The document describes a method for extracting fetal electrocardiogram (FECG) signals from abdominal electrocardiogram (AECG) recordings using a fractional order Butterworth filter and fast independent component analysis. The method involves preprocessing the AECG signals with a fractional Butterworth filter to remove noise. A reference direct FECG signal is selected using cross-correlation. Wavelet transform and fast ICA are then used to separate the FECG signal from the AECG recordings. Performance is evaluated by analyzing extracted FECG features and comparing fetal heart rate to samples in a database. The proposed method achieves accurate FECG extraction and fetal heart rate determination.
Design and Implementation of wireless heart monitor for expectant mothers in ...IJMER
A low cost Maternal & Fetal Heart Rate (MFHR) monitor is introduced in an attempt to reduce or eliminate hypoxic episodes well before the development of fetal asphyxia. MFHR monitoring is sensitive and detects fetal hypoxia early in the evolution to acidosis. The abdominal electrocardiogram (AECG) is the recording of the cardiac activity of both the mother and the fetus. The main challenge is to extract the fetal ECG, which is strongly distorted by maternal component of dominating energy and artifacts like baseline wander and power-line interference which were effectively preprocessed and filtered by using a Kaiser FIR filter having a SNR ratio of 13.68 , filter order of 298 and a Notch filter (fc = 50 Hz) with a bandwidth of 2 Hz respectively. Our endeavor has been to design this MFHR monitoring device using a smartphone. This system continuously monitors the patient’s AECG data especially in the 3rd trimester. For the ongoing research work the maternal AECG signals were taken from the Physionet non-invasive ECG database. The AECG file is transferred from the PC to a microcontroller ATMEGA32A which is interfaced to a Bluetooth module. Data is then transferred wirelessly via Bluetooth to the phone. The smartphone contains an application that displays data received from the Bluetooth module interfaced with a plotter application. This Bluetooth Plotter application plots the ECG waveforms of the content on the phone. Various inferences were effectively made based upon the ECG graphs produced on the phone, thus giving the doctors an alert about the patient’s and Fetal ECG information. Further research will examine the real time patient’s data from the hospital assigned to us.
Amyotrophic lateral sclerosis Disease- Muscle loose their functionality. Regenerative medicine help to diagnose via cellular therapeutic level. (MSC's used to cure)
ANESTHETIC CONSIDERATIONS FOR STEREOTACTIC ELECTROENCEPHALOGRAPHY (SEEG) IMP...Anurag Tewari MD
The refractory seizures have significant impact on the quality of life and increase long term neurologic and non-neurologic complications. Implantation of Stereotactic Electroencephalography (SEEG) leads is one of the newer surgical techniques intended to localize seizure foci with higher accuracy than the conventional methods. Most of the commonly utilized anesthetic agents depress EEG waveforms affecting intra operative monitoring during these surgeries. Hence, the anesthetic goals include a stable induction and maintenance with agents which have minimal effect on EEG. This article discusses the peri-operative considerations of multiple anti-epileptic medications, recent advances in anesthetic management, and important post-operative concerns.
Keywords: Anesthesia, epilepsy surgery, intra-operative EEG, intra operative monitoring, refractory seizures, SEEG, seizure foci, stereotactic electroencephalography
Design and Implementation of wireless heart monitor for expectant mothers in ...IJMER
A low cost Maternal & Fetal Heart Rate (MFHR) monitor is introduced in an attempt to reduce or eliminate hypoxic episodes well before the development of fetal asphyxia. MFHR monitoring is sensitive and detects fetal hypoxia early in the evolution to acidosis. The abdominal electrocardiogram (AECG) is the recording of the cardiac activity of both the mother and the fetus. The main challenge is to extract the fetal ECG, which is strongly distorted by maternal component of dominating energy and artifacts like baseline wander and power-line interference which were effectively preprocessed and filtered by using a Kaiser FIR filter having a SNR ratio of 13.68 , filter order of 298 and a Notch filter (fc = 50 Hz) with a bandwidth of 2 Hz respectively. Our endeavor has been to design this MFHR monitoring device using a smartphone. This system continuously monitors the patient’s AECG data especially in the 3rd trimester. For the ongoing research work the maternal AECG signals were taken from the Physionet non-invasive ECG database. The AECG file is transferred from the PC to a microcontroller ATMEGA32A which is interfaced to a Bluetooth module. Data is then transferred wirelessly via Bluetooth to the phone. The smartphone contains an application that displays data received from the Bluetooth module interfaced with a plotter application. This Bluetooth Plotter application plots the ECG waveforms of the content on the phone. Various inferences were effectively made based upon the ECG graphs produced on the phone, thus giving the doctors an alert about the patient’s and Fetal ECG information. Further research will examine the real time patient’s data from the hospital assigned to us.
Amyotrophic lateral sclerosis Disease- Muscle loose their functionality. Regenerative medicine help to diagnose via cellular therapeutic level. (MSC's used to cure)
ANESTHETIC CONSIDERATIONS FOR STEREOTACTIC ELECTROENCEPHALOGRAPHY (SEEG) IMP...Anurag Tewari MD
The refractory seizures have significant impact on the quality of life and increase long term neurologic and non-neurologic complications. Implantation of Stereotactic Electroencephalography (SEEG) leads is one of the newer surgical techniques intended to localize seizure foci with higher accuracy than the conventional methods. Most of the commonly utilized anesthetic agents depress EEG waveforms affecting intra operative monitoring during these surgeries. Hence, the anesthetic goals include a stable induction and maintenance with agents which have minimal effect on EEG. This article discusses the peri-operative considerations of multiple anti-epileptic medications, recent advances in anesthetic management, and important post-operative concerns.
Keywords: Anesthesia, epilepsy surgery, intra-operative EEG, intra operative monitoring, refractory seizures, SEEG, seizure foci, stereotactic electroencephalography
In vivo characterization of breast tissue by non-invasive bio-impedance measu...ijbesjournal
Biological tissues have complex electrical impedance related to the tissue dimension, the internal structure
and the arrangement of the constituent cells. Since different tissues have different conductivities and
permittivities, the electrical impedance can provide useful information based on heterogeneous tissue
structures, physiological states and functions. In vivo bio-impedance breast measurements proved to be a
dependable method where these measurements can be adopted to characterize breast tissue into normal
and abnormal by a developed normalized coefficient of variation (NCV) as a numerical criterion of the bioimpedance
measurements. In this study 26 breasts in 26 women have been scanned with a homemade
Electrical Bio-impedance System (EBS). Characteristic breast conductivity and permittivity measurements
emerged for Mammographically normal and abnormal cases. CV and NCV are calculated for each case,
and the value of NCVs greater than 1.00 corresponds to abnormalities, particularly tumours while NCVs
less than 1.00 correspond to normal cases. The most promising results of (NCV) for permittivity at 1 MHz,
it detects 73% of abnormal cases including 100% tumor cases while it detects 82% of normal cases. The
numerical criterion NCV of in-vivo bio-impedance measurements of the breast appears to be promising in
breast cancer screening.
https://www.snmclub.com/presentation
PET/MRI Current & Future Status
DALE BAILEY PhD , Principal Physicist
Departement of Nuclear Medicine, Royal North Shore Hospital
Professor in Medical Radiation Sciences, University of Sydney
Sydney, Australia
icrm2018
As per the Syllabus of EC453- Biomedical Instrumentation of the BVM Engineering College, EC Department, the topic -1 slides developed. This is just a basic overview of biomedical instrumentation.
