Συνδυασμός Android και Tensorflow με στόχο την παραγωγή analytics για recommendations για τους χρήστες, βάσει συγκεκριμένων παρατηρήσεων/δεδομένων που συλλέγει για αυτούς η κάθε συσκευή

Ανδρικόπουλος, Βασίλειος

Combination of Android and Tensorflow to produce analytics for recommendations for users, based on specific observations/data that collected about them by each device

Master Thesis

Author

Ανδρικόπουλος, Βασίλειος

Date

2024-12

Abstract

In the context of this thesis, the implementation of an Android application was carried out, the aim of which is to record data from a user's device, during his/her movement, while he/she is walking (movement on foot, not with any means of transport). The aim of recording data from the user's device is to analyze and process them, so that with the help of appropriate machine learning techniques implemented, using Tensorflow, some conclusions of interest can be drawn. More specifically, in this work we were interested in examining whether some inference could be drawn about the number of steps a user could walk, in the Athens area, based on factors such as the weather and the geographical location of the user, combined with time. The next goal was to present these conclusions to the user of the application as suggestions when he/she starts his/her route. In this way a suggestion is given to the user depending on the area he is in, combined with the weather conditions, for the average steps they are advised to take.

Postgraduate Studies Programme

Προηγμένα Συστήματα Πληροφορικής - Ανάπτυξη Λογισμικού και Τεχνητής Νοημοσύνης

Department

Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Πληροφορικής

Number of pages

Language

Greek

URI

https://dione.lib.unipi.gr/xmlui/handle/unipi/17356

Collections

Τμήμα Πληροφορικής

Show full item record

Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα