Sanaa El Fkihi
Mohammed V University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Sanaa El Fkihi.
next generation internet | 2010
Brahim Elbhiri; Sanaa El Fkihi; Rachid Saadane; Driss Aboutajdine
Wireless Sensor Networks (WSNs) have recently become an area of attractive research interest. A WSN consists of low-cost, low power, and energy-constrained sensors responsible for monitoring and reporting a physical phenomenon to the sink node where the end-user can access the data. Reducing energy consumption and enlarging lifetime of the whole WSNs are the important challenges in these fields of applications. To deal with these challenges, clustering algorithms can be used. In this paper we present a new approach called the Spectral Classification based on Near Optimal Clustering in Wireless Sensor Networks (SCNOpC-WSNs). This protocol uses spectral graph theory in order to subdivide the network such that each cluster includes the highest inter-correlated sensors. Simulation results demonstrate that SCNOpC-WSNs distribute energy consumption more effectively among the sensors. Thus, the proposed approach enlarges the network lifetime by as much as 44.8% compared to LEACH.
joint ifip wireless and mobile networking conference | 2013
Brahim Elbhiri; Sanaa El Fkihi; Rachid Saadane; Nourdine Lasaad; Ali Jorio; Driss Aboutajdine
Wireless sensor network has recently become an area of attractive research interest. It consists of low-cost, low power, and energy-constrained sensors responsible for monitoring a physical phenomenon and reporting to sink node where the end-user can access the data. Saving energy and therefore extending the wireless sensor network lifetime, involves great challenges. For these purposes, clustering techniques are largely used. Using many empirical successes of spectral clustering methods, we propose a new algorithm that we called Spectral Classification for Robust Clustering in Wireless Sensor Networks (SCRC-WSN). This protocol is a spectral partitioning method using graph theory technics with the aim to separate the network in a fixed optimal number of clusters. The clusters nodes communicate with an elected node called cluster head, and then the cluster heads communicate the information to the base station. Defining the optimal number of clusters and changing dynamically the cluster head election probability are the SCRC-WSN strongest characteristics. In addition our proposed protocol is a centralized one witch take into account the nodes residual energy to define the cluster heads. We studied the impact of node density on the robustness of the SCRC-WSN algorithm as well as its energy and its lifetime gains. Simulation results show that the proposed algorithm increases the lifetime of a whole network and presents more energy efficiency distribution compared to the Low-Energy Adaptive Clustering Hierarchy (LEACH) approach and the Centralized LEACH (LEACH-C)one.
Journal of Computer Networks and Communications | 2015
Ali Jorio; Sanaa El Fkihi; Brahim Elbhiri; Driss Aboutajdine
Recently wireless sensor network (WSN) has become one of the most interesting networking technologies, since it can be deployed without communication infrastructures. A sensor network is composed of a large number of sensor nodes; these nodes are responsible for supervision of the physical phenomenon and transmission of the periodical results to the base station. Therefore, improving the energy efficiency and maximizing the networking lifetime are the major challenges in this kind of networks. To deal with this, a hierarchical clustering scheme, called Location-Energy Spectral Cluster Algorithm (LESCA), is proposed in this paper. LESCA determines automatically the number of clusters in a network. It is based on spectral classification and considers both the residual energy and some properties of nodes. In fact, our approach uses the K-ways algorithm and proposes new features of the network nodes such as average energy, distance to BS, and distance to clusters centers in order to determine the clusters and to elect the clusters heads of a WSN. The simulation results show that if the clusters are not constructed in an optimal way and/or the number of the clusters is greater or less than the optimal number of clusters, the total consumed energy of the sensor network per round is increased exponentially.
international conference on multimedia computing and systems | 2011
Hinde Anoual; Sanaa El Fkihi; Abdellilah Jilbab; Driss Aboutajdine
Frequently, there is a need to identify vehicle license plates (VLP) in images taken from a camera that is far away from the vehicle for security. The extracted information from vehicle license plates is used for enforcement, access-control, and flow management, e.g. to keep a time record for automatic payment calculations or to fight against crime. Thats make license plates detection crucial and inevitable in the vehicle license plate recognition system. This paper aims to present a new robust method to detect and localize license plates in images. Especially we focus on the Moroccans VLP. The proposed approach is based on edge features and characteristics of license plates characters. Various images including Moroccans VLP taken from different distances and under different angles were used to evaluate the proposed method. The experimental results show that our system can efficiently detect and localize the Moroccans VLP in the images. Indeed, the recall/precision curve of the proposed method proves that 95% precision rate is obtained for recall rate value equals to 81%. In addition, the standard measure of quality is equal to 87.44 %.