Generalized recursive algorithm for fetal electrocardiogram isolation from no...IJECEIAES
Non-invasive maternal electrocardiogram recording is the least unpleasant method to record a weak fetal electrocardiogram signal. The importance of this recording lies in the fact that it reveals crucial information about the fetal health state, especially during the last four weeks of pregnancy. This paper will be concerned with a new adaptive algorithm, namely the generalized recursive algorithm, to isolate and get the fetal electrocardiogram from the abdominal maternal electrocardiogram. This is achieved using a non-invasive method for bi-channel maternal electrocardiogram recordings i.e., with the thoracic maternal electrocardiogram as a reference signal, and the abdominal maternal electrocardiogram as a primary signal. Prior to this procedure, the discrete wavelet transform (DWT) method is applied to the abdominal electrocardiogram signal to clean it from any additive noise and the baseline wandering that is generally present on the raw recordings. The proposed new adaptive filter is shown to deliver improved characteristics through simulations. These simulations were performed on both synthetic and actual signals. This work was compared with the normalized least mean square algorithm.
Effective electroencephalogram based epileptic seizure detection using suppo...IJECEIAES
Epilepsy is one of the widespread disorders. It is a noncommunicable disease that affects the human nerve system. Seizures are abnormal patterns of behavior in the electricity of the brain which produce symptoms like losing consciousness, attention or convulsions in the whole body. This paper demonstrates an effective electroencephalogram (EEG) based seizure detection method using discrete wavelet transformation (DWT) for signal decomposition to extract features. An automatic channel selection method was proposed by the researcher to select the best channel from 23 channels based on maximum variance value. The records were segmented into a nonoverlapping segment with long 1-S. The support vector machine (SVM) model was used to automatically detect segments that contain seizures, using both frequency and time domain statistical moment features. The experimental result was obtained from 24 patients in CHB-MIT database. The average accuracy is 94.1, sensitivity is 93.5, specificity is 94.6 and the false positive rate average is 0.054.
Health electroencephalogram epileptic classification based on Hilbert probabi...IJECEIAES
This paper has proposed a new classification method based on Hilbert probability similarity to detect epileptic seizures from electroencephalogram (EEG) signals. Hilbert similarity probability-based measure is exploited to measure the similarity between signals. The proposed system consisted of models based on Hilbert probability similarity (HPS) to predict the state for the specific EEG signal. Particle swarm optimization (PSO) has been employed for feature selection and extraction. Furthermore, the used dataset in this study is Bonn University's publicly available EEG dataset. Several metrics are calculated to assess the performance of the suggested systems such as accuracy, precision, recall, and F1-score. The experimental results show that the suggested model is an effective tool for classifying EEG signals, with an accuracy of up to 100% for two-class status.
Over the past few decades, the prognosis of neonatal seizures has experienced considerable enhancement due to the improvement in neonatal and infant care. The mortality rate of neonatal seizures has fallen from 40% to 20%, and the relationship between electro encephalogram (EEG) and prognosis has become quite clear. The underlying cause of seizures is a major determinant of the outcome of the disease. For example, patients with secondary seizures and hypoxic-ischemic encephalopathy have only 50% chance of normal development and total recovery, while newborns with secondary seizures and subarachnoid hemorrhage or better hypocalcemia have higher chances of recovery. Searches were conducted by two independent researchers in international (PubMed, Web of Science, Scopus, and Google Scholar) and national (SID and Magiran) databases for related studies from the inception of the databases to September 2017 (without time limitation) in English and Persian languages. It is possible to achieve accurate diagnosis through checking the history before birth and performing a thorough physical examination in some rare cases. Depending on the case, tests or additional actions can be done. EEG is the primary means for diagnosis and may exhibit paroxysmal activity in the difference between seizures or may produce electrographic seizures in cases where seizure is hidden or latent. One of the most important points in the treatment of neonatal seizures is the diagnosis of underlying cause (such as hypoglycemia, meningitis, drug deprivation, and trauma) because such diagnosis facilitates different approaches to control neonatal seizures. Most experts agree to control all clinical and electrographic seizures. Some others focus merely on clinical seizures. Most centers prefer the first approach. An important point before starting an anticonvulsant drug is to decide if the patient needs intravenous and luteinizing treatment with an initial bolus dose, or it can be easy to start treatment with a prescription for a long-acting medication based on the severity of seizure, duration, and frequency.
AUTOMATIC HOME-BASED SCREENING OF OBSTRUCTIVE SLEEP APNEA USING SINGLE CHANNE...ijaia
Obstructive sleep apnea (OSA) is one of the most widespread respiratory diseases today. Complete or relative breathing cessations due to upper airway subsidence during sleep is OSA. It has confirmed potential influence on Covid-19 hospitalization and mortality, and is strongly associated with major comorbidities of severe Covid-19 infection. Un-diagnosed OSA may also lead to a variety of severe physical and mental side-effects. To score OSA severity, nocturnal sleep monitoring is performed under defined protocols and standards called polysomnography (PSG). This method is time-consuming, expensive, and requiring professional sleep technicians. Automatic home-based detection of OSA is welcome and in great demand. It is a fast and effective way for referring OSA suspects to sleep clinics for further monitoring. On-line OSA detection also can be a part of a closed-loop automatic control of the OSA therapeutic/assistive devices. In this paper, several solutions for online OSA detection are introduced and tested on 155 subjects of three different databases. The best combinational solution uses mutual information (MI) analysis for selecting out of ECG and SpO2-based features. Several methods of supervised and unsupervised machine learning are employed to detect apnoeic episodes. To achieve the best performance, the most successful classifiers in four different ternary combination methods are used. The proposed configurations exploit limited use of biological signals, have online working scheme, and exhibit uniform and acceptable performance (over 85%) in all the employed databases. The benefits have not been gathered all together in the previous published methods.
METHODS FOR IMPROVING THE CLASSIFICATION ACCURACY OF BIOMEDICAL SIGNALS BASED...IAEME Publication
Biomedical signals are long records of electrical activity within the human body, and they faithfully represent the state of health of a person. Of the many biomedical signals, focus of this work is on Electro-encephalogram (EEG), Electro-cardiogram (ECG) and Electro-myogram (EMG). It is tiresome for physicians to visually examine the long records of biomedical signals to arrive at conclusions. Automated classification of these signals can largely assist the physicians in their diagnostic process. Classifying a biomedical signal is the process of attaching the signal to a disease state or healthy state. Classification Accuracy (CA) depends on the features extracted from the signal and the classification process involved. Certain critical information on the health of a person is usually hidden in the spectral content of the signal. In this paper, effort is made for the improvement in CA when spectral features are included in the classification process.
