nach oben

2008 | Buch

Kapitel lesen Erstes Kapitel lesen

Mobility, Data Mining and Privacy

Geographic Knowledge Discovery

herausgegeben von: Fosca Giannotti, Dino Pedreschi

Verlag: Springer Berlin Heidelberg

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

The technologies of mobile communications and ubiquitous computing are p- vading our society. Wireless networks are becoming the nerves of our territory, especially in the urban setting; through these nerves, the movement of people and vehicles may be sensed and possibly recorded, thus producing large volumes of mobility data. This is a scenario of great opportunities and risks. On one side, data mining can be put to work to analyse these data, with the purpose of producing useful knowledge in support of sustainable mobility and intelligent transportation systems. On the other side, individual privacy is at risk, as the mobility data may reveal, if misused, highly sensitive personal information. In a nutshell, a novel multi-disciplinary research area is emerging within this challenging con?ict of opportunities and risks and at the crossroads of three s- jects: mobility, data mining and privacy. This book is aimed at shaping up this frontier of research, from a computer science perspective: we investigate the v- ious scienti?c and technologicalachievementsthat are needed to face the challenge, anddiscussthecurrentstate oftheart,theopenproblemsandtheexpectedroad-map of research. Hence, this is a book for researchers: ?rst of all for computer science researchers, from any sub-area of the ?eld, and also for researchers from other disciplines (such as geography, statistics, social sciences, law, telecommunication and transportation engineering) who are willing to engage in a multi-disciplinary research area with potential for broad social and economic impact.

Inhaltsverzeichnis

Frontmatter

Setting the Stage

Mobility, Data Mining and Privacy: A Vision of Convergence

The comprehension of phenomena related to movement — not only of people and vehicles but also of animals and other moving objects — has always been a key issue in many areas of scientific investigation or social analysis. The human geographer, for instance, studies the flows of migrant populations with reference to geography — places that are sources and destinations of migrations — and time. The historian, another example, studies military campaigns and related movements of armies and populations. (A famous instance is the depiction of Napoleon’s March on Moscow, published by C.J. Minard in 1861, discussed in Chap. 1 of this book (see Fig. 1.1); this figure represents with eloquence the fate of Napoleon’s army in the Russian campaign of 1812–1813, by showing the movement of the army together with its dramatically diminishing size during its advance and subsequent retreat.) The ethologist studies animal behaviour by the analysis of movement patterns, based on field observations or, sometimes, on data from tracking devices.

F. Giannotti, D. Pedreschi

1. Basic Concepts of Movement Data

From ancient days, people have observed various moving entities, from insects and fishes to planets and stars, and investigated their movement behaviours. Although methods that were used in earlier times for observation, measurement, recording, and analysis of movements are very different from modern technologies, there is still much to learn from past studies. First, this is the thorough attention paid to the multiple aspects of movement. These include not only the trajectory (path) in space, characteristics of motion itself such as speed and direction, and their dynamics over time but also characteristics and activities of the entities that move. Second, this is the striving to relate movements to properties of their surroundings and to various phenomena and events.

N. Andrienko, G. Andrienko, N. Pelekis, S. Spaccapietra

2. Characterising the Next Generation of Mobile Applications Through a Privacy-Aware Geographic Knowledge Discovery Process

The proliferation of mobile technologies for ‘always-on’ at ‘any-time’ and ‘vanyplace’ has facilitated the generation of huge volume of positioning data sets containing information about the location and the movement of entities through the geographic environment. In principle, every time an entity moves through space, it creates a trajectory (i.e. track or path) representing the history of its past and current locations. Examples of interesting trajectories of moving entities may range from hurricane and tornado tracks [19] to individual trajectories of animals [26] and planes [5]. Specially designed sensors can provide the location of a mobile entity as well as information about the geographic environment where this entity is moving. Current research on mobile technologies such as sensor web, wireless communication and portable computers has been crucial for the development of multi-sensor systems. Their use to sense a geographic environment and mobile entities can include photodiodes to detect light level, accelerometers to provide tilt and vibration measurements, passive infrared sensors to detect the proximity of humans, omni-directional microphones to detect sound and other built-in sensors for temperature, pressure, and CO gas [9].

