Peatuste tuvastamine ja mobiilpositsioneerimise asukohatäpsuse parandamine
Date
2018
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Mobiilioperaatorid koguvad andmeid oma klientide tegevuse kohta mobiilivõrgus. Igal võrgusündmusel on viide mastile, mille külge oli seade parasjagu ühendatud. Teades mastide kattealasid, saab hinnata inimeste trajektoore läbi terve päeva. Nende trajektooride halva ruumilise lahutuse ja ajalise hõreduse tõttu on neist kasuliku informatsiooni eraldamine väljakutsuv ülesanne, mis vajab spetsiifilisi algoritmilisi lahendusi. Trajektooridest paigalseisude tuvastamine on aluseks mitmetele küsimustele lahenduse leidmisele. Selles töös on uuritud ühte paigalseisude leidmise algoritmi ning on tuvastatud mõned selle puudujäägid. Nende puuduste parandamisel muutus algoritm märksa täpsemaks ja töökindlamaks.Lisaks on uuritud trajektooride perioodilisuse kaasamise mõju mudelite asukohahinnangutele.
Mobile operators collect data about their clients' activity in the mobile network. Each event made in the mobile network has reference to the antenna the mobile device was connected to at that time. By knowing the coverage areas of the antennas the peoples' trajectories throughout the day can be approximated. Its spatial coarseness and temporal sparseness makes extracting information from this data a compelling task requiring specially crafted algorithmic tools. Detecting when and where did the mobile device stopped is a crucial step that serves as a basis for subsequent data analysis tasks on this data. Here a state of the art stop detection algorithm is analysed and some shortcomings of it identified. The proposed improvements to these have been shown to improve the performance of the stop detection algorithm significantly. Additionally, the possibility of improving the location accuracy by incorporating periodicity into the movement models is investigated.
Mobile operators collect data about their clients' activity in the mobile network. Each event made in the mobile network has reference to the antenna the mobile device was connected to at that time. By knowing the coverage areas of the antennas the peoples' trajectories throughout the day can be approximated. Its spatial coarseness and temporal sparseness makes extracting information from this data a compelling task requiring specially crafted algorithmic tools. Detecting when and where did the mobile device stopped is a crucial step that serves as a basis for subsequent data analysis tasks on this data. Here a state of the art stop detection algorithm is analysed and some shortcomings of it identified. The proposed improvements to these have been shown to improve the performance of the stop detection algorithm significantly. Additionally, the possibility of improving the location accuracy by incorporating periodicity into the movement models is investigated.