In vivo characterization of breast tissue by non-invasive bio-impedance measu...ijbesjournal
Biological tissues have complex electrical impedance related to the tissue dimension, the internal structure
and the arrangement of the constituent cells. Since different tissues have different conductivities and
permittivities, the electrical impedance can provide useful information based on heterogeneous tissue
structures, physiological states and functions. In vivo bio-impedance breast measurements proved to be a
dependable method where these measurements can be adopted to characterize breast tissue into normal
and abnormal by a developed normalized coefficient of variation (NCV) as a numerical criterion of the bioimpedance
measurements. In this study 26 breasts in 26 women have been scanned with a homemade
Electrical Bio-impedance System (EBS). Characteristic breast conductivity and permittivity measurements
emerged for Mammographically normal and abnormal cases. CV and NCV are calculated for each case,
and the value of NCVs greater than 1.00 corresponds to abnormalities, particularly tumours while NCVs
less than 1.00 correspond to normal cases. The most promising results of (NCV) for permittivity at 1 MHz,
it detects 73% of abnormal cases including 100% tumor cases while it detects 82% of normal cases. The
numerical criterion NCV of in-vivo bio-impedance measurements of the breast appears to be promising in
breast cancer screening.
https://www.snmclub.com/presentation
PET/MRI Current & Future Status
DALE BAILEY PhD , Principal Physicist
Departement of Nuclear Medicine, Royal North Shore Hospital
Professor in Medical Radiation Sciences, University of Sydney
Sydney, Australia
icrm2018
As per the Syllabus of EC453- Biomedical Instrumentation of the BVM Engineering College, EC Department, the topic -1 slides developed. This is just a basic overview of biomedical instrumentation.
Generalized recursive algorithm for fetal electrocardiogram isolation from no...IJECEIAES
Non-invasive maternal electrocardiogram recording is the least unpleasant method to record a weak fetal electrocardiogram signal. The importance of this recording lies in the fact that it reveals crucial information about the fetal health state, especially during the last four weeks of pregnancy. This paper will be concerned with a new adaptive algorithm, namely the generalized recursive algorithm, to isolate and get the fetal electrocardiogram from the abdominal maternal electrocardiogram. This is achieved using a non-invasive method for bi-channel maternal electrocardiogram recordings i.e., with the thoracic maternal electrocardiogram as a reference signal, and the abdominal maternal electrocardiogram as a primary signal. Prior to this procedure, the discrete wavelet transform (DWT) method is applied to the abdominal electrocardiogram signal to clean it from any additive noise and the baseline wandering that is generally present on the raw recordings. The proposed new adaptive filter is shown to deliver improved characteristics through simulations. These simulations were performed on both synthetic and actual signals. This work was compared with the normalized least mean square algorithm.
Effective electroencephalogram based epileptic seizure detection using suppo...IJECEIAES
Epilepsy is one of the widespread disorders. It is a noncommunicable disease that affects the human nerve system. Seizures are abnormal patterns of behavior in the electricity of the brain which produce symptoms like losing consciousness, attention or convulsions in the whole body. This paper demonstrates an effective electroencephalogram (EEG) based seizure detection method using discrete wavelet transformation (DWT) for signal decomposition to extract features. An automatic channel selection method was proposed by the researcher to select the best channel from 23 channels based on maximum variance value. The records were segmented into a nonoverlapping segment with long 1-S. The support vector machine (SVM) model was used to automatically detect segments that contain seizures, using both frequency and time domain statistical moment features. The experimental result was obtained from 24 patients in CHB-MIT database. The average accuracy is 94.1, sensitivity is 93.5, specificity is 94.6 and the false positive rate average is 0.054.
Health electroencephalogram epileptic classification based on Hilbert probabi...IJECEIAES
This paper has proposed a new classification method based on Hilbert probability similarity to detect epileptic seizures from electroencephalogram (EEG) signals. Hilbert similarity probability-based measure is exploited to measure the similarity between signals. The proposed system consisted of models based on Hilbert probability similarity (HPS) to predict the state for the specific EEG signal. Particle swarm optimization (PSO) has been employed for feature selection and extraction. Furthermore, the used dataset in this study is Bonn University's publicly available EEG dataset. Several metrics are calculated to assess the performance of the suggested systems such as accuracy, precision, recall, and F1-score. The experimental results show that the suggested model is an effective tool for classifying EEG signals, with an accuracy of up to 100% for two-class status.
Over the past few decades, the prognosis of neonatal seizures has experienced considerable enhancement due to the improvement in neonatal and infant care. The mortality rate of neonatal seizures has fallen from 40% to 20%, and the relationship between electro encephalogram (EEG) and prognosis has become quite clear. The underlying cause of seizures is a major determinant of the outcome of the disease. For example, patients with secondary seizures and hypoxic-ischemic encephalopathy have only 50% chance of normal development and total recovery, while newborns with secondary seizures and subarachnoid hemorrhage or better hypocalcemia have higher chances of recovery. Searches were conducted by two independent researchers in international (PubMed, Web of Science, Scopus, and Google Scholar) and national (SID and Magiran) databases for related studies from the inception of the databases to September 2017 (without time limitation) in English and Persian languages. It is possible to achieve accurate diagnosis through checking the history before birth and performing a thorough physical examination in some rare cases. Depending on the case, tests or additional actions can be done. EEG is the primary means for diagnosis and may exhibit paroxysmal activity in the difference between seizures or may produce electrographic seizures in cases where seizure is hidden or latent. One of the most important points in the treatment of neonatal seizures is the diagnosis of underlying cause (such as hypoglycemia, meningitis, drug deprivation, and trauma) because such diagnosis facilitates different approaches to control neonatal seizures. Most experts agree to control all clinical and electrographic seizures. Some others focus merely on clinical seizures. Most centers prefer the first approach. An important point before starting an anticonvulsant drug is to decide if the patient needs intravenous and luteinizing treatment with an initial bolus dose, or it can be easy to start treatment with a prescription for a long-acting medication based on the severity of seizure, duration, and frequency.
AUTOMATIC HOME-BASED SCREENING OF OBSTRUCTIVE SLEEP APNEA USING SINGLE CHANNE...ijaia
Obstructive sleep apnea (OSA) is one of the most widespread respiratory diseases today. Complete or relative breathing cessations due to upper airway subsidence during sleep is OSA. It has confirmed potential influence on Covid-19 hospitalization and mortality, and is strongly associated with major comorbidities of severe Covid-19 infection. Un-diagnosed OSA may also lead to a variety of severe physical and mental side-effects. To score OSA severity, nocturnal sleep monitoring is performed under defined protocols and standards called polysomnography (PSG). This method is time-consuming, expensive, and requiring professional sleep technicians. Automatic home-based detection of OSA is welcome and in great demand. It is a fast and effective way for referring OSA suspects to sleep clinics for further monitoring. On-line OSA detection also can be a part of a closed-loop automatic control of the OSA therapeutic/assistive devices. In this paper, several solutions for online OSA detection are introduced and tested on 155 subjects of three different databases. The best combinational solution uses mutual information (MI) analysis for selecting out of ECG and SpO2-based features. Several methods of supervised and unsupervised machine learning are employed to detect apnoeic episodes. To achieve the best performance, the most successful classifiers in four different ternary combination methods are used. The proposed configurations exploit limited use of biological signals, have online working scheme, and exhibit uniform and acceptable performance (over 85%) in all the employed databases. The benefits have not been gathered all together in the previous published methods.
