Application predicting class attendance based on weather » Historie » Revize 3
Revize 2 (Alex Konig, 2021-03-18 22:57) → Revize 3/20 (Roman Kalivoda, 2021-03-19 11:51)
h1. Application predicting class attendance based on weather h2. Data The application Application uses datasets containing historical information about the weather on campus and attendance based on JIS card verifications and historical timetable information 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 training trainig contains the 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 the 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 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 The temperature Temperature will be evaluated with certain tolerance (probably determined experimentally) h3. Datasets Datasets are updated every once in a while with new data. How often update? -> has to trigger re-training the prediction model, probably do not want to update too often. Detect when there's new data, check every day? every x days? h2. Design h3. The output of the Algorithm We need to determine what should be the actual prediction: * A concrete number of students in a class, * information about relative occupancy rate. h2. Motivation TBD h2. Implementation The application is a mobile app, possibly WebGL 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