PUBLICATION

Estimating Blood Pressure from Photoplethysmogram Signal and Demographic Features using Machine Learning Techniques Estimating Blood

Key words: blood pressure; photoplethysmograph, feature selection algorithm; machine learning

Published in : Sensors (IF: 3.27)

Available Link: https://www.mdpi.com/1424-8220/20/11/3127

Hypertension is a potentially unsafe health ailment, which can be indicated directly from the blood pressure (BP). Hypertension always leads to other health complications. Continuous monitoring of BP is very important; however, cuff-based BP measurements are discrete and uncomfortable to the user. To address this need, a cuff-less, continuous, and noninvasive BP measurement system is proposed using the photoplethysmograph (PPG) signal and demographic features using machine learning (ML) algorithms. PPG signals were acquired from 219 subjects, which undergo preprocessing and feature extraction steps. Time, frequency, and time-frequency domain features were extracted from the PPG and their derivative signals. Feature selection techniques were used to reduce the computational complexity and to decrease the chance of over-fitting the ML algorithms. The features were then used to train and evaluate ML algorithms. The best regression models were selected for systolic BP (SBP) and diastolic BP (DBP) estimation individually. Gaussian process regression (GPR) along with the ReliefF feature selection algorithm outperforms other algorithms in estimating SBP and DBP with a root mean square error (RMSE) of 6.74 and 3.59, respectively. This ML model can be implemented in hardware systems to continuously monitor BP and avoid any critical health conditions due to sudden changes.

1. The Design of a Novel Multi-Purpose Fire Fighting Robot with Video Streaming Capability

Research key words: Fire-Fighting, Robot, Image Processing, Face Detection, Vacuum Fan, Water Pump nozzle, Camera, Arduino, cost effective, Radio Controller, Multi-Purpose

Published in: IEEE

Available Link: https://ieeexplore.ieee.org/document/9033931/

In this work we introduce a novel design of a multi-purpose fire-fighting robot which, with the help of a streaming video camera attached to it, transmits live video from its surroundings to a remote location from where the robot can be controlled. The robot can be mobilized and directed to the spot of the fire and throw water at the fire. It uses RF signal for communication and it is capable of performing three different functions related to firefighting operation. First, it can remove smoke from the location of fire using a suction vacuum fan and a cylinder attached to it, so people do not suffocate from smoke inhalation. Second, it takes continuous snaps of its surroundings to detect human faces using Viola-Jones face detection algorithm, so the rescue squad can know from a safe distance if there are trapped people who need to be rescued. Third, it can throw water at the fire at any angle using a rotating nozzle controlled by a remotely controlled servo motor. This multi-purpose fire-fighting robot is inexpensive but reliable. It can effectively reduce the human risk of fire-fighting operation. The design of the robot is cost effective, which makes it especially attractive for deployment in developing countries.