Full-fledged semantic indexing and querying model designed for seamless integration in legacy RDBMS by Tekli, Joe

“…We have conducted a battery of experiments to test the performance of SemIndex, evaluating its construction time, storage size, query processing time, and result quality, in comparison with legacy inverted index. …”
Get full text
Get full text
Get full text
Get full text

Defense against adversarial attacks: robust and efficient compressed optimized neural networks by Insaf Kraidia (19198012)

“…This study compresses the generative pre-trained transformer (GPT) by 65%, saving time and memory without causing performance loss. …”

High-order parametrization of the hypergeometric-Meijer approximants by Abouzeid M. Shalaby (16329062)

“…<p>In this work, we introduce an extension to the hypergeometric algorithm we developed before for the resummation of divergent series.The extension overcome the time-consuming problem we face in the parametrization process of the hypergeometric approximants. …”

Developing a framework for using face recognition in transit payment transactions by HABEH, ORABI MOHAMMAD ABDULLAH

“…The argued face recognition accuracy between 98%-99.2% and average processing time including metro gate opening time ranges between 1114-1400 milliseconds. …”
Get full text

Newton-Raphson based adaptive inverse control scheme for tracking of nonlinear dynamic plants by Shafiq, M.

“…The U-model is utilized to design an adaptive inverse controller by using a simple root-solving algorithm of Newton-Raphson. The synergy of U-model with AIC structure has provided an effective and straight forward method for adaptive tracking of nonlinear plants. …”
Get full text
Get full text

Optimal Routing and Scheduling in E-commerce Logistics using Crowdsourcing Strategies by Mohamed, Eman

Get full text

Optimizing ADWIN for Steady Streams by Moharram, Hassan

“…However, online machine learning comes with many challenges for the different aspects of the learning process, starting from the algorithm design to the evaluation method. …”
Get full text
Get full text
Get full text

Lagrangian tracking in stochastic fields with application to an ensemble of velocity fields in the Red Sea by Issa, Leila

“…To this end, an efficient algorithm for forward and backward tracking of passive particles in stochastic flow-fields is presented. …”
Get full text
Get full text
Get full text
Get full text

A Fully Optical Laser Based System for Damage Detection and Localization in Rail Tracks Using Ultrasonic Rayleigh Waves: A Numerical and Experimental Study by Masurkar, Faeez

“…Further, As the quality of received signals differs at different sensing points as a result of the surface conditions of the specimen, the Self Adaptive Smart Algorithm (SASA) method was adopted to filter out the noise and accurately pinpoint the defect reflected wave packet which ultimately aids in better detection and localization. …”
Get full text

Drones Tracking Adaptation Using Reinforcement Learning: Proximal Policy optimization by Alhadhrami, Esra Ebrahim

“…These outcomes were compared with those of a feed-forward neural network learning, the Castella innovation/ Q values mapping, and fixed Q values. The PPO algorithm yielded promising results. We employed the Stone Soup library to simulate ground truths, measurements, and the Kalman filter tracking process.…”
Get full text

An effective design system for dynamically reconfigurable architectures by Ouaiss, I.

“…The results, obtained on a commercial RC architecture, show that the multiply-reconfigured version of the JPEG compression algorithm achieves reasonable improvement in execution times compared to the one-time configured version.…”
Get full text
Get full text
Get full text
Get full text

FPGA-Based Network Traffic Classification Using Machine Learning by Elnawawy, Mohammed

“…The performed experiments show that 60% of flow packets are a good compromise that ensures high performance in the least processing time. The results of the conducted experiments indicate that random forest outperforms other algorithms achieving a maximum accuracy of 98.5% and an F-score of 0.932. …”
Get full text

Simulations of the penetration of 6061-T6511 aluminum targets by spherical-nosed VAR 4340 steel projectiles by Warren, Thomas

“…In the context of an analysis code, this approximation eliminates the need for discretizing the target as well as the need for a contact algorithm. Thus, this method substantially reduces the computer time and memory requirements. …”
Get full text
Get full text
Get full text

Development of multivariable PID controller gains in presence of measurement noise by Saab, Samer S.

“…It turns out that such convergence requires time-varying gains. Subsequently, novel recursive algorithms providing optimal and sub-optimal time-varying PID gains are proposed for discrete-time varying linear multiple-input multiple-output (MIMO) systems. …”
Get full text
Get full text
Get full text
Get full text

Energy-Efficient Computation Offloading in Vehicular Edge Cloud Computing by Xin Li (51274)

“…Numerical results corroborate that our designed algorithm can gain above 80% execution time conservation and 62% conservation on energy consumption, and it exhibits fast convergence and superior performance compared to benchmark solutions.…”

Approximate XML structure validation based on document–grammar tree similarity by Tekli, Joe

“…In this paper, we propose an original method for measuring the structural similarity between an XML document and an XML grammar (DTD or XSD), considering their most common operators that designate constraints on the existence, repeatability and alternativeness of XML elements/attributes (e.g., ?…”
Get full text
Get full text
Get full text
Get full text

Oversampling techniques for imbalanced data in regression by Samir Brahim Belhaouari (9427347)

“…For tabular data, we also present the Auto-Inflater neural network, utilizing an exponential loss function for Autoencoders. …”

Adaptive PID Controller for a Non Linear Pendulum System Using Recurrent Neural Networks by Jafari, Reza

Get full text

Extreme Early Image Recognition Using Event-Based Vision by Abubakar Abubakar (18278998)

“…It is demonstrated that, on average for all the datasets, the proposed technique recognizes an image 38.7 ms before the first perfect event and 603.4 ms before the last event is received, which is a reduction of 34% and 69% of the time needed, respectively. Further, less processing is required as the image is recognized 9460 events earlier, which is 37% less than waiting for the first perfectly recognized image. …”

Vibration suppression in a cantilever beam using a string-type vibration absorber by Issa, Jimmy S.

“…The string is rigidly connected to the fixed end of the beam and through a spring and damper to a second point on the beam. The finite element method is used to model the system and a reduced order model is obtained through modal reduction performed on both the string and the beam. …”
Get full text
Get full text
Get full text
Get full text