
Faiez GargouriUniversity of Sfax | US · Higher Institute of Computer Sceince and Multimedia of Sfax (ISIM)
Faiez Gargouri
Prof. of computer science
About
471
Publications
110,609
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,909
Citations
Introduction
Featured research
Artificial neural networks (ANNs) are being widely used in supervised machine learning to analyze signals or images for many applications. Using an annotated learning database, one of the main challenges is to optimize the network weights. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively such as gradient-based method, Newton-type method, meta-heuristic method. For the sake of efficiency, regularization is generally used. When non-smooth regularizers are used especially to promote sparse networks, such as the ℓ1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _1$$\end{document} norm, this optimization becomes challenging due to non-differentiability issues of the target criterion. In this paper, we propose an MCMC-based optimization scheme formulated in a Bayesian framework. The proposed scheme solves the above-mentioned sparse optimization problem using an efficient sampling scheme and Hamiltonian dynamics. The designed optimizer is conducted on four (4) datasets, and the results are verified by a comparative study with two CNNs. Promising results show the usefulness of the proposed method to allow ANNs, even with low complexity levels, reaching high accuracy rates of up to 94%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$94\%$$\end{document}. The proposed method is also faster and more robust concerning overfitting issues. More importantly, the training step of the proposed method is much faster than all competing algorithms.
The massive use of ontologies generates a large amount of semantic data. To facilitate their management, persistent solutions for storing and querying these semantic data loads have been proposed. This gave rise to a new type of databases, called ontology-based databases (OBDB). In recent years, the need for data and real-time services has increased significantly in a large number of applications. However, the OBDB does not implement any mechanism to address real-time applications which are characterized, not only by handling large amounts of data, but also by temporal constraints, to which can be submitted data and treatments. As well, geographically extended applications, requiring using real-time databases that manage data and distributed processing are increasingly needed.These applications are managed by Distributed Real-Time DataBase Management System (DRTDBMS). Like any system, the DRTDBMS, often go through overload phases, due to the unpredictable arrival of transactions submitted by users. In order to better manage Quality of Service (QoS) in these systems by facing instability periods, approaches based on Distributed Feedback Control Scheduling (DFCS) were proposed. These approaches does not address the use of ontological data. In this paper, we propose an approach aiming to enhance QoS in DRTDBMS based on data replication. It consists in extending the DFCS architecture by the manipulation of ontological data as well as handling the execution of accessing transactions. In the extension we propose, we study the applicability of different data replication policies. The proposed architecture is then called Replication-Based-Distributed Feedback Control Scheduling Architecture for Real-Time Ontology (Replication-Based-DFCS-RTO). We also show the contribution provided by our approach through simulation results.
Dealing with imperfect temporal data entries in the context of Collective and Personal Memory applications is an imperative matter. Data are structured semantically using an ontology called “Collective Memo Onto”. In this paper, we propose an approach that handles temporal data imperfections in OWL 2. We reduce to four types of imperfection defined in our typology of temporal data imperfections which are imprecision, uncertainty, simultaneously uncertainty and imprecision and conflict. The approach consists of representing imperfect quantitative and qualitative time intervals and time points by extending the 4D-fluents approach and defining new components, as well as reasoning about the handled data by extending the Allen’s Interval algebra. Based on both extensions, we propose an OWL 2 ontology named “TimeOntoImperfection”. The proposed qualitative temporal relations are inferred via a set of 924 SWRL rules. We validate our work by implementing a prototype based on the proposed ontology and we apply it in the context of the Collective Memory Temporal Data.