METHODS FOR IMPROVING THE CLASSIFICATION ACCURACY OF BIOMEDICAL SIGNALS BASED...IAEME Publication
Biomedical signals are long records of electrical activity within the human body, and they faithfully represent the state of health of a person. Of the many biomedical signals, focus of this work is on Electro-encephalogram (EEG), Electro-cardiogram (ECG) and Electro-myogram (EMG). It is tiresome for physicians to visually examine the long records of biomedical signals to arrive at conclusions. Automated classification of these signals can largely assist the physicians in their diagnostic process. Classifying a biomedical signal is the process of attaching the signal to a disease state or healthy state. Classification Accuracy (CA) depends on the features extracted from the signal and the classification process involved. Certain critical information on the health of a person is usually hidden in the spectral content of the signal. In this paper, effort is made for the improvement in CA when spectral features are included in the classification process.
About
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Technical Specifications
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
Key Features
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface
• Compatible with MAFI CCR system
• Copatiable with IDM8000 CCR
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
Application
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Final project report on grocery store management system..pdfKamal Acharya
In today’s fast-changing business environment, it’s extremely important to be able to respond to client needs in the most effective and timely manner. If your customers wish to see your business online and have instant access to your products or services.
Online Grocery Store is an e-commerce website, which retails various grocery products. This project allows viewing various products available enables registered users to purchase desired products instantly using Paytm, UPI payment processor (Instant Pay) and also can place order by using Cash on Delivery (Pay Later) option. This project provides an easy access to Administrators and Managers to view orders placed using Pay Later and Instant Pay options.
In order to develop an e-commerce website, a number of Technologies must be studied and understood. These include multi-tiered architecture, server and client-side scripting techniques, implementation technologies, programming language (such as PHP, HTML, CSS, JavaScript) and MySQL relational databases. This is a project with the objective to develop a basic website where a consumer is provided with a shopping cart website and also to know about the technologies used to develop such a website.
This document will discuss each of the underlying technologies to create and implement an e- commerce website.
Industrial Training at Shahjalal Fertilizer Company Limited (SFCL)MdTanvirMahtab2
This presentation is about the working procedure of Shahjalal Fertilizer Company Limited (SFCL). A Govt. owned Company of Bangladesh Chemical Industries Corporation under Ministry of Industries.
Hierarchical Digital Twin of a Naval Power SystemKerry Sado
A hierarchical digital twin of a Naval DC power system has been developed and experimentally verified. Similar to other state-of-the-art digital twins, this technology creates a digital replica of the physical system executed in real-time or faster, which can modify hardware controls. However, its advantage stems from distributing computational efforts by utilizing a hierarchical structure composed of lower-level digital twin blocks and a higher-level system digital twin. Each digital twin block is associated with a physical subsystem of the hardware and communicates with a singular system digital twin, which creates a system-level response. By extracting information from each level of the hierarchy, power system controls of the hardware were reconfigured autonomously. This hierarchical digital twin development offers several advantages over other digital twins, particularly in the field of naval power systems. The hierarchical structure allows for greater computational efficiency and scalability while the ability to autonomously reconfigure hardware controls offers increased flexibility and responsiveness. The hierarchical decomposition and models utilized were well aligned with the physical twin, as indicated by the maximum deviations between the developed digital twin hierarchy and the hardware.
Explore the innovative world of trenchless pipe repair with our comprehensive guide, "The Benefits and Techniques of Trenchless Pipe Repair." This document delves into the modern methods of repairing underground pipes without the need for extensive excavation, highlighting the numerous advantages and the latest techniques used in the industry.
Learn about the cost savings, reduced environmental impact, and minimal disruption associated with trenchless technology. Discover detailed explanations of popular techniques such as pipe bursting, cured-in-place pipe (CIPP) lining, and directional drilling. Understand how these methods can be applied to various types of infrastructure, from residential plumbing to large-scale municipal systems.
Ideal for homeowners, contractors, engineers, and anyone interested in modern plumbing solutions, this guide provides valuable insights into why trenchless pipe repair is becoming the preferred choice for pipe rehabilitation. Stay informed about the latest advancements and best practices in the field.
Cosmetic shop management system project report.pdfKamal Acharya
Buying new cosmetic products is difficult. It can even be scary for those who have sensitive skin and are prone to skin trouble. The information needed to alleviate this problem is on the back of each product, but it's thought to interpret those ingredient lists unless you have a background in chemistry.
Instead of buying and hoping for the best, we can use data science to help us predict which products may be good fits for us. It includes various function programs to do the above mentioned tasks.
Data file handling has been effectively used in the program.
The automated cosmetic shop management system should deal with the automation of general workflow and administration process of the shop. The main processes of the system focus on customer's request where the system is able to search the most appropriate products and deliver it to the customers. It should help the employees to quickly identify the list of cosmetic product that have reached the minimum quantity and also keep a track of expired date for each cosmetic product. It should help the employees to find the rack number in which the product is placed.It is also Faster and more efficient way.
Runway Orientation Based on the Wind Rose Diagram.pptx
FRACTIONAL ORDER BUTTERWORTH FILTER FOR FETAL ELECTROCARDIOGRAPHIC SIGNAL FEATURE EXTRACTION
1. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
DOI: 10.5121/sipij.2021.12503 45
FRACTIONAL ORDER BUTTERWORTH
FILTER FOR FETAL ELECTROCARDIOGRAPHIC
SIGNAL FEATURE EXTRACTION
Hadi Mohsen Alkanfery1
and Ibrahim Mustafa Mehedi2
1
Electrical and Biomedical Engineering,
King Abdulaziz University, Jeddah, Saudi Arabia
1
Medical Equipment Specialist, Ministry of Health, Najran, Saudi Arabia
2
Electrical and Computer Engineering, King Abdulaziz University,
Jeddah, Saudi Arabia
ABSTRACT
The non-invasive Fetal Electrocardiogram (FECG) signal has become a significant method for monitoring
the fetus's physiological conditions, extracted from the Abdominal Electrocardiogram (AECG) during
pregnancy. The current techniques are limited during delivery for detecting and analyzing fECG. The non -
intrusive fECG recorded from the mother's abdomen is contaminated by a variety of noise sources, can be
a more challenging task for removing the maternal ECG. These contaminated noises have become a major
challenge during the extraction of fetal ECG is managed by uni-modal technique. In this research, a new
method based on the combination of Wavelet Transform (WT) and Fast Independent Component Analysis
(FICA) algorithm approach to extract fECG from AECG recordings of the pregnant woman is proposed.
