A Novel Approach of Fetal ECG Extraction Using Adaptive Filtering

Transcription

1 International Journal of Information Science and Intelligent System, 3(2): 55-70, 2014 A Novel Approach of Fetal ECG Extraction Using Adaptive Filtering P.Rajesh 1, K.Umamaheswari 1, V.Naveen Kumar 2 1 V.R.Siddhartha Engineeringcation College, Vijayawaday, India 2 VIT University, Vellore, India Abstract Received: 30 January 2014; Accepted: 10 March 2014 Fetal electrocardiogram (FECG) extraction has a vital role in medical diagnosis during pregnancy. In this paper, We Proposed a method for removal of background noise and artifacts from FECG signals using adaptive filters has been proposed. The proposed method uses adaptive noise cancellation and digital filters for FECG extraction. Proposed FECG extraction algorithm has been implemented in MATLAB using simulink models. Simulation results show that fetal heart rate can be extracted by counting the peaks of R-R interval from the extracted FECG noise free signal, noise cancellation algorithms are also implemented using simulink in MATLAB. Keywords: ECG, Maternal heart beat, Fetal heart beat, Mean square error, LMS algorithm. Martin Science Publishing. All Rights Reserved. 1. Introduction 1.1 Need for Monitoring Fetal Heart Beat Fetal heart rate monitoring is one of the possible solution to test fetal well being and to diagnose possible abnormalities. Fetal monitoring during pregnancy stage enables the physician to diagnose and recognize the pathologic condition especially asphyxia. The electrocardiogram is the simplest noninvasive diagnostic method for various heart diseases. Fetal ECG signal reflects the electrical activity of the fetal heart and provides valuable information of its physiological state. Non invasive FECG has been used to obtain valuable clinical information about the fetal condition during pregnancy by using skin electrodes placed on the maternal abdomen. The fundamental purpose of this paper is to monitor separate fetal heart rate and maternal heart rate individually is to separate from ECG signal by using Least Mean Square (LMS) algorithm based upon the adaptive filters in MATLAB environment. The additional milestone of

2 56 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) the paper is the investigation and implementation of fetal as well as maternal heart rate monitoring from ECG signal by using adaptive filters in MATLAB environment. The measured fetal electrocardiogram signal from the abdomen of the mother is usually dominated by the maternal heartbeat signal that propagates from the chest cavity to the abdomen. This propagation path can be described as a linear FIR filter with 10 randomized coefficients. In addition, a small amount of uncorrelated Gaussian noise is added to simulate any broadband noise sources within the measurement[1-3]. The maternal electrocardiogram signal is obtained from the chest of the mother. The goal of the adaptive noise canceller in this task is to adaptively remove the maternal heartbeat signal from the fetal electrocardiogram signal. The noise canceller needs a reference signal which is generated from the maternal electrocardiogram to perform this task. Just like the fetal electrocardiogram signal, the maternal electrocardiogram signal will also contain some additive broadband noise. 1.2 General Overview An electrocardiogram is also called an EKG or ECG is a simple, painless test that records the heart's electrical activity. To understand this test, we need to understand how the heart works. With each heartbeat, an electrical signal spreads from the top of the heart to the bottom. As it travels, the signal causes the heart to contract and pump blood. The process repeats with each new heartbeat. The heart's electrical signals set the rhythm of the heartbeat[4-5]. (1) ECG Shows. How fast your heart is beating. Whether the rhythm of your heartbeat is steady or irregular. The strength of electrical signals as they pass through each part of your heart. Doctors use EKGs to detect and study many heart problems. Such as heart attacks, arrhythmias (ah-rith- me-ahs), and heart failure. The test results also can suggest other disorders that affect heart function (2) ECG signal with QRS complex. The figure 1 shows one period of uncorrupted ECG signal with QRS complex. The ECG signal contains the information within the frequency range of around 50 Hz so it is called QRS complex. The QRS complex is a waveform which is most important in all ECG s waveforms and it comes into view in usual and unusual signals in an ECG. An adaptive filter is a digital filter whose characteristics change in an unknown environment input signal. In the advanced era of cellular phone, digital television, wireless communication and digital multimedia commercial services, advanced adaptive signal processing may give the better solution for the technical problem ECG signal describes the electrical activity of the heart. An ECG signal during a cardiac cycle consists of a P wave, QRS complex and T wave. The detection of R-peaks i.e., the peaks of the QRS complex in an abdominal electrocardiogram signal provides information on the heart rate and hence it is an important tool for the physician to identify abnormalities in the heart activities[6-8].