Efficient and accurate early prediction of Alzheimer's disease (AD) based on the neuroimaging data has attracted interest from many researchers to prevent its progression. Deep learning networks have demonstrated an optimal ability to analyse large-scale multimodal neuroimaging for AD classification. The most widely used architecture of deep learning is the Convolution neural networks (CNN) that have shown great potential in AD detection. However CNN does not capture long range dependencies within the input image and does not ensure a good global feature extraction. Furthermore, increasing the receptive field of CNN by increasing the kernels sizes can cause a feature granularity loss. Another limitation is that CNN lacks a weighing mechanism of image features; the network doesn’t focus on the relevant features within the image. Recently,vision transformer have shown an outstanding performance over the CNN and overcomes its main limitations. The vision transformer relies on the self-attention layers. The main drawbacks of this new technique is that it requires a huge amount of training data. In this paper, we combined the main strengths of these two architectures for AD classification. We proposed a new method based on the combination of the Cross ViT and Wide Residual Squeeze-and-Excitation Network. We acquired MRI data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS). We also proposed a new data augmentation based on the self attention progressive generative adversarial neural network to overcome the limitation of the data. Our proposed method achieved 99% classification accuracy and outperforms CNN models.
Personalised medicine is a new approach that ensure a tolerant and optimal diagnosis for the patient basing on his own data and its profile information such as life style, medical history, genetic data, behaviours, and his environment. These data is vital to predict the potential disease progression. Extracting insights from these heterogeneous data is a challenging task. Brain disorders such as neurodegenerative diseases detection and prediction is still an open challenge for research. The early prediction of these diseases is the key solution to prevent their progression. Deep learning methods has shown an outstanding performance on the brain diseases diagnosis such as the Alzheimer’s disease (AD). In this paper we present two contributions. Firstly, we adopt a conditional generative adversarial network for data augmentation based on two datasets the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Open Access Series of Imaging Studies (OASIS) as a solution for the shortage of health information. Additionally, we present a new method for an early detection of the Alzheimer’s disease based on the combination of the Densenet 201 network and the Squeeze and Excitation network. Furthermore, we compare our approach with the traditional Densenet 201, Squeeze and Excitation network and other networks. We figure out that our approach yields best results over these networks. We reach an accuracy of 98%.
Additional affiliations
August 2014 - present
Higher institute of computer science and multimedia
Position
- Managing Director
August 2014 - present
Institut Supérieur Informatique et de multimédia de Sfax
Position
- Managing Director
November 2003 - present
Publications
Publications (471)
Dealing with imperfect temporal data entries in the context of Collective and Personal Memory applications is an imperative matter. Data are structured semantically using an ontology called “Collective Memo Onto”. In this paper, we propose an approach that handles temporal data imperfections in OWL 2. We reduce to four types of imperfection defined...
Efficient and accurate early prediction of Alzheimer's disease (AD) based on the neuroimaging data has attracted interest from many researchers to prevent its progression. Deep learning networks have demonstrated an optimal ability to analyse large-scale multimodal neuroimaging for AD classification. The most widely used architecture of deep learni...
Personalised medicine is a new approach that ensure a tolerant and optimal diagnosis for the patient basing on his own data and its profile information such as life style, medical history, genetic data, behaviours, and his environment. These data is vital to predict the potential disease progression. Extracting insights from these heterogeneous dat...
Artificial neural networks (ANNs) are being widely used in supervised machine learning to analyze signals or images for many applications. Using an annotated learning database, one of the main challenges is to optimize the network weights. A lot of work on solving optimization problems or improving optimization methods in machine learning has been...
Augmented, Virtual and Mixed Reality Technology (AR / VR / MR) - also known as xR technology - is one of the key technologies of digital transformation. Thanks to the existing powerful immersive hardware systems, complex technical and natural systems can be digitally represented in a realistic virtual environment. This enables users to completely i...
Extended Reality technology (xR) contains Augmented, Virtual and Mixed Reality Technology (AR / VR / MR) is one of the key technologies of digital transformation. Thanks to the existing powerful immersive hardware systems, complex technical and natural systems can be digitally represented in a realistic virtual environment. This enables users to co...
Since December 2019, we have detected the appearance of a new virus called COVID-19, which has spread, throughout the world. Everyone today, has given major importance to this new virus. Although we have little knowledge of the disease, doctors and specialists make decisions every day that have a significant impact on public health. There are many...
