Amiruzzaman's repositories
Face-Recognition-Based-Attendance
The Face Recognition Based Attendance System uses face recognition technology to automate student attendance tracking in educational institutions. It captures live video or images, matches them against a registered database of faces, and marks attendance in real-time.
Cyberbullying-Detection-Arabic
Cyberbullying Detection App tailored for the Arabic language. The app is designed to identify instances of cyberbullying in Arabic text using various machine learning and deep learning algorithms.
ECG-Classification-Project
his project involves the classification of ECG (Electrocardiogram) readings to determine whether they are normal or abnormal. The dataset consists of rows, each representing a complete ECG of a patient with 140 data points (readings).
Cyberbullying-Detection-English
A Cyberbullying Detection App designed to identify instances of cyberbullying in English text. The app incorporates a diverse set of machine learning and deep learning algorithms, including BERT, Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), Multi-Layer Perceptron (MLP), and others.
Movie-Ticket-Booking
The POS application includes a secure sign-up and sign-in process, storing admin data in a database for validation. Admin can add movies with details like title, genre, duration, and release date, and view existing movies. Ticket purchases are categorized by age groups, with varying prices, and customer transaction details are stored in database.
Bengali-License-Plate-Detection
Bengali License Plate Detection with YOLO (You Only Look Once) is a computer vision task that focuses on the automatic detection and localization of license plates in images or video frames written in the Bengali language.
Bengali-License-Plate-Reading
Bengali License Plate Reading with EasyOCR is a technology that utilizes the EasyOCR library to extract and interpret license plate information from vehicles registered in the Bengali language. EasyOCR is an open-source optical character recognition (OCR) tool that is specifically designed for reading text in various languages, including Bengali.
Cyberbullying-Detection-Bangla
This repository is dedicated to advancing the field of cyberbullying detection in the Bangla language through the development and thorough evaluation of machine learning and deep learning models. Cyberbullying poses a significant challenge in the digital landscape, and this project aims to provide effective tools for identifying.
Heart-Disease-Classifications
This project involves a classification task using various machine learning algorithms on a heart disease dataset. The dataset comprises features related to heart health, with the target variable indicating the presence or absence of heart disease.
Q-A-Model-Bert-Base-Cased
The Question Answering Model presented in this repository is built on BERT (Bidirectional Encoder Representations from Transformers), a state-of-the-art transformer-based architecture tailored for natural language processing tasks.
Vehicle-Detection-from-Traffic
The vehicle detection project competed in YOLO (You Only Look Once), a real-time object detection system. Using Python, the project aimed to accurately detect and classify vehicles in various scenarios. It involved collecting and annotating a dataset, implementing the YOLO architecture, and fine-tuning the model using transfer learning.
Cyberbullying-Detection-Hinglish
Cyberbullying Detection App specifically designed for the Hinglish language, which is a combination of Hindi and English. The application utilizes various machine learning and deep learning algorithms fine-tuned for natural language processing and classification tasks.
Distil-Bert
DistilBERT, a distilled version of BERT (Bidirectional Encoder Representations from Transformers). DistilBERT is known for its efficiency and reduced computational requirements while retaining significant language understanding capabilities.
Doc-Bot
DocBot, an intelligent conversational agent designed to excel in recognizing and addressing medical inquiries within its specialized domain. Trained on a diverse dataset encompassing diseases like cancer, diabetes, and heart attack, DocBot is tailored to provide valuable insights and engaging responses in the field of health.
Face-Recognition-Login
The login system utilizes face recognition technology for registration and login. It captures and stores facial data, allowing users to authenticate by matching their faces with the registered data. This secure and convenient approach eliminates the need for passwords and offers scalability for a large user base.
History-Bot
HistoryBot is a virtual assistant specializing in historical inquiries. Trained on the intents.json dataset, it is adept at recognizing and responding to a variety of historical questions within its training data's scope. With regular updates, HistoryBot ensures an adaptable and enriching user experience.
Idiom-Detection-NLP
This project pioneers advancements in Natural Language Processing (NLP) by introducing a deep neural network approach to address challenges in interpreting multi-word sentences, detecting idioms, and classifying text. Focusing on text classification, it evaluates various models, with BERT outperforming others with an F1 score of 0.7980.
Otp-Sign-In
The sign-up or login process with OTP created using PHP and PHP Mailer is a secure authentication method. Users register with their details, and PHP generates a random OTP associated with their email.
Parkinson-Disease-Detection
The Parkinson's Disease Detection project utilizes the Oxford Parkinson's Disease dataset with 197 instances and 23 real-valued attributes. Conducting classification tasks, the project employs machine learning models to discriminate between healthy individuals and those with Parkinson's disease.
POS-Site
It is a POS website created by using PHP and JavaScript. It offers functionalities such as company creation, product addition, order placement, and order viewing by date, year, month, and search. The website aims to streamline business operations and improve efficiency in managing companies, products, and orders.
Q-A-Model-Bert-Base-Cased-Squad2
BERT (Bidirectional Encoder Representations from Transformers) known as "Q-A-Model-Bert-Base-Cased-Squad2." BERT, originally proposed by Google, is renowned for its remarkable advancements in Natural Language Processing (NLP) due to its bidirectional contextual awareness.
Q-A-Model-Bert-Large-Uncased
BERT (Bidirectional Encoder Representations from Transformers) known as "bert-large-uncased-whole-word-masking-finetuned-squad." BERT, originally proposed by Google, is renowned for its remarkable advancements in Natural Language Processing (NLP) due to its bidirectional contextual awareness.
Report-Case
Android application designed to provide a user-friendly platform for victims to report cases seamlessly. It aims to be an inclusive tool, accommodating various cases that victims might encounter.
Unity-Based-2D-Game
The 2D Unity game created for this project utilizes voice recognition technology to enable players to control the game using their voice. It also supports keyboard controls. Unity's user-friendly interface and versatile features make it an ideal choice for developing games.
YAFS
Yet Another Fog Simulator (YAFS)