Impact of location history collection schemes on observed human mobility features

Rodríguez-Carrión, Alicia; Das, Sajal K.; Campo, Celeste; Garcia-Rubio, Carlos

doi:10.1109/percomw.2014.6815213

Cited by 8 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, we extend a previous work [12] with the following contributions: (i) in the previous work just the MIT data set was analyzed, here we add a second data set, the UC3M data set, to our analysis; (ii) we transform both data sets (MIT and UC3M) so that we have the same mobility data as if they were collected using the two data collections approaches under study: the one carried out by the mobile phone, and the one carried out by the network; (iii) using the data sets and collection approaches described before, we derived some of the most common mobility features in the literature, highlighting the different statistical distributions obtained in each case; (iv) we propose three filtering techniques to detect and reduce the bias introduced by the collection approaches; and (v) we show how the filtering process affects the observed mobility features under study, by comparing the results to the previous ones.…”

Section: Introductionmentioning

confidence: 61%

Detecting and Reducing Biases in Cellular-Based Mobility Data Sets

Rodríguez-Carrión

Garcia-Rubio

Campo

2018

Entropy

Self Cite

View full text Add to dashboard Cite

Correctly estimating the features characterizing human mobility from mobile phone traces is a key factor to improve the performance of mobile networks, as well as for mobility model design and urban planning. Most related works found their conclusions on location data based on the cells where each user sends or receives calls or messages, data known as Call Detail Records (CDRs). In this work, we test if such data sets provide enough detail on users’ movements so as to accurately estimate some of the most studied mobility features. We perform the analysis using two different data sets, comparing CDRs with respect to an alternative data collection approach. Furthermore, we propose three filtering techniques to reduce the biases detected in the fraction of visits per cell, entropy and entropy rate distributions, and predictability. The analysis highlights the need for contextualizing mobility results with respect to the data used, since the conclusions are biased by the mobile phone traces collection approach.

show abstract

Section: Introductionmentioning

confidence: 61%

Detecting and Reducing Biases in Cellular-Based Mobility Data Sets

Rodríguez-Carrión

Garcia-Rubio

Campo

2018

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…The authors of [17] characterise human mobility by selecting features as the amount of movement, the distributions of visits to PoIs, the entropy of a user's location history and its degree of predictability. We opted for the adoption of the entropy in our work as the characteristic feature, in order to provide a measure of the uncertainty of users' movements.…”

Section: Related Workmentioning

confidence: 99%

A multi‐agent system for itinerary suggestion in smart environments

Paola

Gaglio

Giammanco

et al. 2021

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Modern smart environments pose several challenges, among which the design of intelligent algorithms aimed to assist the users. When a variety of points of interest are available, for instance, trajectory recommendations are needed to suggest users the most suitable itineraries based on their interests and contextual constraints. Unfortunately, in many cases, these interests must be explicitly requested and their lack causes the so-called cold-start problem. Moreover, lengthy travelling distances and excessive crowdedness of specific points of interest make itinerary planning more difficult. To address these aspects, a multi-agent itinerary suggestion system that aims at assisting the users in an online and collaborative way is proposed. A profiling agent is responsible for the detection of groups of users whose movements are characterised by similar semantic, spatial and temporal features; then, a recommendation agent leverages contextual information and dynamically associates the current user with the trajectory clusters according to a Multi-Armed Bandit policy. Framing the trajectory recommendation as a reinforcement learning problem permits to provide high-quality suggestions while avoiding both cold-start and preference elicitation issues. The effectiveness of the approach is demonstrated by some deployments in real-life scenarios, such as smart campuses and theme parks.

show abstract

“…We studied the impact of cellular-based location collection schemes on observed human mobility features [14]. We identified the most basic mobility features: (i) amount of movement (number of cell changes made per day), (ii) variety of visited locations (how many different locations are visited by the user per day), (iii) visits distribution (fraction of visits concentrated by each location), (iv) randomness (uncertainty we have about the next event in a sequence), and (v) predictability (bound of the maximum percentage of correct predictions the best algorithm could ever attain).…”

Section: B Analyzing the Impact Of Individual Movementsmentioning

confidence: 99%

“…We identified the most basic mobility features: (i) amount of movement (number of cell changes made per day), (ii) variety of visited locations (how many different locations are visited by the user per day), (iii) visits distribution (fraction of visits concentrated by each location), (iv) randomness (uncertainty we have about the next event in a sequence), and (v) predictability (bound of the maximum percentage of correct predictions the best algorithm could ever attain). We observed that the traces based on data stored in the network nodes themselves, recording the base transceiver station (BTS) to which the device is connected when the user is making or receiving a call, or sending or receiving a short message, known as call-detailed records (CDR), lead to biased mobility indicators [14].…”

Section: B Analyzing the Impact Of Individual Movementsmentioning

confidence: 99%

INRISCO: INcident monitoRing in Smart COmmunities

et al. 2020

Self Cite

View full text Add to dashboard Cite

Major advances in information and communication technologies (ICTs) make citizens to be considered as sensors in motion. Carrying their mobile devices, moving in their connected vehicles or actively participating in social networks, citizens provide a wealth of information that, after properly processing, can support numerous applications for the benefit of the community. In the context of smart communities, the INRISCO [1] proposal intends for (i) the early detection of abnormal situations in cities (i.e., incidents), (ii) the analysis of whether, according to their impact, those incidents are really adverse for the community; and (iii) the automatic actuation by dissemination of appropriate information to citizens and authorities. Thus, INRISCO will identify and report on incidents in traffic (jam, accident) or public infrastructure (e.g., works, street cut), the occurrence of specific events that affect other citizens' life (e.g., demonstrations, concerts), or environmental problems (e.g., pollution, bad weather). It is of particular interest to this proposal the identification of incidents with a social and economic impact, which affects the quality of life of citizens. INDEX TERMS Early detection of incidents, smart cities, citizen sensor, vehicular communications, big data analysis, social networks.

show abstract

Impact of location history collection schemes on observed human mobility features

Cited by 8 publications

References 13 publications

Detecting and Reducing Biases in Cellular-Based Mobility Data Sets

Detecting and Reducing Biases in Cellular-Based Mobility Data Sets

A multi‐agent system for itinerary suggestion in smart environments

INRISCO: INcident monitoRing in Smart COmmunities

Contact Info

Product

Resources

About