RESEARCH

Classification of healthy and impaired gaits using 3D-Ground Reaction Force (GRF) signals

Visualization of 3D-GRF data collection from force plate with their signal during the stance phase of healthy Gait. “Heel-strike (HS): The initial contact of one foot with the ground, also known as HS, represents the start of the gait cycle. When the center of mass is immediately above the ankle joint center, it is called midstance. During the stance phase, toe-off occurs as the final point of contact”.

Machine Learning for Healthcare

Estimation of Blood Pressure and Respiration rate from PPG Waveform

The objective is to develop novel feature extraction and machine learning model to continuous monitoring of Blood Pressure and Respiration rate. PPG signals will first assess to check signal quality and then randomly divide into two sets. 80% of the data use for training and validation and 20% of the data use for testing the performance of the model. The PPG signals need to preprocess before they were sent for feature extraction. After extracting meaningful features, feature selection techniques will be used to reduce computational complexity and the chance of over-fitting the algorithm. The features will then use to train machine learning algorithms. The best regression model will be selected for Blood Pressure and Respiration estimation individually. We collaborate with several institutions in the Qatar and Malaysia in this particular direction.

Emotion Recognition from PPG waveform

Data Informed Modelling

Dynamic Mode Decomposition
Eigensystem Realization Algorithm
Reduced Order Model

Eigensystem Realization Algorithm (ERA) and Dynamic Mode Decomposition Mode (DMD) are the tool that can produce a reduced order model (ROM) from just input-output data of a given system. We plan to work on a survey of all the techniques and apply them on an array of synthetic and practical data and finally weigh the pros and cons of each technique.

Undergraduate Senior Design Project

Smart Voting System (Duration of the project: 8 month)

Focusing on complete transparency with maximum security a novel type of advanced electronic voting system is introduced in this paper. Identification and verification of voters are assured by microchip embedded National Identity (NID) card and Biometric Fingerprint technology, which is unique for every single voter. Also with the help of live image processing technology, this system becomes more secure and effective. As voting is an individual opinion among multiple, so the second influence is unacceptable. So while voting if multiple faces detected by the camera module of the voting machine, automatically the vote will not be counted. Viola-Jones algorithm for face detection and Local Binary Pattern Histogram (LBPH) algorithm for face recognition has begun the image preparing innovation increasingly exact and faster. Four connected machines work together to accumulate each successful vote in this system. To reduce corrupted situation and to recapture the faith of mass people on the election, this inexpensive and effective system can play a vital role.

Undergraduate Junior Design Project

Multi-Purpose Fire Fighting Robot (Duration of the project: 4 month)

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.

Page updated

Google Sites