are detected for the time-series which exceeds the minimum peak height
which represents the strong Uterine Contractions. The FIG 4 shows an example in which the level
crossing rate is determined for the uterine EMG time series data and the
contractions are estimated as 3 contractions for 10 minutes which are denoted
in circles. Hence the 3 contractions represents the first stage of early labor contractions.
Another vital parameter is monitoring
the Fetal heart beat ,which determines the well-being of the Fetus. The
physician uses this procedure to assess the rhythm and rate of the Fetus’
heartbeat. Under normal circumstances, a Fetus’ heart rate ranges anywhere from
120 beats to 160 beats per minute. This rate can change depending on the
environment the Fetus experiences in the uterus. Obstetricians monitor Fetal
heartbeat practically in every pregnancy,
for observing the changes that could be connected with pregnancy or Labor-related
problems. Furthermore for Preterm Labor medications, Fetal heartbeat monitoring
allows the physician to monitor the effects of the medication on the Fetus.
Fetal heartbeat monitoring is often used for high-risk pregnancies.
0030 If the
Fetus’ heart rate is abnormal, it could mean the Fetus is not getting
sufficient amounts of oxygen or there are other problems. Monitoring the
heartbeat allows the physician to ensure everything is fine with the Fetus
during the pregnancy and through labor. Fetal Heart Rate can offer important clues about
the developing baby’s health because it’s proof that the pregnancy is
going well. FHR decreases slightly during gestation.
0031 A baby’s
heart rate will normally accelerate during a contraction, then slows as the
mother and baby recover. If the baby’s heart rate fails to recover adequately,
medical attention needs to be provided. Normal Fetal Heart Rate ranges from are
120( bpm) to 160 (bpm). Hence the Safety
Margin is: 100(bpm)
< FHR(bpm) < 160(bpm). If the Fetal heart rate deviates from the safety margin then the fetal is prone to high risk of preterm labor, hence the patient needs to be taken immediately to the hospital. 0032 Fetal ECG signal provides valuable information about the fetal heart growth , fetal maturity and health condition is obtained by FECG electrodes on the surface of the abdomen as represented in FIG 1. Maternal electrocardiogram (MECG) is a dominant noise mixed with FECG in abdominal electrocardiogram (AECG) signal. Since the amplitude, strength and magnitude and of MECG is greater than that of the FECG it is often superimposed with MECG and other noises . 0033 Moreover, the baseline drift, power-line interference, gestational age, position of the electrodes, skin impedance and random electrical noise caused by human movement, baseline drift due to poor contact of measurement electrode are some external noises that can affect the Fetal ECG separation . Essential problem is the e?cient suppression of maternal electrocardiogram, since its amplitude many times exceeds the level of the useful signal. As the FECG signals are non-stationary and non-linear in nature, the noise suppression has to be done without losing main information from FECG signals. Suppression of maternal peaks for proper Fetal ECG signal extraction is required without losing main information. 0034 The process of the FECG extraction is done as in FIG 5 .The baseline drift is a low-frequency activity in the AECG signal which may affect the signal analysis. It is mainly due to the respiration, artefacts and electrical noise. It is eliminated by subtracting the mean value of the signal from the signal itself. A notch filter with 50 Hz frequency is applied to attenuate the coupling with the mains for Removal of Powerline Interference. A Butterworth Bandpass Filter of 4-100Hz filter is applied to attenuate the low and high frequency noises. 0035 A Discrete wavelet transform (DWT) is used to decompose the recorded AECG signal which gives adaptive size window with maximum time-frequency resolution. DWT uses short windows at high frequency and long windows at low frequencies. The signal is decomposed by using Daubechie wavelet which is analogous in shape to heart beat. The AECG signal is decomposed by applying a high and low pass filter followed by down sampling operation. The data is down sampled in order to reduce the data rate. 0036 The output of this down sampled data provides the detail as well as approximate values. The approximate coefficients analyse the LF Components and the Detail coefficients analyse the HF Components. The approximate values of the decomposed signal is used to detect the maternal QRS complex. 0037 Once the maternal QRS complex is been detected the signal is divided into frames which are individually analyzed in order to know the exact positions of the QRS complexes. 0038 The positions are then used to generate the maternal template. The generated template is correlated with the maternal signal and the one with the highest correlation is used. Before subtraction of the template with the signal proper aligning of the template to each of the maternal QRS complex is done. For proper alignment the template is scaled with respect to amplitude and width. The subtraction of the best correlating template allows the suppression of the maternal QRS complexes. The output obtained after the maternal ECG subtraction is the fetal ECG signal. 0039The peak detection algorithm is then applied to detect fetal R peak in order to calculate the RR interval. The detected peaks are marked in circles in the FIG 6 . This RR interval is used to calculate the fetal heart rate (FHR). 0040 The IoT Platform 'ThingSpeak' collects the EMG and FHR data via MATLAB by a wireless link (FIG 2) and sends it to the cloud for analysis by providing