Large-scale post-disaster user distributed coverage optimization based on multi-agent reinforcement learning by Wenjun XU, Silei WU, Fengyu WANG, Lan LIN, Guojun LI, Zhi ZHANG

“…In order to quickly restore emergency communication services for large-scale post-disaster users, a distributed intellicise coverage optimization architecture based on multi-agent reinforcement learning (RL) was proposed, which could address the significant differences and dynamics of communication services caused by a large number of access users, and the difficulty of expansion caused by centralized algorithms.Specifically, a distributed k-sums clustering algorithm considering service differences of users was designed in the network characterization layer, which could make each unmanned aerial vehicle base station (UAV-BS) adjust the local networking natively and simply, and obtain states of cluster center for multi-agent RL.In the trajectory control layer, multi-agent soft actor critic (MASAC) with distributed-training-distributed-execution structure was designed for UAV-BS to control trajectory as intelligent nodes.Furthermore, ensemble learning and curriculum learning were integrated to improve the stability and convergence speed of training process.The simulation results show that the proposed distributed k-sums algorithm is superior to the k-means in terms of average load efficiency and clustering balance, and MASAC based trajectory control algorithm can effectively reduce communication interruptions and improve the spectrum efficiency, which outperforms the existing RL algorithms.…”
Get full text

Predicting future morphological changes of lesions from radiotracer uptake in 18F-FDG-PET images. by Ulas Bagci, Jianhua Yao, Kirsten Miller-Jaster, Xinjian Chen, Daniel J Mollura

“…Evaluation of segmentation results indicates that our proposed segmentation algorithm has a mean dice similarity coefficient of 85.75 ± 1.75%. …”
Get full text

CSDK: A Chi-square distribution-Kernel method for image de-noising under the Internet of things big data environment by Lin Teng, Hang Li

“…It also shows a consistent accuracy, edge preservation, and detailed retention improvement compared to the classic de-noising algorithms.…”
Get full text

Research on axial compensation precision puncture control method of prostate puncture robot by Li Bing, Zhu Junwu, Yuan Lipeng

“…Then, an improved adaptive particle swarm optimization (PSO) algorithm based on Levy Flight is proposed to identify parameters of this control model for puncture prostate in this article. …”
Get full text

SART-Type Image Reconstruction from Overlapped Projections by Hengyong Yu, Changguo Ji, Ge Wang

“…Inspired by the single-source simultaneous algebraic reconstruction technique (SART), we hereby develop a multisource SART-type reconstruction algorithm regularized by a sparsity-oriented constraint in the soft-threshold filtering framework to reconstruct images from overlapped projections. …”
Get full text

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

“…Decisions were made solely based on these limited observations. The soft actor-critic (SAC) algorithm was used to control transmission power, with an appropriate reward function and action clipping method. …”
Get full text

Advancing Dynamic Emergency Route Optimization with a Composite Network Deep Reinforcement Learning Model by Jin Zhang, Hao Xu, Ding Liu, Qi Yu

“…This method utilizes the actor–critic framework, combined with attention mechanisms, pointer networks, and long short-term memory neural networks, to determine effective disaster relief path, and it compares the obtained scheduling scheme with the results obtained from the DRL algorithm based on the single-network model and ant colony optimization (ACO) algorithm. …”
Get full text

Large-scale post-disaster user distributed coverage optimization based on multi-agent reinforcement learning by Wenjun XU, Silei WU, Fengyu WANG, Lan LIN, Guojun LI, Zhi ZHANG

“…In order to quickly restore emergency communication services for large-scale post-disaster users, a distributed intellicise coverage optimization architecture based on multi-agent reinforcement learning (RL) was proposed, which could address the significant differences and dynamics of communication services caused by a large number of access users, and the difficulty of expansion caused by centralized algorithms.Specifically, a distributed k-sums clustering algorithm considering service differences of users was designed in the network characterization layer, which could make each unmanned aerial vehicle base station (UAV-BS) adjust the local networking natively and simply, and obtain states of cluster center for multi-agent RL.In the trajectory control layer, multi-agent soft actor critic (MASAC) with distributed-training-distributed-execution structure was designed for UAV-BS to control trajectory as intelligent nodes.Furthermore, ensemble learning and curriculum learning were integrated to improve the stability and convergence speed of training process.The simulation results show that the proposed distributed k-sums algorithm is superior to the k-means in terms of average load efficiency and clustering balance, and MASAC based trajectory control algorithm can effectively reduce communication interruptions and improve the spectrum efficiency, which outperforms the existing RL algorithms.…”
Get full text