Initially, preprocessing of a signal is done by applying a Fractional Order Butterworth Filter (FBWF). To
select the Direct ECG signal which is characterized as a reference signal and the abdominal signal which
is characterized as an input signal to the WT, the cross-correlation technique is used to find the signal with
greater similarity among the available four abdominal signals. The model performance of the proposed
method shows the most frequent similarity of fetal heartbeat rate present in the database can be evaluated
through MAE and MAPE is 0.6 and 0.041209 respectively. Thus the proposed methodology of de-noising
and separation of fECG signals will act as the predominant one and assist in understanding the nature of
the delivery on further analysis.
KEYWORDS
Fetal Electrocardiogram (FECG), Fractional Butterworth Filter (FBW), Fetal Heart Rate (FHR),
pregnancy, Abdominal Electrocardiogram (AECG), Non-invasive.
1. INTRODUCTION
Among 80% of perinatal events, 20% of pregnancies are high risk, whereas the rest are
preventable as per the record of the World Health Organization (WHO). Intelligent detection and
analysis of fECG signals help in identifying the preventable ones at the earlier stage.
Furthermore, fetal deaths worldwide are 2.65 million annually, with 45% of intra-partum deaths
can occur. Heart defects are the primary cause of mortality. Nine out of 1,000 infant children in
the UK are estimated to have a congenital cardiopathy at birth [1]. Using Fetal heart rate activity
many scientific community has developed a brilliant technologies to control the physiological
status of the fetus [2,3]. It is possible to obtain valuable knowledge about the physiological
condition of the fetus by analyzing the fECG waveform. The morphological characteristics of
fetal ECG can be successfully identified using an invasive approach involving an electrode
2. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
46
connected to the fetal scalp. The direct fetal ECG measurement is very time dependent method
that can only be recorded after the membrane ruptures. There are various electrodes mounted on
the mother's abdomen that may also be used to extract fECG from AECG recordings. The
accuracy of fetal heart parameters has recently been demonstrated by an ECG record as well as
their excellent adherence with the values of scalp electrodes. Electro hysterogram (EHG),
Maternal ECG, and fECG are the electrical activity of the uterus that is very strong during
childbirth in which electrophysiological signals are presented in each measurement. Since fetal
ECG seems to be combined with several other causes of disturbance including maternal muscular
noise, skin resistance interference, acoustic noise, respiration caused by fetal movement, and
power line distribution. Today, the fetal monitoring is completely based on the FHR monitoring
assisting Doppler & Ultrasound/ Sonography techniques only and does not integrate the
characteristics of the fECG waveform. The fECG signal provides useful information to define the
variability of FHR and further measures for heart function. Cord compression, fetal heart block,
fetal arrhythmia, fetal malposition such as Asphyxia, Bradycardia, congenital heart disease,
tachycardia, hypoxia, and some other abnormal situations can also be detected by the fECG
analysis [3]. The ranges of FHR should be between 120 and 160 beats per minute. Bradycardia
has the FHR as less than 120 beats and Tachycardia has the FHR greater than 180 beats per
minute. At last, oxygen levels have been associated with changes in the width of the QRS-
complex, PR, and PQ intervals, the P-wave, T-wave, and ST-segment [4].
To utilize the advantages of such a Non-invasive method, several signal processing techniques to
retrieve the fECG from the non-invasive recordings are developed. Besides this, fetal
electrocardiography has not been demonstrated to be an effective method to imagine such major
flaws even during labor. Rather, fetal electrocardiography is often used to diagnose more
common problems including general ischemia caused by fetal positioning that suffocates the
umbilical cord. The noninvasive FECG is contaminated by movement objects, fetal brain activity,
myographic (muscle) signals, and several layers of dielectric physiological environments the
electrical signals must pass, which is the reason for this restriction. So, an efficient algorithm for
extraction fECG from AECG providing an exact cardiograph (morphology) is required.
This research work introduced the design of FBWF is applied for pre-processing of FECG from
the multichannel abdominal ECG recordings in complex w plane. Initially, FBWF has been built
in the w-plane rather than the complex s-plane with integer-order filters. Then the definition of
fractional order derivatives has been discussed with the stability of w-plane linear fractional-
order systems. Then fast ICA (FICA) algorithm with the combination of fast Fourier Transform
(FFT) and the undecimated Wavelet transform (WT) was successfully used to extract FECG from
AECG separation with constant coefficients that changes the weights according to the signal.
Finally, to measure the FHR, fetal R-waves are observed. The R-R intervals are reliable in
duration based on the extracted from the various fECG signals. This study offers a numerical
representation of HR variations around a mean, which reflects a subject's average HR. It is shown
that the HR variability defines the capacity of the heart to respond to and control various stimuli.
This research work aims to monitor the fetus physiological conditions which are non - intrusive
fECG recorded from the mother's abdomen during the pregnancy.
The organization of the paper is as follows. Section 2 presents a literature survey based on
various fetal ECG extraction methods, Section 3 describes a proposed methodology based on pre-
processing, extraction of fetal ECG using FICA, post-processing, and analysis of Fetal ECG
feature extraction stage, Section 4 describes experimental results, Section 5 describes
performance evaluation and Section 6 ends with a conclusion.
3. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
47
2. LITERATURE REVIEW
In recent studies, many researchers have addressed the techniques based on extraction of Fetal
ECG during pregnancy. Initially, this section focuses survey based on extracting fECG such as
the Adaptive filtering technique, WT, and features for analyzing fetal heart rate. Since an
examination of the fECG, which allows for high efficiency and precision in measuring FHR,
there has been an increasing interest in tracking fetal cardiac bioelectric activity for many years.
Invasively recording the fECG are directly from the fetal head while labor whereas non-
invasively recording the fECG are indirectly mounted on the maternal abdominal wall from
electrodes during labor [5]. The amplitude of the Fetal QRS complex (FQRS) in abdominal
signals exceeds 20 V and is highly influenced by the maternal BMI. There are various muscle
interference are available but the most strong and efficient is Maternal Electrocardiogram
(MECG) with a significantly larger amplitude [6]. The fECG signal remains undesirable with
further study due to incomplete MECG suppression [7], FHR determination, preventing the
identification of FQRS complexes, and accurate location of R waves. During labor, an abdominal
fECG and a reference direct fECG had been recorded at the same time. The clinical experts
corrected reference pregnancy signal data obtained from an automated detector. The resulting
data set contains a wide range of clinically relevant FHR interferences, which can establish new
techniques for the study of fECG signals and eventually promote the use and accuracy of
abdominal ECG [8]. To extract FECG signal from AECG signal by utilizing a FIR Adaptive
Noise Canceller (ANC) with adaptive algorithms to update the filter coefficients. Adaptive filters
are suitable for the current problem of interest and Least Mean Square (LMS) are analyzed for
the problem of fECG extraction [9]. The benefit of using FIR ANC is that it has a lower
computational cost and performs better with two input signals, one of which is primary and the
other is reference, as opposed to other non-adaptive techniques such as PCA and ICA, which can
only provide better performance when multichannel input is present. To update adaptive filters in
ANC, LMS and RLS algorithms can be employed. In the literature, both LMS and RLS
algorithms for FECG extraction may be discovered. [10]. To handle this challenge, several
adaptive filtering and artificial intelligence algorithms are used. As an intelligent system,
complex real-world problems require a combination of information, skills, and approaches from
diverse sources. That intelligent system should have human-like abilities, be able to adapt to
changing environments, and learn to improve on its own. [11]. Using an ANC device, the
extracted signal of the FHR from the mother was enhanced. It employs widely used adaptive
Normalized LMS algorithms (NLMS). Fetal extraction and de-noising are suggested in this
paper. The NLMS algorithm is combined with the Savitzky–Golay (SG) filter in this system [12].
