Eman Hassan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Eman Hassan has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Baker Mohammad
Khalifa University, Abu Dhabi, United Arab Emirates
4 shared publications - Hani Saleh
Khalifa University
2 shared publications Shaymaa Elshahaby
Department of Computer and Information Engineering, System on Chip Lab, Center for Cyber-Physical Systems, Khalifa University, Abu Dhabi, United Arab Emirates
2 shared publications- Yahya Zweiri
Advanced Research and Innovation Center (ARIC), Khalifa University of Science and Technology, Abu Dhabi, UAE
2 shared publications - Yasmin Halawani
Department of Electrical and Computer Engineering, System-on-Chip Center (SoCC), Khalifa University, Abu Dhabi, United Arab Emirates
2 shared publications Baker Mohammad
1 shared publication
Latest Publications
- 6 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 16 (2) , 188-202
Reconfigurable In-Memory Computing Using Standard 6T SRAM for BCAM, TCAM, Similarity Indexing, and Logic-in-Memory Operations
In-memory computing (IMC) has emerged as a promising paradigm to overcome the von Neumann bottleneck by performing computations directly within memory, thereby reducing data movement and improving energy efficiency. Among various memory technologies, SRAM-based Content Addressable Memories (CAMs) stand out for their high-speed operation and compatibility with CMOS technology. Prior SRAM-CAM IMC architectures typically rely on modified 8T/10T cells or suffer from trade-offs between accuracy, stability, area, and energy, limiting widespread adoption. To address these limitations, this work introduces a reconfigurable SRAM (R-SRAM) architecture built entirely from unmodified push-rule 6T cells, preserving foundry compatibility while extending functionality beyond existing designs. The proposed macro unifies conventional SRAM, Binary and Ternary CAM (BCAM/TCAM), similarity-index computation, and in-memory bitwise logic (AND, NOR, INV) within a single array. Comprehensive post-layout simulations with Monte Carlo statistical analysis in 22 nm FDSOI validate the design’s functionality, robustness, and performance. Results show 0.44 fJ/bit energy for BCAM/TCAM search, minimal area overhead, and stable cell operation during computation. These findings establish the first demonstration of an unmodified 6T SRAM-based reconfigurable CAM with integrated similarity-index capability, highlighting its potential as a versatile and energy-efficient IMC solution for next-generation AI and low-power edge applications.
- 6 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 16 (2) , 188-202
Reconfigurable In-Memory Computing Using Standard 6T SRAM for BCAM, TCAM, Similarity Indexing, and Logic-in-Memory Operations
In-memory computing (IMC) has emerged as a promising paradigm to overcome the von Neumann bottleneck by performing computations directly within memory, thereby reducing data movement and improving energy efficiency. Among various memory technologies, SRAM-based Content Addressable Memories (CAMs) stand out for their high-speed operation and compatibility with CMOS technology. Prior SRAM-CAM IMC architectures typically rely on modified 8T/10T cells or suffer from trade-offs between accuracy, stability, area, and energy, limiting widespread adoption. To address these limitations, this work introduces a reconfigurable SRAM (R-SRAM) architecture built entirely from unmodified push-rule 6T cells, preserving foundry compatibility while extending functionality beyond existing designs. The proposed macro unifies conventional SRAM, Binary and Ternary CAM (BCAM/TCAM), similarity-index computation, and in-memory bitwise logic (AND, NOR, INV) within a single array. Comprehensive post-layout simulations with Monte Carlo statistical analysis in 22 nm FDSOI validate the design’s functionality, robustness, and performance. Results show 0.44 fJ/bit energy for BCAM/TCAM search, minimal area overhead, and stable cell operation during computation. These findings establish the first demonstration of an unmodified 6T SRAM-based reconfigurable CAM with integrated similarity-index capability, highlighting its potential as a versatile and energy-efficient IMC solution for next-generation AI and low-power edge applications.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Circuits and Systems Magazine
