arpita739

arpita739

Bengali-and-Hindi-Signature-Verification-using-Convolution-Siamese-Network

Verification of off-line signatures is one of the most challenging tasks in biometrics and document forensic science. In this thesis, we deal with Convolutional Siamese Network model which is capable of doing verification of Bengali and Hindi Signature. One particular advantage of Siamese Neural networks is the ability to generalize to new classes that it has not been trained on, and in fact, the number of classes that it is expected to support does not have to be known at training time. Also, the architecture commonly known as the Siamese network helped reduce the amount of training data needed for its implementation. The twin networks with shared weights were trained to learn feature space where similar observations are placed in proximity. Writer Independent verification model has been designed where an accuracy of 91.82% has been obtained for Bengali Dataset and 84% for Hindi Dataset

Building-RNN-LSTM-and-GRU-for-time-series-using-PyTorch

COVID-19-Detection-from-Lung-CT-Scan-Images-using-Transfer-Learning-Approach

From the onset of 2020, Coronavirus disease (COVID-19) has rapidly accelerated worldwide into a stage of a severe pandemic. COVID-19 has infected more than 29 million people and caused more than 900 thousand deaths. Being highly contagious, it causes community transmission explosively. Thus, health care delivery has been disrupted and compromised by lack of testing kits. The COVID-19 infected patient shows severe acute respiratory syndrome. Meanwhile, the scientific community has been on a roll implementing Deep Learning techniques to diagnose COVID- 19 based on lung CT-scans, as computed tomography (CT) is a pertinent screening tool due to its higher sensitivity for recognizing early pneumonic changes. However, large dataset of CT-scan images are not publicly available due to privacy concerns and obtaining very accurate model becomes difficult. Thus to overcome this drawback, transfer learning pre-trained models are used to classify COVID-19 (+ve) and COVID-19 (-ve) patient in the proposed methodology. Including pre-trained models (DenseNet201, VGG16, ResNet50V2, MobileNet) as backbone, a deep learning framework is developed and named as KarNet. For extensive testing analysis of the framework, each model is trained on original (i.e., non-augmented) and manipulated (i.e., augmented) dataset. Among the four pre-trained models of KarNet, the one with DenseNet201 illustrated excellent diagnostic ability with an AUC score of 1.00 and 0.99 for models trained on non-augmented and augmented data set respectively. Even after considerable distortion of images (i.e., augmented dataset) DenseNet201 gained an accuracy of 97% on the testing set, followed by ResNet50V2, MobileNet, VGG16 (96%, 95% and 94% respectively).

Data-Science-Prediction-Models

In this repository you will find prediction model of different data sets taken from kaggle.com . I worked on mini Data science projects as a beginner. Hopefully this will be a stepping stone in my future career of persuing data science.

Data-Science-Project-on-Prediction-of-Bengaluru-Housing-Price

This data science project series walks through step by step process of how to build a real estate price prediction website. I will first build a model using sklearn and linear regression using bangaluru housing prices dataset from kaggle.com. Second step would be to write a python flask server that uses the saved model to serve http requests. Third component is the website built in html, css, bootstrap and javascript that allows user to enter home square ft area, bedrooms etc and it will call python flask server to retrieve the predicted price. During model building I will cover data science concepts such as data loading and cleaning, outlier detection and removal, feature engineering, dimensionality reduction, gridsearchcv for hyperparameter tunning, k fold cross validation etc.

Machine_Learning_Introductory

MNIST-Handwritten-Digit-Recognition-using-CNN

Real-time-Vernacular-Sign-Language-Recognition-using-MediaPipe-and-Machine-Learning

The deaf-mute community have undeniable communication problems in their daily life. Recent developments in artificial intelligence tear down this communication barrier. The main purpose of this paper is to demonstrate a methodology that simplified Sign Language Recognition using MediaPipe’s open-source framework and machine learning algorithm. The predictive model is lightweight and adaptable to smart devices. Multiple sign language datasets such as American, Indian, Italian and Turkey are used for training purpose to analyze the capability of the framework. With an average accuracy of 99%, the proposed model is efficient, precise and robust. Real-time accurate detection using Support Vector Machine (SVM) algorithm without any wearable sensors makes use of this technology more comfortable and easy.

Using-GAN-fill-missing-part-of-Handwritten-Digits

How to build a neural network to fill the missing part of a handwritten digit using GANs

arpita739/Data-Science-Project-on-Prediction-of-Bengaluru-Housing-Price

This data science project series walks through step by step process of how to build a real estate price prediction website. I will first build a model using sklearn and linear regression using bangaluru housing prices dataset from kaggle.com. Second step would be to write a python flask server that uses the saved model to serve http requests. Third component is the website built in html, css, bootstrap and javascript that allows user to enter home square ft area, bedrooms etc and it will call python flask server to retrieve the predicted price. During model building I will cover data science concepts such as data loading and cleaning, outlier detection and removal, feature engineering, dimensionality reduction, gridsearchcv for hyperparameter tunning, k fold cross validation etc.