Wavelet decomposition and an ICA algorithm are used to develop a novel approach. The
proposed method was evaluated and attain 96% accuracy in detecting the R wave of fECG, which
is capable of future research [13]. To remove fetal ECG from the mixed-signal, Vaidya and
Chaitra describe comparing the three separate adaptive filters namely Kalman filter, LMS, and
NLMS. A required inference is reached by comparing the characteristics such as computational
complexity, reliability, signal-to-noise ratio, and stability [14]. MATLAB was used to apply fetal
extraction procedures and the fetal ECG was successfully extracted. The Fast fixed-point
approach for Independent Component Analysis (FastICA) has been widely employed in fECG
extraction. The FastICA algorithm affects the convergence which is responsive to the initial
weight vector. To address this problem, an improved Fast ICA method for extracting fetal ECG
was proposed [15]. Adaptive filtering [5], [16], wavelet analysis [17], matched filtering [18],
blind source separation [19], ICA [20], neural network [21], [22], and Singular Value
Decomposition (SVD) [23] are the most common fetal ECG extraction algorithms are currently
accessible. In case that the source signals are statistically independent, ICA can isolate the source
signals from the mixed signals, without the need for information concerning the source signals
and the combined matrix. ICA is thus regarded as an advantageous tool for fetal ECG extraction.
4. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
48
Researchers have suggested several improving ICAs in recent years, allowing non-Gaussian
signals to be separated.
3. MATERIALS AND METHODS
This research work consists of three major stages. Initially, preprocessing of the signal is done by
using FBWF which is mainly used to eliminate interfering signals such as certain physiological
signals, baseline wander, and power line signals. Then cross-correlation can be used to select the
reference signal as a Direct ECG and the abdominal signal as an input signal based on the greater
similarity between them. Then the extracted signals from Direct and abdominal ECG can be
processed by wavelet transform. This wavelet and the FICA decomposition property helps to
eliminate noise from abdominal signals as well as separate fetal ECGs from the maternal ECG.
After, the extracted features such as QRS peaks were analyzed for FECG signal which is
performed to validate with sample heart rate from the database. The general block diagram of the
work presented in this paper is shown in Figure.1.
Figure 1. Flowchart of the research work
5. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
49
3.1. Pre-processing
The noise from the input fetal ECG signal is removed during preprocessing by applying
fractional-order Butterworth Filter with the suitable and precise cut of frequencies. The signal-to-
noise ratio is minimal during pregnant women since the FHR is just a few uV in amplitude
whereas interfering signals may be represented as hundreds of uV. As a result, FBWF was built
in the w-plane to remove interfering signals. In this paper formulated W plane as (w ¼ sq; q∈ℝ+)
which contains all the possible types of poles such as under, hyper and ultra-damped were also
taken into consideration. In the w-plane, diagnostic design of the filter has been performed, as
well as certain criteria for the position of the poles such as stable and unstable have been
determined. In the case of fractional order, derivation found the principle of classical Butterworth
filter which are kept unchanged whose radius is equal to cut off frequency whereas the poles are
located along with the perimeter of the circle. As a result, the suggested formulation takes into
account all of the stable poles. The relation s = can be used for the w-plane by obtaining the
transfer function and then mapped back into the s-plane. To confirm the maximally flat
Butterworth existence, the corresponding reaction curves are obtained. In the fractional domain,
the resulting complexity would make more difficult generalization filters and fabrication costs are
outweighed by the benefits of greater flexibility. Hence the designing system has been adopted by
considering a relative tradeoff between accuracy and complexity. Therefore, the filter has
truncating up to the first decimal place which is better to realize whose overall order is a fraction.
To improve the characteristics of the frequency domain the accuracy can be increased by intuitive
judgments. The FBW filter considers the stability of fractional linear systems which has been
developed on the line of integer order BW filter [24].
The goal of this study is to extract clean fetal electrocardiogram (fECG) signals from non-
invasive abdominal ECG recordings for monitoring the health of the fetus during pregnancy and
childbirth. The proposed extraction was implemented in MATLAB® by processing the
abdominal and direct ECG with a fractional Butterworth filter for the separation of direct fetal
ECG signals.
3.2. Data Collection
The data obtained from the Abdominal and Direct Fetal Electrocardiogram Database on
PhysioNet is used in this work [23]. Referring to patient 1 and patient 2, a set of multichannel
electrocardiogram (ECG) recordings acquired from two distinct women in labor between 38 and
41 weeks of pregnancy, were used in this study. By using the KOMPOREL system for fetal ECG
manipulation and processing, those recordings were obtained in the Department of Obstetrics at
the Medical University of Silesia (ITAM Institute, Zabrze, Poland) [13]. Four distinct signals
were obtained from the maternal abdomen for each recording, as well as from the fetal head a
reference direct fetal ECG is recorded. All recordings were selected at 1 kHz and coded in 16
bits, with a total duration of 5 minutes. Figure 2 depicts the Investigation of moral characteristics
and also the extraction of the fetal electrocardiogram as the technical outline format. The signal
recorded from the mother’s abdomen and from the fetal head are pre-processed using FBWF. The
pre-processed signal is then used to extract the fetal ECG with the help of FICA and Wavelet
transform technique.
6. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
50
Figure 2. System diagram of FECG extraction
3.3. Phases of pre-processing
Typically, the range of the EHG signal spectrum is between 0.1 Hz to 3Hz in each signal [14].
We used the MATLAB signal processing toolbox to create a high-pass Fractional Butterworth
Filter (FBWF) with a stopband edge frequency of 0.5 Hz and a passband edge frequency of 3 Hz
to eliminate baseline wandering and cancel most EHGs. A narrow band noise of less than 1Hz
centered at 50 Hz is the interference of the power line. We utilized a severe notch filter (Q-factor
equal to 30) at 50 Hz to minimize this noise kind. Furthermore, we constructed a 100th order IIR
Butterworth filter from our bandwidth range (0.5 – 34) Hz to reduce high-frequency noises from
motion artifacts, as the frequencies of relevance for PQRST wave mining are predominantly
situated in the domain.
