Respiratory Health Recommendation System

Overview

Respiratory-Health-Recommendation-System

Respiratory Health Recommendation System based on Air Quality Index Forecasts

This project aims to provide predictions and visualization of Air Quality Index across 100 counties in United States. Air quality index or AQI forecasts are important as it’s one of the most useful measure of air quality calculated from different pollutant concentrations in the air. Currently there are websites providing AQI forecasts but do not provide customized health recommendations. Using this product, Individuals can take appropriate preventive measures based on our recommendations and public authorities can use AQI forecasts to make decisions for policy making, urban planning and well-being of public health. The project is an end to end product that creates forecasts, provides visualizations, and delivers personalized health recommendations.

BigQuery database with an API was used to download EPA data as well as OpenWeatherMap API to compile the last 11 years of data for 6 key atmospheric pollutants which are CO, NO2, PM2.5, PM10, SO2, and O3.

Data was cleaned for missing values. First rolled up data to county level from site level through max aggregation and used time series interpolation to fill in the possible missing values. Afterwards, we were finally able to select 100 counties across US which ensured enough data to effectively allow for model building. The individual pollutants time series data was merged with temperature, pressure, relative humidity, and windspeed to take climate conditions into account as well. As the final data consists of 11 years of data for 100 counties, there are around half a million observation points with 20 columns.

VAR(vector autoregression) has been used which being a multivariate approach, should capture the complexities in the models. Through VAR, novel geospatial effects have also been incorporated in our models, for which we added 5 neighbor counties data for each county for every day.

Thus were created 100 models one for each county using VAR. Best models have been selected using optimum lag(number of past days data to be used into a model) based on AIC and BIC values which were then used to forecast respective pollutant concentration Data and ultimately AQI.

Results were evaluated using Root Mean Square Error values and found out that forecasts are within acceptable error range for most of the counties. VAR is definitely an improvement over ARIMA and further hyper parameter tuning in conjunction with the availability of more recent data will even further improve the quality of forecasts.

Based on our merged and forecast datasets, we have created interactive visualisations, to see the past 11 years trends, and forecasts. Users can choose from 1 to 6 pollutants, data range and counties as per requirement.

Owner
Abhishek Gawabde
Abhishek Gawabde
An Efficient and Effective Framework for Session-based Social Recommendation

SEFrame This repository contains the code for the paper "An Efficient and Effective Framework for Session-based Social Recommendation". Requirements P

Tianwen CHEN 23 Oct 26, 2022
An open source movie recommendation WebApp build by movie buffs and mathematicians that uses cosine similarity on the backend.

Movie Pundit Find your next flick by asking the (almost) all-knowing Movie Pundit Jump to Project Source » View Demo · Report Bug · Request Feature Ta

Kapil Pramod Deshmukh 8 May 28, 2022
Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks

SR-HGNN ICDM-2020 《Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks》 Environments python 3.8 pytorch-1.6 DGL 0.5.

xhc 9 Nov 12, 2022
NVIDIA Merlin is an open source library designed to accelerate recommender systems on NVIDIA’s GPUs.

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in

420 Jan 04, 2023
Mutual Fund Recommender System. Tailor for fund transactions.

Explainable Mutual Fund Recommendation Data Please see 'DATA_DESCRIPTION.md' for mode detail. Recommender System Methods Baseline Collabarative Fiilte

JHJu 2 May 19, 2022
This is our Tensorflow implementation for "Graph-based Embedding Smoothing for Sequential Recommendation" (GES) (TKDE, 2021).

Graph-based Embedding Smoothing (GES) This is our Tensorflow implementation for the paper: Tianyu Zhu, Leilei Sun, and Guoqing Chen. "Graph-based Embe

Tianyu Zhu 15 Nov 29, 2022
[ICDMW 2020] Code and dataset for "DGTN: Dual-channel Graph Transition Network for Session-based Recommendation"

DGTN: Dual-channel Graph Transition Network for Session-based Recommendation This repository contains PyTorch Implementation of ICDMW 2020 (NeuRec @ I

Yujia 25 Nov 17, 2022
A TensorFlow recommendation algorithm and framework in Python.

TensorRec A TensorFlow recommendation algorithm and framework in Python. NOTE: TensorRec is not under active development TensorRec will not be receivi

James Kirk 1.2k Jan 04, 2023
Recommendation System to recommend top books from the dataset

recommendersystem Recommendation System to recommend top books from the dataset Introduction The recom.py is the main program code. The dataset is als

Vishal karur 1 Nov 15, 2021
Use Jupyter Notebooks to demonstrate how to build a Recommender with Apache Spark & Elasticsearch

Recommendation engines are one of the most well known, widely used and highest value use cases for applying machine learning. Despite this, while there are many resources available for the basics of

International Business Machines 793 Dec 18, 2022
A tensorflow implementation of the RecoGCN model in a CIKM'19 paper, titled with "Relation-Aware Graph Convolutional Networks for Agent-Initiated Social E-Commerce Recommendation".

This repo contains a tensorflow implementation of RecoGCN and the experiment dataset Running the RecoGCN model python train.py Example training outp

xfl15 30 Nov 25, 2022
ToR[e]cSys is a PyTorch Framework to implement recommendation system algorithms

ToR[e]cSys is a PyTorch Framework to implement recommendation system algorithms, including but not limited to click-through-rate (CTR) prediction, learning-to-ranking (LTR), and Matrix/Tensor Embeddi

LI, Wai Yin 90 Oct 08, 2022
Graph Neural Networks for Recommender Systems

This repository contains code to train and test GNN models for recommendation, mainly using the Deep Graph Library (DGL).

217 Jan 04, 2023
A PyTorch implementation of "Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information" (WSDM 2021)

FairGNN A PyTorch implementation of "Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information" (

31 Jan 04, 2023
Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems

DANSER-WWW-19 This repository holds the codes for Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recom

Qitian Wu 78 Dec 10, 2022
A Library for Field-aware Factorization Machines

Table of Contents ================= - What is LIBFFM - Overfitting and Early Stopping - Installation - Data Format - Command Line Usage - Examples -

1.6k Dec 05, 2022
Plex-recommender - Get movie recommendations based on your current PleX library

plex-recommender Description: Get movie/tv recommendations based on your current

5 Jul 19, 2022
Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks

Bi-TGCF Tensorflow Implementation of BiTGCF: Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks. in CIKM20

17 Nov 30, 2022
Cross-Domain Recommendation via Preference Propagation GraphNet.

PPGN Codes for CIKM 2019 paper Cross-Domain Recommendation via Preference Propagation GraphNet. Citation Please cite our paper if you find this code u

Information Retrieval Group, Wuhan University, China 20 Dec 15, 2022
RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems

RecSim NG, a probabilistic platform for multi-agent recommender systems simulation. RecSimNG is a scalable, modular, differentiable simulator implemented in Edward2 and TensorFlow. It offers: a power

Google Research 110 Dec 16, 2022