Md Rabiul Ali Sarker

Projects

Travel Assistant Project [Published in Sensors (IF: 3.576)]

A novel approach to navigation and mapping leverages the widespread availability of smartphones equipped with various sensors. The proposed system utilises data from the Accelerometer, Gyroscope, Magnetometer, and GPS in smartphones to generate detailed maps of routes and infrastructures.

Deep Learning-Based Automatic Malaria Parasite Detection from Blood Smear and Its Smartphone-Based Application [Published in Diagnostics (IF: 3.0)]

An automated Convolutional Neural Network (CNN)-based model designed for the diagnosis of malaria from microscopic blood smear images. The primary goal is to reduce the reliance on trained microscopists by leveraging modern deep-learning techniques for accurate and efficient diagnosis. The research employs various strategies, including knowledge distillation, data augmentation, and the use of Autoencoders for feature extraction, followed by classification through Support Vector Machines (SVM) or K-Nearest Neighbours (KNN).

DiChokro - An anti-theft system for bicycles

DiChokro is an affordable solution to tackle bicycle theft in developing countries. It includes a GPS-enabled device with a vibration sensor and processor, installed on the bicycle. The system connects to an Android app via the cloud, offering real-time tracking and secure parking location searches. With a production cost under $30, it ensures accessibility for a wide user base.

Pathik - Augmented Reality based travel application

The Pathik application is an Android-based mobile app that helps users discover and learn about nearby historical sites. Using the phone's GPS, the app locates historical places in the user's vicinity and displays them in a list. Users can select a location from the list to view detailed information and watch a short video about the site, enhancing their understanding of its historical significance.

Pattern-based digital lock system

The Project presents a digital pattern lock system designed for securing electronic devices like doors and safes. It uses a 3x3 keypad (keys 0 to 8) where each keypress is converted from decimal to a 4-bit binary code. A pattern matching unit compares the entered sequence with a stored password, and if matched, triggers an output to unlock the system. The circuit is synchronized with a clock signal for accurate input detection and includes a reset function to clear wrong entries. This design offers a simple yet secure solution by combining user-friendly input with efficient digital processing.