Position closed (at May 15th)
PhD Grants - 2012
Six PhDgrants coadvised by UniTN, FBK and Telecom Italia with title:
Human behavior understanding from mobile phones data and web usage patterns
A deep understanding of peoples’ behavior, individually or by group, is a key factor for next generation services as well as for the creation of smart cities environment with a more efficient transportation network, a better energy management, etc.: both of them have a sustainable economic development and a high quality of life as the final goal. On one hand, the modern (smart) mobile devices allow for a very wide variety of actions (communication, browsing, application execution) and in addition to standard data related to phoning, include many different sources of information coming from sensors (e.g. GPS position, accelerometer data, etc.) that let a close view over individuals, on the other hand the pervasive ICT technologies enable the collection of big data from multiple source (first of all mobile phone network data but also transportation data, energy consumption data, etc.) of extraordinary value because analyzing them we can understand the insight of a city or a territory as never before. The aim of these grants is then to address, from a technological point of view, the challenges that the exploitation of these data for a better understanding of human behavior carries with.
Take a look at the example descriptions below.
For further information, see http://ict.unitn.it (Call XXVIII)
1. Behavior recognition and induction via semantic reasoning over human activity processes
Contact persons: Prof. Luciano Serafini (
) , Michele Vescovi (
The modern (smart) mobile devices allow for a very wide variety of actions (communication, browsing, application execution) and in addition to standard data related to phoning, include many different sources of information coming from sensors (e.g. GPS position,accelerometer data, etc.). This scenario has led to the birth of novel research areas such as context awareness, situation detection, activity recognition, behavior understanding and many others, which aim at exploiting all these information in order to support the user in multiple daily tasks. In parallel, but on a completely different stage, the semantic web and the linked open data made available a huge quantity of semantic data and knowledge, concerning semantic tagging of geographical data (e.g., openstreetmap) or general knowledge about persons, locations, organizations and events, (e.g., available in dbpedia, freebase, etc.) and general terminologic and ontological knowledge (e.g., schema.org, sumo and dolce upper level ontologies, yago2, wordnet and Framenet). The above scenario opens the possibility of new research challenges of combining raw sensor data with semantic information and ontological knowledge for the analysis of human behavior. The implementation of this vision requires and effective and deep integration of techniques from different disciplines in computer science as data mining, machine learning, semantic web and knowledge representation and reasoning. The aim of this PhD proposal is to address key research challenges in these fields and, in particular, to investigate the benefits of applying the semantic based technologies for modeling and reasoningover human activity processes.
The student will develop a research plan which will cover the following three important and complementary aspects:
(i) investigate on models for combining/modifying/extending the standard techniques of data and knowledge processing in order to provide a framework that support reasoning/learning with raw data, information and knowledge.
(ii) definition of reasoning services on top of the applied techniques/formalisms;
(iii) modeling, development and experimentation on practicalreal-world problems in different fields (e-health, smart-city, ...)
The proposed grant will cover the above mentioned aspects with a different main focuses, respectively on the effective integration of semantic/ontological information with raw data processing concerning human activities, and on the development of effective modeling/reasoning over human processes.
2. Understanding multi-source big data in a smart city framework
Contact persons: Prof. Themis Palpanas (
Roberto Larcher (
Modern cities are investing a lot in order to increase their quality of life and their economic competitiveness with a wider perspective which does not disregard the protection of the environment and the social sustainability. In this context the term "smart city" is becoming widely used and it defines an urban area where investments in strategic directions (e.g. transportation, services and ICT infrastructures) create a synergy which boosts a sustainable economic development and a high quality of life. In particular ICT plays a key role in the process of transformation of a traditional city towards a "smart" one, providing a set of powerful and potentially pervasive technologies. A founding requirement of a city in order to be "smart" is the ability of being as much aware as possible of the dynamics, the events and the activities performed on its territory. In other words to have a live (meaning up-to-date, realistic and evolving) picture of the life of the city. ICT can make this requirement possible, by offering state-of-the-art techniques able to produce, to transmit, to store and to process, huge amounts of data gathered from multiple sources. However the efficient achievement of this goal involves a wide set of extremely challenging research topics including the collection, the storage and the analysis of the manifold information concerning the life of a modern city. All the findings of the research activity will be applied to real case studies, in collaboration with local and national companies providing their data (e.g. telephone traffic, energy consumption measurements, traffic passages, etc.). This grant focuses on real world big data analysis issues, including:
(i) investigating data mining technique able to find correlations between the big multi-source data and events happening on the territory
(ii) identifying and refine pattern recognition technique on streaming data in order to implement real-time event detection
(iii) defining visualization strategies able to make easily understandable the result of complex analysis
(iv) the investigation and adaptation of existing approaches to store and integrate huge amount of multi- source streaming data (considering both distributed and not databases)
(v) the definition of smart data aggregations in order to minimize data losses and maximize compression
(vi) the definition of architectures able to make the stored data available at different permission levels
View complete description
3. Human behavior understanding by analyzing mobile phones and web usage patterns
Contact persons: Fabio Pianesi (
), Michele Caraviello (
Nowadays modern mobile devices, also known as smartphones, support the users with an extremely wide variety of services (communication, browsing, application execution) which, indeed, lead many more services provide by the Web to be directly available on the mobile devices, thanks to their broadband connectivity and interface capabilities. Furthermore, the various sources of information coming from the device sensors (e.g. GPS position, accelerometer sensing) allow to a tighter customization of those services with the user experience.This scenario had a twofold effect: first it is still boosting the development of Web services and mobile applications which support the user in his every day experience, and it gave rise to novel research areas such as context awareness, behavior understanding, user profiling and many others. The aim is to exploit the available information in order to tailor the provided services on the needs, the behavior/habits and the profile of the user. Nevertheless, these research areas are extremely challenging because they require to effectively integrating techniques from different disciplines in computer science (such as Knowledge Representation, Semantic Web, Web Services, Data Mining, ...), as well as the integration between technology and the study/modeling of human behaviors and needs.
The aim of this PhD proposal is to address key research challenges in this field and, in particular, to bridge two different research topics. On one side we are interested in exploring the automatic analysis and recognition of the user needs, retrieving and combining semantic information from his browsing history and his queries to mobile applications or services (from the Web).On the other side we want to face automatic user-behavior analysis in order to understand and study, exploiting the information and sensing capabilities given by the mobile device, the strategies implemented by the user to reach his objectives. This study gives a measure of the effectiveness of the information and the support obtained from the chosen applications/services. This second part of the proposed research activities involves also the use of modeling and formalization techniques of complex and highly variable/unpredictable processes, as human processes are. Preferential skills:
- Good background in knowledge representation, ontologies and Semantic Web related technologies.
- Skills in programming
- Some knowledge of processes modeling
4. Mobile User Profiling and Social Interaction
Contact persons: Fabio Pianesi (
), Michele Caraviello (
The rapid global growth of mobile and the advent of the smartphones have opened the way to new and powerful means for user profiling. Smartphones allow for unobtrusive and cost-effective access to previously inaccessible data – e.g., location, other devices in physical proximity, communication data, scheduled events, movement patterns, user interaction with the mobile phone - that can be very valuable in order to promote a more flexible and efficient personalization of delivered services as well as devising entirely new classes of services. The winner of this grant will work in a multidisciplinary team aiming to exploit the life-logging capability of smartphones to characterize as exhaustively as possible the social behavior of smartphone users, the kind of relationships they get involved in and the dynamics of their social networks.
View complete description