3.4. Methods of Independent Component Analysis
To breakdown the multivariable signal into a set of mutually separate non-Gaussian elements, a
statistical method of Independent Component Analysis (ICA) is used, provided that the observed
signals are mathematically specified by the ICA model [5], as a mixture of independent sources;
x = A∙s, where x= [x1, x2, x3, … … xm] T
is the noticed multivariate signal, s = [s1, s2, s3, … … sn] T
is the original unknown multivariate source signal, M is the number of noticed signals, N is the
number of sources and A is the mixing matrix. In order to acquire estimated independent
components y, the goal of ICA is to return the linear unmixing matrix W is such that: y = W. x
Neural algorithms have many benefits towards the Fast ICA they are; It is parallel, Evenly,
distributed, Simple in computation and consumes less memory space. Moreover, independent
components, approximately equal to projection, may be estimated one by one [5]. The TSA
(Time Sample Analysis) independent component analysis VI with which fast ICA approach is
readily adopted thanks to its convergence speed, as offered by the advanced signals processing
toolbox.
3.5. Post-processing
The wavelet function in 5 levels of decomposition enhanced the Fast ICA extraction quality for
ECG signals [l5], using biorthogonal 4.4. The denoise stage of wavelets transformed. We have
used Undecimated Wavelet Transformation (UWT) from the Wavelet Denoise toolbox to remove
the multiband noise from ICA extracted fECG signals. A biorthogonal wavelet filter was chosen
at eight decomposition levels to better identify the acquired signal, and its scaling function is
intricately linked to the shape of the ECG.
7. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
51
Regrettably, even after effectively de-noising with wavelet transforms, some noise components
remained, necessitating the use of additional filtering techniques must be needed to increase the
signal-to-noise (SNR) value. We used FFT and Inverse FFT from the Signal Processing toolbox
to create a signal processing pair consisting of Fast Fourier Transform (FFT) and Inverse Fast
Fourier Transform (IFFT). Signals were translated from time to frequency domain using the FFT
transform, with high and low-frequency components sorted out to highlight undesired noise
components. In the frequency domain, the signal is separated from the first and final 5*FFT
length/sampling rate samples and therefore filtered. After that, the filtered signal is converted
back to the time domain and ready for feature extraction by using IFFT.
3.6. ECG of a fetus with extraction stage
We used a combination of Peak Detector from Signal Operation toolbox and WA Multiscale
Peak Detection from Wavelet Analysis toolbox to extract fECG features to detect QRS peak
positions and maximum amplitudes. Using the Extract Heart Rate, FHR may be detected
automatically for various time intervals of recordings.
4. RESULT AND DISCUSSION
MATLAB® tool is used for extracting fECG for analyzing fetus heart rate. For a better analysis
of the algorithm, the ECG acquired in a real-time scenario will be the best choice. Physionet
provides free web access to PhysioBank, which contains a large collection of recorded
physiologic signals.
The recordings in EDF format have already been preprocessed by filtering for noise removal and
an excellent source of data for evaluating new fECG processing techniques. The database used
for Non-invasive fetal electrocardiogram is involved with the data of 55 series in multichannel
abdominal recordings that have been collected from 10 subjects among the pregnancy period of
21 to 40 weeks. The implemented algorithm is tested on 10 records having a better trace. Figure.
3 (A) and (B) have discussed Direct and followed by abdominal 1, 2, 3, and 4 signals. Figure. 3
(A) corresponding to 1 clinical case of raw ECG signal which contains few uV in amplitude
whereas interfering signals may be represented as hundreds of uV. Figure. 3 (B) shown maternal
ECG signal after removal of hundreds of uV.
Figure.3. (A) Raw ECG signal (B) Pre-processed ECG signal
Figure 4 shown post-processing using FICA and undecimated WT which contains all the QRS
complexes are extracted. The resulting signal obtained fetal ECG which can be separated from
8. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
52
the mother’s ECG. The red color indicates fetal ECG whereas the blue color indicates mother
ECG.
Figure 4. The resulting signal of Fetal ECG separation
4.1. Performance Evaluation
In Figure 5, the analysis of the heart rate signal extracted from fECG is shown. It also recognizes
time slots that increase or decrease in accordance with fetal heart rate normal ranges, with R
waves indicated by a pink peak.
Figure 5. R waves detection in fECG signal
9. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
53
Figure 6. Comparison of beats per minute for 10 different subjects
In figure 6 shows that the proposed method has most frequent similarity except subject 5 which
are mismatched in database samples.
4.2. Calculation of Error Rate
The average of absolute percentage error was calculated for 10 different subjects using the
following formula.
Mean Absolute Error (MAE): The MAE was calculated as the average absolute difference
between the fetal heart rate variability of bits per minute for proposed method(Y) and database
samples (Ŷ ).
MAE = ∑_(i=1)^(n=10)▒(Y_i-Ŷ)/n = 0.6 (1)
Mean Absolute Percentage Error (MAPE): The MAPE was calculated by averaging the
individual absolute percent errors.
MAPE = (∑_(i=1)^(n=10)(Y_i-Ŷ)/n)/n x 100 = 0.041209 (2)
Therefore the performance of the proposed method can be obtained as 0.6 MAE and 0.0412
MAPE percentage error.
5. CONCLUSIONS
During pregnancy, one of the best methods of diagnosis is fetus ECG signals which assist in
analyzing the fetus status in the uterus. However, the requirement of an automated method to
extract the fECG and even analyze by noninvasive recording obtained from the chest and
abdomen of pregnant women. Hence, the proposed method is developed based on FICA and the
undecimated WT that is majorly focused on extracting fECG signals. These techniques were
10. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
54
employed for the cancellation of the mother’s ECG in such records. The combination of
statistical properties and PCA gives a powerful method for studying FECG signals to validate the
heart bit rate. The model performance of the proposed method shows the most frequent similarity
of fetal heartbeat rate present in the database can be evaluated through MAE and MAPE is 0.6
and 0.041209. These techniques can be utilized to develop a real-time fECG monitoring and
analysis system that helps obstetricians detect fetal distress in pregnant women's wombs and take
appropriate measures to help them. In the future, this paper involves qualitative and quantitative
analysis based on the threshold value will find the scoring scheme to indicate severe cases of
abnormality. Moreover, the extension of this paper utilizes the extracting features of fetal heart
rate based on the scoring scheme as the obtained values cross the threshold which depicts high-
risk of pregnancy Whereas if the obtained value is equal or less than the threshold depicts a
possible risk that is indicated of normal pregnancy.
ACKNOWLEDGEMENTS
The authors would like to thank everyone who supported this research.
REFERENCES
[1] J. Behar, F. Andreotti, S. Zaunseder, J. Oster, and G. D. Clifford, “A practical guide to non-invasive
foetal electrocardiogram extraction and analysis,” Physiological measurement, vol. 37, no. 5, p. R1,
2016.
