Conference PaperPDF Available

Konjektif Kalp Yetmezliğinin Hilbert-Huang Dönüşüm ile Analizi

Authors:
  • Iskenderun Technical University
  • Iskenderun Technical University, Hatay, Turkey

Abstract

HHD lineer olmayan ve sabit olmayan sinyaller üzerinde öznitelik belirleme, filtreleme ya da benzeri işlemlere ön işleme olarak sıkça kullanılmaktadır. Bu çalışmada, Hilbert-Huang Transform (HHD) yönteminin kalp ritim sinyallerine uygulanması sonucu elde edilebilecek özniteliklerin belirlenmesi ve kullanılması üzerine çalışmalar yapılmıştır. Konjektif Kalp Yetmezliği (KKY) olan hastaların kontrol grubundan ayırt edilmesi için kullanılmıştır. Çalışmada kalp hızı değişkenlerinden elde edilen RR sinyalleri HHD işleminden geçirilerek içsel mod fonksiyonları (IMF) elde edilmiş, dönüşüm sonrası istatistiksel bilgiler öznitelik olarak çıkarılmıştır. Elde edilen öznitelikler, Yapay Sinir Ağları kullanılarak sınıflandırma başarımı incelenmiştir. Sonuç olarak, elde edilen son sinyallerin istatistiksel öznitelikleri kullanılarak %95.66 sınıflama başarımı elde edilmiştir.
K onjestif Hilber t- ile Analizi
*1, Apdullah YAYIK2, Yakup KUTLU3, Serdar YILDIRIM4, Esen YILDIRIM5
1,3,4,5
2
gokhanaltan@mku.edu.tr, ayayik@kkk.tsk, ykutlu@mku.edu.tr, serdar@mku.edu.tr, eyildirim@mku.edu.tr
Hil bert-Huang (HHD) l ineer olmayan ve
Bu
ve Konjesti f
sinyalleri, HHD
f
(YSA)
5
1.
, Laplace
, Hilbert , Wavelet
[1]. G
HHD bunlardan biridir. HHD, veri analizi konusunda
olmayan ve sabit olmayan sinyaller
[2].
7],
[8
9], ECG sinyallerinde
10]
KKY,
erli kardiyak debinin
-600
konur [6].
, HHD yle elde edilen
KKY nde
. Her
2. M ateryal ve
2.1. Hilber t-Huang (HHD)
HHD
[3]. HHD
Amprik Mod
(AMA
Fonksiyonu . Elde edilen her bir
IMF zaman-
da
elde edilir. HHD
-frekans-enerji
2.1.1. (AMA)
- 159 -
ASYU'2014: AKILLI SİSTEMLERDE YENİLİKLER VE UYGULAMALARI
sin
[2,4]:
sinyalde, sinyalin
ya da
. Herhangi bir t
maksimumlar
ve
, ile
frekans negatif
ve dar sinyallerin
.
AMA yerel
elde edilen yeni sinyalin IMF
yerel ortalama
Bu sin
sin
fonksiyon elde edilinceye kadar devam eder.
ve n
ifade eder [3].
(1)
2.1.2.
sinyalin
[2,3].
fonksiyonunun
halinin y
(2)
HD
(3)
(4)
(5)
edilebilir:
(6)
(7)
AMA her
(4), (5),
(6) ve (7
genlik ya da
frekans m
AMA
a
[3].
- na Hilbert
zgesi denir. Hilbert , Marjinal
si de hesaplanabilir [2,3].
(9)
- 160 -
ASYU'2014: AKILLI SİSTEMLERDE YENİLİKLER VE UYGULAMALARI
2.2.
KKY ve
[5]. Y
KKY hasta v , 8
erkek, 2 bayandan . Normal grup veri
28
.
narak lerin
ve her biri AMA AMA
HHD sinyal elde
HHD
insan ECG RR sinyali ve bu sinyalden elde edilen
83 adet
Daha sonra
,
2.4.
Yapay sinir a (YSA) ,
ile
minimum yapana kadar . Buna modelin
].
Bu
kullan [10,11]:
3.
z test
karakteristikleridirler [7,11].
bulundurularak
saatlik sinyallerden HHD
elde edil
i
Matlab paket program
10 gizli katman, hiperbolik tanjant
Bu
I M F1 I MF2 IM F3 I M F4 I MF5 I MF6 I M F7 I MF8 I M F9 I M F10
Hassasiyet 71.42 78.57 100,00 92.85 92.85 85.71 85.71 85.71 78.57 78.57
Belirlilik 60.00 70.00
100,00
90,00
87.50 77.77 77.77 75.00 66.67 66.67
69.56 78.27 95.65 95.65 86.95 82.60 82.60 78.26 73.91 69.56
- 161 -
ASYU'2014: AKILLI SİSTEMLERDE YENİLİKLER VE UYGULAMALARI
%95.65 gibi g cu
de
5
Hassasiyette ve %100 Belirlilikte tespit
edilebilmektedir.
verilerini kullanarak [13], genlikte ve za
4. K aynaklar
[1] M. Johansson: The Hilbert Transform, Master
[2] A.B. N.E. Huang, Z. Shen, S.R. Long, M.L. Wu,
H.H. Shih,Q. Zheng: The empirical mode
decomposition and Hilbert spectrum for
nonlinear and nonstationary time series analysis,
London A, Vol. 454, pp. 903 995, 1998
[3]
Specific Seizure Prediction Algorithm Using
Hilbert- IEEE-EMBS Intern.