3 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) 57 Figure 1. ECG signal with QRS complex Adaptive filters are used to monitor fetal heart rate and eliminate maternal heart rate from fetal heart rate and they are proposed to obtain the impulse response of the normal QRS complex. In the figure above, an uncorrupted ECG signal shows an original signal graph for ECG signal which demonstrate the diagnosis of heart activities for heart patient. Consequently, it is analysis that how to separate a fetal and maternal heart waves of ECG signal which is a problem for biomedical signal measurement. (3) Heart Mechanism and Purpose of ECG Diagnosis. The heart is a muscular organ, it pump the blood throughout the body and collecting blood circulating back from the body. Electrical impulses are the main source of generation of regular normal heartbeat. The heart muscle must be activated electrically before the beginning of its mechanical function. When the electrical abnormalities of the heart occur then the heart cannot pump blood properly and supply enough to the body and brain. This can cause unconsciousness within second and death within minutes. An ECG recording is important for clinical diagnosis and treatment; it is a graphical recording of electrical impulses generated by heart. The ECG is needed to be done when chest pain occurred such as heart attack, shortness of breath, faster heartbeat, irregular heartbeat, high blood pressure, and high cholesterol, check the heart s electrical activity. 1.3 Objectives of Paper The fundamental aim of this paper is to analyze the fetal heart rate starting with a simple approach from fundamentals of digital signal processing (DSP), digital filters and then adaptive filters with LMS implementations. The power line interference, some other signal frequency tone signals and harmonics impact the ECG signal, which can be described by MATLAB software simulation. The main objective is to separate fetal heart rate from maternal heart rate using LMS adaptive algorithm based upon FIR filter. The goal is to estimate the baby's heartbeat and calculate the period of the signal based on our estimation. An adaptive noise canceller based fetal electrocardiogram extraction method is proposed and implemented. From the simulation results we can conclude that FECG signals can be extracted from the abdominal electrocardiogram signals using LMS algorithm.

4 58 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) 1.4 Introduction to Fetal External fetal heart monitoring is performed by attaching external transducers to the mother's abdomen with elastic straps (see diagram). The transducers use Doppler ultrasound to detect fetal heart movements, and the information is sent to the fetal heart monitor which calculates and records the fetal heart rate on a continuous strip of paper. More modern fetal heart monitors have incorporated microprocessors and mathematical procedures to improve the fetal heart rate signal and the accuracy of the recording. During fetal monitoring, a nurse will evaluate the strip for continuity and adequacy for interpretation, identify the baseline fetal heart rate and presence of variability, determine whether there are accelerations or decelerations from the baseline, identify patterns of uterine contraction, and correlate accelerations and decelerations with the uterine contractions. This will allow the nurse to determine whether the fetal heart rate recording is reassuring, no reassuring, or ominous. A plan can then be developed for the situation to help deliver the baby in the best possible manner. Figure 2. Fetal heart The normal fetal heart rate range is between 120 and 160 beats per minute. A constant variation from the baseline (variability) reflects a healthy nervous system, chemoreceptors, baroreceptors and cardiac responsiveness. Beat-to-beat, or short-term, variability is an important indicator of fetal trouble. Loss of this variability may indicate an ominous condition, but it can also indicate healthy rest-activity in the fetus or depression of the central nervous system due to medication. An increase in variability may indicate acute hypoxia or mechanical compression of the umbilical cord.

