1,720,990 research outputs found
Cellular Flow in mobility Network
No full textNearly all the members of adult population in major
developed countries transport a GSM/UMTS mobile terminal
which, besides its communication purpose, can be seen as a
mobility sensor, i.e. an electronic individual tag. The temporal
and spatial movements of these mobile tags being recorded allows
their flows to be analyzed without placing costly ad hoc sensors
and represents a great potential for road traffic analysis, forecasting, real time monitoring and, ultimately, for the analysis and the
detection of events and processes besides the traffic domain as
well. In this paper a model which integrates mobility constraints
with cellular networks data flow is proposed in order to infer
the flow of users in the underlying mobility infrastructure. An
adaptive flow estimation technique is used to refine the flow
analysis when the complexity of the mobility network increases.
The inference process uses anonymized temporal series of cell
handovers which meet privacy and scalability requirements.
The integrated model has been successfully experimented in the
domain of car accident detection
Emotional book classification from book blurbs
No full textKnowing and predicting opinions of people is considered a strategic added value, interpreting the qualia i.e., the subjective nature of emotional content. The aim of this work is to study the feasibility of an emotion recognition and automated classification of books according to emotional tags, by means of a lexical and semantic analysis of book blurbs. A supervised learning approach is used to determine if a correlation exists between the characteristics of a book blurb and emotional icons associated to the book by users. In this paper the underlying idea of the system is presented, the preprocessing and features extraction phases are described and experimental results on the social network Zazie and its mood tags are discussed
Data Summarization Model for User Action Log Files
No full textDuring last years we have seen an impressive growth and diffusion of applications shared and used by a huge amount of users around the world, like for example social networks, web portals or elearning platforms. Such systems produce in general a large amount of data, normally stored in its raw format in log file systems and databases. To prevent an unmanageable growing of the necessary space to store data and the breakdown of data usability, such data can be condensed and summarized to improve reporting performance and reduce the system load. This data summarization reduces the amount of space that is required to store software data but produces, as a side effect, a decrease of their informative capability due to an information loss. In this work the problem of summarizing data obtained by the log systems of applications with a lot of users is studied. In particular a model to represent these raw data as temporal events collected in time sequences is proposed, methods to reduce the data size, collapsing the descriptions of more events in a unique descriptor or in a smaller set of descriptors, are provided and the optimal summarization problem is posed
Representing Temporal Constraints in PDDL
No full textThis work present a portable technique for solving temporal network planning problems by compilation into equivalent standard classical planning problem domains. A temporal network planning problem specifies goals and initial knowledge in term of constraints among states, actions and events. Recent and performant automated planning systems have adopted the planning domain language PDDL which has became a de-facto standard for benchmark comparisons, unfortunately most of these planners have no capabilities of managing the temporal goals which arise in most real world situations. The presented technique temporal network planning is planner independent, portable and allow to exploit existing classical planners, such as PDDL compliant planners, in order to solve temporal planning problems. The technique is proved to be correct and has been implemented in TNC a temporal network compiler system based on PDDL, which hav
A learning methodology for coherent hybrid probabilistic fuzzy classifiers
No full textWe aim at redesigning the hybrid fuzzy classifier proposed in \cite{demeloetal}
that joins together probabilistic inference with classical Wang-Mendel fuzzy rule bases. We will profit from
coherent probabilistic fuzzy IF-THEN rules, as already described in \cite{colettipetturitivantaggi}, with a novel
elicitation strategy
based on a new learning methodology. This will lead us to propose a probabilistic fuzzy rule based classification algorithm.
The methodology for constructing and drawing inferences from a probabilistic fuzzy rule based classifier guarantees the global coherence of the probability evaluations and allows to take into account
potentially imprecise (lower-upper) probabilistic conclusions.
The proposed classification algorithm will be tested on a doping alert problem and compared with two other fuzzy IF-THEN rule based classifiers on artificial datasets
A Systematic Review of Data Analytics Job Requirements and Online-Courses
No full textData analytics’ growing importance in modern business has left many organizations unprepared in terms of human talent. This study sheds light on the intersection between the analytics job skills currently in demand and the offer of massive online open courses for developing them. We have scraped from the web the description of more than 14,000 job posts and 3,600 Data Analytics online courses to systematically capture the need for data skills and available learning opportunities. By using an original combination of topic modeling and text mining algorithms, we provide a systematic mapping of educational offers with business needs, quantifying their presence and identifying gaps. Our study enables both educational providers to improve their offering on Data Analytics and Human Resources professionals to identify skill development opportunities. Additionally, we introduce a general methodology able to produce systematic mappings of job skills and learning opportunities in any domain
- …
