Farhat Binte Azam's repositories
Heart-Rate-Monitoring-with-Emotion-Detection-using-PPG-GSR-Sensors
It's a wireless device to monitor the heart beat and emotion simultaneously. It takes PPG signal from PPG sensor and estimate the heart beat. It also takes GSR signal through GSR sensor at the same time and detect the emotion change. Through this wireless device we can also detect the heart beat dependency on emotion change. It is portable and work through Bluetooth.
VeinNET
This project is to detect the dorsal vein using an infrared illuminator and then enhancement of vein images is done by using different techniques for identifying the person. The proposed work is related to the implementation of Infrared vein detection and matching system for person identification.
Design-and-Implementation-of-a-MPPT-Charge-Controller-for-a-Standalon-PV-System
This project is mainly concerned with the utilization of such a system in order to achieve a controlled photo-voltaic power using MPPT mechanism. The main aim of this project was to track the maximum power point of the photo-voltaic module so that the maximum possible power can be extracted from the photo-voltaic systems by varying certain conditions in algorithm and set up mechanism. Finally the output data from this project was compared with the other MPPT algorithms in order to attain an improved performance hence a better MPPT system. Furthermore, the system was interfaced with GSM to get a better access of data from anywhere for analysis thus reducing the physical work of data collection.
Vehicle-Classifier
It is a project to classify vehicles. I have made my own data-set with 7000+ images. It has 91% accuracy in Train set and 89% accuracy in Test set.
five-video-classification-methods
Code that accompanies my blog post outlining five video classification methods in Keras and TensorFlow
Rescue-BOT
It is a mechanical system of four wheeled car with two artificial hands. It has also Raspberry pi with a Pi camera for Image Processing. The purpose of this project is to rescue human stuck in those places where no search and rescue team can approach. This BOT is built to go to those places all by own and capture a video of the stuck people through identifying human faces. It can also provide any kind of help to that needy people with his artificial hands. The hands are capable of movement with 3 DOF. It is totally a humanitarian project in the manner of rescuing the helpless people where human are unable to approach.
Video-Action-Transformer-Network-Pytorch-
Implementation of the paper Video Action Transformer Network
Bangla-Handwritten-Grapheme-Classification
Bengali is the 5th most spoken language in the world with hundreds of million of speakers. It’s the official language of Bangladesh and the second most spoken language in India. Considering its reach, there’s significant business and educational interest in developing AI that can optically recognize images of the language handwritten. This challenge hopes to improve on approaches to Bengali recognition.
CepsNET
We propose to use a fusion of Mel-Frequency Cepstral Coefficients (MFCC) and its variants as the input to a 2D-Residual Neural Network architecture to address the presence of channel and additive noise distortion simultaneously.
Classifying-stages-in-the-gonotrophic-cycle-of-mosquitoes
We have designed computer vision techniques to determine stages in the gonotrophic cycle (unfed, fully fed, semi-gravid and gravid)) of female mosquitoes (*Aedes aegypti, Anopheles stephensi, and Culex quinquefasciatus*) from images captured by smartphones.
Mark-NET
This purpose of this repository is to detect abnormal marks on images which is not seen while training.
mosquitoAI
MosquitoAI is an innovative initiative dedicated to developing AI-powered systems tailored for classifying various aspects of mosquito biology, including genus, species, instar, and gender. By leveraging advanced AI techniques, MosquitoAI seeks to provide valuable tools for mosquito surveillance and control, preventing mosquito-borne diseases.
RoboKitchen-Task-Tree-Retrieval
we optimize culinary processes through the use of Functional Object-Oriented Network (FOON) and leveraging Iterative Deepening Search (IDS) and Greedy Best-First Search (GBFS) guided by heuristic functions, we extract task trees for various dishes, seeking to improve the efficiency and accuracy of culinary operations
CrowdNET
CrowdNET
graphemePrepare
Handwritten Bengali Graphemes. Ground Truth and Extraction.
heartnet
Stethoscope Invariant Heart Sound Abnormality Detection