arpita739/Bengali-and-Hindi-Signature-Verification-using-Convolution-Siamese-Network

Verification of off-line signatures is one of the most challenging tasks in biometrics and document forensic science. In this thesis, we deal with Convolutional Siamese Network model which is capable of doing verification of Bengali and Hindi Signature. One particular advantage of Siamese Neural networks is the ability to generalize to new classes that it has not been trained on, and in fact, the number of classes that it is expected to support does not have to be known at training time. Also, the architecture commonly known as the Siamese network helped reduce the amount of training data needed for its implementation. The twin networks with shared weights were trained to learn feature space where similar observations are placed in proximity. Writer Independent verification model has been designed where an accuracy of 91.82% has been obtained for Bengali Dataset and 84% for Hindi Dataset

arpita739/COVID-19-Detection-from-Lung-CT-Scan-Images-using-Transfer-Learning-Approach

From the onset of 2020, Coronavirus disease (COVID-19) has rapidly accelerated worldwide into a stage of a severe pandemic. COVID-19 has infected more than 29 million people and caused more than 900 thousand deaths. Being highly contagious, it causes community transmission explosively. Thus, health care delivery has been disrupted and compromised by lack of testing kits. The COVID-19 infected patient shows severe acute respiratory syndrome. Meanwhile, the scientific community has been on a roll implementing Deep Learning techniques to diagnose COVID- 19 based on lung CT-scans, as computed tomography (CT) is a pertinent screening tool due to its higher sensitivity for recognizing early pneumonic changes. However, large dataset of CT-scan images are not publicly available due to privacy concerns and obtaining very accurate model becomes difficult. Thus to overcome this drawback, transfer learning pre-trained models are used to classify COVID-19 (+ve) and COVID-19 (-ve) patient in the proposed methodology. Including pre-trained models (DenseNet201, VGG16, ResNet50V2, MobileNet) as backbone, a deep learning framework is developed and named as KarNet. For extensive testing analysis of the framework, each model is trained on original (i.e., non-augmented) and manipulated (i.e., augmented) dataset. Among the four pre-trained models of KarNet, the one with DenseNet201 illustrated excellent diagnostic ability with an AUC score of 1.00 and 0.99 for models trained on non-augmented and augmented data set respectively. Even after considerable distortion of images (i.e., augmented dataset) DenseNet201 gained an accuracy of 97% on the testing set, followed by ResNet50V2, MobileNet, VGG16 (96%, 95% and 94% respectively).

arpita739/arpita739

arpita739/Building-RNN-LSTM-and-GRU-for-time-series-using-PyTorch

arpita739/ColdEmailGenerator

Cold Email Generator using Groq, Llama model and ChromaDB

arpita739/Data-Analysis-using-Excel

arpita739/Data-Visualization-using-Tableau

arpita739/dataWeb.github.io

This is for creating GitHub page for MADE-Project(Data Science Salary Analysis)

arpita739/dicom_reader

lets you read DICOM files on a patient level with python

arpita739/Face-Recognition-using-OpenCV

arpita739/im4MEC

Code for the im4MEC model described in the paper 'Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts'.

arpita739/ImageAnalysis

arpita739/labelme

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

arpita739/llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

arpita739/LocalAIVoiceChat

Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.

arpita739/made-template

Template repository for the Methods of Advanced Data Engineering course at FAU

arpita739/meddlr_VORTEX

A flexible ML framework built to simplify medical image reconstruction and analysis experimentation.

arpita739/mediapipe

Cross-platform, customizable ML solutions for live and streaming media.

arpita739/natural-sql

A series of top performing Text to SQL LLMs

arpita739/NL2SQL-LLM

Using Large Language Models (LLMs) to convert natural language queries to sql

arpita739/Practice_Programming

arpita739/Python-Basics

Brush up your python programming basics before heading for machine learning. It consists of basics of python example : dictionaries,iterators,list etc.Do check this out for clearing your concepts of python

arpita739/PythonOOPConcepts

Hello, in this repository you will find ready to do object oriented programming using Python programming language. Code in this repository is not meant for beginners who want to learn from scratch. This code is intended for people who have basic knowledge of OOP concepts and have programming experience in any other language example: C++. You can learn programming using python by having a quick look in the repo, this repository is for people who don't want to read lots of articles or watch videos and directly, want to jump into coding. Leave a star if you like the repository. Thank you 😉

arpita739/quantum

Hybrid Quantum-Classical Machine Learning in TensorFlow

arpita739/Roadmap-To-Learn-Generative-AI-In-2024

Reference

arpita739/segmentation_models.pytorch

Segmentation models with pretrained backbones. PyTorch.

arpita739/SQL-Data-Analysis-and-Visualization-Projects

SQL data analysis & visualization projects using MySQL, PostgreSQL, SQLite, Tableau, Apache Spark and pySpark.

arpita739/T20-World-cup-2022-Cricket-Match-Analysis

End-To-End Data-Analysis project: Webscrapping, Data-Transformation and Data Visualization

arpita739/ticket-chat-ai