Control strategy of robotic manipulator based on multi-task reinforcement learning by Tao Wang, Ziming Ruan, Yuyan Wang, Chong Chen

“…To tackle this issue, instead of uniform parameter sharing, we propose an adjudicate reconfiguration network model, which we integrate into the Soft Actor-Critic (SAC) algorithm to address the optimization problems brought about by parameter sharing in multi-task reinforcement learning algorithms. …”
Get full text

A Hybrid Deep Learning Model for UAV Path Planning in Dynamic Environments by Junchi Zhang, Yanning Xian, Xun Zhu, Hongtao Deng

“…While its variants can converge to the optimal solution, they suffer from more memory and computation consumption. …”
Get full text

Interference-Aware AAV-TBS Coordinated NOMA: Joint User Scheduling, Power Allocation and Trajectory Design by Haiyong Zeng, Rui Zhang, Xu Zhu, Yufei Jiang, Zhongxiang Wei, Fu-Chun Zheng

“…With the proposed scheme, the interference links between TBS and AAV-served users are enabled to carry useful information, therefore, an enhanced degree of freedom is achieved, leading to a much higher sum-rate over the non-coordinated AAV-assisted NOMA systems where the interference of AAV-served users from TBS is extensively suppressed. Moreover, joint optimization of user scheduling, power allocation and AAV three-dimensional (3D) trajectory design is conducted to maximize the sum-rate of edge users while maintaining a high quality of service at cell-center users, with the consideration of imperfect channel estimation: a) A user scheduling principle dedicated for AAV-TBS coordinated NOMA systems is presented, based on which a two-step user scheduling and power allocation (USPA) algorithm is proposed, with the derivation of optimal power allocation solution; b) A joint USPA algorithm is proposed with closed-form results; c) Considering the line of sight (LoS) and non-LoS factors in the air to ground channel, the 3D trajectory of AAV is designed based on successive convex approximation. …”
Get full text

Symmetry-driven embedding of networks in hyperbolic space by Simon Lizotte, Jean-Gabriel Young, Antoine Allard

“…We show that the samples are consistent with current algorithms while providing added credible intervals for the coordinates and all network properties. …”
Get full text

A Metaheuristic Method for the Task Assignment Problem in Continuous-Casting Production by Hongtao Hu, Yiwei Wu, Tingsong Wang

“…An improved solution algorithm based on particle swam optimization is developed to efficiently solve the proposed model. …”
Get full text

State-Aware Energy Management Strategy for Marine Multi-Stack Hybrid Energy Storage Systems Considering Fuel Cell Health by Pan Geng, Jingxuan Xu

“…A hybrid Genetic Algorithm–Particle Swarm Optimization (GA-PSO) approach achieves global optimization. …”
Get full text

RL based transmission power control for energy harvesting sensor by LIU Nanjun, JIA Riheng, XU Wentao, LI Minglu

“…Experimental results demonstrate that the proposed algorithm outperformes baseline strategies and approaches the theoretical optimal in certain scenarios.…”
Get full text

Modeling Analysis of the Relationship between Adolescent Aerobic Exercise and Obesity Reduction Based on Deep Learning by Peng Mu

“…It also explains the constraint conditions that aerobic exercise has to meet in the reduction of adolescent obesity and introduces particle algorithm to establish a model of optimal aerobic exercise to reduce adolescent obesity. …”
Get full text

Improving Secrecy Capacity in the Face of Eavesdropping in SWIPT CIoT Networks With Actor-Critic DRL by Nada Abdel Khalek, Walaa Hamouda

“…We formulate the challenging non-convex optimization problem to maximize secrecy capacity while ensuring spectrum sharing and energy constraints and model the CIoT agent’s decision-making as a model-free Markov decision process (MDP). …”
Get full text

Hybrid precoding and power allocation for mmWave NOMA systems based on time delay line arrays by Gangcan SUN, Xinli WU, Wanming HAO, Zhengyu ZHU