M. Wachowicz, A. Ligtenberg, C. Renso, S. Gürses

3. Wireless Network Data Sources: Tracking and Synthesizing Trajectories

Due to inexpensive modern sensing technologies and extensive use of wireless communication, location information about moving objects is increasing rapidly. Some positioning technologies are based on GPS-equipped devices, while others utilize the infrastructure of the underlying communication network. This opens new opportunities for offering, monitoring, and decision-making novel applications in a variety of fields. To name a few, we have location-based services (LBS), fleet management and traffic control applications, emergency, navigation, and geocoding services. These compose a subset of existing applications where such kind of data comprise the core of the underlying business.

C. Renso, S. Puntoni, E. Frentzos, A. Mazzoni, B. Moelans, N. Pelekis, F. Pini

4. Privacy Protection: Regulations and Technologies, Opportunities and Threats

Information and communication technologies (ICTs) touch many aspects of our lives. The integration of ICTs is enhanced by the advent of mobile, wireless, and ubiquitous technologies. ICTs are increasingly embedded in common services, such as mobile and wireless communication, Internet browsing, credit card e-transactions, and electronic health records. As ICT-based services become ubiquitous, our everyday actions leave behind increasingly detailed digital traces in the information systems of ICT-based service providers. For example, consumers of mobile-phone technologies leave behind traces of geographic position to cellular provider records, Internet users leave behind traces of the Web pages and packet requests of their computers in the access logs of domain and network administrators, and credit card transactions reveal the locations and times where purchases were completed. Traces are an artifact of the design of services, such that their collection and storage are difficult to avoid. To dispatch calls, for instance, the current design of wireless networks requires knowledge of each mobile user’s geographic position. Analogously, DNS servers for the Internet need to know IP addresses to dispatch requests from source to destination computers.

D. Pedreschi, F. Bonchi, F. Turini, V. S. Verykios, M. Atzori, B. Malin, B. Moelans, Y. Saygin

Managing Moving Object and Trajectory Data

5. Trajectory Data Models

Trajectory databases is an important research area that has received a lot of interest in the last decade. The objective of trajectory databases is to extend database technology to support the representation and querying of moving objects and their trajectory.

J. Macedo, C. Vangenot, W. Othman, N. Pelekis, E. Frentzos, B. Kuijpers, I. Ntoutsi, S. Spaccapietra, Y. Theodoridis

6. Trajectory Database Systems

In this chapter, we deal with trajectory database management issues and physical aspects of trajectory database systems, such as indexing and query processing. Our emphasis is on historical databases handling past positions of moving objects represented as trajectories. This is because only such databases can be used in the context of trajectory data warehouses, which is the core subject of this book.

E. Frentzos, N. Pelekis, I. Ntoutsi, Y. Theodoridis

7. Towards Trajectory Data Warehouses

Data warehouses have received the attention of the database community as a technology for integrating all sorts of transactional data, dispersed within organisations whose applications utilise either legacy (non-relational) or advanced relational database systems. Data warehouses form a technological framework for supporting decision-making processes by providing informational data. A data warehouse is defined as a subject-oriented, integrated, time-variant, non-volatile collection of data in support of management of decision-making process [10].

N. Pelekis, A. Raffaetà, M. -L. Damiani, C. Vangenot, G. Marketos, E. Frentzos, I. Ntoutsi, Y. Theodoridis

8. Privacy and Security in Spatiotemporal Data and Trajectories

The European directive 2002/58/EC requires providers of public communication networks and electronic communication services to adopt techniques to ensure data security and privacy. This directive states, among others, that “the provider of a publicly available electronic communication service must take appropriate technical and organizational measures to safeguard the security of its services having regard to the state of the art,” and also that “when location data relating to users can be processed, such data can only be processed when they are made anonymous or with the consent of the user.”

