Standard deviation of fitness value results for tested algorithms. by Nebojsa Bacanin (13932723)

Subjects:

An Example of a WPT-MEC Network. by Hend Bayoumi (22693738)

“…EHRL integrates Reinforcement Learning (RL) with Deep Neural Networks (DNNs) to dynamically optimize binary offloading decisions, which in turn obviates the requirement for manually labeled training data and thus avoids the need for solving complex optimization problems repeatedly. …”

Related Work Summary. by Hend Bayoumi (22693738)

“…EHRL integrates Reinforcement Learning (RL) with Deep Neural Networks (DNNs) to dynamically optimize binary offloading decisions, which in turn obviates the requirement for manually labeled training data and thus avoids the need for solving complex optimization problems repeatedly. …”

Simulation parameters. by Hend Bayoumi (22693738)

“…EHRL integrates Reinforcement Learning (RL) with Deep Neural Networks (DNNs) to dynamically optimize binary offloading decisions, which in turn obviates the requirement for manually labeled training data and thus avoids the need for solving complex optimization problems repeatedly. …”

Training losses for N = 10. by Hend Bayoumi (22693738)

“…EHRL integrates Reinforcement Learning (RL) with Deep Neural Networks (DNNs) to dynamically optimize binary offloading decisions, which in turn obviates the requirement for manually labeled training data and thus avoids the need for solving complex optimization problems repeatedly. …”

Normalized computation rate for N = 10. by Hend Bayoumi (22693738)

“…EHRL integrates Reinforcement Learning (RL) with Deep Neural Networks (DNNs) to dynamically optimize binary offloading decisions, which in turn obviates the requirement for manually labeled training data and thus avoids the need for solving complex optimization problems repeatedly. …”

Summary of Notations Used in this paper. by Hend Bayoumi (22693738)

“…EHRL integrates Reinforcement Learning (RL) with Deep Neural Networks (DNNs) to dynamically optimize binary offloading decisions, which in turn obviates the requirement for manually labeled training data and thus avoids the need for solving complex optimization problems repeatedly. …”

a) Accuracy and b) selected feature size of algorithms on the COVID-19 dataset. by Nebojsa Bacanin (13932723)

Subjects:

Optimizing Kernel Transformations to Handle Binary Class Imbalanced Dataset Classification by Vaibhavi Patel (19843282)

Boxplots analysis of the tested algorithms using average error rate across 21 datasets. by Nebojsa Bacanin (13932723)

Subjects:

S1 Dataset - Novel chaotic oppositional fruit fly optimization algorithm for feature selection applied on COVID 19 patients’ health prediction by Nebojsa Bacanin (13932723)

Subjects:

The result of the best fitness value, mean fitness value, standard deviation of fitness value and feature selection ratio of algorithms on the COVID-19 dataset. by Nebojsa Bacanin (13932723)

Subjects:

CEC 2019 benchmark characteristics. by Nebojsa Bacanin (13932723)

Subjects:

Results of Holm’s step-down procedure. by Nebojsa Bacanin (13932723)

Subjects:

Friedman ranks of tested methods on CEC2019 benchmark functions. by Nebojsa Bacanin (13932723)

Subjects:

V-shaped transfer functions. by Nebojsa Bacanin (13932723)

Subjects:

Resilts of Friedman and Iman-Davenport tests (<i>α</i> = 0.05). by Nebojsa Bacanin (13932723)

Subjects:

Mean fitness and standard deviation results of compared approaches on CEC2019 benchmark functions. by Nebojsa Bacanin (13932723)

Subjects:

Error rate convergence graphs. by Nebojsa Bacanin (13932723)

Subjects:

COVID-19 dataset description. by Nebojsa Bacanin (13932723)

Subjects: