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
Fast Python Collaborative Filtering for Implicit Feedback Datasets

Implicit Fast Python Collaborative Filtering for Implicit Datasets. This project provides fast Python implementations of several different popular rec

Ben Frederickson 3k Dec 31, 2022
A Python implementation of LightFM, a hybrid recommendation algorithm.

LightFM Build status Linux OSX (OpenMP disabled) Windows (OpenMP disabled) LightFM is a Python implementation of a number of popular recommendation al

Lyst 4.2k Jan 02, 2023
Spark-movie-lens - An on-line movie recommender using Spark, Python Flask, and the MovieLens dataset

A scalable on-line movie recommender using Spark and Flask This Apache Spark tutorial will guide you step-by-step into how to use the MovieLens datase

Jose A Dianes 794 Dec 23, 2022
The source code for "Global Context Enhanced Graph Neural Network for Session-based Recommendation".

GCE-GNN Code This is the source code for SIGIR 2020 Paper: Global Context Enhanced Graph Neural Networks for Session-based Recommendation. Requirement

98 Dec 28, 2022
Recommender systems are the systems that are designed to recommend things to the user based on many different factors

Recommender systems are the systems that are designed to recommend things to the user based on many different factors. The recommender system deals with a large volume of information present by filte

Happy N. Monday 3 Feb 15, 2022
Temporal Meta-path Guided Explainable Recommendation (WSDM2021)

Temporal Meta-path Guided Explainable Recommendation (WSDM2021) TMER Code of paper "Temporal Meta-path Guided Explainable Recommendation". Requirement

Yicong Li 13 Nov 30, 2022
Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

57 Nov 03, 2022
Detecting Beneficial Feature Interactions for Recommender Systems, AAAI 2021

Detecting Beneficial Feature Interactions for Recommender Systems (L0-SIGN) This is our implementation for the paper: Su, Y., Zhang, R., Erfani, S., &

26 Nov 22, 2022
Collaborative variational bandwidth auto-encoder (VBAE) for recommender systems.

Collaborative Variational Bandwidth Auto-encoder The codes are associated with the following paper: Collaborative Variational Bandwidth Auto-encoder f

Yaochen Zhu 14 Dec 11, 2022
Real time recommendation playground

concierge A continuous learning collaborative filter1 deployed with a light web server2. Distributed updates are live (real time pubsub + delta traini

Mark Essel 16 Nov 07, 2022
This library intends to be a reference for recommendation engines in Python

Crab - A Python Library for Recommendation Engines

Marcel Caraciolo 85 Oct 04, 2021
Code for ICML2019 Paper "Compositional Invariance Constraints for Graph Embeddings"

Dependencies NOTE: This code has been updated, if you were using this repo earlier and experienced issues that was due to an outaded codebase. Please

Avishek (Joey) Bose 43 Nov 25, 2022
Codes for AAAI'21 paper 'Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation'

DHCN Codes for AAAI 2021 paper 'Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation'. Please note that the default link

Xin Xia 124 Dec 14, 2022
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

Annoy Annoy (Approximate Nearest Neighbors Oh Yeah) is a C++ library with Python bindings to search for points in space that are close to a given quer

Spotify 10.6k Jan 01, 2023
Elliot is a comprehensive recommendation framework that analyzes the recommendation problem from the researcher's perspective.

Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation

Information Systems Lab @ Polytechnic University of Bari 215 Nov 29, 2022
Movie Recommender System

Movie-Recommender-System Movie-Recommender-System is a web application using which a user can select his/her watched movie from list and system will r

1 Jul 14, 2022
RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation

RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation Pytorch based implemention of Relational Temporal

28 Dec 28, 2022
The official implementation of "DGCN: Diversified Recommendation with Graph Convolutional Networks" (WWW '21)

DGCN This is the official implementation of our WWW'21 paper: Yu Zheng, Chen Gao, Liang Chen, Depeng Jin, Yong Li, DGCN: Diversified Recommendation wi

FIB LAB, Tsinghua University 37 Dec 18, 2022
It is a movie recommender web application which is developed using the Python.

Movie Recommendation 🍿 System Watch Tutorial for this project Source IMDB Movie 5000 Dataset Inspired from this original repository. Features Simple

Kushal Bhavsar 10 Dec 26, 2022
This is our implementation of GHCF: Graph Heterogeneous Collaborative Filtering (AAAI 2021)

GHCF This is our implementation of the paper: Chong Chen, Weizhi Ma, Min Zhang, Zhaowei Wang, Xiuqiang He, Chenyang Wang, Yiqun Liu and Shaoping Ma. 2

Chong Chen 53 Dec 05, 2022