Conf on BHI. Hong Kong, Shenzhen 2012
[4] Y. Hou, H.Tian, "An automatic modulation
recognition algorithm based on HHD
Image and Signal Processing(CTSP), 3rd
International Cong,vol.8,pp.3577-3581, 2010.
[5] Goldberger, A.L., Amaral, L.A.N., vd. 2000.
PhysioBank, PhysioToolkit, and PhysioNet:
101(23), e215 e220.
[6]
HRV indices with wavelet entropy measures
improves to performance in diagnosing
c
vol. 37, no. 10, pp. 1502 10, Oct. 2007.
[7] -
Huang Transform to the data of blood glucose
Student's Conference STC 2007, Faculty
of Mechanical Engineering, Czech Technical
University, Prague
[8] -Huang Transform,
its features and appl
Student's Conference STC 2007, Faculty of
Mechanical Engineering, Czech Technical
University, Prague
[9] -
Signal Processing and Communications
Applications Conference (SIU2013), pp,1-
4, April 2013,DOI: 10.1109/SIU.2013.6531183
[10]
of Atrial Fibrillation Using Empirical Mode
[11] Duda, R.O., Hart, P.E., Stork, D.G. 2000. Pattern
[12] E. D. -fuzzy inference
system for classification of ECG signals using
Lyapunov exponent
Biomed., 2009.
[13]
to Detect Congestive Heart Failure Using
Second-
Cardiol. Res. Pract., vol. 2009, p. 807379, Jan.
2009.
[14] -time CHF detection from ECG
Comput. Biol. Med., vol. 43, no. 10, pp. 1556
62, Oct. 2013.
[15] Y. Isler, and M. Kuntalp, Heart Rate
Normalization in the Analysis of Heart Rate
Variability in Congestive Heart Failure,
Proceedings of the IMechE Part H: Journal of
Engineering in Medicine, vol. 224(3), 453-463,
2010
- 162 -
ASYU'2014: AKILLI SİSTEMLERDE YENİLİKLER VE UYGULAMALARI
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Automatic detection of different cardiac abnormalities is an emerging field of study in assistive diagnosis technology for ca rdiac diseases. Atrial fibrillation (AF) is a kind of arrhythmia which increases risk of heart attack especially to the older people. Detection of AF at the early stage may cause prevention of serious stoke. This paper presents a method of automatic detection of AF by using higher order statistical moments of ECG signal in Empirical Mode Decomposition (EMD) domain. The proposed technique operates in two stages. First stage consists of decomposition of denoised ECG into intrinsic mode functions (IMF) and derives the statistical parameters like variance and standard deviation for classification from each IMF. In the second s tage these features are used by a supervised classifier to distinguish between normal and AF ECG rhythms. The performance of this method is tested with the MIT-BIH arrhythmia data base. Possibility to use different IMFs is also tested and 96% sensitivity is achieved in IMF 4.
Article
Full-text available
A new method for analysing nonlinear and non-stationary data has been developed. The key part of the method is the `empirical mode decomposition' method with which any complicated data set can be decomposed into a finite and often small number of 'intrinsic mode functions' that admit well-behaved Hilbert transforms. This decomposition method is adaptive, and, therefore, highly efficient. Since the decomposition is based on the local characteristic time scale of the data, it is applicable to nonlinear and non-stationary processes. With the Hilbert transform, the 'instrinic mode functions' yield instantaneous frequencies as functions of time that give sharp identifications of imbedded structures. The final presentation of the results is an energy-frequency-time distribution, designated as the Hilbert spectrum. In this method, the main conceptual innovations are the introduction of `intrinsic mode functions' based on local properties of the signal, which make the instantaneous frequency meaningful; and th
Article
Full-text available
A classification system to detect congestive heart failure (CHF) patients from normal (N) patients is described. The classification procedure uses the k-nearest neighbor algorithm and uses features from the second-order difference plot (SODP) obtained from Holter monitor cardiac RR intervals. The classification system which employs a statistical procedure to obtain the final result gave a success rate of 100% to distinguish CHF patients from normal patients. For this study the Holter monitor data of 36 normal and 36 CHF patients were used. The classification system using standard deviation of RR intervals also performed well, although it did not match the 100% success rate using the features from SODP. However, the success rate for classification using this procedure for SDRR was many fold higher compared to using a threshold. The classification system in this paper will be a valuable asset to the clinician, in the detection congestive heart failure.
