Abdennaceur Kachouri

• Professor
• Engineer at University of Sfax

Cognitive fatigue (CF) is a complex disorder that affects the human being efficiency in work and daily activities. Researchers are actively exploring various physiological signals to monitor fatigue, with electroencephalography (EEG) being considered a top indicator for recognizing cognitive fatigue. Traditionally, fatigue patterns are visually mar...

Electroencephalogram (EEG) data are susceptible to artifacts, such as lapses in concentration or poor imagination, which can significantly impact the accuracy of disease diagnosis in e-health applications. To mitigate this issue, the use of machine learning (ML) and potentially artificial intelligence (AI) solutions to accurately identify outliers...

This paper introduces a new Distributed State Variable Estimation Algorithm (DSVEA). This algorithm is developed based on the Kalman filter for estimating the state variables of large-scale systems. This new approach involves decomposing the large-scale state estimation problem into several interconnected local sub-estimation problems. To demonstra...

This paper proposes a distributed joint parameter and state variables estimation algorithm for large-scale state-space interconnected systems. In this distributed estimation scheme, each interconnected sub-system is described by a linear discrete-time state space mathematical model. Each sub-system is supposed to be controlled by an intelligent con...

Objectives The present study is designed to explore the process of epileptic patterns’ automatic detection, specifically, epileptic spikes and high-frequency oscillations (HFOs), via a selection of machine learning (ML) techniques. The primary motivation for conducting such a research lies mainly in the need to investigate the long-term electroence...

Interictal high-frequency oscillations (HFOs) recorded in intracranial electroencephalographic (iEEG) signals are reliable biomarkers for the epileptogenic zone. Visual identification of these particular events is manually time-consuming and is subject to clinicians’ expertise. Moreover, differentiating them from other transient events such as inte...

This paper deals with parameter estimation problem of large‐scale systems. A recursive distributed parameter estimation algorithm, based on the minimization of the prediction estimation error method, is developed. Specifically, the class of large‐scale systems that are composed of several interconnected sub‐systems is considered. Each interconnecte...

Electroencephalogram (EEG) data suffer from artifacts such as poor imagination or loss of concen-tration during the recognition process. The negative impact of artifacts on the quality of informationand EEG signal analysis reduces the Quality of Service "QoS" and Quality of Information "QoI" ine-health applications. This negative impact can be avoi...

Abstract: Spontaneous High Frequency Oscillations (HFOs) have been considered as emerging specific biomarkers of the epileptogenic region. As a first issue, a significant difference in the implementation of automatic HFOs detection methods can sometimes occur between researchers. In addition, clinicians are not even particularly familiar with the c...

IoT presents a new technology that aims to interconnect numerous smart devices to provide operators with many smart services. Generally, wireless sensor networks (WSNs) are the key paradigm that ensures Internet of Things (IoT) applications. Due to the limitation of energy sensor resources, the IoT-based WSN is an energy efficiency strategy. In thi...

The localization of the epileptogenic zone (EZ) is crucial for the successful surgical treatment of epileptic patients who suffer from drug-resistant epilepsy. In this paper, we propose a new approach for EZ localization. The partial directed coherence approach and the outstrength parameter derived from graph theory are used to characterize the syn...

Standardized by Internet Engineering Task Force (IETF) working group, RPL (Routing Protocol for Low Power and Lossy networks) stands as an effective IPV6 Routing Protocol that establishes a path between any sensor and the sink wich typically collect the information generated by a wireless sensor network. For this purpose, RPL constructs a Destinati...

High Frequency Oscillations (HFOs) occurring in the range of [30–500 Hz] in epileptic intracranial ElectroEncephaloGraphic (iEEG) signals have recently proven to be good biomarkers for localizing the epileptogenic zone. Identifying these particular cerebral events and their discrimination from other transient events like interictal epileptic spikes...

Characterizing epileptogenic zones EZ (sources responsible of excessive discharges) would assist a neurologist during epilepsy diagnosis. Locating efficiently these abnormal sources among magnetoencephalography (MEG) biomarker is obtained by several inverse problem techniques. These techniques present different assumptions and particular epileptic...

Density-based algorithms are important data clustering techniques used to find arbitrary shaped clusters and outliers. Recently, outlier detectors through density-based clustering are applied to supervise data streams including wireless sensor networks (WSN’s). In this article, we compare two density-based methods, DBSCAN and OPTICS, using proposed...

