Project..

My All project Link:..

.All project link 


●    NewsNet: a hybrid CNN and RNN based model to categories Bangla Newspaper (To be submitted soon, therefore code is not available yet)

NewsNet is an innovative model we have developed for categorizing Bangla newspapers. Leveraging a hybrid approach using Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), the model ensures robust and accurate classification.

Tools: CNN, RNN, Embedding Layer,NLP,Deep Learning

●       Sentiment analysis on coronavirus-related tweets from a Kaggle dataset by utilizing Word2Vec embeddings with ML models (link)

I performed sentiment analysis on coronavirus-related tweets from a Kaggle dataset, utilizing Word2Vec embeddings with ML models like XGBoost, SVM, Random Forest, and Logistic Regression. Model performance was evaluated using metrics like accuracy, confusion matrices, and classification reports to discern sentiment in the tweet.

Tools: XGBoost, SVM, Random Forest, and Logistic Regression, Embedding Layer, Sentiment analysis

●       Automated Bangla News Classification: A Machine Learning Approach(link)

Utilizing XGBoost for pattern recognition, SVM for non-linear relationships, and an ensemble of Random Forest, AdaBoost, and Logistic Regression, my Bangla news categorization achieves precision through diverse modeling. This comprehensive approach ensures accurate classification, capturing linguistic nuances and cultural references in Bangla news articles.

 

Tools: Random Forest, XGBoost, SVM, and Logistic Regression, Embedding Layer

●       Fine-Tuning BERT for E-commerce Text Classification: A Multi-category Approach (link)

In this project, we leverage the power of the BERT (Bidirectional Encoder Representations from Transformers) model for fine-tuned multi-category text classification in the context of E-commerce. Through the fine-tuning process, we train the BERT model to capture nuanced features and context-specific information present in E-commerce texts.

 

Tools: ML, BERT, LLM, Preprocessing, Neural network, text classification

●       Web-ML Diabetes Predictor: Empowering Health Awareness Online (Link)

In this project, I have deployed machine model in Django to create a robust a web application for diabetics prediction. The system employs advanced machine learning techniques to analyze these features and provide personalized predictions, empowering users to take proactive steps towards managing their health and reducing the risk of diabetes-related complications.

Tools: HTML, CSS, JavaScript, Django, Machine Learning model

●       AI -based web system for Male female prediction (link)

I've created an AI-powered web app for gender prediction, utilizing multiple ML models within the Django framework. The application, enhanced with HTML, CSS, and JavaScript, delivers a seamless and intuitive experience for predicting gender based on input data.

Tools: TensorFlow, HTML, CSS, Java script, Machine learning models, React js,Django and MySQL





OOP project..

Data structure project...

1.https://sites.google.com/diu.edu.bd/ms-for-volunteer/home