- Vol. 26 (3) , 89-92
Empowering Women’s Role in Biomedical Sciences and Technologies: A Women in Circuits and Systems (WiCAS) Forum at IEEE BioCAS 2025 [DEICAS, WiCAS and YPCAS Highlights]
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Circuits and Systems Magazine
- Vol. 26 (3) , 89-92
Empowering Women’s Role in Biomedical Sciences and Technologies: A Women in Circuits and Systems (WiCAS) Forum at IEEE BioCAS 2025 [DEICAS, WiCAS and YPCAS Highlights]
- 22 August 2025
- Published by Springer Nature
- p. 93-105
The Impact of Artificial Intelligence on Flipped Learning and Online Learning
- 22 August 2025
- Published by Springer Nature
- p. 93-105
The Impact of Artificial Intelligence on Flipped Learning and Online Learning
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (1) , 157-171
TransHD: Spatial Transformer Features Extraction for HDC Synergetic Learning
Artificial intelligence (AI) relies on pattern recognition and classification algorithms to achieve accurate and efficient decision-making. Convolutional neural networks (CNNs) are the state-of-the-art for processing 2D image data, but their high computational and data requirements limit their use in resource-constrained environments. Hyperdimensional computing (HDC) offers a lightweight alternative, excelling in 1D tasks, but struggles to achieve competitive accuracy for 2D image classification. Hybrid frameworks combining HDC with CNNs have been proposed to improve accuracy but inherit the computational demands of deep learning, making them unsuitable for edge and IoT devices. To address this, we propose TransHD, a framework integrating lightweight spatial transformer networks (STNs) with HDC to enhance image classification performance while maintaining efficiency. TransHD achieves up to 9% higher accuracy than base HDC models on MNIST and Fashion-MNIST using only 30% of the training data, and reduces computational complexity by 2.5x through optimized STN feature map usage. On resource-constrained platforms like the Raspberry Pi 4, TransHD accelerates inference times by 3.4x and improves energy efficiency by 3.2x, with an accuracy trade-off of approximately 3% compared to CNNs. This study demonstrates the potential of combining HDC with STNs to develop efficient AI solutions for IoT and edge computing, where low energy consumption and computational efficiency are critical.
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (1) , 157-171
TransHD: Spatial Transformer Features Extraction for HDC Synergetic Learning
Artificial intelligence (AI) relies on pattern recognition and classification algorithms to achieve accurate and efficient decision-making. Convolutional neural networks (CNNs) are the state-of-the-art for processing 2D image data, but their high computational and data requirements limit their use in resource-constrained environments. Hyperdimensional computing (HDC) offers a lightweight alternative, excelling in 1D tasks, but struggles to achieve competitive accuracy for 2D image classification. Hybrid frameworks combining HDC with CNNs have been proposed to improve accuracy but inherit the computational demands of deep learning, making them unsuitable for edge and IoT devices. To address this, we propose TransHD, a framework integrating lightweight spatial transformer networks (STNs) with HDC to enhance image classification performance while maintaining efficiency. TransHD achieves up to 9% higher accuracy than base HDC models on MNIST and Fashion-MNIST using only 30% of the training data, and reduces computational complexity by 2.5x through optimized STN feature map usage. On resource-constrained platforms like the Raspberry Pi 4, TransHD accelerates inference times by 3.4x and improves energy efficiency by 3.2x, with an accuracy trade-off of approximately 3% compared to CNNs. This study demonstrates the potential of combining HDC with STNs to develop efficient AI solutions for IoT and edge computing, where low energy consumption and computational efficiency are critical.
