Sonia Ben Hassen

Sonia Ben Hassen

Auto-generated profile, based on publicly available information

Sonia Ben Hassen

University of Sfax

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 January 2024 in Neurocomputing
Verified
Journal Article
Closed access
SHSonia Ben Hassen
Sonia Ben Hassen
MNMohamed Neji
Mohamed Neji
ZHZain Hussain
Zain Hussain
AHAmir Hussain
Amir Hussain
AAAdel M. Alimi
Adel M. Alimi
MFMondher Frikha
Mondher Frikha

22 March 2019 in IEEE Access
Verified
Journal Article
Open access
SHSonia Ben Hassen
Sonia Ben Hassen
FBFaouzi Bellili
Faouzi Bellili
ASAbdelaziz Samet
Abdelaziz Samet
Sofiène AffesSofiène Affes
Sofiène Affes
In this paper, we introduce for the first time a new method for the estimation of the angular parameters [i.e., central directions of arrival (DOAs) and angular spreads] of multiple non-circular and incoherently-distributed (ID) sources. The new method is derived by going through three different stages to finally obtain a robust solution that allows decoupling the estimation of each central DOA from its associated angular spread by means of two consecutive 1-D searches. By doing so, we reduce significantly the complexity of the proposed technique as compared to the brute-force 2D grid search solution. This new technique is also oblivious to the sources’ angular distribution or any mismatch thereof. By analyzing its performance, we show that our new estimator outperforms most well-known state-of-the-art techniques in terms of estimation accuracy and robustness, especially for small DOA separations and/or low SNR levels. We also derive an explicit expression for the stochastic Cramér-Rao lower bounds (CRLBs) of the of the underlying estimation problem. These CRLBs are compared to those for circular ID signals. It will be shown that the noncircularity of the signals is more informative about the angular parameters when the sources have different angular distributions and/or when the angular spreads increase. Besides, the noncircular CRLBs depend on the noncircularity rate, the noncircularity phase separation and the DOA separation.

1 October 2024 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
MAMay Mowaffaq Al-Taee
May Mowaffaq Al-Taee
SNSonia Ben Hassen Neji
Sonia Ben Hassen Neji
MFMondher Frikha
Mondher Frikha
Recognizing Arabic offline handwritten words still faces various challenges because of the diversity of writing styles and the overlap between the words and characters. Therefore, building an effective system to solve these challenges has always been difficult, which has led to a lack of published research in this field. This study introduces two new models to recognize handwritten Arabic words based on the Faster region-convolution neural network (Faster R-CNN). These models employ two pre-trained networks during the feature extraction phase: The visual geometry group-16 (VGG-16) network and the residual network (ResNet50) network. To help with overlapping detections and make localization more accurate, a soft non-maximum suppression (Soft-NMS) strategy is used in post-processing. Models are independently trained and tested on two groups of data from the Institut Für Nachrichtentechnik/Ecole Nationale d’Ingénieurs de Tunis (IFN/ENIT) dataset. The first group includes one word in each image, while the second contains multiple words. Test results showed that the proposed models give excellent results compared to others. The results of VGG16 and ResNet50 with the first dataset reached accuracy rates of 100% and 99.5%, respectively. Meanwhile, the accuracy of the second group reached 91.4% and 100% with VGG16 and ResNet50, respectively.