Node selection method in federated learning based on deep reinforcement learning by Wenchen HE, Shaoyong GUO, Xuesong QIU, Liandong CHEN, Suxiang ZHANG

“…To cope with the impact of different device computing capabilities and non-independent uniformly distributed data on federated learning performance, and to efficiently schedule terminal devices to complete model aggregation, a method of node selection based on deep reinforcement learning was proposed.It considered training quality and efficiency of heterogeneous terminal devices, and filtrate malicious nodes to guarantee higher model accuracy and shorter training delay of federated learning.Firstly, according to characteristics of model distributed training in federated learning, a node selection system model based on deep reinforcement learning was constructed.Secondly, considering such factors as device training delay, model transmission delay and accuracy, an optimization model of accuracy for node selection was proposed.Finally, the problem model was constructed as a Markov decision process and a node selection algorithm based on distributed proximal strategy optimization was designed to obtain a reasonable set of devices before each training iteration to complete model aggregation.Simulation results demonstrate that the proposed method significantly improves the accuracy and training speed of federated learning, and its convergence and robustness are also well.…”
Get full text

Adaptive Temporal Reinforcement Learning for Mapping Complex Maritime Environmental State Spaces in Autonomous Ship Navigation by Ruolan Zhang, Xinyu Qin, Mingyang Pan, Shaoxi Li, Helong Shen

“…The model integrates an enhanced Proximal Policy Optimization (PPO) algorithm for efficient policy iteration optimization. …”
Get full text

Enhancing phase change thermal energy storage material properties prediction with digital technologies by Minghao Yu, Jing Liu, Cheng Chen, Mingyue Li

“…To address these limitations, the integration of digital technologies, such as computational modeling and machine learning (ML), has become increasingly important.MethodsThis paper proposes a hybrid multiscale modeling framework that integrates molecular dynamics (MD) simulations, finite element methods (FEM) from continuum mechanics, and supervised ML algorithms—including deep neural networks and gradient boosting regressors—to enable accurate and efficient prediction of material properties across scales. …”
Get full text

A Novel Local Binary Patterns-Based Approach and Proposed CNN Model to Diagnose Breast Cancer by Analyzing Histopathology Images by Mehmet Gul

“…The histopathology images improved with the QS-LBP method were then analyzed with the most commonly used Random Forest and Optimized Forest algorithms among machine learning algorithms. …”
Get full text

Multi-Skilled Project Scheduling for High-End Equipment Development Considering Newcomer Cultivation and Duration Uncertainty by Yaohui Liu, Ronggui Ding, Shanshan Liu, Lei Wang

“…Therefore, we put forward an adaptive simulation–optimization approach featuring two-fold: a simulation module capable of dynamically adjusting sample sizes based on convergence feedback and evaluating solutions with improved efficiency and stable accuracy; a tailored non-dominated sorting genetic algorithm II (NSGA-II) with adaptive evolutionary operators that enhance search effectiveness and ensure the identification of a well-distributed Pareto front. …”
Get full text

Development of a Weighted Average Ensemble Model for Predicting Officially Assessed Land Prices Using Grid Map Data and SHAP by Surin Im, Kangmin Kim, Geunhee Lee, Hoi-Jeong Lim

“…The model analyzes the impact of key variables through SHAP for improved interpretability. …”
Get full text

Development and validation of a machine learning-based risk prediction model for stroke-associated pneumonia in older adult hemorrhagic stroke by Yi Cao, Yi Cao, Haipeng Deng, Shaoyun Liu, Xi Zeng, Yangyang Gou, Weiting Zhang, Yixinyuan Li, Hua Yang, Min Peng

“…The results indicated that among the four machine learning algorithms (XGBoost, LR, SVM, and Naive Bayes), the LR model demonstrated the best and most stable predictive performance. …”
Get full text

A variable threshold ring signature scheme for privacy protection in smart city blockchain applications by Guo Hongzhi, Qin Haowen

“…We further introduce an optimized batch-verification algorithm that cuts the number of expensive pairing checks per signature from O(n) to $$O(1) + n$$ O ( 1 ) + n , dramatically improving throughput. …”
Get full text

Three-Dimensional Shape Reconstruction from Digital Freehand Design Sketching Based on Deep Learning Techniques by Ding Zhou, Guohua Wei, Xiaojun Yuan

Get full text

Enhancing Aerosol Vertical Distribution Retrieval With Combined LSTM and Transformer Model From OCO-2 O2 A-Band Observations by YuXuan Wang, RuFang Ti, ZhenHai Liu, Xiao Liu, HaiXiao Yu, YiChen Wei, YiZhe Fan, YuYao Wang, HongLian Huang, XiaoBing Sun

