Application of Fuzzy Decision Tree for Signal Classification

Rabcan, Jan; Levashenko, Vitaly; Zaitseva, Elena; Subbotin, Sergey

doi:10.1109/tii.2019.2904845

Cited by 39 publications

(27 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Анализ использования алгоритмов FDT при решении практических задач представлен в [13][14][15]. Эти работы показывают, что их применение в классификационные задачи позволяют получить хорошие результаты.…”

Section: в о зр а с т (A 1 ) д о х о д (A 2 ) с т а ж (A 3 ) за ло г unclassified

Building Decision Support Systems based on Fuzzy Data

Levashenko¹,

Liashenko²,

Kuchuk³

2020

A.I.S.

Self Cite

View full text Add to dashboard Cite

Section: в о зр а с т (A 1 ) д о х о д (A 2 ) с т а ж (A 3 ) за ло г unclassified

Building Decision Support Systems based on Fuzzy Data

Levashenko¹,

Liashenko²,

Kuchuk³

2020

A.I.S.

Self Cite

View full text Add to dashboard Cite

“…Typical classifiers used in the second step need numerical attributes for the classification, but EEG signal is represented as a function of time which cannot be directly classified. Therefore, this signal should be transformed into samples of numerical attributes in the step of signal preprocessing [15], [16], [17], which is also known as the step of the preliminary transformation. EEG signal is preprocessed to remove noise and extract useful information needed for the next step of classification.…”

Section: Introductionmentioning

confidence: 99%

“…The output of the first step is a set of numerical attributes that are used in the classification step. Existing studies of EEG signal classification focus on various classifiers, such as Support Vector Machine (SVM) [23], [24], k-nearest neighbor (kNN) [25], decision tree [15], [21], or neural networks [14], [26]. Special approaches based on evolution methods and clustering analysis have been considered for EEG signal classification in [25], [27].…”

Section: Introductionmentioning

confidence: 99%

Review of Methods for EEG Signal Classification and Development of New Fuzzy Classification-Based Approach

2020

Self Cite

View full text Add to dashboard Cite

The analysis of EEG signal is a relevant problem in health informatics, and its development can help in detection of epileptic's seizures. The diagnosis is based on classification of EEG signal. Different methods and algorithms for classification of EEG signals with an accepted level of reliability and accuracy have been developed over years. All these methods have two steps that are signal preprocessing and classification. The goal of the preprocessing step is removing noise and reduction of the initial signal dimensionality. The signal dimensionality reduction is required by classification methods, but its result is a loss of small information before the classification. In this paper, an approach for EEG signal classification that takes this loss of information into account is considered. The novelty of the considered approach is usage of fuzzy classifier in the classification step. This classifier allows taking uncertainty of initial data into account, which is caused by loss of some information during dimensionality reduction of initial signal. However, application of fuzzy classifier needs modification of the preprocessing step because it requires data in fuzzy form. Therefore, fuzzification procedure is added to the preprocessing step. In this paper, Fuzzy Decision Tree (FDT) is used as the fuzzy classifier for the epileptic's seizure detection. Its application allows achieving 99.5% accuracy of the classification of epileptic's seizure. The comparison with other studies shows that FDT is very effective for task of epileptic's seizure detection.

show abstract

“…To detect an insulation fault, especially a line-to-earth fault, which potentially introduces an electric shock hazard or fire hazard, a suitable protective device of a proper sensitivity level should be selected and applied. The type of protective device and its operational algorithm depends on the type of power network (grounded, ungrounded, overhead line, cable line) [4,5], the necessity of detection of an arc fault [6,7], distorted voltages [8], special signals [9], DC currents [10,11], and the necessity of detection of non-sinusoidal alternating earth fault currents. Special attention should be given to the currents comprising very-low-frequency components [12] or high-order harmonics [13][14][15][16][17][18][19], as in circuits with power electronics converters [20].…”

Section: Introductionmentioning

confidence: 99%

Testing Sensitivity of A-Type Residual Current Devices to Earth Fault Currents with Harmonics

Czapp

2020

Sensors

View full text Add to dashboard Cite

In many applications, modern current-using equipment utilizes power electronic converters to control the consumed power and to adjust the motor speed. Such equipment is used both in industrial and domestic installations. A characteristic feature of the converters is producing distorted earth fault currents, which contain a wide spectrum of harmonics, including high-order harmonics. Nowadays, protection against electric shock in low-voltage power systems is commonly performed with the use of residual current devices (RCDs). In the presence of harmonics, the RCDs may have a tripping current significantly different from that provided for the nominal sinusoidal waveform. Thus, in some cases, protection against electric shock may not be effective. The aim of this paper is to present the result of a wide-range laboratory test of the sensitivity of A-type RCDs in the presence of harmonics. This test has shown that the behavior of RCDs in the presence of harmonics can be varied, including the cases in which the RCD does not react to the distorted earth fault current, as well as cases in which the sensitivity of the RCD is increased. The properties of the main elements of RCDs, including the current sensor, for high-frequency current components are discussed as well.2 of 20 may prevent a person from fatal electric shock, provided that the RCD's rated residual operating current does not exceed 30 mA, which is assumed as the threshold of ventricular fibrillation [3].

show abstract

Application of Fuzzy Decision Tree for Signal Classification

Cited by 39 publications

References 33 publications

Building Decision Support Systems based on Fuzzy Data

Building Decision Support Systems based on Fuzzy Data

Review of Methods for EEG Signal Classification and Development of New Fuzzy Classification-Based Approach

Testing Sensitivity of A-Type Residual Current Devices to Earth Fault Currents with Harmonics

Contact Info

Product

Resources

About