Reading and interpreting the medical image still remains the most challenging task in radiology. Through the important achievement of deep Convolutional Neural Networks (CNN) in the context of medical image classification, various clinical applications have been provided to detect lesions from Magnetic Resonance Imaging (MRI) and Computed Tomograph...
The massive use of ontologies generates a large amount of semantic data. To facilitate their management, persistent solutions for storing and querying these semantic data loads have been proposed. This gave rise to a new type of databases, called ontology-based databases (OBDB). In recent years, the need for data and real-time services has increase...
Enterprise Information System (EIS) must cover the interoperability criteria inside its “application view” scope. Nevertheless, the urbanization approach, on which we rely to implement this EIS, has to deal with “horizontal fit” and “traversal fit” problems: lack of intra and inter-applicative communications problems. To overcome these deficiencies...
Typically, to implement a data warehouse, we have to extract the data from relational databases, XML files, etc., which are very used by companies. Since today’s data are generated from social media, GPS data, sensor data, surveillance data, etc., which are maintained in NoSQL databases, we are talking about big data warehouses (BDW). Hence, there...
With the proliferation of textual data on the web, efficient access to pertinent information to meet user’s needs becomes an important problem in information retrieval field. Semantic relationships between terms plays an important role in information retrieval field in order to disambiguate document content.
Modern graph database management systems use graph structures for semantic queries with nodes, edges, and properties to connect to and store information. Due to their schema-less nature, inappropriate data migration and manipulation can lead to severe data loss during the data query process. Data migration in graph databases strongly depends on gra...
Latest research studies on multi-dimensional design have combined business data with User-Generated Content (UGC). They have integrated new analytical aspects, such as user’s behavior, sentiments, opinions or topics of interest, to ameliorate decisional analysis. In this paper, we deal with the complexity of designing topics dimension schema due to...
Dealing with temporal data imperfections in Semantic Web is still under focus. In this paper, we propose an approach based on the possibility theory to represent and reason about time intervals that are simultaneously uncertain and imprecise in OWL2. We start by calculating the possibility and necessity degrees related to the imprecision and uncert...
Temporal data given by Alzheimer's patients are mostly uncertain. Many approaches have been proposed to handle certain temporal data and lack uncertain ones. This paper proposes an approach to represent and reason about quantitative time intervals and points and qualitative relations between them. It is suitable to handle certain and uncertain temp...
Background:
The COVID-19 lockdown could engender disruption to lifestyle behaviors, thus impairing mental wellbeing in the general population. This study investigated whether sociodemographic variables, changes in physical activity, and sleep quality from pre- to during lockdown were predictors of change in mental wellbeing in quarantined older ad...
The emergence of the Internet of Things (IoT) in the medical field has led to the massive deployment of a myriad of medical connected objects (MCOs). These MCOs are being developed and implemented for remote healthcare monitoring purposes including elderly patients with chronic diseases, pregnant women, and patients with disabilities. Accordingly,...
Nowadays, the virtual learning environment has become an ideal tool for professional self-development and bringing courses for various learner audiences across the world. There is currently an increasing interest in researching the topic of learner dropout and low completion in distance learning, with one of the main concerns being elevated rates o...
Performance is one of the major topics for organizations seeking continuous improvements. Evidently, evaluating the performance of business process model is a necessary step to reduce time, cost and to indicate whether the company goals are successfully achieved or not. In the literature, several researchers refers to different techniques that aim...
This book constitutes the thoroughly refereed proceedings of the 5th International Conference on Information and Knowledge Systems, ICIKS 2021, which was held online during June 22-23, 2021.
The International Conference on Information and Knowledge Systems (ICIKS 2021) gathered both researchers and practitioners in the fields of Information Systems...
