Elisabetta Binaghi

A fuzzy set-based accuracy assessment of soft classification

Despite the sizable achievements obtained, the use of soft classifiers is still limited by the lack of well-assessed and adequate methods for evaluating the accuracy of their outputs. This paper proposes a new method that uses the fuzzy set theory to extend the applicability of the traditional error matrix method to the evaluation of soft classifiers. It is designed to cope with those situations in which classification and/or reference data are expressed in multimembership form and the grades of membership represent diAerent levels of approximation to intrinsically vague classes. ” 1999 Elsevier Science B.V. All rights reserved.

Slope Instability Zonation: a Comparison Between Certainty Factor and Fuzzy Dempster–Shafer Approaches

This paper presents a comparison between two methodologies for the evaluation of slope instability and the production of instability maps, using a probabilistic approach and a hybrid possibilistic and credibilistic approach. The first is the Certainty Factor method, and the second is based on Fuzzy Logic integrated with the Dempster–Shafer theory. These methodologies are applied to the 1 : 50,000 scale Fabriano (Marche, Italy) geological map sheet. The results are represented as histograms where the accuracy of the prediction is shown, and the comparison of the results of the methods is discussed.

Content-based filtering in on-line social networks

This paper proposes a system enforcing content-based message filtering for On-line Social Networks (OSNs). The system allows OSN users to have a direct control on the messages posted on their walls. This is achieved through a flexible rule-based system, that allows a user to customize the filtering criteria to be applied to their walls, and a Machine Learning based soft classifier automatically labelling messages in support of content-based filtering.

Comparison of the multilayer perceptron with neuro-fuzzy techniques in the estimation of cover class mixture in remotely sensed data

Mixed pixels are a major source of inconvenience in the classification of remotely sensed data. This paper compares MLP with so-called neuro-fuzzy algorithms in the estimation of pixel component cover classes. Two neuro-fuzzy networks are selected from the literature as representatives of soft classifiers featuring different combinations of fuzzy set-theoretic principles with neural network learning mechanisms. These networks are: 1) the fuzzy multilayer perceptron (FMLP) and 2) a two-stage hybrid (TSH) learning neural network whose unsupervised first stage consists of the fully self-organizing simplified adaptive resonance theory (FOSART) clustering model, FMLP, TSH, and MLP are compared on CLASSITEST, a standard set of synthetic images where per-pixel proportions of cover class mixtures are known a priori. Results are assessed by means of evaluation tools specifically developed for the comparison of soft classifiers. Experimental results show that classification accuracies of FMLP and TSH are comparable, whereas TSH is faster to train than FMLP. On the other hand, FMLP and TSW outperform MLP when little prior knowledge is available for training the network, i.e., when no fuzzy training sites, describing intermediate label assignments, are available.

A cognitive pyramid for contextual classification of remote sensing images

Many cases of remote sensing classification present complicated patterns that cannot be identified on the basis of spectral data alone, but require contextual methods that base class discrimination on the spatial relationships between the individual pixel and local and global configurations of neighboring pixels. However, the use of contextual classification is still limited by critical issues, such as complexity and problem dependency. We propose here a contextual classification strategy for object recognition in remote sensing images in an attempt to solve recognition tasks operatively. The salient characteristics of the strategy are the definition of a multiresolution feature extraction procedure exploiting human perception and the use of soft neural classification based on the multilayer perceptron model. Three experiments were conducted to evaluate the performance of the methodology, one in an easily controlled domain using synthetic images, the other two in real domains involving builtup pattern recognition in panchromatic aerial photographs and high-resolution satellite images.

IMAGE RETRIEVAL USING FUZZY EVALUATION OF COLOR SIMILARITY

The paper describes the design and implementation of an information retrieval system using color as the index in its color image archive. Salient aspects of this approach are the use of direct visual representation of color in querying and of fuzzy set theory to formally represent intrinsic human uncertainty in evaluating the similarity between colors (query interpretation). The steps in which the information retrieval strategy is organized are illustrated, and an example of its application given, showing how the implemented system can be tailored to manage archives of images representing fabric samples.

A System to Filter Unwanted Messages from OSN User Walls

One fundamental issue in todays Online Social Networks (OSNs) is to give users the ability to control the messages posted on their own private space to avoid that unwanted content is displayed. Up...One fundamental issue in todays Online Social Networks (OSNs) is to give users the ability to control the messages posted on their own private space to avoid that unwanted content is displayed. Up to now, OSNs provide little support to this requirement. To fill the gap, in this paper, we propose a system allowing OSN users to have a direct control on the messages posted on their walls. This is achieved through a flexible rule-based system, that allows users to customize the filtering criteria to be applied to their walls, and a Machine Learning-based soft classifier automatically labeling messages in support of content-based filtering.

An online document clustering technique for short web contents

Document clustering techniques have been applied in several areas, with the web as one of the most recent and influential. Both general-purpose and text-oriented techniques exist and can be used to cluster a collection of documents in many ways. This work proposes a novel heuristic online document clustering model that can be specialized with a variety of text-oriented similarity measures. An experimental evaluation of the proposed model was conducted in the e-commerce domain. Performances were measured using a clustering-oriented metric based on F-Measure and compared with those obtained by other well-known approaches. The obtained results confirm the validity of the proposed method both for batch scenarios and online scenarios where document collections can grow over time.

A neural model for fuzzy Dempster–Shafer classifiers

Abstract This paper presents a supervised classification model integrating fuzzy reasoning and Dempster–Shafer propagation of evidence has been built on top of connectionist techniques to address classification tasks in which vagueness and ambiguity coexist. The salient aspect of the approach is the integration within a neuro-fuzzy system of knowledge structures and inferences for evidential reasoning based on Dempster–Shafer theory. In this context the learning task can be formulated as the search for the most adequate “ingredients” of the fuzzy and Dempster–Shafer frameworks such as the fuzzy aggregation operators, for fusing data from different sources and focal elements, and basic probability assignments, describing the contributions of evidence in the inference scheme. The new neural model allows us to establish a complete correspondence between connectionist elements and fuzzy and Dempster–Shafer ingredients, ensuring both a high level of interpretability, and transparency and high performance in classification. Experiments with simulated data show that the network can cope well with problems of different complexity. The experiments with real data show the superiority of the neural implementation with respect to the symbolic representation, and prove that the integration of the propagation of evidence provides better classification results and fuzzy reasoning within connectionist schema than those obtained by pure neuro-fuzzy models.

Fuzzy reasoning approach to similarity evaluation in image analysis

In image analysis, the concept of similarity has been widely explored and various measures of similarity, or of distance, have been proposed that yield a quantitative evaluation. There are cases, however, in which the evaluation of similarity should reproduce the judgment of a human observer based mainly on qualitative and, possibly, subjective appraisal of perceptual features. This process is best modeled as a cognitive process based on knowledge structures and inference strategies, able to incorporate the human reasoning mechanisms and to handle their inherent uncertainties. This articlea proposes a general strategy for similarity evaluation in image analysis considered as a cognitive process. A salient aspect is the use of fuzzy logic propositions to represent knowledge structures, and fuzzy reasoning to model inference mechanisms. Specific similarity evaluation procedures are presented that demonstrate how the same general strategy can be applied to different image analysis problems.