Wahida Mansouri

Wahida Mansouri

Auto-generated profile, based on publicly available information

Wahida Mansouri

Department of Computer Science and Information Technology, Faculty of Sciences and Arts, Turaif, Northern Border University, Arar, Saudi Arabia

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
1 December 2024 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
ADAbdulbasit Darem
Abdulbasit Darem
TATareq M. Alkhaldi
Tareq M. Alkhaldi
AAAsma A. Alhashmi
Asma A. Alhashmi
WMWahida Mansouri
Wahida Mansouri
AAAbed Saif Alghawli
Abed Saif Alghawli
Tawfik Al-HadhramiTawfik Al-Hadhrami
Tawfik Al-Hadhrami

16 July 2024 in International Journal of Information Technology
Verified
Journal Article
Closed access
PDF file
WMWahida Ali Mansouri
Wahida Ali Mansouri
DEDoaa Mohammed Elmourssi
Doaa Mohammed Elmourssi
WEWiam Almalih Elyass
Wiam Almalih Elyass

16 April 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
FAFatma S. Alrayes
Fatma S. Alrayes
HAHamed Alqahtani
Hamed Alqahtani
WMWahida Mansouri
Wahida Mansouri
AAAsma Alshuhail
Asma Alshuhail
WAWafa Sulaiman Almukadi
Wafa Sulaiman Almukadi
AMAhmed Mahmud
Ahmed Mahmud
Violence recognition in surveillance videos is a vital feature of current security systems. It can improve complete security measures, making it essential in generating safe public places and defending against unforeseen security tasks. Real risk and violence detection in surveillance videos signify a cutting-edge use of deep learning (DL) technologies. By using innovative neural networks, this plan proposes to improve safety by quickly classifying possible threats and occurrences of violence within surveillance footage. The system influences DL models to examine complex visual patterns, differentiating between normal actions and potential safety risks. This real-time detection ability allows instant responses and involvements, donating to a proactive technique in safeguarding public safety and the security of critical infrastructures. Integrating DL methods in surveillance video study showcases the probability for sophisticated, intelligent methods to enlarge classical safety measures, delivering fast and effective threat recognition in different environments. This study presents a DeepGuard model for Real-Time Threat Recognition using Golden Jackal Optimization with Deep Learning. The purpose of the DeepGuard model is to identify violence and non-violence events in the surveillance videos. In the DeepGuard model, an improved ShuffleNetv2 model can be applied to derivate the intrinsic and complex features from the input images. Besides, the Golden Jackal Optimization (GJO) model can be applied for the optimal hyperparameter tuning of the improved ShuffleNetv2 model. The DeepGuard model uses long short-term memory neural networks (LSTM-NNs) for violence detection. The performance evaluation of the DeepGuard model takes place using benchmark datasets. The experimental outcomes of the DeepGuard model obtained optimum performance with 99.00% and 98.63% when related to other techniques in terms of distinct measures.

16 July 2025 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
FAFatimah Alhayan
Fatimah Alhayan
GKGaganjot Kaur
Gaganjot Kaur
SASultan Alanazi
Sultan Alanazi
MRMohammed Burhanur Rehman
Mohammed Burhanur Rehman
WMWahida Mansouri
Wahida Mansouri
HAHanadi Alkhudhayr
Hanadi Alkhudhayr
Fault injection is a critical technique for assessing the reliability of field programmable gate array (FPGA)-based embedded systems, particularly in radiation-prone and safety-critical applications. Conventional fault injection methods, such as bit upset fault injection testing (BUFIT), single critical fault injection testing (SCFIT), and dynamic partial reconfiguration (DPR), suffer from high resource overhead, slow injection speeds, and limited adaptability, making them inadequate for real-time fault resilience evaluation. This article introduces the dynamic adaptive fault injection server (DA-FIS), a high-speed, scalable, and resource-efficient fault injection framework designed to overcome these limitations. Unlike traditional methods, DA-FIS employs a configurable LFSR-based fault generator that enables adaptive and real-time fault injection based on workload sensitivity and system conditions. The proposed framework integrates masking logic and dynamic propagation tracking, allowing precise injection of single-event upsets (SEUs) and multiple-bit upsets (MBUs) into FPGA configuration memory and logic without disturbing non-targeted regions. DA-FIS is implemented on the Xilinx Zynq-7000 FPGA and evaluated across multiple benchmark workloads, including the Bubble Sort algorithm, 4-bit adder, 4-bit multiplier, and counter-based logic circuits. Experimental results demonstrate that DA-FIS achieves a fault injection rate of 111.1 faults per second, outperforming BUFIT (53.4 faults/s), SCFIT (27 faults/s), and DPR (18.5 faults/s), with 30% lower FPGA resource overhead compared to SCFIT. The adaptive architecture ensures seamless scalability across different FPGA platforms, making it suitable for space electronics, automotive safety systems, and high-performance computing. Additionally, DA-FIS supports real-time error model adjustments, enabling researchers to analyze fault propagation, error correction strategies, and security vulnerabilities in FPGA-based architectures. This work establishes DA-FIS as a superior fault injection framework, offering high-speed, precision-controlled fault testing while maintaining minimal FPGA overhead and enhanced scalability. Future research will explore machine learning-assisted fault modeling and self-healing FPGA architectures to further enhance FPGA fault resilience in safety-critical and autonomous systems.

27 December 2025 in International Journal of Information Technology
Verified
Journal Article
Closed access
PDF file
WMWahida Mansouri
Wahida Mansouri
SASomia Asklany
Somia Asklany

11 November 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
NANuha Alruwais
Nuha Alruwais
HAHadeel Alsolai
Hadeel Alsolai
MMMohammed Maray
Mohammed Maray
WMWahida Mansouri
Wahida Mansouri
ASAlanoud Subahi
Alanoud Subahi
MSMutasim Al Sadig
Mutasim Al Sadig
In the Internet of Things (IoT) field, massive quantities of smart devices are connected, producing enormous data sizes that need developed management methods. One general task in a smart environment is the capability to precisely recognize and classify diverse kinds of objects using these methods. The evolution of technologies and advancements in structure brings several challenges, such as managing and controlling the entire process, ensuring protection at the server, security in smart homes, and more. A robust and flexible deep learning (DL) technique is presented to achieve appliance classification without restrictions on user behaviour. The approach reflects combined load reports throughout the shared process. DL presents great models for analyzing and processing IoT sensor data, permitting accurate appliance recognition. This study presents a Lightweight Deep Evidence Fusion Framework for Smart Home Appliance Detection and Classification (LDEFF-SHADC) model. The primary objective of the LDEFF-SHADC technique is to establish a robust framework for detecting and classifying smart home appliances using IoT device data. The LDEFF-SHADC approach performs data normalization using linear scaling normalization (LSN) to ensure uniformity and enhance processing efficiency. The improved snake optimization (ISO) model is utilized for the feature selection process to reduce dimensionality while preserving critical information effectively. In addition, a hybrid framework integrating gated recurrent units and the multi-head attention (GRU-MHA) classifier is implemented to classify and detect smart home appliances. The improved sparrow search optimization algorithm (ISSA) is employed to fine-tune the parameters of the GRU-MHA model and achieve enhanced optimization performance. The stimulated outcome investigation of the LDEFF-SHADC technique is examined under the IoT device recognition dataset. The performance validation of the LDEFF-SHADC technique portrayed a superior accuracy value of 98.90% over existing models.