Outputs (97)

FiDRL: Flexible Invocation-Based Deep Reinforcement Learning for DVFS Scheduling in Embedded Systems (2024)
Journal Article
Li, J., Jiang, W., He, Y., Yang, Q., Gao, A., Ha, Y., Özcan, E., Bai, R., Cui, T., & Yu, H. (2024). FiDRL: Flexible Invocation-Based Deep Reinforcement Learning for DVFS Scheduling in Embedded Systems. IEEE Transactions on Computers, https://doi.org/10.1109/TC.2024.3465933

Deep Reinforcement Learning (DRL)-based Dynamic Voltage Frequency Scaling (DVFS) has shown great promise for energy conservation in embedded systems. While many works were devoted to validating its efficacy or improving its performance, few discuss t... Read More about FiDRL: Flexible Invocation-Based Deep Reinforcement Learning for DVFS Scheduling in Embedded Systems.

Gase: graph attention sampling with edges fusion for solving vehicle routing problems (2024)
Journal Article
Wang, Z., Bai, R., Khan, F., Özcan, E., & Zhang, T. (2024). Gase: graph attention sampling with edges fusion for solving vehicle routing problems. Memetic Computing, 16(3), 337–353. https://doi.org/10.1007/s12293-024-00428-0

Learning-based methods have become increasingly popular for solving vehicle routing problems (VRP) due to their near-optimal performance and fast inference speed. Among them, the combination of deep reinforcement learning and graph representation all... Read More about Gase: graph attention sampling with edges fusion for solving vehicle routing problems.

CUDA-based parallel local search for the set-union knapsack problem (2024)
Journal Article
Sonuç, E., & Özcan, E. (2024). CUDA-based parallel local search for the set-union knapsack problem. Knowledge-Based Systems, 299, Article 112095. https://doi.org/10.1016/j.knosys.2024.112095

The Set-Union Knapsack Problem (SUKP) is a complex combinatorial optimisation problem with applications in resource allocation, portfolio selection, and logistics. This paper presents a parallel local search algorithm for solving SU... Read More about CUDA-based parallel local search for the set-union knapsack problem.

Constructing selection hyper-heuristics for open vehicle routing with time delay neural networks using multiple experts (2024)
Journal Article
Tyasnurita, R., Özcan, E., Drake, J. H., & Asta, S. (2024). Constructing selection hyper-heuristics for open vehicle routing with time delay neural networks using multiple experts. Knowledge-Based Systems, 295, Article 111731. https://doi.org/10.1016/j.knosys.2024.111731

Hyper-heuristics are general purpose search methods for solving computationally difficult problems. A selection hyper-heuristic is composed of two key components: a heuristic selection method and move acceptance criterion. Under an iterative single-p... Read More about Constructing selection hyper-heuristics for open vehicle routing with time delay neural networks using multiple experts.

Ensemble strategy using particle swarm optimisation variant and enhanced local search capability (2023)
Journal Article
Hong, L., Wang, G., Özcan, E., & Woodward, J. (2023). Ensemble strategy using particle swarm optimisation variant and enhanced local search capability. Swarm and Evolutionary Computation, 84, Article 101452. https://doi.org/10.1016/j.swevo.2023.101452

Particle swarm optimisation is a population-based algorithm for evolutionary computation. A notable recent research direction has been to combine different effective mechanisms to enhance both exploration and exploitation capabilities while employing... Read More about Ensemble strategy using particle swarm optimisation variant and enhanced local search capability.

A sequential quadratic programming based strategy for particle swarm optimization on single-objective numerical optimization (2023)
Journal Article
Hong, L., Yu, X., Tao, G., Özcan, E., & Woodward, J. (2024). A sequential quadratic programming based strategy for particle swarm optimization on single-objective numerical optimization. Complex and Intelligent Systems, 10(2), 2421-2443. https://doi.org/10.1007/s40747-023-01269-z

Over the last decade, particle swarm optimization has become increasingly sophisticated because well-balanced exploration and exploitation mechanisms have been proposed. The sequential quadratic programming method, which is widely used for real-param... Read More about A sequential quadratic programming based strategy for particle swarm optimization on single-objective numerical optimization.

An adaptive greedy heuristic for large scale airline crew pairing problems (2023)
Journal Article
Zeren, B., Özcan, E., & Deveci, M. (2024). An adaptive greedy heuristic for large scale airline crew pairing problems. Journal of Air Transport Management, 114, Article 102492. https://doi.org/10.1016/j.jairtraman.2023.102492

A crew pairing represents a sequence of flight legs that constitute a crew work allocation, starting and ending at the same crew base. A complete set of crew pairings covers all flight legs in the timetable of an airline for a given planning horizon.... Read More about An adaptive greedy heuristic for large scale airline crew pairing problems.

ML meets MLn: machine learning in ligand promoted homogeneous catalysis (2023)
Journal Article
Hirst, J. D., Boobier, S., Coughlan, J., Streets, J., Jacob, P. L., Pugh, O., …Woodward, S. (2023). ML meets MLn: machine learning in ligand promoted homogeneous catalysis. Artificial Intelligence Chemistry, 1(2), Article 100006. https://doi.org/10.1016/j.aichem.2023.100006

The benefits of using machine learning approaches in the design, optimisation and understanding of homogeneous catalytic processes are being increasingly realised. We focus on the understanding and implementation of key concepts, which serve as condu... Read More about ML meets MLn: machine learning in ligand promoted homogeneous catalysis.

Multi-objective topology optimisation for acoustic porous materials using gradient-based, gradient-free, and hybrid strategies (2023)
Journal Article
Ramamoorthy, V. T., Özcan, E., Parkes, A. J., Jaouen, L., & Bécot, F.-X. (2023). Multi-objective topology optimisation for acoustic porous materials using gradient-based, gradient-free, and hybrid strategies. Journal of the Acoustical Society of America, 153(5), Article 2945. https://doi.org/10.1121/10.0019455

When designing passive sound-attenuation structures, one of the challenging problems that arise is optimally distributing acoustic porous materials within a design region so as to maximise sound absorption while minimising material usage. To identify... Read More about Multi-objective topology optimisation for acoustic porous materials using gradient-based, gradient-free, and hybrid strategies.

Layup time for an Automated Fibre Placement process in the framework of a detailed sizing optimisation (2023)
Journal Article
Ntourmas, G., Glock, F., Daoud, F., Schuhmacher, G., Chronopoulos, D., Özcan, E., & Ninić, J. (2023). Layup time for an Automated Fibre Placement process in the framework of a detailed sizing optimisation. Composites Part B: Engineering, 258, Article 110714. https://doi.org/10.1016/j.compositesb.2023.110714

Automatic Fibre Placement manufacturing processes have become the aerospace industry standard for the production of large-scale composite components. Besides the challenges linked with the manufacturing of such components, their design process is als... Read More about Layup time for an Automated Fibre Placement process in the framework of a detailed sizing optimisation.