“…Specifically,the Dinkelbach method is applied in the outer layer to transform the fractional structure of the objective function in EE optimization into a subtractive structure, and the non-convex objective function is transformed into a convex function by using mathematical tools in the inner layer, and then an iterative algorithm based on alternating optimization (AO) is proposed for power allocation, and finally the solution of the initial problem is obtained by circular iteration in both inner and outer layers. …”
Get full text

Leveraging Interactive Evolutionary Computation to Induce Serendipity in Informal Learning by Satoko Inoue, Emmanuel Ayedoun, Hiroshi Takenouchi, Masataka Tokumaru

“…We conducted both numerical simulations and experimental evaluations to assess the effectiveness of our content optimization algorithm and the impact of our approach on inducing serendipity in informal learning environments. …”
Get full text

UAV Mission Path Planning Based on Reinforcement Learning in Dynamic Environment by Gui Fu, Yang Gao, Liwen Liu, Mingye Yang, Xinyu Zhu

“…The path planning and optimization of UAV in dynamic environment is studied, and the path planning algorithm and Hungarian algorithm are added. …”
Get full text

User Cost Minimization and Load Balancing for Multiple Electric Vehicle Charging Stations Based on Deep Reinforcement Learning by Yongxiang Xia, Zhongyi Cheng, Jiaqi Zhang, Xi Chen

“…In the second stage, we use the DRL algorithm. In the DRL algorithm, we design a novel reward function that enables charging stations to meet user charging demands while minimizing user charging costs and reducing the load gap among distribution networks. …”
Get full text

SV-SAE: Layer-Wise Pruning for Autoencoder Based on Link Contributions by Joohong Rheey, Hyunggon Park

“…This paper introduces a layer-wise pruning algorithm specifically for multilayer perceptron-based autoencoders. …”
Get full text

YOLO-APDM: Improved YOLOv8 for Road Target Detection in Infrared Images by Song Ling, Xianggong Hong, Yongchao Liu

“…A new algorithm called YOLO-APDM is proposed to address low quality and multi-scale target detection issues in infrared road scenes. …”
Get full text

Multiobjective Coverage Control Strategy for Energy-Efficient Wireless Sensor Networks by Hui Zhou, Tian Liang, Chen Xu, Jing Xie

“…A new evolutionary algorithm named Multiobjective free search algorithm (MOFS) is designed for WSN optimization problem based on fitness functions and binary coding schemes. …”
Get full text

Deep Q-Learning-Based Resource Management in IRS-Assisted VLC Systems by Ahmed Al Hammadi, Lina Bariah, Sami Muhaidat, Mahmoud Al-Qutayri, Paschalis C. Sofotasios, Merouane Debbah

“…Moreover, the synergy between the MPF and the DQL algorithms is investigated. To this end, we demonstrate that the MPF algorithm maximizes the fairness amongst the users while the DQL algorithm maximizes the overall SE and improves the robustness against the noise. …”
Get full text

Multi-Vehicle Object Recognition Method Based on YOLOv7-W by Xin Liu, Jingbin Zhao, Zhi Zhang, Rongxing Wu, Xun Li

“…To improve the matching accuracy of prior frames, the k-means++ clustering algorithm is employed to optimize the prior frame parameters. …”
Get full text

Lightweight CNN-Based Visual Perception Method for Assessing Local Environment Complexity of Unmanned Surface Vehicle by Tulin Li, Xiufeng Zhang, Yingbo Huang, Chunxi Yang

“…Subsequently, this identification result can be used as feedback for the heuristic algorithm to optimize and plan the USV’s path. The simulation results indicate that the developed model achieves an 80% reduction in model size while maintaining an accuracy exceeding 90%. …”
Get full text

Deep Reinforcement Learning Assisted UAV Path Planning Relying on Cumulative Reward Mode and Region Segmentation by Zhipeng Wang, Soon Xin Ng, Mohammed EI-Hajjar

“…Our proposed region segmentation aims to reduce the probability of DRL agents falling into local optimal trap, while our proposed cumulative reward model takes into account the distance from the node to the destination and the density of obstacles near the node, which solves the problem of sparse training data faced by the DRL algorithms in the path planning task. …”
Get full text