BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//TUC//Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Athens
TZNAME:EEST
DTSTART:19700329T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0300
TZNAME:EET
DTSTART:19701025T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CREATED:20221013T084720Z
LAST-MODIFIED:20221013T084720Z
DTSTAMP:20260510T085037Z
UID:1778392237@tuc.gr
SUMMARY:Παρουσίαση Διπλωματικής Εργασίας κ. 
 Ρεντζεπόπουλου Αθανασίου - Σχολή ΗΜΜ
 Υ
LOCATION:
DESCRIPTION:https://www.tuc.gr/el/to-polytechnei
 o/ilektronikes-ypiresies/imerologio/
 imerologio-ekdiloseon-1?tx_tucevents
 2_tuceventsdisplay%5Baction%5D=show&
 tx_tucevents2_tuceventsdisplay%5Bcon
 troller%5D=Event&tx_tucevents2_tucev
 entsdisplay%5Bevent%5D=5838&cHash=ca
 431d7c8ed62b080054e3cc19cd5882\nΠΟΛΥ
 ΤΕΧΝΕΙΟ ΚΡΗΤΗΣ\n Σχολή Ηλεκτρολόγων 
 Μηχανικών και Μηχανικών Υπολογιστών\
 n Πρόγραμμα Προπτυχιακών Σπουδών\n Π
 ΑΡΟΥΣΙΑΣΗ ΔΙΠΛΩΜΑΤΙΚΗΣ ΕΡΓΑΣΙΑΣ\n ΑΘ
 ΑΝΑΣΙΟΥ ΡΕΝΤΖΕΠΟΠΟΥΛΟΥ\n με θέμα\n Π
 λατφόρμα αξιολόγησης αλγορίθμων συμπ
 ερασμού με δεδομένα από δίκτυα αισθη
 τήρων\n A platform to benchmark infe
 rence algorithms based on sensor net
 work data\n Εξεταστική Επιτροπή\n Κα
 θηγητής Άγγελος Μπλέτσας (επιβλέπων)
 \n Αναπληρωτής Καθηγητής Βασίλειος Σ
 αμολαδάς\n Καθηγητής Γεώργιος Καρυστ
 ινός\n \nAbstract\n This work offers
  an online tool to perform inference
  on sensor network (e.g. soil moistu
 re) measurements/data. The design pr
 oblem is approached by creating a we
 b-based user interface (UI) applicat
 ion based on microservices with a sc
 alable back-end that runs the algori
 thms and a database storage. Algorit
 hms are expected to be Python script
 s developed offline and tested eithe
 r offline or online. This multi-moda
 l operation poses a compatibility co
 ncern. We create a library that excl
 usively handles data input and outpu
 t for the scripts that import it. We
  create different variations of the 
 library depending on the context of 
 the user scripts. We also explore a 
 powerful way of executing scripts, i
 n the back-end of the web app, allow
 ing for robust interruption of runni
 ng scripts and parallel execution. T
 he user experience is also accounted
  for, with responsive web UI and sou
 rce code analysis to automatically f
 ind out the number and type of input
  streams. Finally, we test the syste
 m by utilizing the library to parse 
 and pre-process data and implement a
 n inference algorithm to run on the 
 pre-processed data. A demo on large-
 scale soil moisture data is also pro
 vided.\n
STATUS:CONFIRMED
ORGANIZER;RSVP=FALSE;CN=TUC;CUTYPE=TUC:mailto:webmaster@tuc.gr
DTSTART:20221014T150000
DTEND:20221014T160000
TRANSP:OPAQUE
CLASS:DEFAULT
END:VEVENT
END:VCALENDAR