5 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) 59 Figure 3. Extracting Fetal ECG signal 1.5 Classification of Fetal Heart Rate Category I Normal Category II Indeterminate Category III Abnormal Figure 4. Cardiac electric field vectors of mother and fetus and Placement of leads Fetal heart rate pattern to be the most common during labor occurring 77.9% of the time. The category II pattern occurred 22% of the time during labor, and the category III pattern occurred rarely, only 0.004% of the time during labor. There has been some concern that the non specific nature and large number of fetal heart rate patterns within category II diminishes its usefulness as an indicator of fetal condition.

6 60 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) Figure 5. Cancelling the Maternal ECG from Fetal ECG (1) Category I: Normal. The fetal heart rate tracing shows ALL of the following: Baseline FHR BPM, moderate FHR variability, accelerations may be present or absent, no late or variable decelerations, may have early decelerations. Strongly predictive of normal acid-base status at the time of Fetal Heart Rate Monitoring. (2) Category II: Indeterminate. The fetal heart rate tracing shows any of the following: Tachycardia, bradycardia without absent variability, minimal variability, absent variability without recurrent decelerations, marked variability, absence of accelerations after stimulation, recurrent variable decelerations with minimal or moderate variability, prolonged deceleration more than 2minutes but less than 10 minutes, recurrent late decelerations with moderate variability, variable decelerations with other characteristics such as slow return to baseline, and "overshoot". Not predictive of abnormal fetal acid-base status, but requires continued surveillance and reevaluation. (3) Category III: Abnormal. The fetal heart rate tracing shows either of the following: Sinusoidal pattern or absent variability with recurrent late decelerations, recurrent variable decelerations, or bradycardia. Predictive of abnormal fetal-acid base status at the time of observation. Depending on the clinical situation, efforts to expeditiously resolve the underlying cause of the abnormal fetal heart rate pattern shows. 2. Adaptive Filters 2.1 Introduction of Adaptive Filter The adaptive filter can be defined as, a filter which self adjust its transfer function according to an optimizing algorithm and object can be achieved by the modification of its characteristics. Adaptive signal processing has been introduced. Adaptive filters are extensively used in the variety of applications and they had been firstly proposed by Kelly of Bell Telephone Laboratories around 1965, most of the applications are in telecommunications for the cancellation of noise and echo in the transmission channel and also used in digital controller for active noise control.

7 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) 61 An adaptive filter is a digital filter whose characteristics change in an unknown environment input signal. In the advanced era of cellular phone, digital television, wireless communication and digital multimedia commercial services, advanced adaptive signal processing may give the better solution for the technical problem. The adaptive filter is also used in the field of biomedical, sonar, radar and image signal processing, telecommunication for noise cancellation etc. 2.2 Explanation of Adaptive Filter Adaptive signal processing is more famous due to the property of its digital techniques which is characterized by flexibility and accuracy in the field of communication and control. In the advancement of digital signal processing s application, adaptive filter become more popular in different devices such as medical monitoring equipments, mobile phones and other communication devices. Most of the adaptive filters are digital due to the complexity of optimizing algorithm, which perform digital signal processing and adapt their performance based on the input signal. When the fixed specification of any application is unknown or cannot be satisfied by time invariant filters then an adaptive filter can manipulate this problem. 2.3 Adaptive Filters and Digital Signal Processing The design of digital filter requires the approved specification with fixed coefficients. If this specification is time varying or not accessible then this problem can be manipulated by digital filter with adaptive coefficients, which is known as adaptive filter. Digital signal processing has well-known repute in the modern times, which is used for the number of different applications in different fields of technologies; biomedical engineering is one of them where the unwanted signal from original ECG can be removed by digital filters. In the modern era of communication system, adaptive signal processing is one of the most important technologies used for numbers of different algorithms. Generally the main problem in the biomedical systems is noise cancellation, which is considered as adaptive noise cancellation in hitech and mature technology found in the in biomedical systems, telecommunications systems, industrial control, aerospace, and music etc. Adaptive filtering is the technique which is used to set the parameters.it is one of several tools which are made available by the digital signal processing (DSP). Usually filters are essential part of any system which performs any kind of manipulation or signal processing to eliminate any unwanted portion or noise induced in the signal. So the digital filters have an appearance in the form of adaptive filtering, which provides better performance by adjusting to changes in the noise factors. 2.4 Adaptive Filtering Adaptive filtering is properly used due to its esteemed knowledge of signal makeup,signal analysis is related to the adaptive processing. Literally, the word adaptive means to adjust with other environment (system) by having the same response as the system itself to some phenomenon which is taking place in its surroundings or technically the system which tries to adjust its parameters, depending upon the other system s behavior and its surrounding. The