- Open Access
- 22 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Reconfigurable In-Memory Computing Using Standard 6T SRAM for BCAM, TCAM, Similarity Indexing, and Logic-in-Memory Operations
In-memory computing (IMC) has emerged as a promising paradigm to overcome the von Neumann bottleneck by performing computations directly within memory, thereby significantly reducing data movement and enhancing energy efficiency. Among various memory technologies, SRAM-Content Addressable Memories (CAMs) based IMC stands out due to its high-speed operation and compatibility with existing CMOS technology. Nevertheless, existing SRAM-CAM based IMC architectures often encounter trade-offs between computational accuracy, stability, and energy efficiency, which hinders their widespread adoption. To tackle these limitations, the proposed reconfigurable SRAM (R-SRAM) architecture integrates both analog and digital computation, utilizing a standard SRAM array alongside a modified peripheral circuit to support multiple functionalities. These include conventional SRAM operation, Binary and Ternary CAM (BCAM and TCAM), similarity index computation, and bitwise logical operations such as AND, NOR, and inversion (INV). Comprehensive post-layout simulations with Monte Carlo statistical analysis for 22nm FDSOI foundry process technology are performed to validate functionality, robustness, and performance. Simulation results indicate a significant improvement in energy per operation, measured at 0.44 femtojoules (fJ)/bit for the BCAM/TCAM search operation, while adding minimal area overhead and maintaining cell stability during computation. These findings underscore the potential of hybrid SRAM-based IMC architectures for next-generation low-power computing, especially for AI applications.
- 22 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessReconfigurable In-Memory Computing Using Standard 6T SRAM for BCAM, TCAM, Similarity Indexing, and Logic-in-Memory Operations
In-memory computing (IMC) has emerged as a promising paradigm to overcome the von Neumann bottleneck by performing computations directly within memory, thereby significantly reducing data movement and enhancing energy efficiency. Among various memory technologies, SRAM-Content Addressable Memories (CAMs) based IMC stands out due to its high-speed operation and compatibility with existing CMOS technology. Nevertheless, existing SRAM-CAM based IMC architectures often encounter trade-offs between computational accuracy, stability, and energy efficiency, which hinders their widespread adoption. To tackle these limitations, the proposed reconfigurable SRAM (R-SRAM) architecture integrates both analog and digital computation, utilizing a standard SRAM array alongside a modified peripheral circuit to support multiple functionalities. These include conventional SRAM operation, Binary and Ternary CAM (BCAM and TCAM), similarity index computation, and bitwise logical operations such as AND, NOR, and inversion (INV). Comprehensive post-layout simulations with Monte Carlo statistical analysis for 22nm FDSOI foundry process technology are performed to validate functionality, robustness, and performance. Simulation results indicate a significant improvement in energy per operation, measured at 0.44 femtojoules (fJ)/bit for the BCAM/TCAM search operation, while adding minimal area overhead and maintaining cell stability during computation. These findings underscore the potential of hybrid SRAM-based IMC architectures for next-generation low-power computing, especially for AI applications.
- Open Access
- 4 May 2024
- Published by Elsevier in Internet of Things
- Vol. 26
Efficient event-based robotic grasping perception using hyperdimensional computing
- 4 May 2024
- Published by Elsevier in Internet of Things
- Vol. 26
Open AccessEfficient event-based robotic grasping perception using hyperdimensional computing
- Open Access
- 16 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 97651-97664
Hyper-Dimensional Computing Challenges and Opportunities for AI Applications
Brain-inspired architectures are gaining increased attention, especially for edge devices to perform cognitive tasks utilizing its limited energy budget and computing resources. Hyperdimensional computing (HDC) paradigm is an emerging framework inspired by an abstract representation of neuronal circuits’ attributes in the human brain. That includes a fully holographic random representation, high-dimension vectors representing data, and robustness to uncertainty. The basic HDC pipeline consists of an encoding, training and comparison stages. The encoding algorithm maps different representations of inputs into a single class and stores them in the associative memory (AM) throughout the training stage. Later, during the inference stage, the similarity is computed between the query vector, which is encoded using the same encoding model, and the stored classes in the AM. HDC has shown promising results for 1D applications using less power, and lower latency than state-of-the-art digital neural networks (DNN). While in 2D applications, convolutional neural network (CNN) still achieves higher classification accuracy at the expense of more computations. In this paper, a comprehensive study on the HDC paradigm, main algorithms, and its implementation is presented. Moreover, the main state-of-the-art HDC architectures for 1D and 2D applications are highlighted. The article also analyzes two competing paradigms, namely, HDC and CNN, in terms of accuracy, complexity, and the number of operations. The paper concluded by highlighting challenges and recommendations for future directions on the HDC framework.
