Osman Hasan
YOU?
Author Swipe
View article: Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems
Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems Open
Neuromorphic Continual Learning (NCL) paradigm leverages Spiking Neural Networks (SNNs) to enable continual learning (CL) capabilities for AI systems to adapt to dynamically changing environments. Currently, the state-of-the-art employ a m…
View article: An Approach for Hardware Trojan Detection Using Triple Modular Redundancy in Approximate Synthesis (HT-TRAPS)
An Approach for Hardware Trojan Detection Using Triple Modular Redundancy in Approximate Synthesis (HT-TRAPS) Open
View article: Continual Learning With Neuromorphic Computing: Foundations, Methods, and Emerging Applications
Continual Learning With Neuromorphic Computing: Foundations, Methods, and Emerging Applications Open
The challenging deployment of compute- and memory-intensive methods from Deep Neural Network (DNN)-based Continual Learning (CL), underscores the critical need for a paradigm shift towards more efficient approaches. Neuromorphic Continual …
View article: Formalization of Biological Circuit Block Diagrams for formally analyzing Biomedical Control Systems in pHRI Applications
Formalization of Biological Circuit Block Diagrams for formally analyzing Biomedical Control Systems in pHRI Applications Open
The control of Biomedical Systems in Physical Human-Robot Interaction (pHRI) plays a pivotal role in achieving the desired behavior by ensuring the intended transfer function and stability of subsystems within the overall system. Tradition…
View article: Magnetic Field Level Improvement using the Composite Cross-Arm Method for Overhead Transmission Lines by Ansys Maxwell Finite Element Model
Magnetic Field Level Improvement using the Composite Cross-Arm Method for Overhead Transmission Lines by Ansys Maxwell Finite Element Model Open
Living near overhead transmission lines has become more common nowadays, where magnetic field radiation has always been a public concern regarding the effect of MF radiation from OTL on the occurrence probability of cancerous diseases. In …
View article: Continual Learning with Neuromorphic Computing: Theories, Methods, and Applications
Continual Learning with Neuromorphic Computing: Theories, Methods, and Applications Open
To adapt to real-world dynamics, intelligent systems need to assimilate new knowledge without catastrophic forgetting, where learning new tasks leads to a degradation in performance on old tasks. To address this, continual learning concept…
View article: Formal performance analysis of optimal relays-based protection scheme for automated distribution networks
Formal performance analysis of optimal relays-based protection scheme for automated distribution networks Open
The dominance of dual-setting directional overcurrent relays (DS-DOCRs) based protection schemes and associated high-reliability requirements require rigorous verification of these schemes before deployment. Traditionally, numerical and si…
View article: Harnessing Fpga and Approximate Computing for Efficient Mea Signal Processing in Neuroscience
Harnessing Fpga and Approximate Computing for Efficient Mea Signal Processing in Neuroscience Open
View article: Scaling Model Checking for Neural Network Analysis via State-Space Reduction and Input Segmentation
Scaling Model Checking for Neural Network Analysis via State-Space Reduction and Input Segmentation Open
Owing to their remarkable learning capabilities and performance in real-world applica- tions, the use of machine learning systems based on Deep Neural Networks (DNNs) has been continuously increasing. However, various case studies and empi…
View article: A Framework for Open World Object Detection
A Framework for Open World Object Detection Open
Open World Object Detection (OWOD) is a computer vision task that focuses on real-world scenarios where object detection algorithms need to not only detect known and labeled objects but also handle novel and unknown objects that were not s…
View article: QuanDA: GPU Accelerated Quantitative Deep Neural Network Analysis
QuanDA: GPU Accelerated Quantitative Deep Neural Network Analysis Open
Over the past years, numerous studies demonstrated the vulnerability of deep neural networks (DNNs) to make correct classifications in the presence of small noise. This motivated the formal analysis of DNNs to ensure that they delineate ac…
View article: PN2Maude: An automatic tool to generate Maude specification for Petri net models
PN2Maude: An automatic tool to generate Maude specification for Petri net models Open
Currently, Model-Driven Engineering (MDE) plays a key role in the software development process as it aims to handle their increasing complexity and focuses on the automatic generation of code and/or specifications from system models. This …
View article: Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)
Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version) Open
Owing to their remarkable learning capabilities and performance in real-world applications, the use of machine learning systems based on Neural Networks (NNs) has been continuously increasing. However, various case studies and empirical fi…
View article: UnbiasedNets: a dataset diversification framework for robustness bias alleviation in neural networks
UnbiasedNets: a dataset diversification framework for robustness bias alleviation in neural networks Open
Performance of trained neural network (NN) models, in terms of testing accuracy, has improved remarkably over the past several years, especially with the advent of deep learning. However, even the most accurate NNs can be biased toward a s…
