situation of varying machine load during the production process, where by observed primary symptoms are influenced greatly. This concerns generalized symptoms too, so decision making process and forecasting is disturbed. But we can apply some new data smoothing procedure called singular spectrum analysis (SSA), to eliminate load influenced symptom fluctuation, and obtain the machine wear trend only. This seems to be true, as it was shown in the paper, but special care should be taken to choose smoothing approximation order properly.

PL

Zastosowanie rozkładu SVD do wydobycia informacji o uszkodzeniu z symptomowej macierzy obserwacji (ang. SOM) wydaje się być wystarczająco uzasadnione, szczególnie dla danych pochodzących z wielu rzeczywistych przypadków diagnostycznych. Jednakże w wielu przypadkach mamy do czynienia z sytuacją zmiennych obciążeń maszyny podczas procesu produkcji, silnie wpływających na obserwowane symptomy. Dotyczy to także symptomów uogólnionych, co utrudnia proces podejmowania decyzji i prognozowania. Możemy jednak zastosować pewną nową procedurę wygładzania nazywaną analizą widma szczególnego (ang. SSA), aby wyeliminować obciążenia wpływające na fluktuacje symptomu i otrzymać tylko trend zużycia maszyny. Wydaje się to być prawdą, jak zostało pokazane w pracy, jednak z zachowaniem szczególnej uwagi w poprawnym wyborze rzędu przybliżenia w procedurze wygładzania.