Intelligent Classification Method for Rail Defects in Magnetic Flux Leakage Testing Based on Feature Selection and Parameter Optimization by Kailun Ji, Ping Wang, Yinliang Jia

“…Three key innovations drive this research: (1) A dynamic PSO algorithm incorporating adaptive learning factors and nonlinear inertia weight for precise RBF parameter optimization; (2) A hierarchical feature processing strategy combining mutual information selection with correlation-based dimensionality reduction; (3) Adaptive model architecture adjustment for small-sample scenarios. …”
Get full text

Smart IoT Energy Optimisation and Localisation Monitoring for E-Bike Sharing by Mawada Mohamed, Siti Fauziah Toha, Md Ataur Rahman, Moh. Khairudin

“…However, existing systems face challenges such as limited input parameters for modeling, leading to inefficiencies in energy optimization algorithms and power assist mechanisms. …”
Get full text

Hybrid optimization of thermally-enhanced Zn-Fe LDH catalysts for fenton-like reactions: Integrating design of experiments with machine learning models for optimisation by Ramadhan Muhammad Naufal, Nawwal Hikmah, Dessy Ariyanti

“…This study presents a novel hybrid modeling framework that combines Response Surface Methodology (RSM) with machine learning (ML) algorithms– Support Vector Regression (SVR) and Gradient Boosting Regression (GBR)– to contribute to the predictive modeling and optimization of thermally-activated ZnFe-LDH based Fenton catalysis. …”
Get full text

Enhancing Global Optimization through the Integration of Multiverse Optimizer with Opposition-Based Learning by Vu Hong Son Pham, Nghiep Trinh Nguyen Dang, Van Nam Nguyen

“…The effectiveness of iMVO is assessed through a series of tests involving both classical and IEEE CEC 2021 benchmark functions, demonstrating competitive performance against established algorithms. Moreover, the applicability of iMVO to real-world challenges is validated through its successful deployment in civil engineering tasks, particularly in optimizing truss designs and managing time-cost tradeoffs. …”
Get full text

Green-fitting scheduling equilibrium model of virtual power plant based on cooperative game with improved shapley value under new-type power system by Shuo Zhang, Luming Pang, Yingzi Li, Yuanli Chen, Kangxiang Li, Meixia Zheng

“…To solve the model effectively, the improved particle swarm optimization algorithm has been employed. …”
Get full text

Balancing line hardening, distributed generation and de-energization for wildfire risk mitigation with microgrid formation by Mengqi Yao, Shunbo Lei, Weimin Wu, Duncan S. Callaway

“…The objective is to balance the desire to enhance system resilience while minimizing the system upgrade cost against wildfires. An adopted column-and-constraint generation algorithm is developed to solve the model and obtain the optimal decisions. …”
Get full text

Comprehensive Evaluation of Bankruptcy Prediction in Taiwanese Firms Using Multiple Machine Learning Models by Hung V. Pham, Tuan Chu, Tuan M. Le, Hieu M. Tran, Huong T.K. Tran, Khanh N. Yen, Son V. T. Dao

“…After selecting the best features, these were used to train the three ML algorithms, and hyper-parameter optimization was implemented to boost model performance. …”
Get full text

Advanced hybrid computational analysis of febuxostat solubility using machine learning in supercritical processing method by Turki Al Hagbani, Rami M. Alzhrani, Majed Ahmed Algarni

Get full text

An Underwater Localization Algorithm Based on the Internet of Vessels by Ziqi Wang, Ying Guo, Fei Li, Yuhang Chen, Jiyan Wei

“…The algorithm is composed of three stages: crowdsensing, denoising, and aggregation-based optimization. …”
Get full text

Analysis of Weak Links in the Mechanized Mining of Underground Metal Mines: Insights from Machine Learning and SHAP Explainability Models by Chengye Yang, Keping Zhou, Jielin Li

“…By leveraging data from 88 stopes at Guangxi Tongkeng Mine over a decade, we constructed a comprehensive dataset encompassing drilling, charging, blasting, ventilation, support, ore drawing, and maintenance. The XGBoost algorithm was employed to model factors influencing stope production capacity (PC), with its parameters optimized using the Marine Predator Algorithm (MPA). …”
Get full text

An intelligent algorithm for identifying dropped blocks in wellbores by Qian Wang, Zixuan Yang, Chenxi Ye, Wenbao Zhai, Xiao Feng

“…The XGBoost algorithm was then used to optimize the feature parameters and improve the classification model. …”
Get full text