8 62 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) systems which carries out its functionality after under going the process of adaptation is called filter. The term filter means to take the unnecessary particles (frequency component) from its input signal and process them to generate required output under certain specific rules There are various principal options for the implementation of adaptive signal processing, e.g. the LMS algorithm. The adaptive filters are much famous due to their economical quality, fast processing, their short period of time adaptation and residual error is small after adaptation. Adaptive filtering is the most important technique which is used in number of biomedical applications. The basic principal of adaptive filter can be understood by understanding the adaptive filtering which is showed in the figure 4. The error signal e(n) can be generated by the output of the programmable, variable-coefficient digital filter subtracted from a reference signal y(n). Figure 6. Principle of an Adaptive Filter The adaptive filter can be classified in the following areas The optimization criterion The algorithm for coefficient updating The programmable filter structure The type of signal processed 2.5 The General Structure of Adaptive Filters There are number of different structures for the implementation of adaptive filter the type for the structure chosen is based on the requirement of the application and computational complexity of the process. The basic structure of the adaptive filter is shown in figure 7, here the input signal is filtered for the required output and then passed through further processing. The filter s output is observed by determines its quality for particular application. After measuring the quality is examined by a circuit whether it is need to improve the quality of the output signal. This processing loop continues until the filter s parameters are adjusted properly, so the filter s output quality should be as good as possible. The choice of filter structure and adaptation algorithm is important for the design of adaptive filter,the structure can be non-recursive or recursive.

9 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) 63 Figure 7. The general structure of an adaptive filter 2.6 Performance, Stability and Robustness of the Adaptive Algorithm The performance of the adaptive algorithm is important for all systems, it is also essential how adaptive system is functioning. For any application the adaptive algorithm provides competent performance evaluations for the structures of various filters and adaptive algorithm. The LMS algorithm is the most popular adaptive algorithm and its performance is dependent on the filter order, signal condition and convergence parameter (μ).the adaptive system is used for the solution for any practical problem the question appears about the stability of adaptive algorithm whether or not the algorithm is stable. In general the adaptive filters based on FIR structure are naturally stable. To satisfy the robustness of the adaptive algorithm the value of step size μ needs to be small. Robustness is an important criterion which is difficult to measure in a quantitative approach. The satisfaction for the robustness of the adaptive algorithm can be gained by the removal of external noise. 3. LMS Algorithm LMS algorithm was developed by Widrow and Hoff in It is widely used in various applications of adaptive filtering. The main features that attracted the use of the LMS algorithm are low computational complexity, proof of convergence in stationary environments and stable behavior when implemented with finite precision arithmetic. Figure 8. LMS algorithm

10 64 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) A path that changes the signal x is called h. Transfer function of this filter is not known in the beginning. The task of LMS algorithm is to estimate the transfer function of the filter.the result of the signal distortion is calculated by convolution and is denoted by d. In this case d is the echo and h is the transfer function of the hybrid. The adaptive algorithm tries to create a filter w. The transfer function in turn is used for calculating an estimate of the echo. The echo estimate is denoted by y. The signals are added so that the output signal from the algorithm is where e denotes the error signal. e=d-y (1) The error signal and the input signal x are used for the estimation of the filter coefficient vector w. One of the main problems associated with choosing filter weight is that the path h is not stationary. Therefore, the filter weights must be updated frequently so that the adjustment to the variations can be performed. The filter is a FIR filter with the form W= W 0 (n)+w 1 (n)z W N-1 (n)z -(N-1) (2) The LMS algorithm is a type of adaptive filter known as stochastic gradient based algorithm as it utilizes the gradient vector of the filter tap weights to converge on the optimal Weiner solution. With each iteration of the LMS algorithm, the filter tap weights of the adaptive filter are updated according to the following formula W(n+1)=w(n)+2µe(n)x(n) (3) Here x(n) is the input vector of time delayed input values, x(n) = [x(n) x(n-1) x(n-2)..x(n- N+1) T.The vector w(n) = [w0(n) w1(n) w2(n).. wn-1(n)] T represents the coefficients of the adaptive FIR filter tap weight vector at time n. The parameter µ is known as the step size parameter and is a small positive constant. This step size parameter controls the influence of the updating factor. Selection of a suitable value for µ is imperative to the performance of the LMS algorithm, if the value is too small the time the adaptive filter takes to converge on the optimal solution will be too long; if µ is too large the adaptive filter becomes unstable and its output diverges. 3.1 Implementation of the LMS algorithm Each iteration of the LMS algorithm requires 3 distinct steps in this order: (1) The output of the FIR filter, y(n) is calculated using equation (4)

