Projekt

Obecné

Profil

Application predicting class attendance based on weather » Historie » Revize 2

Revize 1 (Alex Konig, 2021-03-18 18:45) → Revize 2/20 (Alex Konig, 2021-03-18 22:57)

h1. Application predicting class attendance based on weather 

 h2. Data 

 Application uses datasets containing historical information about weather on campus and attendance based on JIS card verifications and historical timetable informations 
 * JIS data http://opendata.zcu.cz/Snimace-JIS.html 
 * Timetable data http://opendata.zcu.cz/Obsazeni-mistnosti.html 
 * Weather data http://opendata.zcu.cz/Energeticky-dispecink.html 

 -> rozvrh udává kolik lidí tam mělo bejt, plus vzít JISky kolik tam bylo (-> můžu mít procentuelní zastoupení) / ?autentizační systém kolik lidí se přihlásilo na pc? 

 h3. Weather 

 Weather data for model trainig contains following information: date, temperature, wind, rain, light in k lux 

 User can input weather values manually, by selecting options from a form 
 * values: temperature, wind, rain, sunny/overcast/partly cloudy 
 There also is an option for data to be automatically downloaded from a server upon request from user 

 Current options for data sources 
 * RSS from yr.no http://www.kanonbra.com/rss/yr_forecast_rss.php?language=en_US&location=%C4%8Ceahkka/Plze%C5%88sk%C3%BD_Kraj/Plze%C5%88 
 * RSS from yahoo weather (might be a problem with authorisation) https://www.yahoo.com/news/weather/czech-republic/plze%C5%88sk%C3%BD/plze%C5%88-796166/ 
 * json from wttr.in http://wttr.in/Plzen,czechia?format=j1 
 App provides the ability to ask for data from today or days in future, and give hourly time specifics (this time will be then approximated into values morning, noon, afternoon, night) 
 Again the app will use the following values: temperature, wind, rain, sunny/overcast/partly cloudy 

 Notes: 
 Values sunny/overcast/partly cloudy will be translated into lux values 
 Temperature will be evaluated with certain tolerance (probably determined experimentally) 


 h3. Datasets 

 Datasets are updated every once in a while - updating with new data. How often update? data from zcu open data servers 
 -> has to trigger re-training the prediction model, probably do not want to update too often. 
 Detect when - how often? if there's new data, check every day? something new? every x days? 

 h2. Motivation 

 TBD 

 h2. Implementation 

 The application is a mobile app, possibly webgl app 
 It is developed in unity which provides more possibilities for export with modifications for given platforms 

 - prediction model (pluses and minuses ?) 
	 - neuron network 
	 - bayes