Aims
Prognosis of lung mathology severity after Covid-19 infection using chest X-ray time series
Background
We have been inspired by methods analysing time series of images in remote sensing for change detection. During the current Covid-19 pandemic, our motivation is to provide an automatic tool to predict severity of lung pathologies due to Covi...
Symptoms of psychological distress and disorder have been widely reported in people under quarantine during the COVID-19 pandemic; in addition to severe disruption of peoples' daily activity and sleep patterns. This study investigates the association between physical-activity levels and sleep patterns in quarantined individuals. An international Go...
The number of audiovisual documents available on the web is exponentially increasing due to the rise of the number of videos produced every day. The recent progress in audiovisual documents field has made it possible to popularize the exchange of these documents in many domains. More generally, the interest in the indexing potential of audiovisual...
Background
Public health recommendations and government measures during the COVID-19 pandemic have enforced restrictions on daily-living. While these measures are imperative to abate the spreading of COVID-19, the impact of these restrictions on mental health and emotional wellbeing is undefined. Therefore, an international online survey (ECLB-COVI...
This work proposes a deep learning algorithm based on the Convolutional Neural Network (CNN) architecture to detect HepatoCellular Carcinoma (HCC) from liver DCE-MRI (Dynamic Contrast-Enhanced MRI) sequences. The Deep Learning technique is an artificial intelligence technique (AI) that tries to imitate the human brain work in the training data and...
In this paper, we propose an ontology-based approach for representing and reasoning about certain and uncertain temporal data. It handles temporal data in terms of quantitative time intervals and points and the qualitative relations between them (e.g., “before”). It includes three parts. (1) We extend the 4D-fluents approach with certain ontologica...
Public health recommendations and governmental measures during the new coronavirus disease (COVID-19) pandemic have enforced numerous restrictions on daily living including social distancing, isolation, and home confinement. While these measures are imperative to mitigate spreading of COVID-19, the impact of these restrictions on psychosocial healt...
Although recognised as effective measures to curb the spread of the COVID-19 outbreak, social
distancing and self-isolation have been suggested to generate a burden throughout the population. To provide
scientific data to help identify risk factors for the psychosocial strain during the COVID-19 outbreak, an international
cross-disciplinary online...
Enterprise Information Systems supporting business processes are to be characterized by integrity, flexibility, and interoperability. Nevertheless, the “three fit” problems (considered in the current paper) obstruct the achievement of those desired features both at the business-infrastructure and technical-infrastructure EIS levels: “vertical fit”...
Making the most from virtual learning environments captivates researchers, enhancing the learning experience and reducing the withdrawal rate. In that regard, this article presents a framework for a withdrawal prediction model for the data of the Open University, one of the largest distance-learning institutions. The main contributions of this work...
COVID-19 pandemic have resulted in numerous restrictions on daily living including social
distancing, isolation and home confinement. While these measures are imperative to abate the
spreading of COVID-19, the impact of these restrictions on health behaviours and lifestyles at home
is undefined. Therefore, an international online survey was launche...
Background:
Public health recommendations and governmental measures during the COVID-19 pandemic have resulted in numerous restrictions on daily living including social distancing, isolation and home confinement. While these measures are imperative to abate the spreading of COVID-19, the impact of these restrictions on health behaviours and lifest...
Background
Public health recommendations and governmental measures during the COVID-19 pandemic have enforced numerous restrictions on daily living including social distancing, isolation and home confinement. While these measures are imperative to mitigate spreading of COVID-19, the impact of these restrictions on psychosocial health is undefined....
Background:
Although recognised as effective measures to curb the spread of the COVID-19 outbreak, social distancing and self-isolation, have been suggested to generate burden throughout the population. To provide scientific data to help identify risk-factors for the psychosocial strain during the COVID-19 outbreak, an international cross-discipli...
Background:
Public health recommendations and government measures during the COVID-19 pandemic have enforced restrictions on daily living, which may include social distancing, remote work/school, and home confinement. While these measures are imperative to abate the spreading of COVID-19, the impact of these restrictions on mental health and emoti...