11 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) 65 (2) The value of the error estimation is calculated using equation the following equation. e(n)=d(n)-y(n) (5) (3) The tap weights of the FIR vector are updated in preparation for the next iteration, by equation (6). (6) The main reason for the LMS algorithms popularity in adaptive filtering is its computational simplicity, making it easier to implement than all other commonly used adaptive algorithms. For each iteration the LMS algorithm requires 2N additions and 2N+1 multiplications (N for calculating the output, y(n), one for 2µe(n) and an additional N for the scalar by vector multiplication). 4. Simulations Results 4.1 Main Objective The goal was to implement and analyze removal of maternal signal by using adaptive techniques from original ECG signal. Removal of maternal signal from ECG signal and how to apply the adaptive LMS algorithm for removing of maternal signal and its harmonic from signals that has been corrupted and the original information contained by unwanted interferences was the main purpose of the paper. The additional milestone of the paper was the investigation and implementation for the removal of fetal signal from original ECG signal in MATLAB environment. Number of algorithms can be implemented on the ECG signal to remove different type of unwanted signals. In this thesis, two different types for removal of unknown signals have been implemented. Removal of maternal signal by Adaptive LMS Algorithm from ECG Signal. Removal of fetal signal by Adaptive LMS algorithm from ECG signal. While the thesis problem and purpose was not as simple to solve and implement as it might, the possible benefits were enormous. The challenges for the project were the study of most sensitive biomedical monitoring equipment such as Electrocardiogram (ECG), electroencephalogram (EEG) and electromyography (EMG). The thesis is basically research oriented; therefore sufficient reference materials were not available easily. The results, analysis, implementation and conclusion of the thesis are totally depends upon better understanding of ECG signal s simulation and calculation. It was totally out of domain so a lot of journals, research papers, internet, university library database and books are read to analyze and understand it in a better way. 4.2 Designing by DSP Technique In digital signal processing (DSP) it mainly encounters with discrete time signals which are functions of integers. The signals are also represented by mathematical functions like sinusoidal

