About the lab

The Electro Medical and Speech Technology (EMST) Laboratory was set up in the department of Electronics and Electrical Engineering (EEE), Indian Institute of Technology (IIT) Guwahati during 2004. The laboratory focuses on the research and development activities related to biomedical signal and image processing, speech signal processing, coding and technology areas.
Some of the current topics of interest include speech enhancement, speaker recognition, children speech recognition, speech synthesis, stressed speech processing, fundus image processing, ECG signal processing, Seismocardiographic Signal Processing, 3-dimensional Seismoglottogram Processing, biometrics and handwriting data processing.

Featured research (10)

Non-contact human body vital parameter measurements are getting more attention and have been extensively studied in a short span of time. One of such techniques is the heart rate (HR) estimation based on video recording of human face known as remote photoplethysmogram (rPPG). Usually, the recorded video gets contaminated due to illumination variation of ambient light, motion artifacts, and other environmental factors. Thus, extracting a reliable rPPG signal is a challenging task. In this paper, a novel spatial-temporal filtering method is proposed that utilizes 2D variational mode decomposition (2D-VMD) along with azimuthally averaged power spectrum density (AAPSD) and multimode kurtosis to extract a reliable rPPG signal. The robustness of the proposed algorithm is tested and validated using our own database and the publicly available standard dataset. The obtained experimental results are compared with the reference PPG signal measurements. Also, the proposed method is compared with the well-established independent component analysis (ICA)-based method. The performance results show that the non-contact HR estimated by the proposed method dramatically reduces the error and it proves our method to be superior than the existing method.
Pulse transit time (PTT) has been widely used for cuffless blood pressure (BP) measurement. But, it requires more than one cardiovascular signals involving more than one sensing device. In this paper, we propose a method for cuffless continuous blood pressure measurement with the help of left ventricular ejection time (LVET). A MEMS-based accelerometric sensor acquires a seismocardiogram (SCG) signal at the chest surface, and then, the LVET information is extracted. Both systolic and diastolic blood pressures are estimated by calibrating the system with the original arterial blood pressures of the subjects. The performance evaluation is done using different statistical quantitative measures for the proposed method. The performance is also compared with two earlier approaches, where PTT intervals are measured from electrocardiogram (ECG)-photoplethysmogram (PPG) and SCG-PPG pairs, respectively. The performance results clearly show that the proposed method is comparable with the state-of-the-art methods. Also, the estimated blood pressure is compared with the original one, measured through a reference system. It gives the mean errors of the systolic and diastolic BPs within the range of -0.197±3.332 mmHg and -1.299±2.578 mmHg, respectively. The BPs estimation errors satisfy the requirements of the IEEE standard 5±8 mmHg deviation, and thus, our method may be used for ubiquitous continuous blood pressure monitoring.
In this paper, aortic ejected blood-flow and aortic pressure is investigated as an independent tool for diagnosing cardiovascular risk. This study presents vibrocarotidography (ViCG), a novel noninvasive and nonintrusive way to measure aortic blood-flow variations in each heartbeat through carotid arteries. Most of the existing state-of-the-art works suggested to use contact-based pressure sensors and non-contact sensing devices, including wave radar and laser Doppler vibrometer (LDV) for carotid pulse acquisition. However, these sensors have operational design limitations, and poor immunity against environmental noises. To address these issues, the proposed method uses a miniaturized and cost-efficient micro-electro-mechanical system (MEMS)-based accelerometer sensor to record the vibrational pulsations on common carotid artery. The paper presents our developed electronic circuitry for ViCG signal acquisition and signal processing perspective for estimating indispensable cardiac events. The study focuses to show the ViCG signal as an alternative measure of central blood flow variations. Significance of the ViCG signal is exhibited by assessing the rate of pulsations and comparing with the heart-rhythms measured from the reference ECG and PPG signals. A quantitative Bland-Altman analysis shows a mean difference of-0.01 ms and correlation coefficient of 0.93 (R-squared) between the cardiac intervals measured from the ViCG and ECG signals. Whereas, they are found to be 0.03 ms and 0.92 for the ViCG-PPG signal pair. They reveal a highly strong correlation and agreement for heart cycle estimation. The performance analysis suggest that the ViCG signal acquired through a simple MEMS-based accelerometer can be utilized as a surrogate of central blood flow measurement and may be employed for continuous health monitoring in personalized-, home-, and hospital-healthcare systems.
As a vital risk stratification tool, heart rate variability (HRV) has the ability to provide early warning signs for many life-threatening diseases. This paper presents a study on reliable cardiac cycle extraction and HRV measurement with a seismocardiographic (SCG) method. Like R-peaks in an ECG, the proposed method relies on peaks corresponding to aortic valve opening (AO) instants in an SCG signal. Due to better reliability and accessibility, the SCG signal is selected for the study. Initially, the prominent AO peaks in an SCG signal are estimated using our previously proposed modified variational mode decomposition (MVMD) based approach. In the present method, the detection performance of AO peaks is improved by employing a decision-rule-based post-processing scheme. Subsequently, tachogram of AO–AO intervals is used for the estimation of HRV parameters. A set of real-time signals collected in various physiological conditions and the SCG signals taken from a publicly available standard database are used to test and validate the proposed method. Experimental results clearly tell that the cardiac intervals obtained from the SCG signal using the proposed method can be used for HRV analysis. Also, the resulted parameters of HRV analysis on ECG and SCG exhibit strong correlation and agreement that shows the effectiveness of the proposed method.
In this work, a seismocardiogram (SCG) based breathing-state measuring method is proposed for m-health applications. The aim of the proposed framework is to assess the human respiratory system by identifying degree-of-breathings, such as breathlessness, normal breathing, and long and labored breathing. For this, it is needed to measure cardiac-induced chest-wall vibrations, reflected in the SCG signal. Orthogonal subspace projection is employed to extract the SCG cycles with the help of a concurrent ECG signal. Subsequently, fifteen statistically significant morphological-features are extracted from each of the SCG cycles. These features can efficiently characterize physiological changes due to varying respiratory-rates. Stacked autoencoder (SAE) based architecture is employed for the identification of different respiratory-effort levels. The performance of the proposed method is evaluated and compared with other standard classifiers for 1147 analyzed SCG-beats. The proposed method gives an overall average accuracy of 91.45% in recognizing three different breathing states. The quantitative analysis of the performance results clearly shows the effectiveness of the proposed framework. It may be employed in various healthcare applications, such as pre-screening medical sensors and IoT based remote health-monitoring systems.

Lab head

L.N. Sharma
  • Department of Electronics and Electrical Engineering (EEE)
About L.N. Sharma
  • L.N. Sharma currently works at the Department of Electronics and Electrical Engineering (EEE), Indian Institute of Technology Guwahati. Their current project is 'Cardiac Pathology and Signal Processing.'

Members (23)

Rohit Sinha
  • Indian Institute of Technology Guwahati
S. Dandapat
  • Indian Institute of Technology Guwahati
M. Sabarimalai Manikandan
  • Indian Institute of Technology Bhubaneswar
S. R. Nirmala
  • Gauhati University
Anil Mahanta
  • Indian Institute of Technology Guwahati
Krishnamoorthy Palanisamy
  • Philips Research India
Vikram C M
  • Arizona State University
Tilendra Choudhary
  • Emory University
A. K. Gogoi
A. K. Gogoi
  • Not confirmed yet
G. Siva Reddy
G. Siva Reddy
  • Not confirmed yet
Puspanjali Sharma
Puspanjali Sharma
  • Not confirmed yet