international conference on multimedia computing and systems | 2016
Anas Abouyahya; Sanaa El Fkihi; Rachid Oulad Haj Thami; Driss Aboutajdine
The recognition of an expression seems obvious and easy when classified by the human brain. However, it is clearly difficult for a computer to detect human face, extract all of the components characterizing the facial expression and then determine its classification from a single image. Moreover, based on videos, the process becomes even more complex because it must take simultaneously into account the temporal and spatial information available. Also, It should be noted that facial features have an important fact to developing a robust face representation because it aims to select the best of features and reduce dimensionality of features set by finding a new set which contains most of the face features information. For those reasons, this paper present several features extraction approaches for facial expressions recognition as state-of-the-art review.
International Conference on Networked Systems | 2014
Noureddine Assad; Brahim Elbhiri; Sanaa El Fkihi; Moulay Ahmed Faqihi; Mohamed Ouadou; Driss Aboutajdine
In this paper we analyze the intrusion detection in a homogeneous Wireless Sensor Network that is defined as a mechanism to monitor and detect unauthorized intrusions or anomalous moving attackers in area of interest. The quality of deterministic deployment can be determined sufficiently by analysis, before the deployment. However, when random deployment is required, determining the deployment quality becomes challenging and depends directly on node density. The major question is centered on the network coverage problem, how can we guarantee that each point of the region is covered by the required number of sensors? To deal with this, probabilistic intrusion detection models are adopted, called single and multi sensing probability detection and the deployment quality issue is surveyed and analyzed in terms of coverage. We evaluate our probabilistic model in homogeneous wireless sensor network, in term of sensing range, node density, and intrusion distance.
international symposium on visual computing | 2010
Hajar Bouirouga; Sanaa El Fkihi; Abdelilah Jilbab; M'hamed Bakrim
In this paper, we propose a real-time system that can categorize input videos into adult or non-adult videos. First, we compare and contrast the most significant skin detection techniques, feature extraction techniques and classification methods. Then, we give an analysis of the significant test results. After careful examination it was decided that an optimal system is gave by a model Bayes-Hsv.
Archive | 2016
Ali Jorio; Sanaa El Fkihi; Brahim Elbhiri; Driss Aboutajdine
A Wireless Sensor Network (WSN) is composed of a large number of autonomous and compact devices called sensor nodes. This network can be an effective tool for gathering data in a variety of environments. However, these sensor nodes have some constraints due to their limited energy, storage capacity and computing power. Clustering is a kind of a technique which is used to reduce energy consumption and to extend network lifetime. Hence, multi-hop communication is often required when the communication range of the sensor nodes is limited or the number of sensor nodes is very large in a network. In this paper, we propose a multi-hop spectral clustering algorithm to organize the sensor nodes in a WSN into clusters. Simulation results show that the proposed algorithm performs better in reducing the energy consumption of sensors and effectively improves the WSN lifetime.
international conference on multimedia computing and systems | 2014
Ali Jorio; Sanaa El Fkihi; Brahim Elbhiri; Driss Aboutajdine
A Wireless Sensor Network (WSN) is composed of a large number of autonomous and compact devices called sensor nodes. This network can be an effective tool for gathering data in a variety of environments. However, These sensor nodes have some constraints due to their limited energy, storage capacity and computing power. Therefor, saving energy and, thus extending the WSN lifetime entails great challenges. In order to prolong the lifetime of WSN, this study presents a hierarchical clustering algorithm based on spectral classification (HCA-SC). First, to overcome the ideal distribution of clusters, HCA-SC partition the network by spectral classification algorithm. Second, for each cluster, HCA-SC selects a node as a cluster head with regard residual energy and distance from base station. Simulation results showed that our algorithm performs better in reducing the energy consumption of sensor nodes and effectively improves the lifetime of wireless sensor networks.
international conference on big data | 2018
Mohamed Admi; Sanaa El Fkihi; Rdouan Faizi
In this paper, we propose a novel method for detecting license plates (LP) in images. The proposed algorithm is an extension of Maximally Stable Extremal Regions (MSER) for extracting candidate text region of LP. The approach is more robust to edge and more powerful thanks to its stability, and robustness against the changes of scale and illumination. We propose a novel method based on a bilateral filter as well as an adaptive dynamic threshold so as to improve the MSER results. Besides, we consider the outer tangent of circles intersection for filtering the region with the same orientation, and finally a character classifier based on geometrical and statistical constraints of character to eliminate false detection. Thus, our proposal consists of three steps namely, image preprocessing, candidate license plate character detection, and finally filtering and grouping to eliminate false detection.