BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:What makes urban areas lively and safe?
DTSTART:20161031T141500
DTEND:20161031T151500
DTSTAMP:20260916T002737Z
UID:300accf89af4e73eb0cd694bd985906177ba297ad2416ff455f9a675
CATEGORIES:Conferences - Seminars
DESCRIPTION:Bruno Lepri leads the Mobile and Social Computing Lab (MobS)
  and is vice-responsible of the Complex Data Analytics research line at B
 runo Kessler Foundation (Trento\, Italy). Bruno is also research affili
 ate at the MIT Media Lab working with the Human Dynamics group and the MIT
  Connection Science initiative\, where he is one of the researchers contri
 buting to Social Physics. He recently launched an alliance between MIT and
  FBK on Human Dynamics Observatories. He is also a senior research affilia
 te of Data-Pop Alliance\, the first think-tank on Big Data and Developmen
 t co-created by the Harvard Humanitarian Initiative\, MIT Media Lab\, Over
 seas Development Institute\, and Flowminder to promote a people-centered B
 ig Data revolution. He holds a Ph.D. in Computer Science from the Universi
 ty of Trento. \nHis research interests include computational social scien
 ce\, big data and personal data\, pervasive and ubiquitous computing\, and
  human behavior understanding.\nPolicy makers\, urban planners\, architect
 s\, sociologists\, and economists are interested in creating urban areas t
 hat are both lively and safe. But are the safety and liveliness of neighbo
 rhoods independent characteristics? Or are they just two sides of the same
  coin?\nIn my talk\, I first discuss our work on verifying the Jane Jacobs
 's four conditions necessary for the promotion of urban life in the Italia
 n context. We have done so by operationalizing her concepts in new ways: w
 e used mobile phone records to extract a proxy for urban vitality and Web 
 data to extract structural proxies for urban diversity. As Jacobs envision
 ed\, vitality and diversity are intimately linked. Moreover\, to paraphras
 e the Jacobs' four conditions in the Italian context\, we might say that a
 ctive Italian districts have dense concentrations of workers\, third place
 s at walking distance\, small streets\, and historical buildings.\nThen\, 
 I describe a recent work we did on exploring the connection between the le
 vels of activity and the perception of safety of neighborhoods in two majo
 r Italian cities by combining mobile phone data (as a proxy for liveliness
 ) with scores of perceived safety estimated using a Convolutional Neural N
 etwork trained on a dataset of Google Street View images scored using a cr
 owdsourced visual perception survey. Our results show that (i) safer looki
 ng neighborhoods are more active than what is expected from their populati
 on density\, employee density\, and distance to the city centre\; and (ii)
  that the correlation between appearance of safety and activity is positiv
 e\, strong\, and signicant\, for females and people over 50\, but negative
  for people under 30\, suggesting that the behavioral impact of perception
  depends on the demographic of the population. Finally\, we use occlusion 
 techniques to identify the urban features that contribute to the appearanc
 e of safety\, finding that greenery and streets facing windows contribute 
 to a positive appearance of safety. These results suggest that urban appea
 rance modulates levels of human activity and\, consequently\, a neighborho
 od's rate of natural surveillance.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR