Ratshih Sayed

Dr. Ratshih Sayed

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
16 March 2023 in IEEE Access
Verified
Journal Article
Open access
RSRatshih Sayed
Ratshih Sayed
HAHaytham Azmi
Haytham Azmi
HShttps://scholar.google.com/citations?hl=en&user=ibqBDS4AAAAJ Shawkey
https://scholar.google.com/citations?hl=en&user=ibqBDS4AAAAJ Shawkey
AKA. H. Khalil
A. H. Khalil
MRMohamed Refky
Mohamed Refky
This paper presents an extensive literature review on Binary Neural Network (BNN). BNN utilizes binary weights and activation function parameters to substitute the full-precision values. In digital implementations, BNN replaces the complex calculations of Convolutional Neural Networks (CNNs) with simple bitwise operations. BNN optimizes large computation and memory storage requirements, which leads to less area and power consumption compared to full-precision models. Although there are many advantages of BNN, the binarization process has a significant impact on the performance and accuracy of the generated models. To reflect the state-of-the-art in BNN and explore how to develop and improve BNN-based models, we conduct a systematic literature review on BNN with data extracted from 239 research studies. Our review discusses various BNN architectures and the optimization approaches developed to improve their performance. There are three main research directions in BNN: accuracy optimization, compression optimization, and acceleration optimization. The accuracy optimization approaches include quantization error reduction, special regularization, gradient error minimization, and network structure. The compression optimization approaches combine fractional BNN and pruning. The acceleration optimization approaches comprise computing in-memory, FPGA-based implementations, and ASIC-based implementations. At the end of our review, we present a comprehensive analysis of BNN applications and their evaluation metrics. Also, we shed some light on the most common BNN challenges and the future research trends of BNN.

21 October 2020 in IEEE Access
Verified
Journal Article
Open access
RSRatshih Sayed
Ratshih Sayed
HAHaytham Azmi
Haytham Azmi
ANAmin M. Nassar
Amin M. Nassar
HShttps://scholar.google.com/citations?hl=en&user=ibqBDS4AAAAJ Shawkey
https://scholar.google.com/citations?hl=en&user=ibqBDS4AAAAJ Shawkey
This paper presents a novel framework that automates the creation of a trained-classifier integrated circuit from a dataset. The framework accepts a dataset in a comma-separated value format and performs several processing steps to create a trained model. After creating the model, the framework generates a tree-based machine learning classifier in two formats; Extensible Markup Language (XML) and Verilog. We use the XML representation to present the hierarchy of the generated tree and the Verilog code as a hardware description language representation of the trained model. Our framework uses the Verilog code as an input to a Field programmable Gate Array (FPGA) design validation flow. Then, we automate the Application Specific Integrated Circuit (ASIC) flow implementation and build a customized classifier integrated circuit. The novelty of the proposed framework lies in bridging the gap between machine learning model training and its hardware design when dealing with machine learning classifier’s implementation. Our framework addresses several challenges related to the design automation and implementation of customized machine learning classifier chips from raw dataset files. We discuss these challenges in detail in this paper and explain how researchers can use our proposed framework to build low-cost, high-performance classifier chips. Our framework operates at 100 MHZ and achieves 80.79% average 10-fold cross-validation accuracy across five different datasets.

31 May 2025 in The Journal of Supercomputing
Verified
Journal Article
Open access
PDF file
RSRatshih Sayed
Ratshih Sayed
HDH. H. Draz
H. H. Draz
HAHaytham Azmi
Haytham Azmi
Convolutional Neural Networks (CNNs) proved highly successful in various applications, including image classification. CNNs demand a massive number of mathematical operations that represent a challenge in hardware implementation, especially for limited-resource devices or edge-computing devices. This paper presents Binary Weight CNN (BW-CNN) accelerator that can be deployed on Field Programmable Gate Array (FPGA). The BW-CNN provides efficient hardware optimization, by using 1-bit representation for weights and 2-bit representation for activations to minimize the model size and reduce the number of required multiplications. Moreover, binary weights enable the system to avoid memory access time bottleneck for reading the weights because they are saved on-chip. The BW-CNN supports hardware/software co-design approach for hardware acceleration. The proposed BW-CNN is implemented using Virtex UltraScale FPGA VCU108 Evaluation Kit. The BW-CNN is evaluated on the Modified National Institute of Standards and Technology (MNIST) dataset achieving 98.45% accuracy and consumes power of 3.599 W.

25 August 2026 in Biosensors
Verified
Journal Article
Open access
PDF file
Dalia ElsheakhDalia Elsheakh
Dalia Elsheakh
RSRatshih Sayed
Ratshih Sayed
HDH. H. Draz
H. H. Draz
GIGhada H. Ibrahim
Ghada H. Ibrahim
HShttps://scholar.google.com/citations?hl=en&user=ibqBDS4AAAAJ Shawkey
https://scholar.google.com/citations?hl=en&user=ibqBDS4AAAAJ Shawkey
Diabetes is a major worldwide health concern, which emphasizes the critical need for precise and continuous glucose monitoring devices. This paper introduces a novel, non-invasive method for continuous blood glucose monitoring using on-chip multi-arm sensors designed as earbuds by using UMC 0.18 μm technology. The proposed sensor uses the dielectric characteristics of the earbud to detect variations in glucose levels while operating at various resonant frequencies, including 32, 42, 64, and 94 GHz. The sensitivity of the proposed method was evaluated using a reflection coefficient criterion of ∣S11∣≤−6 dB, confirming its ability to achieve accurate detection when implemented within an earbud device. A 3D electromagnetic high-frequency structure simulator (HFSS) is used to validate the simulation. Only |S11| data are used to determine the glucose concentrations in the blinded prediction group. The results demonstrate a strong correlation between sensor responses and glucose levels. The sensor achieved a sensitivity of 12.4 MHz/mg/dL, 6 dB/mg/dL. Moreover, the earbud’s homogeneous tissue architecture and naturally low eccrine sweat gland density lessen susceptibility to confounding physiological variables commonly observed in microwave-based glucose detection. As a major advancement in biomedical sensing technology, this wearable system provides a precise and useful method for non-invasive glucose monitoring.