Wyniki wyszukiwania - BazTech

1

Automated detection of myocardial infarction in ECG using modified Stockwell transform and phase distribution pattern from time-frequency analysis

Swain Sushree Satvatee, Patra Dipti, Singh Yengkhom Omesh

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

1174--1189

EN

Myocardial infarction (MI), usually referred as heart attack, takes place when blood circulation stops to specific portion of the heart resulting permanent damage to the heart muscles. It is an important task to identify the occurrence of MI from the ECG recordings efficiently. Most of the detection procedures include advanced signal processing methods, more ECG features and composite classifiers, making the overall procedure complex. This paper aims at automated identification of MI using modified Stockwell transform (MST) based time-frequency analysis and a phase information distribution pattern method. The morphologi-cal, pathological and temporal alterations in ECG waveforms resulting from the onset of MI are noticed in the phase distribution pattern of the ECG signal. Two discriminating features, utterly reflecting these alterations, are recognized for 12 leads of the MI affected ECG signal. Prior informations regarding the pathological characteristics of the specific disease are required for the correct detection of MI using few numbers of ECG leads. Thus, in this paper 12 lead ECG signals have been considered for identification of MI. The two-class classification problem with MI class and healthy individual class is performed using the threshold based classification regulation. Both healthy control and MI affected ECG signals are collected from the PTB diagnostic ECG database. The accuracy, sensitivity and specificity are found to be 99.93%, 99.97% and 99.30% for detection of MI. The proposed method has got the superiority in terms of simplicity of features, small feature dimension and simpler classification rule ensuring faster, accurate and easier MI detection.

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

Charakterystyka częstotliwościowo-czasowa drgań sejsmicznych wywołanych wstrząsami górniczymi

Marcak H., Kłosiński J.

Archives of Mining Sciences

|

2004

|

Vol. 49, nr 2

193-204

PL

Wstrząsy sejsmiczne wywołane pracami górniczymi mogą być źródłem uszkodzeń budynków w rejonach górniczych. Prowadzi się ciągłą rejestrację drgań sejsmicznych wywołanych wstrząsami górniczymi. W artykule pokazano, że istotnym parametrem, który wpływa na wielkość wzmocnienia drgań przez konstrukcje budowlane, jest długość trwania wzmocnionej części widma sygnałowego, którą można wyznaczyć z transformacji Stockwella sygnałów sejsmicznych. Taka zależność dotyczy zarówno rejestracji sejsmicznych pochodzących od trzęsień Ziemi jak również od wstrząsów górniczych.

EN

Generally, Poland is aseismic country. Damages of buildings in our country are caused mainly by mining tremors related with sudden upsetting of equilibrium in exploitation area. Seismic oscillations sometimes have energy from […] Joules. Influence of these tremors on building objects is described in nurnerous scientific publications (Dubiriski, Mutke 1998; Maciqg 2000; Lasocki et al. 2000; Cianciara et al. 2000; Dubinski. Mutke 2001; Mutke et al. 2002). There is a similarity between reacting of buildings on seismic forcing caused by earthquake and mining tremors but there are differences resulting from different structures of seismic signals of these two sources. Frequency band, in which the oscillations caused by these different sources propagate, is shifted (seismic oscillations from mining tremors propagate in higher band), seismic signals from these tremors are shorter and less energetic. There are difficulties in assesment of seismic oscillations effects in the mining areas. Especially, it concerns Copper Basin where appear very strong tremors under the urbanized area. There is continuous recording of seismic oscillations in this area. Measure points are 3-component (vertical Z-component, horizontal X- and Y-component) stations installed on the building in Polkowice. Between other places they are located on: [...] floor, in the pillar and in the ground near the building on Hubal Str. These records were used in presented calculations. These records were from 2002, February 19 at 9:33 pm. in the distance 1236 m from tremor focus with seismic energy 1,6 x […] Joules. We will show that assesment of seismic oscillation effects on the base of maximum value can be inappropriate. To investigating the changes of seismic signal spectrum can be used the method proposed by Stockwell (1996). Calculations of local spectrum is conducted in Gaussian window, which width depends from parameter [tau]. This spectrum is assigned to time instant, in the middle of time window. By shifting this time window two-dimensional image of frequency-time structure can be obtained. On the figures 3a, 3b, 3c are showed records in the ground, on pillar and […] floor, respectively on the building on Hubal Str. in Polkowice. These records concern X, Y, Z components. Looking on these distributions, it can noticed that the value of maximum acceleration in the ground and pillar is not connected with value of acceleration on the 12th floor. Ratio between acceleration of Y-component on the […] floor to the pillar is almost equal to 1,7 but for Y-component this ratio exceeds 3. For Z-component this ratio is equal 0,7. Maximum acceleration in pillar is twice lesser than in the ground for Y-component and 3,5 times bigger for Z-component and almost as big as for Y-component. This diversification of maximum accelerations in the ground indicates that quantity can't be the basis to assesment of deformation degree of building under the influence of seismic oscillations. Principal element which differs these results from records in the ground is occuring relatively strong anomaly in Stockwell transform of X-component in the frequency range below 5 Hz. This strong effect goes on relatively long in records from pillar and on the […] floor (from 9 to 12 seconds). The strongest effects in the Y-component transform in the ground occur at frequency 8 Hz (they are longer on records from pillar). Maximum intensity of Stockwell transform anomaly for Z-component is twice bigger than X-component for the ground and […] floor about 30 times) and occurs in the 20-25 Hz frequency range. For X- and Y-components intensity of high-frequency oscillations recorded on the ground is approximately equal to pillar. But for low frequencies of records from pillar are stronger in compa-rision with those from the ground (maximum intensity for Y-component in the pillar in the range of a few Hz arises several times in comparision with the ground). In the case of Z-component we observe amplification in high-frequency range what can be result of elimination of attenuation in the nearsurface ground layer. It must be given attention to the fact that intensive elements of Stockwell transform for Z-component in the pillar are rather short. It appeared that only oscillations length in the low frequency range has the influence on the oscillations magnitude on the 12th floor. X-component, which was the weakest in the pillar, was strongly amplified creating in the records on […] floor the structure, which can be dangerous for construction. Whereas the strongest oscillations in the Z direction are scaterred by building. This example seems to confirm the conviction that Stockwell transform of seismic records allows much fully to estimate the influence of oscillations on the buildings. Showed example points that effects caused by both earthquakes and mining tremors depends considerably on the length of low-frequency seismic signals characteristics and this parameter should be taken into account in the assesment of the risk of desctructing the buildings under the influence of seismic waves.