Though research on the Semantic Web has progressed at a steady pace, its promise has yet to be realized. One major difficulty is that, by its very nature, the Semantic Web is a large, uncensored system to which anyone may contribute. This raises the question of how much credence to give each source. We cannot expect each user to know the trustworthiness of each source, nor would we want to assign top-down or global credibility values due to the subjective nature of trust. We tackle this problem by employing a web of trust, in which each user maintains trusts in a small number of other users. We then compose these trusts into trust values for all other users. The result of our computation is not an agglomerate "trustworthiness" of each user. Instead, each user receives a personalized set of trusts, which may vary widely from person to person. We define properties for combination functions which merge such trusts, and define a class of functions for which merging may be done locally while maintaining these properties. We give examples of specific functions and apply them to data from Epinions and our BibServ bibliography server. Experiments confirm that the methods are robust to noise, and do not put unreasonable expectations on users. We hope that these methods will help move the Semantic Web closer to fulfilling its promise.

Trust management for the Semantic Web

The B Book

http://www.umbertostraccia.it/cs/download/papers/JWS08/JWS08.pdf

Managing uncertainty and vagueness in description logics for the Semantic Web

https://www.um.edu.mt/library/oar/bitstream/123456789/22142/1/bt45-aij.pdf

Automatic generation of textual summaries from neonatal intensive care data

Preferences in AI: An overview

In many fields of automated information processing it becomes crucial to consider imprecise, uncertain or inconsistent pieces of information. Therefore, integrating uncertainty factors in argumentation theory is of paramount importance. Recently, several argumentation based approaches have emerged to model uncertain data with probabilities. In this paper, we propose a new argumentation system called evidential argumentation framework that takes into account imprecision and uncertainty modeled by means of evidence theory. Indeed, evidence theory brings new semantics since arguments represent expert opinions with several weighted alternatives. Then, the evidential argumentation framework is studied in the light of both Smets and Demspter-Shafer interpretations of evidence theory. For each interpretation, we generalize Dung’s standard semantics with illustrative examples. We also investigate several preference criteria for pairwise comparison of extensions in order to select the ones that represent potential solutions to a given decision making problem.

Argumentation Framework Based on Evidence Theory

In many applications domains, time modeling has a fundamental role. Allen temporal relations are one of the most used and known formalisms for modeling and handling temporal data. However, classical Allen relations deal only with crisp time information, but time is often subjective and fuzzy. This paper discusses a disjunctive view of temporal relations between fuzzy time intervals. This approach is mostly based on an extension of Allen relations allowing to compare two fuzzy time intervals. By leveraging some particular fuzzy comparison indices, this extension is implemented in the Fuzz - TIME tool developed in our previous works.

Modeling temporal relations between Fuzzy TIME intervals: A disjunctive view

Uncertain data are obvious in a lot of domains such as sensor networks, multimedia, social media, etc. Top-k queries provide ordered results according to a defined score. This kind of queries represents an important tool for exploring uncertain data. Most of works cope with certain data and with probabilistic top-k queries. However, at the best of our knowledge there is no work that exploits the Top-k semantics in the Evidence Theory context. In this paper, we introduce a new score function suitable for Evidential Data. Since the result of the score function is an interval, we adopt a comparison method for ranking intervals. Finally we extend the usual semantics/interpretations of top-k queries to the evidential scenario.

On Top-K Queries Over Evidential Data.

This paper introduces a new type of database queries involving preferences. The idea is to consider competitive conditional preference clauses structured as a tree, of the type “preferably P1 or ⋅⋅⋅ or Pn; if P1 then preferably P1,1 or …; if P2 then preferably P2,1 or …,” where the Pis are not exclusive (thus the notion of competition). The paper defines two possible interpretations of such queries and outlines two evaluation techniques which follow from them. © 2010 Wiley Periodicals, Inc. © 2011 Wiley Periodicals, Inc.

On database queries involving competitive conditional preferences

Dempster-Shafer theory is an essential tool for modelling and reasoning under uncertainty, and it is an effective approach for multisensor data fusion. It is extensively deployed in many fields such as fault diagnosis, image processing, pattern recognition, etc. However, Dempster’s combination rule is often subject to counter-intuitive results when the sources highly conflict; several methods have been proposed in the literature to solve this problem. In this paper, a weighted evidence combination method based on evidence distance, evidence angle, and information volume is proposed to overcome the shortcomings of the classical Dempster’s combination rule. To investigate the effectiveness and performance of the proposed method, a comparative study with different state of the art methods using both benchmark numerical example and Fault diagnosis application has been carried out.

Allel Hadjali

Papers

Argumentation Framework Based on Evidence Theory

Modeling temporal relations between Fuzzy TIME intervals: A disjunctive view

On Top-K Queries Over Evidential Data.

On database queries involving competitive conditional preferences

An Advanced Weighted Evidence Combination Method for Multisensor Data Fusion in IoT