DAP: A dataset-agnostic predictor of neural network performance حسب Sui Paul Ang (18460605)

Adaptive Federated Learning Architecture To Mitigate Non-IID Through Multi-Objective GA-Based Efficient Client Selection حسب Ajaj, Mohamad

"…Federated Learning (FL) has emerged as a promising framework for collaborative model training across distributed devices without centralizing sensitive data. …"
احصل على النص الكامل
احصل على النص الكامل
احصل على النص الكامل

Data Redundancy Management in Connected Environments حسب Mansour, Elio

"…We describe its modules, and clustering-based algorithms. Moreover, our proposal detects temporal, and spatial-temporal redundancies in order to consider both static and mobile devices/sensors. …"
احصل على النص الكامل
احصل على النص الكامل
احصل على النص الكامل
احصل على النص الكامل

R-CONV++: uncovering privacy vulnerabilities through analytical gradient inversion attacks حسب Tamer Ahmed Eltaras (22565414)

"…<p dir="ltr">Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. …"

Predictive modelling in times of public health emergencies: patients’ non-transport decisions during the COVID-19 pandemic حسب Hassan Farhat (9000509)

Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method حسب Mohamed Massaoudi (16888710)

"…The proposed forecasting tool incorporates a base model and meta-model layers. The first-layer base learner combines extreme learning machines, extremely randomized trees, k-nearest neighbor, and mondrian forest models. …"

A kernelization algorithm for d-Hitting Set حسب Abu-Khzam, Faisal N.

"…For 3-Hitting Set, an arbitrary instance is reduced into an equivalent one that contains at most 5k2+k elements. This kernelization is an improvement over previously known methods that guarantee cubic-order kernels. …"
احصل على النص الكامل
احصل على النص الكامل
احصل على النص الكامل

Particle swarm optimization algorithm: review and applications حسب Abualigah, Laith

"…Particle swarm optimization (PSO) is a heuristic global optimization technique and an optimization algorithm that is swarm intelligence-based. It is based on studies into the movement of bird flocks. …"
احصل على النص الكامل

Scatter Search algorithm for Protein Structure Prediction حسب Mansour, Nashat

"…In this paper, we present a Scatter Search (SS) algorithm for predicting 3D structures of proteins based on torsion angles representation. …"
احصل على النص الكامل
احصل على النص الكامل
احصل على النص الكامل

A Novel Fault Diagnosis of Uncertain Systems Based on Interval Gaussian Process Regression: Application to Wind Energy Conversion Systems حسب Majdi Mansouri (16869885)

The Effects of Data Mining on Small Businesses in Dubai حسب AlMutawa, Rasha

"…While there are numerous studies on the best data mining models and their uses, even on certain industries, this study focuses on the applications more than the algorithms and models and their usefulness for small businesses specifically. …"
احصل على النص الكامل

Enhanced PSO-Based NN for Failures Detection in Uncertain Wind Energy Systems حسب Khaled Dhibi (16891524)

"…First, a feature selection tool using PSO Algorithm is developed. Then, in order to maximize the diversity between data samples and improve the effectiveness of using PSO algorithm for feature selection, the Euclidean distance metric is used in order to reduce the data and maximize the diversity between data samples. …"

An Improved Genghis Khan Optimizer based on Enhanced Solution Quality Strategy for Global Optimization and Feature Selection Problems حسب Abdel-Salam, Mahmoud

"…The primary goals of feature selection are to decrease the number of dimensions and enhance classification accuracy in many domains, such as text classification, large-scale data analysis, and pattern recognition. Several metaheuristics, such as the Genghis Khan Shark Optimizer Algorithm (GKSO), can assist in optimizing the FS issue. …"
احصل على النص الكامل

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

"…<p dir="ltr">While deep learning algorithms have advanced to a great extent, they are all designed for frame-based imagers that capture images at a high frame rate, which leads to a high storage requirement, heavy computations, and very high power consumption. …"

Block constrained pressure residual preconditioning for two-phase flow in porous media by mixed hybrid finite elements حسب Stefano Nardean (14151900)

"…<p dir="ltr">This work proposes an original preconditioner that couples the Constrained Pressure Residual (CPR) method with block preconditioning for the efficient solution of the linearized systems of equations arising from fully implicit multiphase flow models. …"

A Survey of Machine Learning Innovations in Ambulance Services: Allocation, Routing, and Demand Estimation حسب Reem Tluli (22282702)

"…ML algorithms could play a pivotal role in dynamically allocating resources, devising efficient routes, and predicting demand patterns. …"

Intelligent Rapidly-Exploring Random Tree Star Algorithm حسب Ahmed, Khidir Galal Eldin Khidir

احصل على النص الكامل

Application of Data Mining to Predict and Diagnose Diabetic Retinopathy حسب Haniyeh, Maryam

احصل على النص الكامل

Social spider optimization algorithm: survey and new applications حسب Abualigah, Laith

"…This survey studied the SSO and compared it with other PSO algorithms to find the best-performing algorithm based on a benchmark. …"
احصل على النص الكامل

An improved quorum selection algorithm (IQSA). (c2007) حسب Younes, Samer

احصل على النص الكامل
احصل على النص الكامل