Recognizing persons in a video surveillance scene in the real world is attractive and is now showing an increasing interest. The task of person Re-Identification (Re-ID) consists in assigning the same identifier to all instances of a particular individual captured in a series of images or videos, even after the occurrence of significant gaps over t...

Purpose – The purpose of this paper is to deal with the classification improvement of pollutant using WO3 gases sensors. To evaluate the discrimination capacity, some experiments were achieved using three gases: ozone, ethanol, acetone and a mixture of ozone and ethanol via four WO3 sensors. Design/methodology/approach – To improve the classificati...

Robust MAC represents a critical tool whereby several devices could simultaneously access the M2M network channel. Simplex MAC protocols, whether reservation or contention based, as predominantly figuring in the relevant literature associated works, may not be able to provide a scalable solution for M2M networks enclosing a large number of heteroge...

A power-efficient K-means clustering algorithm for Wireless Sensor Networks (WSN) is proposed. This algorithm aims to manage the consumption of energy by WS nodes and enhance the running time for WSN given space constraints. WS node cluster formation is structured as a sample space partition in k-means for the reason that the radio channel is unsta...

Nowadays, Granger causality techniques are frequently applied to investigate complex dynamical systems such as brain networks. Indeed, various derivations have been proposed from the initially basic definition of the Granger causality concept to deal with two fundamental issues of how to cope with dynamical nonlinearities when they are present and...

In this paper, we present a new design of cryptosystem characterized by an optimized substitution box (S-box) and random permutation. Our proposed S-box is generated using a modified genetic algorithm. The crossover process is performed with sophisticated research using the best previous population. We use randomness and ergodicity of the logistic...

Wireless Sensor Networks (WSNs)-based networking systems introduces to transfer from traditional industry to digital industry, commonly known as the fourth stage of industrialization (Industry 4.0). The WSN is an encouraging technology for many industrial applications because of their several potential benefits. However, they impose several challen...

1. Wearable sensor ‎which is connected to Internet of things (IoT) based big data i.e. data mining ‎analysis in healthcare.‎ 2. Artificial intelligence (AI) techniques to ‎predict the diseases(DEEP LEARNING).‎

Hierarchical architecture, in combination with static structure, is a productive approach to Wireless Sensor Networks (WSNs) scalability as well as efficiency. Sensor nodes, a dual-layer framework, are extensively explored for several scenarios. This paper demonstrates the proposed novel clustering methodology representing it as the Minimum Weight...

The authors propose a novel multiple weight low energy adaptive clustering hierarchy (MW‐LEACH) protocol for wireless sensor networks. In MW‐LEACH, they select the cluster heads (CHs) based on the residual energy, the distances between the CHs, and an optimal number of member nodes. The nodes are selected from the initial set based on the high resi...

With the advent of the Internet of Things Technologies (IOT), smart homes, and smart city applications, E-Nose was created. Almost of gas sensors consisting the electronic nose system suffer from cross sensitivity and lack of selectivity. Coupling smart gas sensors with artificial intelligence algorithms can thus empower conventional gas sensing te...

The topic of Person Re-Identification (Re-ID) is currently attracting much interest from researchers due to the various possible applications such as behavior recognition, person tracking and safety purposes at public places. General approach is to extract discriminative color and texture features from images and calculate their distances as a meas...

L’originalité de notre projet concerne la proposition et la simulation d’une méthode de géolocalisation et de suivi de patients dans un milieu médicalisé pour une utilisation en intérieur. L’objectif majeur de cette étude est de réaliser un compromis satisfaisant entre précision de positionnement, complexité de calcul et coût énergétique.

Cette thèse s’inscrit dans le cadre d’une thèse en cotutelle entre l’école nationale d’ingénieurs de Sfax (ENIS) et le conservatoire national d’arts et métiers de paris (CNAM) qui a pour objectif de proposer des solutions innovantes en termes de synchronisation, de consommation d’énergie, de qualité de service, de fusion et d’agrégation de données...

Energy harvesting from the human body is considered as an effective solution for powering biomedical systems. In particular, the piezoelectric energy recovery from mechanical vibrations of the human body represents the most promising solution. The harvested power depends on several factors such as the geometry, the size and materials used for the p...