Bearing Fault Prediction Based on Mixed Domain Features and GWO-SVM by Xuan Zhou, Ruiyang Xia, Zhaodong Zhang, Sasa Duan, Mao Cheng, Chengjiang Zhou, Min Mao

“…First, the wavelet soft threshold is used to remove the noise of the original signal and then the empirical Fourier decomposition (EFD) is used in the decomposition and reconstruct signals. …”
Get full text

A Three-Stage-Concatenated Non-Linear MMSE Interference Rejection Combining Aided MIMO-OFDM Receiver and its EXIT-Chart Analysis by Jue Chen, Siyao Lu, Tsang-Yi Wang, Jwo-Yuh Wu, Chih-Peng Li, Soon Xin Ng, Robert G. Maunder, Lajos Hanzo

“…It also generates the soft information, enabling turbo equalization, wherein iterative detector and decoder iteratively exchange their soft information. …”
Get full text

LncRNAs regulates cell death in osteosarcoma by Ping’an Zou, Zhiwei Tao, Zhengxu Yang, Tao Xiong, Zhi Deng, Qincan Chen, Li Niu

Get full text

Gridless DOA Estimation with Extended Array Aperture in Automotive Radar Applications by Pengyu Jiang, Silin Gao, Jie Zhao, Zhe Zhang, Bingchen Zhang

“…Simulation results show that our proposed algorithm significantly improves reconstruction accuracy compared to the iterative soft threshold (IST) algorithm while maintaining the same computational complexity. …”
Get full text

Study on Predicting Blueberry Hardness from Images for Adjusting Mechanical Gripper Force by Hao Yin, Wenxin Li, Han Wang, Yuhuan Li, Jiang Liu, Baogang Li

“…Blueberries, with their soft texture and delicate skin, present significant challenges for achieving precise and non-damaging mechanical harvesting. …”
Get full text

Evaluation method of hydrophobicity of composite insulators based on improved Mask R-CNN by SHENG Fei, CAO Liu, LIU Yulong, HUANG Jie, HUANG Yaqian, ZHU Yanqing

“…In this paper, the classification problem is transformed into the target detection problem, and the improved mask region-based convolutional neural network (Mask R-CNN) algorithm is used to evaluate the hydrophobicity level of composite insulators. …”
Get full text

Fault detection in beam structure using adaptive immune based approach by Sasmita Sahu, Shakti P. Jena

“…Later one such method has been developed in the concepts of adaptive immune based technique (Adaptive Clonal Section Algorithm-ACSA) which is the combination of an artificial immune (Clonal Selection Algorithm) and Regression Analysis (RA). …”
Get full text

An enhanced genetic-based multi-objective mathematical model for industrial supply chain network. by Yanchun Li

“…Therefore, in the emerging industrial supply chain network, a model for the multi-objective problem was made using a meta-heuristic approach, specifically the improved genetic algorithm, which is a type of soft computing. To create the initial population, a hybrid approach that combines topology theory and the random search method was adopted, which resulted in a modification of the conventional single roulette wheel selection procedure. …”
Get full text

Geodata Processing Methodology on GIS Platforms When Creating Spatial Development Plans of Territorial Communities: Case of Ukraine by Olena Kopishynska, Yurii Utkin, Ihor Sliusar, Leonid Flehantov, Mykola Somych, Oksana Yakovlieva, Olena Scryl

“…The study selects the Cadastr.UA system on the Soft.Farm platform, developed by Ukrainian company Quart Soft, as a notably user-friendly and promising GIS for land accounting and auditing. …”
Get full text

Enhanced Mobile Multiple-Input Multiple-Output Underwater Acoustic Communications by Kexin Zhao, Jun Ling, Jian Li

“…In particular, this paper reviews the linear minimum mean-squared error (LMMSE) based soft-input soft-output equalizer involved in the turbo equalization scheme and adopts a fast implementation of the equalizer that achieves negligible detection performance degradation compared to its direct implementation counterpart. …”
Get full text

Experience of using internal fixation in the treatment of patients with inflammatory complications of mandibular fractures: a retrospective study by Alexander S. Pankratov, Zauri P. Gotsiridze, Mariya A. Karalkina

“…Group B consisted of patients who had no suppurative process in soft tissues, which allowed them undergoing one-stage surgical treatment. …”
Get full text

Targets Spatial Coordinates Calculation in Angle-Difference Rangefinder Passive Location Complexes by Numerical Iterative Methods by A. A. Dmitrenko, S. Y. Sedyshev

Get full text