Article
Abstrakt: Hilbert Huangova transformace (HHT) je doplněním Hilbertovy transformace o metodu EMD (Empirical Mode Decomposition), která rozkládá výchozí data na sadu funkcí -vnitřní modální funkce (Intrisic Mode Function -IMF) a významně tak rozšiřuje možnosti použití na analýzu širokého spektra nelineárních a nestacionárních signálů. Tento článek se zaměřuje na možnosti analýzy dat glykemických profilů pomocí HHT. Mechanismus ovlivňování glykemie v lidském těle je stejně jako většina biologických procesů natolik komplexní, že jej nelze považovat za lineární ani stacionární. Proto byla zvolena pro analýzu právě metoda HHT. Abstract: Hilbert-Huang Transform (HHT) complements Hilbert Transform by EMD method (Empirical Mode Decomposition). EMD decomposes original data to function series IMF (Intrinsic Mode Function) and this significantly extends possibilities of use on wide spectra of nonlinear and nonstationary signals analysis. This paper targets the analyse of blood glucose profiles possibilities by HHT. Mechanism of blood glucose interaction in human body is very compound event like most of biological processes. So it can't be thought to be neither linear nor stationary. That's why HHT method was selected for this analyse.
Conference Paper
Epilepsy is a neurological disorder that affects about 50 million people around the world. EEG signal processing plays an important role in detection and prediction of epileptic seizures. The aim of this study is to develop a method for early seizure prediction based on Hilbert-Huang Transform. In this patient specific method, EEG signals are decomposed into Intrinsic Mode Functions (IMFs) and first 5 IMFs are used to obtain features for classification of preictal and interictal recordings. Proposed method was tested on Freiburg EEG database. A total of 58 hours of preictal data, prior to 87 seizures, and 490 hours of interictal data were examined. Algorithm resulted in 89.66% sensitivity (78 of 87 seizures) and 0.49 FPs/h using 30 seconds EEG segment with 50% overlap.
Article
In order to solve the problem of signal classification and recognition in communication reconnaissance, a novel automatic modulation recognition algorithm based on HHT and SVD is presented in this paper. The instantaneous feature parameters of received signal are extracted using HHT. Then, singular values of matrix which is composed of instantaneous parameters are used as characteristic vector and inputted to the generalized regression neural network (GRNN) to recognize the modulation of the signal. The simulation results show that application of this approach enables the system to identify the hiding location and the modulation of common communication signals, such as MASK, MFSK and MPSK, with a higher recognition ratio.
Article
In this study, the effects of heart rate (HR) normalization in the analysis of the heart rate variability (HRV) were investigated to distinguish 29 patients with congestive heart failure from 54 healthy subjects in the control group. In the analysis performed, the best accuracy performances of optimal combination of standard short-term HRV measures and of HR-normalized short-term HRV measures are compared. A genetic algorithm is used to select the best features from among all possible combinations of these measures. A k-nearest-neighbour (KNN) classifier is used to evaluate the performances of the feature combinations in classifying these two data groups. The results imply that using both min-max and HR normalization improves the performance of the classification. The maximum accuracy is achieved as 93.98 per cent using k = 3 and k = 5 for the KNN classifier with the perfect positive predictivity values.
Article
This paper describes the application of adaptive neuro-fuzzy inference system (ANFIS) model for classification of electrocardiogram (ECG) signals. Decision making was performed in two stages: feature extraction by computation of Lyapunov exponents and classification by the ANFIS trained with the backpropagation gradient descent method in combination with the least squares method. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, and atrial fibrillation beat) obtained from the PhysioBank database were classified by four ANFIS classifiers. To improve diagnostic accuracy, the fifth ANFIS classifier (combining ANFIS) was trained using the outputs of the four ANFIS classifiers as input data. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the saliency of features on classification of the ECG signals were obtained through analysis of the ANFIS. The performance of the ANFIS model was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed ANFIS model has potential in classifying the ECG signals.
Article
In this study, best combination of short-term heart rate variability (HRV) measures are sought for to distinguish 29 patients with congestive heart failure (CHF) from 54 healthy subjects in the control group. In the analysis performed, in addition to the standard HRV measures, wavelet entropy measures are also used. A genetic algorithm is used to select the best ones from among all possible combinations of these measures. A k-nearest neighbor classifier is used to evaluate the performance of the feature combinations in classifying these two groups. The results imply that two combinations of all HRV measures, both of which include wavelet entropy measures, have the highest discrimination power in terms of sensitivity and specificity values.