[2] Mohamed Yacin S and Vennila M, Extended Kalman filtering for fetal ECG extraction using Hilbert-
Huang transform, Int. J. of Biomedical Engineering and Technology, Vol. 18, No. 1, pp 14-29, 2015
[3] G. D. Clifford, I. Silva, J. Behar, and G. B. Moody, “Non-invasive fetal ECG analysis,” Physiological
measurement, vol. 35, no. 8, p. 1521, 2014.
[4] G. Lamesgin, Y. Kassaw, and D. Assefa, “Extraction of fetal ECG from abdominal ECG and heart
rate variability analysis,” in Afro-European Conference for Industrial Advancement, 2015, pp. 65–76.
[5] R. Martinek et al., “Non-invasive fetal monitoring: A maternal surface ECG electrode placement-
based novel approach for optimization of adaptive filter control parameters using the LMS and RLS
algorithms,” Sensors, vol. 17, no. 5, p. 1154, 2017.
[6] E. Fotiadou, J. O. Van Laar, S. G. Oei, and R. Vullings, “Enhancement of low-quality fetal
electrocardiogram based on time-sequenced adaptive filtering,” Medical & biological engineering &
computing, vol. 56, no. 12, pp. 2313–2323, 2018.
[7] I. Mousavian, M. B. Shamsollahi, and E. Fatemizadeh, “Noninvasive fetal ECG extraction using
doubly constrained block-term decomposition,” Math. Biosci. Eng, vol. 17, no. 1, pp. 144–159, 2019.
[8] A. Matonia et al., “Fetal electrocardiograms, direct and abdominal with reference heartbeat
annotations,” Scientific data, vol. 7, no. 1, pp. 1–14, 2020.
[9] C. N. Praneeth, J. D. K. Abel, D. Samiappan, R. Kumar, S. P. Kumar, and P. V. Nitin, “A
COMPARISON ON VARIANTS OF LMS USED IN FIR ADAPTIVE NOISE CANCELLERS FOR
FETAL ECG EXTRACTION,” Biomedical Engineering: Applications, Basis and Communications,
vol. 32, no. 04, p. 2050026, 2020.
[10] P. Sutha and V. E. Jayanthi, “Fetal electrocardiogram extraction and analysis using adaptive noise
cancellation and wavelet transformation techniques,” Journal of medical systems, vol. 42, no. 1, pp.
1–18, 2018.
[11] M. Pradeepa and S. Kumaraperumal, “ADAPTIVE FILTERING AND ARTIFICIAL
IN℡LIGENCE METHODS ON FETAL ECG EXTRACTION,” Journal of Critical Reviews, vol. 7,
no. 7, pp. 295–299, 2020.
[12] A. Ghasemi, F. Shama, G. Karimi, and F. Khosravi, “Recovery and noise cancelling of the fetal heart
signal using a combination of NLMS algorithm and SG filter,” Circuit World, 2020.
[13] S. L. Lima-Herrera, C. Alvarado-Serrano, and P. R. Hernández-Rodríguez, “Fetal ECG extraction
based on adaptive filters and Wavelet Transform: Validation and application in fetal heart rate
variability analysis,” in 2016 13th International Conference on Electrical Engineering, Computing
Science and Automatic Control (CCE), 2016, pp. 1–6.
11. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
55
[14] R. R. Vaidya and N. Chaitra, “Comparison of Adaptive filters in extraction of Fetal ECG,” in 2020
International Conference on Smart Electronics and Communication (ICOSEC), 2020, pp. 1066–
1070.
[15] L. Yuan, Z. Zhou, Y. Yuan, and S. Wu, “An improved FastICA method for fetal ECG extraction,”
Computational and mathematical methods in medicine, vol. 2018, 2018.
[16] J. Behar, A. Johnson, G. D. Clifford, and J. Oster, “A comparison of single channel fetal ECG
extraction methods,” Annals of biomedical engineering, vol. 42, no. 6, pp. 1340–1353, 2014.
[17] S. Wu, Y. Shen, Z. Zhou, L. Lin, Y. Zeng, and X. Gao, “Research of fetal ECG extraction using
wavelet analysis and adaptive filtering,” Computers in biology and medicine, vol. 43, no. 10, pp.
1622–1627, 2013.
[18] A. Dessì, D. Pani, and L. Raffo, “An advanced algorithm for fetal heart rate estimation from non-
invasive low electrode density recordings,” Physiological measurement, vol. 35, no. 8, p. 1621, 2014.
[19] A. Ghazdali, A. Hakim, A. Laghrib, N. Mamouni, and S. Raghay, “A new method for the extraction
of fetal ECG from the dependent abdominal signals using blind source separation and adaptive noise
cancellation techniques,” Theoretical Biology and Medical Modelling, vol. 12, no. 1, pp. 1–20, 2015.
[20] G. Da Poian, R. Bernardini, and R. Rinaldo, “Separation and analysis of fetal-ECG signals from
compressed sensed abdominal ECG recordings,” IEEE Transactions on Biomedical Engineering, vol.
63, no. 6, pp. 1269–1279, 2015.
[21] M. Lukoševičius and V. Marozas, “Noninvasive fetal QRS detection using an echo state network and
dynamic programming,” Physiological measurement, vol. 35, no. 8, p. 1685, 2014.
[22] N. A. Sait, M. Thangarajan, and U. Snehalatha, “Neural network based on Verilog HDL for fetal
ECG extraction,” International Journal of Biomedical Research, vol. 7, no. 10, pp. 698–701, 2016.
[23] N. Zhang et al., “A novel technique for fetal ECG extraction using single-channel abdominal
recording,” Sensors, vol. 17, no. 3, p. 457, 2017.
[24] A. Acharya, S. Das, I. Pan, and S. Das, “Extending the concept of analog Butterworth filter for
fractional order systems,” Signal processing, vol. 94, pp. 409–420, 2014.
12. Signal & Image Processing: An International Journal (SIPIJ) Vol.12, No.5, October 2021
56
AUTHORS
Hadi Mohsen Alkanfery received bachelor degree in Biomedical Equipment
Technology from Majmaah University, Saudi Arabia. Currently he is pursuing
Master of Science in Electrical and Biomedical Engineering in King Abdulaziz
University, Saudi Arabia. He also works as a Medical Equipment Specialist in
Ministry of Health, Najran, Saudi Arabia.
Ibrahim Mustafa Mehedi received B.Sc. in Electrical and Electronic Engineering in 2000 from RUET,
Bangladesh. He received the MSc. in Aerospace Engineering from UPM, Malaysia in
2005. Obtaining a Japanese Govt. MEXT scholarship he completed his PhD in
Electrical Engineering and Information Systems in 2011 while he was a Research
Assistant of the Global Center of Excellence(GCOE) of the University of Tokyo and
Japan Aerospace Exploration Agency(JAXA), Sagamihara, Japan. He joined King
Abdulaziz University, Jeddah, Saudi Arabia, in November 2012, where he is
currently an Associate Professor, and is a research member of the Center of
Excellence in Intelligent Engineering Systems (CEIES). Prior to that he worked at
KFUPM, and the CocaCola Bottling Plant. His research interests include space robotics, modern control
system design and implementation, renewable energy, organic solar cells etc.