12 66 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) function or linear difference equations. In this thesis it deals with two signals i.e. input ECG signal (50 Hz) and noise signal (50 Hz) from power line source. In the case of removal of maternal signal by adaptive LMS algorithm, this was implemented because it is easy to implement and exhibits stability in performance. The ECG signal of 50 Hz is taken and mixed with maternal signal of 50 Hz if nothing is known about noise signal then it cannot be subtracted from ECG signal. But in this case the maternal signal of 50 Hz is eliminated by using adaptive LMS algorithm which estimates the noise related to input noise and subtracts it from input signal to generate the estimated signal s output. The LMS algorithm changes the filter coefficients and working system subtracts it from the actual system s outputs. The frequencies among 47Hz and 53Hz are more critical for ECG signal of 50Hz. These frequencies can be noise for the ECG signal and due to it the quality of ECG recording can be get down. So nothing seems to be best to use adaptive filter which overcome the information loss in the ECG recording. For a good DSP system it must fulfil many requirements, i.e. it must respond to all input frequencies, should be stable, more reliable for the manipulation of signals. The most important objective for the choice of adaptive filters was its ability to adjust the filter s coefficients and the main designating factor was how to define rules or algorithms that upgrade coefficients. The adaptive filters judge the performance from signal and it also tract the signal, develop the solution and determine how filter coefficients should be upgraded. 4.3 MATLAB Software Implementation MATLAB is the most useful environment for engineering and technology implementations software package. It is used for the specific purpose in different fields of technology based on electronic programming, scientific & engineering graphical illustration, accurate numerical calculations and algorithms development etc. The algorithm has been designed and implemented the least mean square (LMS) adaptive filter based upon the FIR filtering using MATLAB environment. The FIR adaptive filter has then implemented there and LMS algorithm has been developed to remove the maternal signal from original ECG signal. The simulation results with graphs for ECG signal were then plotted to compare the filtered output by putting different values of LMS step size and filter tap to visually measure the simulation program performance. Finally the algorithm implementation and verification has been presented which increases the reason for the selection of LMS algorithm based on FIR filters in MATLAB environment. The effect of μ on convergence rate and stability for the LMS adaptive filter has been examined to achieve the desire results. The simulation of harmonics of high frequency noise has also been generated to find out another filtration method in MATLAB environment. The general notch rejection filter and windowed sinc low pass filter has been developed in MATLAB for the implementation and removal of maternal and fetal signals to achieve the required output. 4.4 Verification for Refinement of Signal by LMS

13 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) 67 The verification for refinement of signal by LSM can be done with the removal of maternal signal from ECG signal The ECG signal has been taken and LMS adaptive filter algorithm has been developed. The original ECG signal is displayed in MATLAB environment as combination of maternal signal and fetal signal which is displayed as mixed signal. The adaptive filter has been implemented by using LMS algorithm, FIR filter has been designed. The original ECG Signal (mixed signal). Error signal and Adaptive LMS filtered output signal have been displayed. The output is nearly same as the ECG input signal. The measured fetal electrocardiogram signal from the abdomen of the mother is usually dominated by the maternal heartbeat signal that propagates from the chest cavity to the abdomen. This propagation path can be described as a linear FIR filter with 10 randomized coefficients. In addition, a small amount of uncorrelated Gaussian noise is added to simulate any broadband noise sources within the measurement. The maternal electrocardiogram signal is obtained from the chest of the mother. The goal of the adaptive noise canceller in this task is to adaptively remove the maternal heartbeat signal from the fetal electrocardiogram signal. The noise canceller needs a reference signal generated from the maternal electrocardiogram to perform this task. Just like the fetal electrocardiogram signal, the maternal electrocardiogram signal will contain some additive broadband noise. Figure 9. Mixed Signals (Fetal and Maternal)

14 68 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) Figure 10. Unwanted ECG Signal (Maternal) Figure 11. Desired ECG Signal (Fetal) 4.5 Algorithm Implementation and Verification To verify the performance of Biomedical signals play a critical role in the diagnosis of patients. ECG is a medical monitoring device which is used for the diagnosis of heart patient. As maternal signal is major problem in ECG signal,an algorithm for the LMS adaptive filter was suggested, as the ECG signal can be variously mixed with maternal signal. The LMS adaptive filter is widely used to filter the ECG signal as its convergence causes good performance.