The present paper proposes an improved adaptive differential evolution algorithm, the IL-SHADE algorithm, to solve Economic Dispatch Problems (EDPs) taking into account practical constraints, such as transmission network losses, ramp rate limit, prohibited operation zone and valve point effect. The IL-SHADE algorithm is introduced as an improved ve...

In this paper, we propose a new method for optical image encryption using fractional Fourier transform, DNA sequence operation and chaos theory. Random phase masks are generated using iterative Lorenz map and the plain image is transformed to a DNA matrix. This matrix is combined with the random phase mask and then transformed three times using the...

Electroencephalography (EEG) is a common tool used for the detection of epileptic seizures. However, the visual analysis of long-term EEG recordings is characterized by its subjectivity, time-consuming procedure and its erroneous detection. Various epileptic seizure detection algorithms have been proposed to deal with such issues. In this study, a...

L’équipe "Microélectronique et Electronique Médicale" du LETI de l’École Nationale d’Ingénieurs de Sfax (ENIS), en collaboration avec l’unité de recherche neuro pédiatrie, UR12ES16, service de neurologie pédiatrique, Hédi Chaker, Sfax, les associations AUE et Al Majarra; organisent une Journée Scientifique pour les doctorants, les étudiants en méde...

Metal oxide gas sensors have enabled gas and vapor detection with high sensitivity. However, this type of sensor suffer from lack of selectivity. Noise spectroscopy is one of solution to improve the selectivity. In this paper, we propose a technique based on using low-frequency noise to extract new features, which form unique gas signatures. By app...

In this article, a novel 3D meandered planar inverted‐F antenna (PIFA) is proposed for dual band application targeting Wireless Body Area Network (WBAN). The proposed antenna is printed on the casing of a 3D‐base‐station model having a size of 88 × 95 × 10.2 mm3. The proposed PIFA covers two bands including medical implant communication service (MI...

The present paper exhibits a fully distributed cooperative algorithm based on consensus protocols to solve the economic dispatch problem (EDP) in the concept of the smart grids. In particular, the proposed protocol eliminates the need for a leader or a coordinated center and considers the vulnerability of the communication networks such as the link...

In a Wireless Sensor Network, one of the important issues is minimizing energy consumption without losing accuracy during data transmission. Communication must be released in an optimized way, which enhances energy efficiency in the networks. By applying various techniques especially node balance set, the network lifetime is increased and delay is...

The prediction of the hearing thresholds using the pure tone audiometer is an essential part of the hearing test to know the sensitivity of the human hearing. In this paper, we present a pure tone audiometer implemented in MATLAB development environment for a personal computer. A flowchart presents the different steps to facilitate the use of the g...

The present research is designed to present an Improved Success-History based Adaptive Differential Evolution (L-SHADE) algorithm to solve a practical Economic Dispatch Problem (EDP). Simultaneously involving both of the multiple fuel option and valve-point effects make the EDP formulation more and more complex non-smooth optimization issue. Noting...

In this paper, we presented the design and simulation results of a platinum meander–spiral combination micro heater for a zinc oxide (ZnO) gas sensor. As a first step, different optimizations have been performed using a finite element analysis in order to obtain a compromise between maximum temperature, maximum homogeneity in active area and minimu...

In this paper, a meandered loop antenna, useful for medical cardiac monitoring application, more specifically, for heart beating close scrutiny is designed and experimentally tested. The proposed antenna is operating at the MICS band displays a high flexibility which allowing it to be curved easily around the heart's wall. In both, Simulation and m...

Methods By applying various techniques especially node balance set, the network lifetime is increased and delay is minimized. To accomplish node balance set, Cluster Head (CH) determination mechanism is implemented and clustering based load balanced is established. Further, the enactment of the anticipated designs is established through simulations...

An electronic nose is an intelligent system which consists of a sensor network and a pattern recognition system able to know simple and complex odors. As the human nose, the artificial nose must learn to recognize different odors: the learning phase. There are several types of sensors such as fiber optic sensors, piezoelectric sensors, and sensor t...

Combined Economic Environmental Dispatch Problem (CEEDP) is one of the greatest challenges of the future smart grids. It aims at reducing the total cost during the power production process considering the growing environmental impact due to the emission of gaseous pollutants of fossil fuels. This paper develops a robust distributed algorithm based...

