Mobile User Profiler

Sisinf Lab logo

Application description

Nowadays smartphones play a significant role in gathering relevant data about their owners. Micro-devices embedded in Personal Digital Assistants (PDAs) perform a continuous sensing, the phone call lists, PIM (Personal Information Manager), text messages and so on allow to collect and mine data enough for a high-level description of daily activities of a user.

A smart profiling agent [1] has been proposed able to perform an automated profile annotation by adopting Semantic Web languages. The crawler agent runs on the user smartphone and performs a multimodal (i.e., involving several heterogeneous data sources) and continuous sensing collecting and processing information without human intervention. The multimodality requires specialized analyses for each kind of collected data. The agent mines the user habits automatically and annotates them in a logic-based formalism to build a daily profile to be further exploited in context-aware knowledge-based applications.

The proposed user agent is intended as a part of a more complex Home and Building Automation (HBA) Multi Agent System (MAS) [2] leveraging the semantic-based evolution of the KNX domotic protocol. Figure 1 sketches the general architecture of the profiling agent. The data mining life cycle consists of the following subsequent stages:
  1. gathering
  2. feature extraction
  3. classification and interpretation
  4. semantic annotation
High-level information about user activities, whereabouts, mental and physical status is inferred and annotated w.r.t. a reference HBA ontology. In particular three modules fully characterize the agent at the moment:
  • Points of Interest Recognition
  • Transportation Mode Recognition
  • User Activity Recognition
An overall evaluation of the proposed approach has been carried out following a reference user for a period of 14 months. Results reported in [1] refer to the first 60 days of observation.

Figure 1: Reference Architecture and Screenshots.


Publications

  1. M. Ruta, F. Scioscia, G. Loseto, E. Di Sciascio. Semantic-based resource discovery and orchestration in Home and Building Automation: a multi-agent approach. IEEE Transactions on Industrial Informatics , Volume 10, Number 1, page 730-741, 2014.

  2. G. Loseto, M. Ruta, F. Scioscia, E. Di Sciascio, M. Mongiello. Mining the user profile from a smartphone: a multimodal agent framework. 14th Workshop on Objects and Agents (WOA 2013), December 2013.

Download

Project coordinators


Valid XHTML 1.1   Valid CSS

:: hosted by SisInf Lab http://sisinflab.poliba.it ::