C-level road irregularity sample. by Jianwei Liu (163716)

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

The workflow diagram for the gene expression biomarker study which involve using principal component analysis (PCA) to reduce the number of features (principal components), thus re... by Aninda Astuti (21736334)

Multi objective optimization design process. by Xueyong Pan (20390363)

“…Subsequently, response surface experiments were conducted to analyze the width parameters of various flow channels in the liquid cooled plate Finally, the Design of Experiment (DOE) was employed to conduct optimal Latin hypercube sampling on the flow channel depth (<i>H</i>), mass flow (<i>Q</i>), and inlet and outlet diameter (<i>d</i>), combined with a genetic algorithm for multi-objective analysis. …”

Proposed Algorithm. by Hend Bayoumi (22693738)

“…Hence, an Energy-Harvesting Reinforcement Learning-based Offloading Decision Algorithm (EHRL) is proposed. 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. …”

Comparisons between ADAM and NADAM optimizers. by Hend Bayoumi (22693738)

“…Hence, an Energy-Harvesting Reinforcement Learning-based Offloading Decision Algorithm (EHRL) is proposed. 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. …”

Optimal Latin square sampling distribution. by Xueyong Pan (20390363)

“…Subsequently, response surface experiments were conducted to analyze the width parameters of various flow channels in the liquid cooled plate Finally, the Design of Experiment (DOE) was employed to conduct optimal Latin hypercube sampling on the flow channel depth (<i>H</i>), mass flow (<i>Q</i>), and inlet and outlet diameter (<i>d</i>), combined with a genetic algorithm for multi-objective analysis. …”

The flowchart of Algorithm 2. by Jing Xu (15337)

“…To solve this optimization model, a multi-level optimization algorithm is designed. …”

PANet network design. by Mengqi Yuan (4852555)

“…Finally, a bidirectional feature pyramid network (BiFPN) was integrated to optimize feature fusion, leveraging a bidirectional information transfer mechanism and an adaptive feature selection strategy. …”

BiFPN network design. by Mengqi Yuan (4852555)

“…Finally, a bidirectional feature pyramid network (BiFPN) was integrated to optimize feature fusion, leveraging a bidirectional information transfer mechanism and an adaptive feature selection strategy. …”

Design variables and range of values. by Xueyong Pan (20390363)

“…Subsequently, response surface experiments were conducted to analyze the width parameters of various flow channels in the liquid cooled plate Finally, the Design of Experiment (DOE) was employed to conduct optimal Latin hypercube sampling on the flow channel depth (<i>H</i>), mass flow (<i>Q</i>), and inlet and outlet diameter (<i>d</i>), combined with a genetic algorithm for multi-objective analysis. …”

Feasibility diagram of design points. by Xueyong Pan (20390363)

“…Subsequently, response surface experiments were conducted to analyze the width parameters of various flow channels in the liquid cooled plate Finally, the Design of Experiment (DOE) was employed to conduct optimal Latin hypercube sampling on the flow channel depth (<i>H</i>), mass flow (<i>Q</i>), and inlet and outlet diameter (<i>d</i>), combined with a genetic algorithm for multi-objective analysis. …”

The sampled values and the fitted values. by Hongjun Meng (5031806)

Third setting: batch optimization. by Camille Gontier (9442304)

Sample points and numerical simulation results. by Xueyong Pan (20390363)

“…Subsequently, response surface experiments were conducted to analyze the width parameters of various flow channels in the liquid cooled plate Finally, the Design of Experiment (DOE) was employed to conduct optimal Latin hypercube sampling on the flow channel depth (<i>H</i>), mass flow (<i>Q</i>), and inlet and outlet diameter (<i>d</i>), combined with a genetic algorithm for multi-objective analysis. …”

Three sensor sample data with noise data. by Tang Ruipeng (20141334)

Simulation sample. by Xiaogang Li (299205)

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

“…Hence, an Energy-Harvesting Reinforcement Learning-based Offloading Decision Algorithm (EHRL) is proposed. 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)

“…Hence, an Energy-Harvesting Reinforcement Learning-based Offloading Decision Algorithm (EHRL) is proposed. 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)

“…Hence, an Energy-Harvesting Reinforcement Learning-based Offloading Decision Algorithm (EHRL) is proposed. 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. …”