Classification of uterine EMG signals by using Normalized Wavelet Packet Energy

Diab, Mohamad O.; Moslem, Bassam; Khalil, Mohamad; Marque, Catherine

doi:10.1109/melcon.2012.6196443

Cited by 10 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various methods have previously been proposed for EHG analysis, comprising statistical approaches (Horoba et al 1999), filtering techniques (Ramondt et al 1986, Horoba et al 2001, fast Fourier transform (FFT) and wavelet transform based methods (Buhimschi et al 1997, Eswaran et al 2002, Diab et al 2012b, as well as evaluation of nonlinear connectivity (Diab et al 2012a). However, only recent studies focused on EHG analysis as an alternative method for quantitative IUP estimation (Jezewski et al 2005, Skowronski et al 2006, Rabotti et al 2008.…”

Section: Introductionmentioning

confidence: 99%

Low-complexity intrauterine pressure estimation using the Teager energy operator on electrohysterographic recordings

Rooijakkers¹,

Rabotti²,

Oei³

et al. 2014

Physiol. Meas.

View full text Add to dashboard Cite

Monitoring the progression of maternal uterine activity provides important prognostic information during pregnancy and parturition. Currently used methods for intrauterine pressure (IUP) measurement are unsuitable for long-term observation of uterine activity. The abdominally measured electrohysterogram (EHG) provides a non-invasive alternative to the existing methods for long-term ambulatory uterine contraction monitoring. A new low-complexity method for IUP estimation based on the Teager energy (TE) operator is proposed. The TE operator was used as it mimics the physiologic phenomena underlying the generation of the EHG signals. Several EHG signal analysis methods for IUP estimation from the literature are compared with the new TE method. The comparison is based on correlation and root mean square error of the IUP estimate with the gold standard internally measured IUP as well as their respective computational complexity. The proposed method results in a superior IUP estimation accuracy and complexity compared to state-of-the-art methods from the literature, with a complexity as much as 55 times lower. Therefore, the proposed method offers a valuable new option for long-term ambulatory uterine monitoring.

show abstract

Section: Introductionmentioning

confidence: 99%

Low-complexity intrauterine pressure estimation using the Teager energy operator on electrohysterographic recordings

Rooijakkers¹,

Rabotti²,

Oei³

et al. 2014

Physiol. Meas.

View full text Add to dashboard Cite

show abstract

“…Five different mother wavelet families sym5, sym8, db4, db8 and coif5 were used in this work. These wavelets were chosen based on their efficiency for biomedical signal classification [16][17][18][19]. b) Classification The Naïve-Bayes is a simple classifier with applications like spam mail filtering, weather prediction and medical diagnosis [26].…”

Section: Methodsmentioning

confidence: 99%

“…Khushaba et al [16] used wavelet packet features for classification of driver drowsiness using sym5 as mother wavelet. Normalized wavelet packet energy extracted from uterine EMG signals used as feature to the ANN classifier [17]. The dimension space reduced using principal component analysis on three level wavelet packets by the authors.…”

Section: Introductionmentioning

confidence: 99%

Comparison of different feature extraction methods for the analysis of uterine magnetomyography signals to predict term labor

Babu¹,

Kumar²

2018

IJET

View full text Add to dashboard Cite

The prediction of term labor by analyzing the uterine magnetomyographic signals attempted in this research. The existing works did not focus on the classification of the signals. Publicly available MIT-BIH database records were divided into term-labor and term-nonlabor groups. This research presents two methods for feature extraction, discrete wavelet transform and wavelet packet transform. Energy, standard deviation, variance, entropy and waveform length of transform coefficients used in the first method. The normalized logarithmic energy of wavelet coefficients from each packet of the total wavelet packet tree used as the feature space for the second method. The labor assessment done through the classification of the features by using five different classifiers for different mother wavelet families. Discrete wavelet transform features extracted using coif5 wavelet with random subspace classification gives the accuracy, precision and FPrates of 93.9286%, 94.2014% and 5.7986% respectively. Using sym8 wavelet for wavelet packet transform features classified with SVM classifier performed well with 95.8763% accuracy, 95.9719% precision and 4.0281% FPrate. The results obtained from the research will be helpful in term labor assessment and understanding the parturition process.

show abstract

“…The process is repeated until the resulting mean satisfies the two aforementioned properties of IMF. More details on the use of EMD can be found in (9). The HHT methodology is described as follows: Let X(t) be the MMG signal, IMF i (t) be the i th IMF function, and R(t) be the residue of the signal.…”

Section: Empirical Mode Decomposition (Emd) Methodsmentioning

confidence: 99%

“…The sifting process is terminated if the difference between the successive IMFs is less than a prefixed tolerance defined as follows: (2) SD can have a value between 0.2 and 0.3 according to (9). In all of our calculations, we set SD to 0.2 for a more sensitive difference between siftings.…”

Section: Empirical Mode Decomposition (Emd) Methodsmentioning

confidence: 99%

Hilbert–Huang transform in detecting and analyzing the uterine contraction activities

Aydın

Demirer

Bayrak

2015

J Turkish German Gynecol Assoc

View full text Add to dashboard Cite

Results:After comparing the IUPC and other mother-perceived contraction (STIM) datasets with HHT results, we were able to visually detect contraction locations in the HHT-processed uterine signals. For verification and validation purposes, when we further analyzed the delay time between two signals, the mechanical activity (i.e., IUPC) following the electrical activity (i.e., magnetic signal) was observed. In conclusion, our experimentations using the method introduced here revealed that there is a 75% correlation between the results obtained by HHT and IUPC data. Conclusion:This study compared uterine contractions and changes in the intrauterine pressure with results obtained by HHT. In addition, using IUPC data as a validation guide, we showed that the HHT approach can be used for noise removal. There is a need for time-saving and non-subjective automatic contraction detection in the field of prenatal examination. (J Turk Ger Gynecol Assoc 2015; 16: 195-202)

show abstract

Classification of uterine EMG signals by using Normalized Wavelet Packet Energy

Cited by 10 publications

References 10 publications

Low-complexity intrauterine pressure estimation using the Teager energy operator on electrohysterographic recordings

Low-complexity intrauterine pressure estimation using the Teager energy operator on electrohysterographic recordings

Comparison of different feature extraction methods for the analysis of uterine magnetomyography signals to predict term labor

Hilbert–Huang transform in detecting and analyzing the uterine contraction activities

Contact Info

Product

Resources

About