Qualification: 
M.Tech, B-Tech
shereenas@am.amrita.edu

Shereena Shaji currently serves as Research Assistant at the Amrita Center for Wireless Networks & Applications (Amrita WNA), Amritapuri.

Education

YEAR DEGREE/PROGRAM INSTITUTION
2015 M. Tech. degree in Wireless Networks & Applications Amrita School of Engineering
2013 B.Tech in Electronics and Communication Institution of Engineers in India(IEI)

Research Group : Wireless Healthcare Systems

Publications

Publication Type: Conference Paper

Year of Publication Publication Type Title

2018

Conference Paper

Shereena Shaji and Dr. Maneesha V. Ramesh, “Performance Enhancement of a Wearable Wireless ECG device Using Efficient Signal Processing Techniques”, in Fifth International Conference on Signal Processing & Integrated Networks", SPIN 2018, 2018.[Abstract]


In rural India, about 22.9% of death are due to heart diseases ]. Non-accessibility to efficient healthcare services in rural areas is one of the leading causes of this loss of life. Even though wearable devices are considered to be one of the efficient ways to provide better healthcare services, many doctors discourage the usage of these devices due to the noise and motion artifacts present in the signals acquired by these wearable devices. This research work mainly focuses on the performance enhancement of AmritaSpandanm, a wearable wireless ECG device that will enable to provide real-time ECG signals even when the patient is involved in routine activities. For this, a context aware system is designed and developed to continuously collect the physical activity, classify the real-time signals using an innovative classifier algorithm and tag the ECG signal based on the classifier results. Using the results from the classifier algorithm, the motion artifacts in the ECG data are removed using two methods, namely Adaptive Filtering and Wavelet Transform. The complete system has been implemented and tested on 35 individuals. The results obtained using wavelet transform shows 99 percentage of classification compared to the adaptive filtering method and therefore, wavelet transform is a better method to remove the motion artifacts. Hence the proposed system is capable to capture both the physical activity and ECG data of individuals and to provide an ECG signal free from noise and motion artifacts

More »»

2018

Conference Paper

A. Luke, Shereena Shaji, and K. A. Unnikrishna Menon, “Motion Artifact Removal and Feature Extraction from PPG Signals Using Efficient Signal Processing Algorithms”, in 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2018.[Abstract]


The performance of wearable Photoplethysmographic Biosensors can be highly influenced by the motion artifacts. This work proposes a performance enhancement algorithm which can remove the effect of motion artifacts caused by the voluntary movements during various physical activities of an individual. We have developed and implemented three motion artifact removal algorithms namely, ICA-Adaptive Filter Algorithm, Butterworth-ICA-Adaptive Filter Algorithm and Butterworth-Wavelet Transform Algorithm. These three algorithms were analyzed under four fingertip movements like vertical movement, horizontal movement, shivering, and applying pressure. Based on the analysis we found that the Butterworth-Wavelet Transform Algorithm is better in providing high Signal to Noise Ratio (SNR) without compromising any signal characteristics and the algorithm validation was done by extracting Heart Rate (HR) and Peripheral Oxygen Saturation (SpO2) values using Photoplethysmographic (PPG) signals obtained from available Biosensor. The results are found promising and suggest that the Butterworth-Wavelet Transform Algorithm provides motion artifact-free PPG signal for accurate feature extraction.

More »»

2018

Conference Paper

A. Luke, Shereena Shaji, and Menon, U., “Performance Enhancement of a Photoplethysmographic Biosensor Using Efficient Signal Processing Techniques”, in 2018 3rd International Conference for Convergence in Technology (I2CT), 2018.[Abstract]


The Photoplethysmographic Biosensors can be used to monitor various physiological parameters like arterial oxygen saturation, glucose level in the blood, heart rate, blood pressure etc. But the Photoplethysmographic signals could be contaminated by various noise sources. The performance limitation due to the motion artifacts is very high compared to that due to other noise sources. Conventional filtering techniques are incapable to get rid of motion artifacts effectively and completely due to the frequency overlapping between the motion artifacts and the clean Photoplethysmographic signal. This work focuses on the performance enhancement of the Photoplethysmographic Biosensor by removing the effect of motion artifacts caused by the voluntary movements of the individual. The obj ective was achieved by developing an algorithm which is capable of providing motion artifact-free Photoplethysmographic signal during various physical activities of an individual without compromising any signal characteristics. We have developed three motion artifact removal algorithms: Butterworth-Wavelet Algorithm, Adaptive Normalized Least Mean Square Algorithm and Adaptive Recursive Least Square Algorithm. The three algorithms were performed on hundred samples collected from twenty-five subj ects under four fingertip movements like shivering, vertical movement, horizontal movement and applying pressure. Based on the SNR analysis, Butterworth-Wavelet Algorithm was found better in providing high SNR

More »»

2016

Conference Paper

Shereena Shaji, Dr. Maneesha V. Ramesh, and Menon, V. N., “Real-time Processing and Analysis for Activity Classification to Enhance Wearable Wireless ecg”, in Proceedings of the Second International Conference on Computer and Communication Technologies, 2016.[Abstract]


Health care facilities of our rural India are in a state of utter indigence. Over three-fifths of those who live in rural areas have to travel more than 5 km to reach a hospital and the health care services is becoming out of reach for the economically backward society of India. Currently, as the rural community experiences about 22.9% of death due to heart diseases [1], there is a need to improve the remote ECG monitoring devices to cater the needs of rural India. The existing wearable ECG devices experience several issues to accurately detect the type of heart diseases due to the presence of motion artifacts, and to warn the doctor during critical conditions. Hence, even though wearable devices are finding their place in today’s healthcare systems, the above mentioned issues discourages a doctor in depending upon it. So to enhance the existing wearable ECG device, a context aware system was designed to collect the BMA (Body Movement Activity). In this research work an innovative BMA classifier has been designed to classify the physical activities of users, from the real-time data received from context aware device. The test results of the BMA classifier integrated with the complete system shows that algorithm developed in this work is capable of classifying the user activity such as walking, jogging, sitting, standing, upstairs, downstairs, and lying down, with an accuracy of 96.66%.

More »»
PDF iconReal-time-Processing-and-Analysis-for-Activity-Classification-to-Enhance-Wearable-Wireless-ECG.pdf