Swapnil Tiwari's repositories
Time-Series-And-Anomaly-Detection
In this repository, I have used ARIMA,SARIMA,AutoArima,ANN,CNN and LSTMs for time series modelling and Anomaly detection has been done using LSTM+Autoencoders.
Recommender-Systems-Using-ML-DL-And-Market-Basket-Analysis
This repository consists of collaborative filtering Recommender systems like Similarity Recommenders, KNN Recommenders, using Apple's Turicreate, A matrix Factorization system from scratch and a Deep Learning Recommender System which learns using embeddings. Besides this Market Basket Analysis using Apriori Algorithm has also been done. Deployment of Embedding Based Recommender Systems have also been done on local host using Streamlit, Fast API and PyWebIO.
Twitter-US-Airline-Sentiment-Analysis
In this repository I have utilised 6 different NLP Models to predict the sentiments of the user as per the twitter reviews on airline. The dataset is Twitter US Airline Sentiment. The best models each from ML and DL have been deployed. It employs text preprocessing,
Designing-P-PI-and-PID-Controllers-in-Python
This repository utilises python to design Proportional, PI and PID cntrollers in python and depicting their Peak Times, Maximum Overshoots and settling time using signal Processing and matlab libraries
COVID-19-Radiography-Results-Prediction-Using-CNNs
In this repository I have utilised Convolutional Neural Networks to predict whether the images detect a covid+ve patient, viral pneumonic patient and a normal patient. The dataset is Covid 19 Radiography Database which has been updated as on 5 January 2021
DPhi-Datathon-Data-Sprint-22-Concrete-Crack-Image-Classification-
I achieved 9th rank in the recently held DPhi Datathon for Concrete Crack Image Classification where I achieved an accuracy of 99.902% in the test dataset. Here I will share my approach with how I did that.
Topic-Classification-of-Dutch-News-Articles-using-Attention
Here, Heirarchial Attention Models have been employed to classify the Dutch news Articles with improved accuracy.