V. S. Verykios, M. L. Damiani, A. Gkoulalas-Divanis

Mining Spatiotemporal and Trajectory Data

9. Knowledge Discovery from Geographical Data

During the last decade, data miners became aware of geographical data. Today, knowledge discovery from geographic data is still an open research field but promises to be a solid starting point for developing solutions for mining spatiotemporal patterns in a knowledge-rich territory. As many concepts of geographic feature extraction and data mining are not commonly known within the data mining community, but need to be understood before advancing to spatiotemporal data mining, this chapter provides an introduction to basic concepts of knowledge discovery from geographical data.

S. Rinzivillo, F. Turini, V. Bogorny, C. Körner, B. Kuijpers, M. May

10. Spatiotemporal Data Mining

After the introduction and development of the relational database model between 1970 and the 1980s, this model proved to be insufficiently expressive for specific applications dealing with, for instance, temporal data, spatial data and multi-media data. From the mid-1980s, this has led to the development of domain-specific database systems, the first being temporal databases, later followed by spatial database systems.

M. Nanni, B. Kuijpers, C. Körner, M. May, D. Pedreschi

11. Privacy in Spatiotemporal Data Mining

Privacy is an essential requirement for the provision of electronic and knowledgebased services in modern e-business, e-commerce, e-government, and e-health environments. Nowadays, service providers can easily track individuals’ actions, behaviors, and habits. Given large data collections of person-specific information, providers can mine data to learn patterns, models, and trends that can be used to provide personalized services. The potential benefits of data mining are substantial, but it is evident that the collection and analysis of sensitive personal data arouses concerns about citizens’ privacy, confidentiality, and freedom.

F. Bonchi, Y. Saygin, V. S. Verykios, M. Atzori, A. Gkoulalas-Divanis, S. V. Kaya, E. Savaş

12. Querying and Reasoning for Spatiotemporal Data Mining

In the previous chapters, we studied movement data from several perspectives: the application opportunities, the type of analytical questions, the modeling requirements, and the challenges for mining. Moreover, the complexity of the overall analysis process was pointed out several times. The analytical questions posed by the end user need to be translated into several tasks such as choose analysis methods, prepare the data for application of these methods, apply the methods to the data, and interpret and evaluate the results obtained. To clarify these issues, let us consider an example involving the following analytical questions:

Describe the collective movement behavior of the population (or a given subset) of entiti es during the whole time period (or a given interval)
Find the entity subsets and time periods with the collective movement behavior corresponding to a given pattern
Compare the collective movement behaviors of the entities on given time intervals

It is evident that there is a huge distance between these analytical questions and the complex computations needed to answer them. In fact, answering the above questions requires combining several forms of knowledge and the cooperation among solvers of different nature: we need spatiotemporal reasoning supporting deductive inferences along with inductive mechanisms, in conjunction with statistical methods.

G. Manco, M. Baglioni, F. Giannotti, B. Kuijpers, A. Raffaetà, C. Renso

13. Visual Analytics Methods for Movement Data

All the power of computational techniques for data processing and analysis is worthless without human analysts choosing appropriate methods depending on data characteristics, setting parameters and controlling the work of the methods, interpreting results obtained, understanding what to do next, reasoning, and drawing conclusions. To enable effective work of human analysts, relevant information must be presented to them in an adequate way. Since visual representation of information greatly promotes man’s perception and cognition, visual displays of data and results of computational processing play a very important role in analysis.

G. Andrienko, N. Andrienko, I. Kopanakis, A. Ligtenberg, S. Wrobel

Titel: Mobility, Data Mining and Privacy
herausgegeben von: Fosca Giannotti
Dino Pedreschi
Verlag: Springer Berlin Heidelberg
Electronic ISBN: 978-3-540-75177-9
Print ISBN: 978-3-540-75176-2
DOI: https://doi.org/10.1007/978-3-540-75177-9

Springer Professional