15 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) 69 The LMS adaptive algorithm, ECG signal has been selected and evaluated the performance of the proposed filtering technique. The MATLAB environment was used for the simulation of ECG signal. The code contents of the source file used in this thesis were collected from various sources. For the completion of code, the collected contents were modified according to the application s requirement and placed in the required sequence. To design the FIR filter, these source files were used to configure the DSP technique. After designing of FIR filter the LMS algorithm has been executed and verified. Two basic processes are involved when the LMS algorithm is applied, a filter process involving the computation of the output of FIR filter produced by a vector of tap inputs and an estimation error signal calculated by comparing this output to a desired response. LMS algorithm is extensively used in different application of adaptive filtering due to its computational simplicity and FIR filter is also popular because of its simplicity and inherent stability. An important parameter is the step size μ, it affects the convergence rate and stability of the LMS adaptive filter. Moreover another method has been implemented for the removing of maternal signal from original ECG signal. The original ECG signal has been taken and mixed with the hum and then both the ECG and Hum signals are added with high, frequency noise of 375 Hz. After passing the ECG signal with both noises through notch filter, the ECG signal with high frequency noise remains. Then this remaining signal with high frequency noise has been passed through the windowed sinc low pass filter to get rid of high frequency noise. By use this method the original ECG signal can be retrieved. By investigating this method, it has been concluded that the overall result of the technique is achieved. The main goal for the removal of maternal signal to achieve extracting fetal signal. 5. Conclusion and Future scope In brief, the accuracy of output depends on how many variations of signals are used as input and the target in the network. Furthermore, in this approach, learning rate and momentum is also an important factor to affect the desired FECG signal. FECG signal contains the valuable information that could assist clinicians in making more appropriate and timely decisions. The technique, adaptive filtering approach has been used to extract the FECG signal from the abdominal ECG that is the acceptable output. An adaptive filter is used in applications that require different filter characteristics in response to variable signal conditions. The speed of adaptation and accuracy of the noise cancellation after adaptation are important measures of performance for noise cancellation algorithm. The goal of the adaptive filter is to match the filter coefficients to the noise so that the adaptive filter can subtract the noise out from signal. The digital signal processing techniques with MATLAB package for medical monitoring equipments (ECG) provides the real concepts along with the theoretical backgrounds of extracting the fetal heart beat signal from original ECG signal. This enhances the understanding and self confidence in the field of electronics and biomedical engineering. In this paper, the

16 70 P.Rajesh, et al. / International Journal of Information Science and Intelligent System (2014) adaptive signal processing filtering technique based on LMS algorithm could be implemented for more signals and also improvement of the thesis can be further implemented with different algorithms such as NLMS and RLS to achieve the desired results. It could also be used to investigate and implement the extraction of maternal heart beat from ECG signal. Acknowledgments The Authors would like to express heartfelt gratitude to Prof.Ganapati Panda,Dean, School of Electrical Sciences, Indian Institute of Technology, Bhubaneswar, for supplying real time applications areas of adaptive filters. The Authors are indebted profoundly grateful to Dr.G.N.Swamy, Head, Department of Electronics Instrumentation Engineering,for his kind and whole hearted support and valuable guidance throughout the paper. The Authors extend thanks to Dr.G.Sambasivarao, principal,v.r Siddhartha Engineering College, Vijayawada, A.P. The Authors express thanks and acknowledges the support given by department of Electronics and Instrumentation Engineering, V.R Siddhartha Engineering College, Vijayawada. References [1] Freeman, R. K. Garite, T.J.,Nageotte,M. P.,and Miller,L.A., Fetal heart rate monitoring, LWW,2012. [2] Kumar, A., Dewan, L., Singh, M., and Kurukshetra, H., Realtime monitoring system for ECG signal using virtual instrumentation, IEEE Transactions on Biology and Biomedicine, vol. 3, pp , [3] Ferrara,E.R., and Windrow,B., Fetal electrocardiogram enhancement by time-sequenced adaptive filtering, IEEE Trans. Biomed. Eng. 29, pp , [4] Peters, M., Crowe, J., Pieri, J. F., Quartero H., Hayes-Gill, B., James, D., Stinstra, J., and Shakespeare, S., Monitoring the Fetal heart noninvasively: a review of methods, Journal of perinatal medicine, vol. 29, no. 5, pp , [5] Ananthanag, K., and Sahambi, L., Investigation of blind source separation methods for extraction of fetal ECG, In Canadian Conference on Electrical and Computer Engineering. May [6] Haykin, S., Adaptive Filter Theory, 3rd Edition, Prentice Hall [7] Widrow, B., Adaptive Noise Cancelling: Principles and Applications, Proc. IEEE, vol. 63, pp , Dec [8] John, R. G. Jr., Adaptive Noise Canceling Applied to Sinusoidal Interferences,IEEE Trans. ASSP, Vol. ASSP-25, no. 6, pp , 1977