Projekt

Obecné

Profil

Upravit Historie

Wiki »

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

Alex Konig, 2021-03-18 22:57

1 1 Alex Konig 
h1. Application predicting class attendance based on weather
2 





    3
    
    
    
h2. Data





    4
    
    
    





    5
    
    
    
Application uses datasets containing historical information about weather on campus and attendance based on JIS card verifications and historical timetable informations





    6
    
    
    
* JIS data http://opendata.zcu.cz/Snimace-JIS.html





    7
    
    
    
* Timetable data http://opendata.zcu.cz/Obsazeni-mistnosti.html





    8
    
    
    
* Weather data http://opendata.zcu.cz/Energeticky-dispecink.html





    9
    
    
    





    10
    
    
    
-> 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?





    11
    
    
    





    12
    
    
    
h3. Weather





    13
    
    
    





    14
    
    
    
Weather data for model trainig contains following information: date, temperature, wind, rain, light in k lux





    15
    
    
    





    16
    
    
    
User can input weather values manually, by selecting options from a form





    17
    
    
    
* values: temperature, wind, rain, sunny/overcast/partly cloudy





    18
    
    
    
There also is an option for data to be automatically downloaded from a server upon request from user





    19
    
    
    





    20
    
    
    
Current options for data sources





    21
    
    
    
* 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





    22
    
    
    
* 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/





    23
    
    
    
* json from wttr.in http://wttr.in/Plzen,czechia?format=j1





    24
    
    
    
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)





    25
    
    
    
Again the app will use the following values: temperature, wind, rain, sunny/overcast/partly cloudy





    26
    
    
    





    27
    
    
    
Notes:





    28
    
    
    
Values sunny/overcast/partly cloudy will be translated into lux values





    29
    
    
    
Temperature will be evaluated with certain tolerance (probably determined experimentally)





    30
    
    
    





    31
    
    
    





    32
    
    
    
h3. Datasets





    33
    
    
    





    34
    2
    Alex Konig
    
Datasets are updated every once in a while with new data. How often update?





    35
    
    
    
-> has to trigger re-training the prediction model, probably do not want to update too often.





    36
    
    
    
Detect when there's new data, check every day? every x days?





    37
    1
    Alex Konig
    





    38
    
    
    
h2. Motivation





    39
    
    
    





    40
    
    
    
TBD





    41
    
    
    





    42
    
    
    
h2. Implementation





    43
    
    
    





    44
    
    
    
The application is a mobile app, possibly webgl app





    45
    
    
    
It is developed in unity which provides more possibilities for export with modifications for given platforms





    46
    
    
    





    47
    
    
    
- prediction model (pluses and minuses ?)





    48
    
    
    
	- neuron network





    49
    
    
    
	- bayes