ArtsAutosBooksBusinessEducationEntertainmentFamilyFashionFoodGamesGenderHealthHolidaysHomeHubPagesPersonal FinancePetsPoliticsReligionSportsTechnologyTravel

Article Report: Approaching the Limit of Predictability in Human Mobility by Lu et al 2013

Updated on July 15, 2014

Study Problem

The study addresses the travel patterns of people in Code de Ivory in order to find out the movement uncertainties of these people by use of prediction algorithms. In achieving this goal, the researchers investigated the actual locations, which every mobile user in the sample had visited. The researchers wanted to know whether prediction of human mobility was a realistic measure. Through evaluating the maximum performance and predictability of the actual prediction algorithms on users of mobile phones, the researchers had an aim of filling the knowledge gap in determining the maximum predictability of the prediction algorithms. Another problem assessed by the authors was the mobility patterns of the population that was under study. In this case, the Cote d’Ivoire population after the civil war that occurred in the country in 2011.

Stakeholders

In this study, stakeholders include the public in Code-Ivoir, the researchers themselves because they are the ones who conducted the study, the government since the research findings will assist them to predict mobility of people with unquestionable behavior or just citizens for planning of resources and other researchers who will use the research findings for study purposes. Other stakeholders in this study include epidemic modelers, traffic planners, and disaster management teams who will find the findings useful in predicting people’s movement patterns.

Data Collection and Measurement

The travel patterns of 500,000 people in Cote d'Ivoire was obtained by use of mobile phone call data records provided by the orange phone company. The data was derived from the detail records of the sampled users who were kept anonymous throughout the study. These subscribers were those who had been active from Dec 1, 2011 to May 1 2012 in CIV. The location of the users was given as the sub- prefecture location from the Orange companies’ mobile tower. The actual time destinations which these individuals visited were collected by use of mobile gargets that were equipped with global systems of positioning capabilities, access points with wireless local area networks, and cell towers for the mobile phones.

Travel uncertainties were measured by use of entropy method. These took into consideration, the temporal correlation of personal trajectories and frequencies. The researchers also implemented a series of models that are based on the Markov chain(MC)in their prediction of the real location that were visited by the mobile phone user.

With regard to the measure of mobility, the researchers employed the average travel distance and the trajectory radius of gyration ( rg) so as to measure the mobility pattern of these people. Since the study was interested in finding out the mobility behavior for people who were stable and in long term movements in relation to short term movements, the researchers emphasized on analyzing predictability and entropy of the daily movement activities of people. According to this measure, large entropies are an indication of higher disorder and apparently decrease the predictability of people’s movements.

According to these researchers, the use of these predictability measurements offered them the ability to investigate the temporal correlation, and spatial distribution of personal trajectory and data as well enhancing their predictive power with these algorithms. The researchers went on to implement various models of Markov chain (MC) in investigating on how close they could get to in achieving algorithms for real predictions.

Nature of the Study

This study is quantitative in nature. This is because it relied on phone call data records of 500,000 persons in Cote d'Ivoire, a Western African nation who were using mobile gargets. The Orange Telecom company offered these data. This sample was obtained from the population of five million people that were at that time possessing mobile phones in the country. Quantitative research is concerned on quantifying the correlation between two elements. The purpose of quantitative research is to determine the association between one element hereby referred as an independent variable in relation to another (referred as dependent variable) (Balkin, 2009). Balkin, furthure explains that students of research or researchers have an obligation to understand research and how it is conducted in order to apply evidence based practice. Balkin goes on to articulate that quantitative research is necessary as it helps researchers in applying evidence based practice. The two elements correlated in this research was the prediction of mobility patterns of individuals and the prediction algorithms.

Hypothesis

The researcher’s hypothesis was that, predictability in measuring the individual mobility patterns is high. This means that the hypothesis was not a null hypothesis. In verification of this hypothesis, the authors implemented various Markov chain (MC) models that assisted in predicting the factual location which each user had visited. According to the authors they had relied on the scientific evidence that Markov chain models had a prediction accuracy as high as 88% for trajectories that were stationary and around 96% for trajectories that were non - stationary (Gambs et al, 2012).

Independent and Dependent Variable

The study’s dependent variable was predictability of individual travel patterns while the independent variable was type of measurement algorithms used. In other words, the accuracy in predictability of mobility patterns depended on the algorithm used.

Data Analysis

The authors of the study analyzed the findings by largely focusing on predictability and entropy of the day to- day mobility of people. The disorder or uncertainty of the trajectories was measured by use of entropy. According to these authors, larger entropy could be interpreted as greater uncertainty or disorder and consequently lowers the predictability of a person’s movement. Other ways of analyzing the findings included the use of a Deweke Diagnostic, which detected convergence failure by way of comparing the values in MarMMarkov lowere chain to those in its latter part.

