Lamaa Sellami

Bio: Lamaa Sellami is an academic researcher from University of Gabès. The author has contributed to research in topics: Computer science & Linear system. The author has an hindex of 2, co-authored 6 publications receiving 10 citations.

State estimation for switched linear systems

Abstract: In this paper, we address the problem of state estimation of linear switched discrete time models from a finite set of input-output data. This is a challenging problem since it requires estimating the active discrete state and its continuous observer. In fact, we propose a hybrid state observer design which consists of two stages. The first allows to determine the active discrete state using a classification algorithm that associated the current data to its appropriate submodel. The second stage is used to estimate the corresponding continuous observer. Simulation results are presented to illustrate the performance of the proposed method.

Self-adaptative multi-kernel algorithm for switched linear systems identification

Abstract: This paper deals with the problem of switched linear system identification. This is one of the most difficult problems since it involves both the estimation of the linear sub-models and the switchi...

Multilayer Video Encoding for QoS Managing of Video Streaming in VANET Environment

Abstract: Efficient delivery and maintenance of the quality of service (QoS) of audio/video streams transmitted over VANETs for mobile and heterogeneous nodes are one of the major challenges in the convergence of this network type and these services. In this context, we propose an inter-layer approach for multimedia stream transmission in a VANET environment (VSMENET). The main idea of our work is based on the dynamic adaptation of the transmission rate according to the physical rate available in the VANET. VSMENET is all about eliminating downtime during video playback by vehicle users. This involves adapting the quality of the video to the actual performance of the VANETs, intelligent encoding of video on the Road Side Units (RSU) side, and finally continuous maintenance of the calculation tasks on the RSU side and sufficient video data on the vehicle node side. Thus, we are interested in the process of evaluating the strict parameters of the VANETs, influencing the video transmission. For example, we propose, on the one hand, an architecture for intelligent data selection and good clock synchronization, and, on the other hand, efficient management of the availability and consumption of video data. We used the NetSim simulator to test the proposed approach performance. To this end, several algorithms such as OCLFEC, MAC, ShieldHEVC, and AntArmour have been implemented for such a performance comparison. Our work suggests that VSMENET is well concerning the average lifetime of the video packets and their delivery rate (more than 9% gain compared with other approaches).

Hybrid observer design for a class of hybrid dynamic systems

Abstract: Hybrid observer design is addressed for a class of discrete-time linear switched systems whose switching mechanism is unknown. The hybrid observation problem consists in determining the estimation of the current mode and the continuous observer for continuous behavior from a finite set of input-output data. First, the current mode is estimated using a classification algorithm that associates the current data to its appropriate submodel. Second, the continuous observer is determined by the resolution of linear matrix inequalities. A comparative study of the proposed approach with the k-means method was achieved in simulation. A numerical example was reported to evaluated the proposed method.

Land Cover Classification Based on Fused Data from GF-1 and MODIS NDVI Time Series

Abstract: Accurate regional and global information on land cover and its changes over time is crucial for environmental monitoring, land management, and planning. In this study, we selected Fengning County, in China’s Hebei Province, as a case study area. Using satellite data, we generated fused normalized-difference vegetation index (NDVI) data with high spatial and temporal resolution by utilizing the STARFM algorithm to produce a fused GF-1 and MODIS NDVI dataset. We extracted seven phenological parameters (including the start, end, and length of the growing season, base value, mid-season date, maximum NDVI, seasonal NDVI amplitude) from a fused NDVI time-series after reconstruction using the TIMESAT software. We developed four classification scenarios based on different combinations of GF-1 spectral features, the fused NDVI time-series, and the phenological parameters. We then classified the land cover using a support vector machine and analyzed the classification accuracies. We found that the proposed method achieved satisfactory classification results, and that the combination of the fused NDVI data with the extracted phenological parameters significantly improved classification accuracy. The classification accuracy based on the composited GF-1 multi-spectral bands combined with the phenological parameters was the highest among the four scenarios, with an overall classification accuracy of 88.8% and a Kappa coefficient of 0.8714, which represent increases of 9.3 percentage points and 0.1073, respectively, compared with GF-1 spectral data alone. The producer’s and user’s accuracy for different land cover types improved, with a few exceptions, and cropland and broadleaf forest had the largest increase.

Comparative Performance Evaluation of Intrusion Detection Based on Machine Learning in In-Vehicle Controller Area Network Bus

Abstract: Communication between the nodes in a vehicle is performed using many protocols. The most common of these is known as the Controller Area Network (CAN). The functionality of the CAN protocol is based on sending messages from one node to all others throughout a bus. Messages are sent without either source or destination addresses. Consequently, it is simple for an attacker to inject malicious messages. This may lead to some nodes malfunctioning or total system failure, which can affect the safety of the driver as well as the vehicle. Detecting intrusions is a challenging problem in the context of using CAN bus for in-vehicle communication. Most existing work focuses on the physical aspects without taking into consideration the data itself. Machine Learning (ML) tools, especially classification techniques, have been widely used to address similar problems. In this paper, we use and compare several ML techniques to deal with the problem of detecting intrusions in in-vehicle communication. An experimental study is performed using a real dataset extracted from a KIA Soul car. Compared to previous work, which focuses on detecting intrusions based on the physical aspect, this paper aims to concentrate on the application of data analysis and statistical learning techniques. Furthermore, the paper provides a comparative study of the most common ML techniques. The results show that the techniques under consideration in this paper outperform other techniques that have been used previously.

Contribution à la Synthèse d’ObservateursPour les Systèmes Hybrides

Abstract: Le but de cette these est la synthese d’observateurs pour les systemes dynamiques hybrides modelises par les reseaux de Petri differentiels. Ces systemes sont definis structurellement par la cooperation de deux sous systemes, l'un de type continu et le second de type evenementiel. Ainsi, ce memoire debute par une introduction aux notions de l’aspect hybride. Nous poursuivons alors notre preambule par les differentes methodes de modelisation et d’analyse de stabilite de ces systemes. La methodologie de la modelisation des systemes hybrides par le modele retenu est egalement explicitee et illustree a travers des exemples simules. La strategie d’estimation de l’etat hybride s’appuie sur un schema d’observation combinant un observateur de reseau de Petri et d’un observateur continu de Luenberger en interaction. A partir du marquage discret initial, l’observateur continu estime l’etat continu du systeme. Ce dernier est exploite par l’observateur discret pour la detection de nouvel evenement. Ainsi, l’observateur discret restitue le mode discret en estimant le marquage discret et fourni le mode actif a l’observateur continu. Les gains de l’estimation sont calcules pour obtenir une convergence exponentielle de l’observateur continu aussi bien dans le cas ou l’observateur discret detecte correctement le mode que dans le cas echec. De la meme maniere que les cas precedents, des approches de synthese se basant sur la contrainte du temps de sejour sont egalement prise en consideration. Pareillement, En absence de l’etat hybride la commande par retour d’etat est analysee. Les techniques de la synthese dans ce cadre s’appuient sur le principe de separation. Les conditions de stabilisation et d’estimation sont formulees sous forme d’un ensemble d’inegalites matricielles (LMI).

Discrete-time estimation of switched stochastic polynomial systems and its application to reconstruction of induction motor variables:

Abstract: This paper presents a solution to the filtering problem for a class of stochastic discrete-time nonlinear polynomial systems with switching in the state equation over linear observations and its ap...