This work suggests to detect abnormalities from spatial distribution of data using a numerical outlier data detector in a wireless sensor network (WSN). The detector is able to find anomalous from one or many events by using KNN technique and Euclidian distance. WSN uses a Low Energy Adaptive Clustering Hierarchy protocol (LEACH), where we compute...

Energy management is one of the most challengesfor the future smart grids.It aims toreduce the total operation cost when producing a certain amount of power. In this paper a distributed consensus protocol is investigated to resolve the Economic Dispatch Problem (EDP) in the next generation of power system, considering the power balance constraint a...

Combined economic environmental dispatch problem (CEEDP) is one of the greatest challenges of the future smart grids. It aims at reducing the total cost during the power production process considering the growing environmental impact due to the emission of gaseous pollutants of fossil fuels. This study develops a robust distributed algorithm based...

The design of a micro hotplate is very important since it is a key component of micro-sensors, particularly gas sensors. A WO3 gas sensor requires a maximum temperature of 300 °C for ozone detection. This paper discussed the design and simulation of a novel platinum micro heater model, the meander-spiral combination form, at a temperature of 300 °C...

GPS is well recognized as the best procedure for outdoor localization. However, it presents limits in indoor localization due to particular geometric difficulties that necessitate specific solution to locate a target inside a building. Also, radio frequency technologies have many disadvantages in indoor localization. Bluetooth and Radio Frequency I...

L’objectif de notre thèse est de concevoir des nouveaux algorithmes de clustering pour les réseaux de capteurs sans fil. Le but majeur est la minimisation de la consommation d’énergie au niveau construction de clusters et au niveau de la transmission de données à la station de base. Les algorithmes proposés ne sont dédiés à un type particulier des...

Software radio technology offers the ability to develop radio architectures with programmable intermediate frequency, bandwidth, modulation and coding schemes. The Field Programmable Spoils Array (FPGA) is important in applications multi-standard software radio, and represents a solution to have a platform reconfigurable. This paper presents an app...

Purpose In this paper, a novel hybrid approach aimed at solving the problem of cross-selectivity of gases in electronic nose (E-nose) using the combination classifiers of support vector machine (SVM) and k-nearest neighbors (KNN) methods was proposed. Design/methodology/approach First, three WO 3 sensors E-nose system was used for data acquisition...

Wireless Multimedia Sensor Networks (WMSNs) are a particular instance of Wireless Sensor Networks that support the transmission of multimedia data such as video, image or sound. Those multimedia data should be delivered with a variety of predefined levels of Quality of Service swhich imposes the development of specific routing protocols. In this pa...

More recently, wireless sensor networks (WSN) have been widely recognized as a highly emerging technology. WSN is made up of a set of sensors, whose sole source of energy is the battery. As sensors are usually used in inaccessible areas, replacing or recharging the battery turns out to be almost impossible. It is actually, energy consumption which...

Wireless Sensor Network is composed of small, low cost, low energy, and multifunctional sensors. In addition, this network could have scalability, topology, synchronization, radio-coverage, safety and security constraints . Therefore, our challenge is to classify data into normal and abnormal measurements using outlier detection methods. This paper...

In acoustic channel it is known that low available bandwidth, highly varying multipath, large propagation delays, noise and physical channel properties variation, in addition to the power consumption restrict the efficiency of underwater wireless acoustic systems. The physical characteristics of Mediterranean channel such as depth, salinity and esp...

Due to the development of transducer performances, the underwater acoustic communications have made some considerable progress [1]. This progress is based on a heavy survey that tries to make the equivalent electronic piezoelectric transducer model in order to anticipate with accuracy its performances by using perfect simulator. So to predict piezo...

Hierarchical architecture with fixed structure is an effective scheme to make Wireless Sensor Networks (WSNs) scalable and energy-efficient. Clustering the sensor nodes is a well-known two-layered architecture suitable for WSNs and has been extensively explored for different purposes and applications. In this paper a novel clustering approach calle...

The advent of smart devices and continuous expansions of smart environments make Wireless sensor networks (WSNs) an important part of our daily lives. The usage of a myriad of devices in self-organizing networks in a various fields such as home monitoring, medical and military etc. requires an efficient delivery of sensed information. For this nece...