Study Findings

In general, the study findings from this research indicated that human mobility was largely dependent on historical behaviors. In addition, the authors also found out that maximum predictability was a practical theoretical limit for the latent predictive power. Further, the authors realized that, maximum predictably is a target that could be approachable for the purpose of actual prediction accuracy.

Additional research questions

Some of the additional questions generated by this study include: in what areas could the data on individual mobility patterns be applied. In other words, how can such data be made useful. The second research question is on how these algorithms that measure mobility could be improved for more prediction accuracy in the mobility patterns.

Comments

    0 of 8192 characters used
    Post Comment

    No comments yet.

    working

    This website uses cookies

    As a user in the EEA, your approval is needed on a few things. To provide a better website experience, hubpages.com uses cookies (and other similar technologies) and may collect, process, and share personal data. Please choose which areas of our service you consent to our doing so.

    For more information on managing or withdrawing consents and how we handle data, visit our Privacy Policy at: https://hubpages.com/privacy-policy#gdpr

    Show Details
    Necessary
    HubPages Device IDThis is used to identify particular browsers or devices when the access the service, and is used for security reasons.
    LoginThis is necessary to sign in to the HubPages Service.
    Google RecaptchaThis is used to prevent bots and spam. (Privacy Policy)
    AkismetThis is used to detect comment spam. (Privacy Policy)
    HubPages Google AnalyticsThis is used to provide data on traffic to our website, all personally identifyable data is anonymized. (Privacy Policy)
    HubPages Traffic PixelThis is used to collect data on traffic to articles and other pages on our site. Unless you are signed in to a HubPages account, all personally identifiable information is anonymized.
    Amazon Web ServicesThis is a cloud services platform that we used to host our service. (Privacy Policy)
    CloudflareThis is a cloud CDN service that we use to efficiently deliver files required for our service to operate such as javascript, cascading style sheets, images, and videos. (Privacy Policy)
    Google Hosted LibrariesJavascript software libraries such as jQuery are loaded at endpoints on the googleapis.com or gstatic.com domains, for performance and efficiency reasons. (Privacy Policy)
    Features
    Google Custom SearchThis is feature allows you to search the site. (Privacy Policy)
    Google MapsSome articles have Google Maps embedded in them. (Privacy Policy)
    Google ChartsThis is used to display charts and graphs on articles and the author center. (Privacy Policy)
    Google AdSense Host APIThis service allows you to sign up for or associate a Google AdSense account with HubPages, so that you can earn money from ads on your articles. No data is shared unless you engage with this feature. (Privacy Policy)
    Google YouTubeSome articles have YouTube videos embedded in them. (Privacy Policy)
    VimeoSome articles have Vimeo videos embedded in them. (Privacy Policy)
    PaypalThis is used for a registered author who enrolls in the HubPages Earnings program and requests to be paid via PayPal. No data is shared with Paypal unless you engage with this feature. (Privacy Policy)
    Facebook LoginYou can use this to streamline signing up for, or signing in to your Hubpages account. No data is shared with Facebook unless you engage with this feature. (Privacy Policy)
    MavenThis supports the Maven widget and search functionality. (Privacy Policy)
    Marketing
    Google AdSenseThis is an ad network. (Privacy Policy)
    Google DoubleClickGoogle provides ad serving technology and runs an ad network. (Privacy Policy)
    Index ExchangeThis is an ad network. (Privacy Policy)
    SovrnThis is an ad network. (Privacy Policy)
    Facebook AdsThis is an ad network. (Privacy Policy)
    Amazon Unified Ad MarketplaceThis is an ad network. (Privacy Policy)
    AppNexusThis is an ad network. (Privacy Policy)
    OpenxThis is an ad network. (Privacy Policy)
    Rubicon ProjectThis is an ad network. (Privacy Policy)
    TripleLiftThis is an ad network. (Privacy Policy)
    Say MediaWe partner with Say Media to deliver ad campaigns on our sites. (Privacy Policy)
    Remarketing PixelsWe may use remarketing pixels from advertising networks such as Google AdWords, Bing Ads, and Facebook in order to advertise the HubPages Service to people that have visited our sites.
    Conversion Tracking PixelsWe may use conversion tracking pixels from advertising networks such as Google AdWords, Bing Ads, and Facebook in order to identify when an advertisement has successfully resulted in the desired action, such as signing up for the HubPages Service or publishing an article on the HubPages Service.
    Statistics
    Author Google AnalyticsThis is used to provide traffic data and reports to the authors of articles on the HubPages Service. (Privacy Policy)
    ComscoreComScore is a media measurement and analytics company providing marketing data and analytics to enterprises, media and advertising agencies, and publishers. Non-consent will result in ComScore only processing obfuscated personal data. (Privacy Policy)
    Amazon Tracking PixelSome articles display amazon products as part of the Amazon Affiliate program, this pixel provides traffic statistics for those products (Privacy Policy)