Raouia Ayachi

Brain Tumor Segmentation Using Support Vector Machines

One of the challenging tasks in the medical area is brain tumor segmentation which consists on the extraction process of tumor regions from images. Generally, this task is done manually by medical experts which is not always obvious due to the similarity between tumor and normal tissues and the high diversity in tumors appearance. Thus, automating medical image segmentation remains a real challenge which has attracted the attention of several researchers in last years. In this paper, we will focus on segmentation of Magnetic Resonance brain Images (MRI). Our idea is to consider this problem as a classification problem where the aim is to distinguish between normal and abnormal pixels on the basis of several features, namely intensities and texture. More precisely, we propose to use Support Vector Machine (SVM) which is within popular and well motivating classification methods. The experimental study will be carried on Gliomas dataset representing different tumor shapes, locations, sizes and image intensities.

Proactive and reactive e-government services recommendation

AbstractGovernmental portals designed to provide electronic services are generally overloaded with information that may hinder the effectiveness of e-government services. This paper proposes a new framework to supply citizens with adapted content and personalized services that satisfy their requirements and fit with their profiles in order to guarantee universal access to governmental services. The proposed reactive and proactive solutions combine several recommendation techniques that use different data sources i.e., citizen profile, social media databases, citizen’s feedback databases and service databases. It is shown that recommender systems provide citizens with accessible personalized e-government services.

Decision Model for Policy Makers in the Context of Citizens Engagement

Citizens’ engagement is considered as one of the important dimensions for the development of smart cities since, in the vision of a city of the future (smart city), citizens will be more and more involved in the decision-making process of different issues related to the development of a city. In this context, policy makers face a decision problem where they have to integrate a new dimension, which is the voice of the citizens’ decision. This article proposes a tool based on multicriteria decision making methods to provide decision makers with the best alternative(s) that are based on citizens’ opinions. In order to tackle the potential interdependencies between criteria and also between alternatives in the selection process, we apply a hybrid model integrating the analytical network process and an extended version of technique for order performance by similarity to ideal solution to support group decision-making. The proposed model is applied in the context of participatory budgeting (PB) where citizens decide on the projects in which the money can be invested. This process is complex since it encompasses multiple interdependent criteria that may be conflicting with each other and that are used to take decisions. To illustrate our approach, we will apply the proposed technique for the case study of La Marsa, a city in the north of the capital Tunis (Tunisia) that adopted, since 2014, a PB strategy in which citizens proposed alternatives on how an amount of money can be used to lighten specific streets in the city.

Probability-Possibility Transformation:

Probability-possibility transformation is a purely mechanical transformation of probabilistic support to possibilistic support and vice versa. In this paper, we apply the most common transformations to graphical models, i.e., Bayesian into possibilistic networks. We show that existing transformations are not appropriate to transform Bayesian networks to possibilistic ones since they cannot preserve the information incorporated in joint distributions. Therefore, we propose new consitency properties, exclusively useful for graphical models transformations.

Compiling min-based possibilistic causal networks: a mutilated-based approach

Qualitative causal possibilistic networks are important tools for handling uncertain information in the possibility theory framework. Despite their importance, no compilation has been performed to ensure causal reasoning in possibility theory framework. This paper proposes two compilation-based inference algorithms for min-based possibilistic causal networks. The first is a possibilistic adaptation of the probabilistic inference method [8] and the second is a purely possibilistic approach. Both of them are based on an encoding of the network into a propositional theory and a compilation of this output in order to efficiently compute the effect of both observations and interventions, while adopting a mutilation strategy.

A novel personalized academic venue hybrid recommender

To see his work accepted and published, a researcher should submit it to the most appropriate conferences or journals. When a researcher schedules to submit his paper, it is generally difficult to him to find an upcoming conference that fits his research topics and also his requirements. To tackle this problem, we propose a personalized academic venue recommendation solution related to venues in the computer science field. Since generally researchers who are cited in the references share the same research interests with a target researcher, our approach is based on bibliographic data augmented by citation relationships between papers. The main idea is to recommend venues on the basis of those of his co-authors, co-citers and co-affiliated. The reliability of each researcher is taken into account to make recommendations. Then, call of papers data are used to recommend personalized upcoming conferences to a given researcher. Our hybrid recommendation system is able to filter out irrelevant conferences that do not respond to the researchers requirements (ranking, publisher, location). The cold start problem for young researchers is also taken into account. Experiments with the bibliographic citation dataset show that our new approach outperforms the standard collaborative filtering and provides accurate recommendation.

Inference using compiled min-based possibilistic causal networks in the presence of interventions

Qualitative possibilistic causal networks are important tools for handling uncertain information in the possibility theory framework. Contrary to possibilistic networks (Ayachi et al., 2011 [2]), the compilation principle has not been exploited to ensure causal reasoning in the possibility theory framework. This paper proposes mutilated-based inference approaches and augmented-based inference approaches for qualitative possibilistic causal networks using two compilation methods. The first one is a possibilistic adaptation of the probabilistic inference approach (Darwiche, 2002 [13]) and the second is a purely possibilistic approach based on the transformation of the graphical-based representation into a logic-based one (Benferhat et al., 2002 [3]). Each of the proposed methods encodes the network or the possibilistic knowledge base into a propositional base and compiles this output in order to efficiently compute the effect of both observations and interventions. This paper also reports on a set of experimental results showing cases in which augmentation outperforms mutilation under compilation and vice versa.

Possibilistic Local Structure for Compiling Min-Based Networks

Compiling graphical models has recently been triggered much research. First investigations were established in the probabilistic framework. This paper studies compilation-based inference in min-based possibilistic networks. We first take advantage of the idempotency property of the min operator to enhance an existing compilation-based inference method in the possibilistic framework. Then, we propose a new CNF encoding which fits well with the particular case of binary networks.

Experimental comparative study of compilation-based inference in bayesian and possibilitic networks

Graphical models are important tools for representing and analyzing uncertain information. Diverse inference methods were developed for efficient computations in these models. In particular, compilation-based inference has recently triggered much research, especially in the probabilistic and the possibilistic frameworks. Even though the inference process follows the same principle in the two frameworks, it depends strongly on the specificity of each of them, namely in the interpretation of handled values (probability\possibility) and appropriate operators (*\min and +\max). This paper emphasizes on common points and unveils differences between the compilation-based inference process in the probabilistic and the possibilistic setting from a spatial viewpoint.

Inference Using Compiled Product-Based Possibilistic Networks

Possibilistic networks are important graphical tools for representing and reasoning under uncertain pieces of information. In possibility theory, there are two kinds of possibilistic networks depending if possibilistic conditioning is based on the minimum or on the product operator. This paper explores inference in product-based possibilistic networks using compilation. This paper also reports on a set of experimental results comparing product-based possibilistic networks and min-based possibilistic networks from a spatial point of view.