- 16 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 97651-97664
Open AccessHyper-Dimensional Computing Challenges and Opportunities for AI Applications
Brain-inspired architectures are gaining increased attention, especially for edge devices to perform cognitive tasks utilizing its limited energy budget and computing resources. Hyperdimensional computing (HDC) paradigm is an emerging framework inspired by an abstract representation of neuronal circuits’ attributes in the human brain. That includes a fully holographic random representation, high-dimension vectors representing data, and robustness to uncertainty. The basic HDC pipeline consists of an encoding, training and comparison stages. The encoding algorithm maps different representations of inputs into a single class and stores them in the associative memory (AM) throughout the training stage. Later, during the inference stage, the similarity is computed between the query vector, which is encoded using the same encoding model, and the stored classes in the AM. HDC has shown promising results for 1D applications using less power, and lower latency than state-of-the-art digital neural networks (DNN). While in 2D applications, convolutional neural network (CNN) still achieves higher classification accuracy at the expense of more computations. In this paper, a comprehensive study on the HDC paradigm, main algorithms, and its implementation is presented. Moreover, the main state-of-the-art HDC architectures for 1D and 2D applications are highlighted. The article also analyzes two competing paradigms, namely, HDC and CNN, in terms of accuracy, complexity, and the number of operations. The paper concluded by highlighting challenges and recommendations for future directions on the HDC framework.
- Open Access
Neuromorphic Vision Based Contact-Level Classification in Robotic Grasping Applications
In recent years, robotic sorting is widely used in the industry, which is driven by necessity and opportunity. In this paper, a novel neuromorphic vision-based tactile sensing approach for robotic sorting application is proposed. This approach has low latency and low power consumption when compared to conventional vision-based tactile sensing techniques. Two Machine Learning (ML) methods, namely, Support Vector Machine (SVM) and Dynamic Time Warping-K Nearest Neighbor (DTW-KNN), are developed to classify material hardness, object size, and grasping force. An Event-Based Object Grasping (EBOG) experimental setup is developed to acquire datasets, where 243 experiments are produced to train the proposed classifiers. Based on predictions of the classifiers, objects can be automatically sorted. If the prediction accuracy is below a certain threshold, the gripper re-adjusts and re-grasps until reaching a proper grasp. The proposed ML method achieves good prediction accuracy, which shows the effectiveness and the applicability of the proposed approach. The experimental results show that the developed SVM model outperforms the DTW-KNN model in term of accuracy and efficiency for real time contact-level classification.
Open AccessNeuromorphic Vision Based Contact-Level Classification in Robotic Grasping Applications
In recent years, robotic sorting is widely used in the industry, which is driven by necessity and opportunity. In this paper, a novel neuromorphic vision-based tactile sensing approach for robotic sorting application is proposed. This approach has low latency and low power consumption when compared to conventional vision-based tactile sensing techniques. Two Machine Learning (ML) methods, namely, Support Vector Machine (SVM) and Dynamic Time Warping-K Nearest Neighbor (DTW-KNN), are developed to classify material hardness, object size, and grasping force. An Event-Based Object Grasping (EBOG) experimental setup is developed to acquire datasets, where 243 experiments are produced to train the proposed classifiers. Based on predictions of the classifiers, objects can be automatically sorted. If the prediction accuracy is below a certain threshold, the gripper re-adjusts and re-grasps until reaching a proper grasp. The proposed ML method achieves good prediction accuracy, which shows the effectiveness and the applicability of the proposed approach. The experimental results show that the developed SVM model outperforms the DTW-KNN model in term of accuracy and efficiency for real time contact-level classification.
- 12 November 2017
- Published by Springer Nature
- p. 323-336
Circle Formation in Multi-robot Systems with Limited Visibility
- 12 November 2017
- Published by Springer Nature
- p. 323-336
Circle Formation in Multi-robot Systems with Limited Visibility