View article: Approximate Computing-Based Processing of MEA Signals on FPGA
Approximate Computing-Based Processing of MEA Signals on FPGA Open
Microelectrode arrays (MEAs) are essential equipment in neuroscience for studying the nervous system’s behavior and organization. MEAs are arrays of parallel electrodes that work by sensing the extracellular potential of neurons in their p…
View article: Signgraph: An Efficient and Accurate Pose-Based Graph Convolution Approach Toward Sign Language Recognition
Signgraph: An Efficient and Accurate Pose-Based Graph Convolution Approach Toward Sign Language Recognition Open
Sign language recognition (SLR) enables the deaf and speech-impaired community to integrate and communicate effectively with the rest of society. Word level or isolated SLR is a fundamental yet complex task with the main objective of using…
View article: Mipa-Resgcn: A Multi-Input Part Attention Based Residual Graph Convolution Framework for Sign Language Recognition
Mipa-Resgcn: A Multi-Input Part Attention Based Residual Graph Convolution Framework for Sign Language Recognition Open
View article: On the Formalization of the Heat Conduction Problem in HOL
On the Formalization of the Heat Conduction Problem in HOL Open
Partial Differential Equations (PDEs) are widely used for modeling the physical phenomena and analyzing the dynamical behavior of many engineering and physical systems. The heat equation is one of the most well-known PDEs that captures the…
View article: Metaheuristic Algorithms for Proof Searching in HOL4
Metaheuristic Algorithms for Proof Searching in HOL4 Open
User guided proof development in interactive theorem proving is a manual and time consuming activity.For automating proof searching and optimization in a higher-order logic proof assistant, we provide two metaheuristic algorithms that are …
View article: Formal analysis of 2D image processing filters using higher-order logic theorem proving
Formal analysis of 2D image processing filters using higher-order logic theorem proving Open
View article: The Exclusion’s Legality and Normality in Laila Halaby’s Once in a Promised Land
The Exclusion’s Legality and Normality in Laila Halaby’s Once in a Promised Land Open
This paper is devoted to dissecting the emerging aspects of exclusion and otherness that characterize Post-Modernity by referring to the specific context of the US culture as presented in Laila Halaby’s Once in a Promised Land (2007). What…
View article: Towards the Formal Performance Analysis of Multistate Coherent Systems using HOL Theorem Proving
Towards the Formal Performance Analysis of Multistate Coherent Systems using HOL Theorem Proving Open
Many practical engineering systems and their components have multiple performance levels and failure modes. If these systems form a monotonically increasing structure function (system model) with respect to the performance of their compone…
View article: Formalization of Bond Graph using Higher-order-logic Theorem Proving
Formalization of Bond Graph using Higher-order-logic Theorem Proving Open
Bond graph is a unified graphical approach for describing the dynamics of complex engineering and physical systems and is widely adopted in a variety of domains, such as, electrical, mechanical, medical, thermal and fluid mechanics. Tradit…
View article: Chronic kidney disease diagnosis using decision tree algorithms
Chronic kidney disease diagnosis using decision tree algorithms Open
View article: An Enhanced Rewriting Logic Based Semantics for High-Level Petri nets
An Enhanced Rewriting Logic Based Semantics for High-Level Petri nets Open
International audience
View article: Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks
Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks Open
Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions. The purpose of this study is to review the state-of-the-art methods that allow co…
View article: Formal verification of Matrix based MATLAB models using interactive theorem proving
Formal verification of Matrix based MATLAB models using interactive theorem proving Open
MATLAB is a software based analysis environment that supports a high-level programing language and is widely used to model and analyze systems in various domains of engineering and sciences. Traditionally, the analysis of MATLAB models is …
View article: BioNetExplorer: Architecture-Space Exploration of Biosignal Processing Deep Neural Networks for Wearables
BioNetExplorer: Architecture-Space Exploration of Biosignal Processing Deep Neural Networks for Wearables Open
In this work, we propose the BioNetExplorer framework to systematically\ngenerate and explore multiple DNN architectures for bio-signal processing in\nwearables. Our framework adapts key neural architecture parameters to search\nfor an emb…
View article: Additional file 1 of Chronic kidney disease diagnosis using decision tree algorithms
Additional file 1 of Chronic kidney disease diagnosis using decision tree algorithms Open
Additional file 1.
View article: How childhood diseases awareness contributes to minimize the risk of disease severity in children under five age: an evolutionarystudy
How childhood diseases awareness contributes to minimize the risk of disease severity in children under five age: an evolutionarystudy Open
Objective: To scrutinise the contribution of childhood disease awareness in mothers to minimise the risk of disease severity in children aged <5, and to evaluate the effectiveness of a proposed app in this context.
Methods: The evolutiona…