Recent sources of Big Data offer new possibilities for urban mobility and accessibility studies. This thesis work originates from the Safari Njema project, winner of the social engagement and responsibility programme of Politecnico di Milano, Polisocial Award 2018. Through the use of analytics tools, the project proposes solutions for the improvement of mobility planning in African cities, predominantly based on informal transport systems. With a focus on Maputo, as pilot case, the proposed place-based and bottom-up mobility development plans are cost-effective alternatives to formal models. In this thesis, in particular, an innovative method to extract valuable information from anonymous mobile phone data for use in accessibility studies is presented. The accessibility analysis was addressed to healthcare facilities, chosen as places of interest, and was based on estimates of travel times to the facilities obtained with a kernel smoothing regression of travel times derived from GPS data provided by the company Cuebiq. In the first case study the main health centers in the Greater Maputo were examined. A fully data-driven approach is not only cheaper than traditional methods of collecting information, but, in view of the increasing spread of smartphones, it can achieve good levels of accuracy. In addition, a time-sensitive accessibility study was tested for the Central Hospital of Maputo, differentiating between working and non-working days. In the second case study the proposed method was applied in the Lombardy region to study the accessibility of the Niguarda Ca’ Granda Hospital in Milan considering the variations due to the COVID-19 pandemic and the consequent restriction measures applied by the government, showing how a dynamic approach can adapt to changes due to factors not taken into consideration in traditional static methods.
Le recenti fonti di Big Data offrono nuove possibilità per gli studi sulla mobilità urbana e sull’accessibilità. Questo lavoro di tesi nasce dal progetto Safari Njema, vincitore del programma di impegno e responsabilità sociale del Politecnico di Milano, Polisocial Award 2018. Attraverso l’uso di strumenti di analytics, il progetto propone soluzioni per il miglioramento della gestione della mobilità nelle grandi città africane, che si basa principalmente su sistemi di trasporto informali. Con focus su Maputo, che fa da caso pilota, i piani di sviluppo place-based e bottom-up della mobilità proposti costituiscono alternative economiche ai modelli formali. In questa tesi, in particolare, è presentato un metodo innovativo per estrarre informazioni utili da dati anonimi provenienti dalla telefonia mobile, successivamente utilizzate in studi di accessibilità. L’analisi di accessibilità è stata finalizzata alle strutture di assistenza sanitaria, scelte come luoghi di interesse, ed è stata basata sulle stime dei tempi di viaggio alle strutture, ottenute con kernel smoothing regression dei tempi di viaggio ricavati dai dati GPS forniti dalla compagnia Cuebiq. Nel primo caso studio sono stati presi in esame i principali centri sanitari nella Grande Maputo. Un approccio interamente guidato dai dati non solo è più economico rispetto ai tradizionali metodi di raccolta di informazioni, ma, in vista di una diffusione sempre crescente degli smartphone, può ottenere dei buoni livelli di accuratezza. Inoltre si è testato uno studio dinamico dell’accessibilità all’Ospedale Centrale di Maputo che tenesse conto delle variazioni nel corso della settimana, differenziando giorni lavorativi e giorni festivi. Nel secondo caso studio il metodo proposto è stato applicato nella regione Lombardia per studiare l’accessibilità all’Ospedale Niguarda Ca’ Granda di Milano considerando le variazioni dovute alla pandemia COVID-19 e le conseguenti misure di restrizione applicate dal governo, mostrando come un approccio dinamico possa adattarsi a cambiamenti dovuti a fattori non presi in considerazioni nei tradizionali metodi statici.
Accessibility maps from global positioning system data. Two case studies : Maputo and Milan
Zazzetti, Elena
2019/2020
Abstract
Recent sources of Big Data offer new possibilities for urban mobility and accessibility studies. This thesis work originates from the Safari Njema project, winner of the social engagement and responsibility programme of Politecnico di Milano, Polisocial Award 2018. Through the use of analytics tools, the project proposes solutions for the improvement of mobility planning in African cities, predominantly based on informal transport systems. With a focus on Maputo, as pilot case, the proposed place-based and bottom-up mobility development plans are cost-effective alternatives to formal models. In this thesis, in particular, an innovative method to extract valuable information from anonymous mobile phone data for use in accessibility studies is presented. The accessibility analysis was addressed to healthcare facilities, chosen as places of interest, and was based on estimates of travel times to the facilities obtained with a kernel smoothing regression of travel times derived from GPS data provided by the company Cuebiq. In the first case study the main health centers in the Greater Maputo were examined. A fully data-driven approach is not only cheaper than traditional methods of collecting information, but, in view of the increasing spread of smartphones, it can achieve good levels of accuracy. In addition, a time-sensitive accessibility study was tested for the Central Hospital of Maputo, differentiating between working and non-working days. In the second case study the proposed method was applied in the Lombardy region to study the accessibility of the Niguarda Ca’ Granda Hospital in Milan considering the variations due to the COVID-19 pandemic and the consequent restriction measures applied by the government, showing how a dynamic approach can adapt to changes due to factors not taken into consideration in traditional static methods.| File | Dimensione | Formato | |
|---|---|---|---|
|
ElenaZazzetti.pdf
non accessibile
Descrizione: Accessibility maps from global positioning system data. Two case studies: Maputo and Milan
Dimensione
19.47 MB
Formato
Adobe PDF
|
19.47 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/166597