Background
Public health recommendations and governmental measures during the COVID-19 pandemic have enforced numerous restrictions on daily living including social distancing, isolation and home confinement. While these measures are imperative to abate the spreading of COVID-19, the impact of these restrictions on health behaviours and lifestyle a...
Humanity is facing nowadays a dramatic pandemic episode with the Coronavirus propagation over all continents. The Covid-19 disease is still not well characterized, and many research teams all over the world are working on either therapeutic or vaccination issues. Massive testing is one of the main recommendations. In addition to laboratory tests, i...
Humanity is facing nowadays a dramatic pandemic episode with the Coronavirus propagation over all continents. The Covid-19 disease is still not well characterized, and many research teams all over the world are working on either ther- apeutic or vaccination issues. Massive testing is one of the main recommendations. In addition to laboratory tests,...
Nowadays, the use of the Internet of Things (IoT) in diverse applications becomes very popular. Accordingly, a proliferation of objects with remote sensing, actuation, analysis, and sharing capabilities will be interconnected on top of heterogeneous communication networks. Their deployment contexts are continuously changed, which imply a change in...
Owing to the absolute significance of the business process management, companies have become thoroughly oriented toward a good modeling of the business processes. Although the business process modeling is a substantial part in workflow automation, business process designers often misunderstand domain concepts or relationships due to their lack of p...
Big Data emerged after a big explosion of data from the Web 2.0, digital sensors, and social media applications such as Facebook, Twitter, etc. In this constant growth of data, many domains are influenced, especially the decisional support system domain, where the integration of processes should be adapted to support this huge amount of data to imp...
Before talking about the security tools we must first think about what we should protect and how we should distinguish information that seems to be sensitive and identifiable among heterogeneous data that spread over several sources like Facebook, twitter and several other suppliers of big data. Thus, in this paper we proved a method of identifying...
Big volumes of data cannot be processed by traditional warehouses and OLAP servers which are based on RDBMS solutions. As an alternative solution, Not only SQL (NoSQL) databases are becoming increasingly popular as they have interesting strengths such as scalability and flexibility for an OLAP system. As NoSQL database offer great flexibility, they...
The past few years has seen the rapid growth of educational data mining approaches for the analysis of data obtained from the virtual learning environments (VLE). However, due to the open and online characteristics of VLEs, vast majority of learners may enroll and drop a course freely, resulting in high dropout rates problem. One of the key element...
As one of NoSQL data models, graph oriented databases are highly recommended to store and manage interconnected data. Used as back-end for today applications, NoSQL databases come with the challenge of effectively managing data evolution. In fact, NoSQL graph oriented databases offer a great flexibility. Usually such flexibility helps developers to...
Based on the assumption that users generally tend to use entities proposed by friends rather than strangers and that trust among friends significantly correlates with user’s trends, we decided to refer to research conducted on the evolving field of social trust computation. Although many models were proposed to analyze computational trust for vario...
Enterprise Information System (EIS) must cover the interoperability criterion between its business and technical infrastructures. Nevertheless, the “vertical fit” problems, which has deduced from the business infrastructure handicap the exploitation of this criterion. To overcome this failure, we propose in this paper our solutions to reduce the ga...
Ontology, as a useful knowledge engineering technique, has been widely used for reducing ambiguity and helping with information sharing. It is considered originally to be clear, comprehensive, and with well-defined format. It characterizes several domains purposes description through structured and formalized languages. In various areas of research...
Today eHealth is an emerging area becoming increasingly reliant upon medical information and communication technology.
The implementation of an eHealth strategy is important today to meet health goals, notably: promoting the effectiveness of medical data treatment and data retrieval, and improving the information flow between doctors and patients....
Social trust-based recommendation systems are currently based on the computation of the level of trust in users' interactions or on a combination of trust and similarity scores while generating recommendations. In this research paper, we propose a framework for a recommender system that is based on users' preferences on the one hand and on the opin...