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

GSB: GNGS and SAG-BiGRU network for malware dynamic detection. by Zhanhui Hu, Guangzhong Liu, Xinyu Xiang, Yanping Li, Siqing Zhuang

“…For solving the problem, this study proposed the GNGS algorithm to construct a new balance dataset for the model algorithm to pay more attention to the feature learning of the minority attacks' malware to improve the detection rate of attacks' malware. …”
Get full text

CSL-SFNet for Cooperative Spectrum Sensing in Cognitive Satellite Network with GEO and LEO Satellites by Kai Yang, Shengbo Hu, Xin Zhang, Tingting Yan, Manqin Zhu

“…The simulation results demonstrate that the proposed algorithm can achieve a detection probability of 90% when the signal-to-noise ratio is −20 dB; it has a shorter running time and always outperforms the other CSS algorithms.…”
Get full text

Inversion Study of Mechanical Parameters of Tunnel Surrounding Rock Based on Similar Test by Xianyun Wang, Hewei Cui, Hailiang Xu, Dong An, Yimin Song

“…Based on similar model tests and finite element simulations, inversion study of the mechanical parameters of the tunnel surrounding rock by combining artificial fish swarm algorithm (AFSA) and digital scattering correlation method is carried out. …”
Get full text

Advancing Over-the-Air Federated Learning through Deep Reinforcement Learning in UAV-Assisted Networks with Movable Antennas by Mohsen Ahmadzadeh, Saeid Pakravan, Ghosheh Hodtani

“…Numerical results demonstrate that the proposed algorithm outperforms benchmarks such as Advantage Actor-Critic(A2C) and Soft Actor-Critic (SAC).…”
Get full text

System Verification and FPGA Implementation of Hardware Preemptive Scheduler for RISC-V Processor by Ionel Zagan, Vasile Gheorghita Gaitan

“…The overall purpose of this paper is to present the hardware scheduler accelerator (HwSA) concept based on the RISC-V 4-stage pipeline CPU, where the scheduling algorithm is implemented in hardware. The proposed system is compared with existing soft-core processors using different parameters, such as the field-programmable gate arrays (FPGA) resources used for implementation, frequency, instruction set architecture (ISA), scheduler type, and the number of pipeline stages. …”
Get full text

SA3C-ID: a novel network intrusion detection model using feature selection and adversarial training by Wanwei Huang, Haobin Tian, Lei Wang, Sunan Wang, Kun Wang, Songze Li

“…Next, the network intrusion detection process is modeled as a Markov decision process and integrated with the Soft Actor-Critic (SAC) reinforcement learning algorithm, with a view to constructing agents; In the context of adversarial training, two agents, designated as the attacker and the defender, are defined to perform asynchronous adversarial training. …”
Get full text

Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements by Cheng Chen, Guan-Nian Chen, Song Feng, Xiao-Zhen Fan, Liang-Tong Zhan, Yun-Min Chen

Get full text

Multi-objective artificial-intelligence-based parameter tuning of antennas using variable-fidelity machine learning by Slawomir Koziel, Anna Pietrenko-Dabrowska, Stanislaw Szczepanski

“…Due to the reliance on computationally-expensive electromagnetic (EM) simulations, the use of conventional algorithms is prohibitive. These costs can be reduced by appropriate algorithmic tools involving surrogate modeling and soft computing methods. …”
Get full text

Autonomous Dogfight Decision-Making for Air Combat Based on Reinforcement Learning with Automatic Opponent Sampling by Can Chen, Tao Song, Li Mo, Maolong Lv, Defu Lin

“…The training outcomes demonstrate that this improved PPO algorithm with an AOS framework outperforms existing reinforcement learning methods such as the soft actor–critic (SAC) algorithm and the PPO algorithm with prioritized fictitious self-play (PFSP). …”
Get full text

Estimation of Vs30 and site classification of Bhaktapur district, Nepal using microtremor array measurement by Roshan Prajapati, Salim Dhonju, Subeg Man Bijukchhen, Michiko Shigefuji, Nobuo Takai

“…The elevated eastern and southeastern areas with high Vs30 were categorized as dense soil or soft rock, whereas the areas with low Vs30 that had suffered significant damage during the 2015 Gorkha earthquake were classified as soft soil sites. …”
Get full text

Deep reinforcement learning for path planning of autonomous mobile robots in complicated environments by Zhijie Zhang, Hao Fu, Juan Yang, Yunhan Lin

