Ahmed Bakr

Ahmed Bakr

Auto-generated profile, based on publicly available information

Ahmed Bakr

Computer Science Department, The University of Alabama, AL, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
1 April 2016
Verified
Conference Paper
Closed access
MSMay Salama
May Salama
ABAhmed Bakr
Ahmed Bakr
Electromyogram signal is a biomedical signal that measures electrical activity produced in a muscle during its contraction. This work presents a prototype system for moving a prosthetic lower arm, without prior operation intervention, using electrodes that measure electromyogram (EMG) signals placed on two muscles only. The signals are then read by sensors connected to Arduino microcontroller, processed and passed to MATLAB via Bluetooth where features are extracted and input to a neural network to classify one out of six movements. A servo motor receives a driving signal to move the simulated arm to the required position. The system enables the arm to do six movements without any external help. The system results are compared to other systems' results and it was able to achieve 99.7% classification rate which is considered, among other systems, the highest for classifying six movements.

1 February 2021 in Computer Science
Verified
Journal Article
Closed access
PDF file
ABAhmed Mohamed Bakr
Ahmed Mohamed Bakr
MSMay Ahmed Salama
May Ahmed Salama
AAAbdelwahab Alsammak
Abdelwahab Alsammak
Real-time systems must avoid hazardous situations. To achieve this, their functionality should be investigated under time constraints. In this paper, a modeling based on Hierarchical Communicating Real-time State Machine (H- CRSM) and analysis methodology is proposed to examine statically ANSI-C code to obtain the hazardous events in the input system. A hazardous event equation is taken as input to the proposed system. The output is a list of hazardous scenarios. A path in the code showing the cause of the undesirable event is associated with each hazardous scenario. The strength of the proposed methodology is that the process of hazardous situations detection does not require running the ANSI-C program multiple times with different input values. It also focuses on analyzing the software level of the life cycle. Most of the verification tools check the system level. The system level may be bug-free but the software level may not.

17 September 2026 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
ABAhmed Bakr
Ahmed Bakr
AGAugusto Garcia-Agundez
Augusto Garcia-Agundez
TATravis Atkison
Travis Atkison
VRVivek A. Rudrapatna
Vivek A. Rudrapatna
TGTrinabh Gupta
Trinabh Gupta

12 December 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
ABAhmed Bakr
Ahmed Bakr
TATravis Atkison
Travis Atkison
ZZubair Fadlullah
Zubair Fadlullah
Mostafa M. FoudaMostafa M. Fouda
Mostafa M. Fouda
Most existing image-based parking space detection and classification methods assume that all training data reside in a single, centralized location—an unrealistic scenario that yields models unable to generalize to new parking lots. Furthermore, privacy concerns prevent lot owners from sharing raw images, limiting collaboration. To overcome these challenges, we present ParkFL, the first federated learning (FL) framework for parking space detection and classification that trains models across distributed client sites without exchanging raw image data. Built on NVIDIA federated learning application runtime environment (NVFlare), ParkFL demonstrates model-agnosticism through evaluation on two deep-learning architectures. We benchmark four federated algorithms—FedAvg, FedProx, FedOpt, and SCAFFOLD—using real-world datasets. Despite training on noncentralized, heterogeneous data, ParkFL achieves 99.5% mean average precision (mAP), matching the accuracy of state-of-the-art centralized models on the same parking lots. When evaluated on images from different parking lots, ParkFL significantly outperforms models trained solely on individual-site data, which achieve 25.6% mAP, even though ParkFL never accesses raw images from other sites. Communication overhead remains below 3% of total training time, demonstrating a scalable, privacy-preserving solution with nearly state-of-the-art performance. We release ParkFL code at https://github.com/ahmedmbakr/ParkFL.

18 December 2023 in TechRxiv
Verified
Preprint
Open access
PDF file
ABAhmed Bakr
Ahmed Bakr
AAAhmad Alsharif
Ahmad Alsharif
The huge amount of data produced by billions of distributed Internet of Things (IoT) devices creates unprecedented opportunities for several fields and industries. These data can drive informed decision-making, enhance operational efficiency, and improve the quality of life for individuals and communities. IoT data marketplaces have evolved as a solution to allow trading data assets, where data consumers can acquire IoT data streams to improve data analytics and offer innovative services, while data providers can monetize their IoT data. The realization of trustworthy marketplace, however, faces significant impediments due to the lack of mutual trust between data providers and consumers with the absence of a central marketplace operator trusted by all entities. In this paper, we focus on developing a trustworthy and decentralized solution for real-time IoT data marketplaces. First, we propose Multi-authority Attribute-Based Encryption with Revocation and Accountability (MABERA), a novel trustworthy Multi-authority Attribute-Based Encryption (MA-ABE) that supports attribute-level revocation and accountability. Then, we propose a trustworthy and decentralized solution for real-time IoT data marketplaces that integrates MABERA with several cryptographic primitives to ensure data confidentiality, fair exchange, fine-grained access control, and accountability. We demonstrate that our solutions provide the desired security properties, and the simulation results show that our solutions are feasible and efficient.