Matching heterogeneous ontologies with adaptive evolutionary algorithm by Xingsi Xue, Haolin Wang, Xin Zhou, Guojun Mao, Hai Zhu

“…Ontology matching technique uses the similarity measure to determine the correspondences between two heterogeneous ontology entities. In order to improve the quality of ontology alignment, it is necessary to combine different kinds of similarity measures, and how to optimize the aggregating weights is called the ontology meta-matching problem. …”
Get full text

CRIMINALISTIC CHARACTERISTICS OF CRIMES RELATED TO ILLEGAL ACCESS TO COMPUTER INFORMATION by KHARISOVA Zarina Irekovna

Get full text

Optimization of Low-Loss, High-Birefringence, Single-Layer, Annular, Hollow, Anti-Resonant Fiber Using a Surrogate Model-Assisted Gradient Descent Method by Lihong Zhai, Sijie Zhang, Jiyang Luo, Gang Huang, Zihan Liu

“…This paper proposes a novel optimization method for hollow-core, anti-resonant fiber based on a gradient descent algorithm assisted via a radial basis-function surrogate model. …”
Get full text

A Novel Framework for Improving Soil Organic Carbon Mapping Accuracy by Mining Temporal Features of Time-Series Sentinel-1 Data by Zhibo Cui, Bifeng Hu, Songchao Chen, Nan Wang, Defang Luo, Jie Peng

“…The findings revealed the following: (1) The correlation between time-series S-1 data and SOC exhibited both interannual and monthly variations, with the optimal monitoring period from July to October. The data volume was reduced by 73.27% relative to the initial time-series dataset when the optimal monitoring period was determined. (2) Introducing time-series S-1 data into SOC mapping significantly improved CNN-LSTM model performance (R² = 0.80, RPD = 2.24, RMSE = 1.11 g kg⁻¹). …”
Get full text

RTRS algorithm in low-power Internet of things by Yuchen CHEN, Yuan CAO, Laipeng ZHANG, Lianghui DING, Feng YANG

“…Considering the feature of periodical uplink data transmission in IEEE 802.11ah low-power wide area network (LWPAN),a real-time RAW setting (RTRS) algorithm was proposed.Multiple node send data to an access point (AP),and the uplink channel resources were divided into Beacon periods in time.During a Beacon period,AP firstly predicted the next data uploading time and the total amount of devices that will upload data in the next Beacon period.The AP calculated the optimal RAW parameters for minimum energy cost and broadcasted the information to all node.Then all devices upload data according to the RAW scheduling.The simulation results show that the current network state can be predicted accurately according to the upload time of the terminal in the last period.According to the predicted state,raw configuration parameters can be dynamically adjusted and the energy efficiency can be significantly improved.…”
Get full text

RTRS algorithm in low-power Internet of things by Yuchen CHEN, Yuan CAO, Laipeng ZHANG, Lianghui DING, Feng YANG

“…Considering the feature of periodical uplink data transmission in IEEE 802.11ah low-power wide area network (LWPAN),a real-time RAW setting (RTRS) algorithm was proposed.Multiple node send data to an access point (AP),and the uplink channel resources were divided into Beacon periods in time.During a Beacon period,AP firstly predicted the next data uploading time and the total amount of devices that will upload data in the next Beacon period.The AP calculated the optimal RAW parameters for minimum energy cost and broadcasted the information to all node.Then all devices upload data according to the RAW scheduling.The simulation results show that the current network state can be predicted accurately according to the upload time of the terminal in the last period.According to the predicted state,raw configuration parameters can be dynamically adjusted and the energy efficiency can be significantly improved.…”
Get full text

Cooperative routing algorithm based on game theory by Kun XIE, Shen-lin DUAN, Ji-gang WEN, Shi-ming HE

“…VMIMO routing among groups was modeled as a repeated routing game. To improve the data delivery ratio, a fit function was proposed to evaluate the nodes' credit for participating in packet for-warding. …”
Get full text

Cooperative routing algorithm based on game theory by Kun XIE, Shen-lin DUAN, Ji-gang WEN, Shi-ming HE

“…VMIMO routing among groups was modeled as a repeated routing game. To improve the data delivery ratio, a fit function was proposed to evaluate the nodes' credit for participating in packet for-warding. …”
Get full text

An intelligent attention based deep convoluted learning (IADCL) model for smart healthcare security by J. Maruthupandi, S. Sivakumar, B. Lakshmi Dhevi, S. Prasanna, R. Karpaga Priya, Shitharth Selvarajan

Get full text