“…To tackle these challenges, the Gated Attention Prioritized Experience Replay Soft Actor-Critic (GAP_ SAC) algorithm is proposed. …”
Get full text

MAARS: Multiagent Actor–Critic Approach for Resource Allocation and Network Slicing in Multiaccess Edge Computing by Ducsun Lim, Inwhee Joe

“…This paper presents a novel algorithm to address resource allocation and network-slicing challenges in multiaccess edge computing (MEC) networks. …”
Get full text

Performance of 256QAM in LTE-Hi indoor scenario by Shan LIU, Cheng TAO, Liu LIU

“…In order to solve the traffic explosion of indoor and hotspots,LTE-Hi was put forward by 3GPP organization in Release12.Due to the coverage particularity of indoor and hotspots scenarios,the organization introduced 256QAM to improve system performance.According to the 256QAM constellation given in the standard,a soft demodulation algorithm based on border distance decision was deduced.Through a simulation of the UE SINR distribution in the LTE-Hi scenario,the feasibility of the 256QAM was proved and according to the CQI/MCS/TBS signaling table changed for 256QAM,link level simulation showed the 256QAM and 64QAM throughput in comparison under different EVM index.Finally,the system performance with and without the introduction of 256QAM under different scenarios was evaluated.…”
Get full text

Performance of 256QAM in LTE-Hi indoor scenario by Shan LIU, Cheng TAO, Liu LIU

“…In order to solve the traffic explosion of indoor and hotspots,LTE-Hi was put forward by 3GPP organization in Release12.Due to the coverage particularity of indoor and hotspots scenarios,the organization introduced 256QAM to improve system performance.According to the 256QAM constellation given in the standard,a soft demodulation algorithm based on border distance decision was deduced.Through a simulation of the UE SINR distribution in the LTE-Hi scenario,the feasibility of the 256QAM was proved and according to the CQI/MCS/TBS signaling table changed for 256QAM,link level simulation showed the 256QAM and 64QAM throughput in comparison under different EVM index.Finally,the system performance with and without the introduction of 256QAM under different scenarios was evaluated.…”
Get full text

Advanced Braille recognition based on protein biomimetic skin mechanical sensors by Nianfeng Zhang, Ailing Yang, Andeng Liu, Guoxi Shao, Xixi Wang, Yingjin Luo, Zhihua Liu, Yating Shi, Na Li, Wenxi Guo, Wu Qiu, Dapeng Yang

Get full text

Investigation on the Role of Artificial Intelligence in Measurement System by P. A. Rezvy, Venkata Lakshmi Narayana Komanapalli

“…Hardware approach with soft computation has reduced non linearity error by 84.63% for thermocouple linearization, meanwhile novel hybrid approach using genetic algorithm (GA) and particle swarm optimization (PSO) combined with back propagation neural network (BPNN) have reduced mean absolute percentage error to 1.2 % for industrial weir than conventional hardware approaches using sensors and signal conditioning circuits but at higher computational cost. …”
Get full text

Research on Sensitivity Improvement Methods for RTD Fluxgates Based on Feedback-Driven Stochastic Resonance with PSO by Rui Wang, Na Pang, Haibo Guo, Xu Hu, Guo Li, Fei Li

“…In this paper, based on the study of the excitation signal and input noise characteristics, the stochastic resonance is proposed to be realized by adding feedback by taking advantage of the high hysteresis loop rectangular ratio, low coercivity and bistability characteristics of the soft magnetic material core. Simulink is used to construct the sensor model of odd polynomial feedback control, and the Particle Swarm Optimization (PSO) algorithm is used to optimize the coefficients of the feedback function so that the sensor reaches a resonance state, thus reducing the noise interference and improving the sensitivity of the sensor. …”
Get full text

Multi-Task Reinforcement Learning Based on Parallel Recombination Networks by Manlu Liu, Qingbo Zhang, Weimin Qian

“…By combining the proposed ’Soft Parallel Recombination Network’ method with the SAC algorithm (PRSAC) and validating it on the Meta-world multi-task training platform, the experimental results demonstrate that the proposed method significantly outperforms existing baseline algorithms in terms of sample efficiency and performance.…”
Get full text

The search for the holy grail in cavovarus foot by Lucas Furtado da Fonseca, Rodrigo Cortes Vicente, Leonardo Fernandez Maringolo

“…Methods: This narrative review outlines a stepwise strategy for the surgical correction of cavovarus foot, emphasizing the role of soft tissue releases, tendon transfers, osteotomies, and fusions. …”
Get full text