“…Furthermore, a physics-based, information-driven band selection method was developed to simplify input data and reduce complexity. To enhance the algorithm's applicability, the model was applied across the entire African continent and adjacent water bodies. …”
Get full text

PolSAR Forest Height Estimation Enhancement With Polarimetric Rotation Domain Features and Multivariate Sensitivity Analysis by Fu-Gen Jiang, Ming-Dian Li, Si-Wei Chen

“…Then, we propose a Bayesian-optimized ensemble learning algorithm to improve the accuracy of forest height estimation. …”
Get full text

Advanced clustering and transfer learning based approach for rice leaf disease segmentation and classification by Samia Nawaz Yousafzai, Fahd N. Al-Wesabi, Hadeel Alsolai, Shouki A. Ebad, Inzamam Mashood Nasir, Emad Fadhal, Adel Thaljaoui

“…Also, the tent chaotic particle snow ablation optimizer is added into the learning process in order to improve the learning process and shorten the time of convergence. …”
Get full text

Research on Fault Diagnosis of Traction Power Supply System Based on PSO-LSSVM by Lei ZHANG

“…According to the working principle and characteristics of the train power supply system, the relationship between the fault phenomenon and the origin was analyzed, and the characteristic signals used for fault diagnosis were extracted. A fault diagnosis model based on PSO optimized least squares support vector machine was established, and PCA algorithm was used to extract data characteristics as input of fault diagnosis model, and reduce input dimension. …”
Get full text

Adaptive Quantum-Inspired Evolution for Denoising PCG Signals in Unseen Noise Conditions by Lubna Siddiqui, Ashish Mani, Jaspal Singh

“…The filter coefficients were optimised using the proposed QiEA with Adaptive Rotation Gate Operator (ARGO). The proposed algorithm accelerates convergence towards optimal solutions based on fitness feedback, improving filter optimisation while clamping rotation angles to maintain algorithm stability. …”
Get full text

Large Language Model–Assisted Risk-of-Bias Assessment in Randomized Controlled Trials Using the Revised Risk-of-Bias Tool: Usability Study by Jiajie Huang, Honghao Lai, Weilong Zhao, Danni Xia, Chunyang Bai, Mingyao Sun, Jianing Liu, Jiayi Liu, Bei Pan, Jinhui Tian, Long Ge

“…When domain judgments were derived from LLM-generated signaling questions using the RoB2 algorithm rather than direct LLM domain judgments, accuracy improved substantially for Domain 2 (adhering; 55-95) and overall (adhering; 70-90). …”
Get full text

Satellite-Derived Bathymetry Combined With Sentinel-2 and ICESat-2 Datasets Using Deep Learning by Weidong Zhu, Yanying Huang, Tiantian Cao, Xiaoshan Zhang, Qidi Xie, Kuifeng Luan, Wei Shen, Ziya Zou

“…The model employs BOA to optimize the key hyperparameters of the CNN-BILSTM architecture, thereby improving inversion performance. …”
Get full text

Research on Key Technologies of Virtual Coupling Control System for Autonomous-rail Rapid Tram by HUANG Qiang, YUAN Xiwen, HU Yunqing, LI Cheng, HUANG Ruipeng, TANG Xiang

“…A safe braking model of autonomous-rail rapid tram is initiatively used to derive the minimum space headway for operation safety between coupled formations, and the collaborative planning and MPC-based collaborative control algorithms utilizing an optimal control approach are applied to guarantee the safe, punctual, comfortable, and efficient operation of coupled formations. …”
Get full text

Development and validation of an interpretable multi-task model to predict outcomes in patients with rhabdomyolysis: a multicenter retrospective cohort studyResearch in context by Chunli Liu, Jie Shi, Fengjuan Wang, Duo Li, Yu Luo, Bofan Yang, Yunlong Zhao, Li Zhang, Dingwei Yang, Heng Jin, Jie Song, Xiaoqin Guo, Haojun Fan, Qi Lv

“…Twenty-two clinical features available within the first 24 h of admission were selected to develop the prediction models. Ten machine learning (ML) algorithms were applied to construct multi-task prediction models. …”
Get full text

Detecting Anomalies in Hydraulically Adjusted Servomotors Based on a Multi-Scale One-Dimensional Residual Neural Network and GA-SVDD by Xukang Yang, Anqi Jiang, Wanlu Jiang, Yonghui Zhao, Enyu Tang, Zhiqian Qi

“…This model uses a multi-scale one-dimensional residual neural network (M1D_ResNet) for feature extraction and a genetic algorithm (GA)-optimized support vector data description (SVDD). …”
Get full text

Machine Learning in the National Economy by Azamjon A. Usmonov

“…Methods of cleaning, normalization, and data transformation were used for data processing to improve model accuracy. The practical part of the study included the development of machine learning algorithms for predicting economic indexes. …”
Get full text