haku: @supervisor Virrantaus, Kirsi / yhteensä: 163
viite: 15 / 163
| Tekijä: | Raja, Muneeba |
| Työn nimi: | Exploring human mobility patterns based on geotagged Flickr photos |
| Julkaisutyyppi: | Diplomityö |
| Julkaisuvuosi: | 2015 |
| Sivut: | vi + 51 s. + liitt. 11 Kieli: eng |
| Koulu/Laitos/Osasto: | Insinööritieteiden korkeakoulu |
| Oppiaine: | Geoinformation Technology (IA3002) |
| Valvoja: | Virrantaus, Kirsi |
| Ohjaaja: | Ott, Jörg |
| Elektroninen julkaisu: | http://urn.fi/URN:NBN:fi:aalto-201512165581 |
| Sijainti: | P1 Ark Aalto 3254 | Arkisto |
| Avainsanat: | pattern mining movement patterns micro-mobility spatial-temporal analysis Flickr geotagged images |
| Tiivistelmä (eng): | Predicting human mobility behaviour has long been a topic of scientific interest. Such studies generally rely on tracking human movements through a range of data collection methodologies such as using GPS trackers, cellular network data etc. Some of this data may be confidential or hard to acquire. This thesis explores if existing publicly available data on online photo sharing platforms can be used to determine human mobility patterns with reasonable accuracy. We choose the Flickr website as the data collection medium as it has an extensive user base actively sharing photos many of which, have geo tags embedded in them which are preserved by Flickr. Our analysis reveals that while the data from Flickr is sparse and discontinuous making it unsuitable for reliable mobility prediction, typical human mobility trends based on time of day, day of week and month of the year can still be extracted. Such interesting patterns could be potentially used in traffic engineering domains or for user profiling purpoes. More specifically, we describe how to obtain a subset of frequent active users and their information from Flickr, and the sliding window mechanism to filter the active periods of the users. Later we explain the various statistical methods applied on the filtered subset of data to identify the categories in which users could be classified, mainly short distance travellers and long distance travellers. The short distance travellers are considered for mobility trends prediction. |
| ED: | 2016-01-17 |
INSSI tietueen numero: 52706
+ lisää koriin
INSSI