Name: PRASANJIT DEY
Type: User
Company: SFI Centre for Research Training in Digitally-Enhanced Reality (d-real) at TU Dublin
Bio: My area of interest Deep Learning, Machine Learning and Computer Vision
Location: Dublin, Ireland
Blog: https://prasanjit-dey.github.io/
PRASANJIT DEY's Projects
Welcome to quote our published papers, and the codes have been uploaded.
Time Series Analysis of Air Pollutants(PM2.5) using LSTM model
I predict air quality index of a city in China using a Long Short Term Memory (LSTM) neural network. for a year. Executed time series analysis
FuseDeepNet to predict PM2.5 concentration
COVID-19 prediction using ARIMA model
Cryptocurrency Price Prediction Using LSTM neural network
CO2 gas concentration prediction using LSTM model
We developed an IoT-based RFID card reader applied in taking attendance in school.
A wrapper layer for stacking layers horizontally
This is the official implementation for AAAI-23 paper "Are Transformers Effective for Time Series Forecasting?"
Repository for the medium article about data preprocessing
NO2 and CO concentration prediction.
The official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"
The fundamental package for scientific computing with Python.
Real-time object detects from video stitching, and the final result is shown in a web browser using generate URL.
Forecasting exchange rates by using commodities prices
long-short-term memory and a bidirectional gated recurrent unit (BiLSTM−BiGRU) to predict PM2.5 concentration
Prasanjit Dey Personal Website
In the project, we have preprocessed and cleaned the CSV data. Then cleaned dataset is used for machine learning model training and testing purposes.
Unofficial implementation of paper “Particle Swarm Optimization for Hyper-Parameter Selection in Deep Neural Networks” using Tensorflow/Keras
https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1
This page presents a list of satellite imagery datasets with a temporal dimension, mainly satellite image time series (SITS) and satellite videos, for various computer vision and deep learning tasks. It covers multi-temporal datasets with more than two acquisitions but not bi-temporal datasets.
Developed a novel algorithm to predict air pollution levels with state-of-art accuracy using deep learning and GoogleMaps satellite images