Detection method of small size defects on pipeline weld surface based on improved YOLOv7. by Xiangqian Xu, Wenting Hou, Xing Li

“…The experimental results show that the defect detection mAP@0.5 based on the improved YOLOv7 algorithm can reach 72.2%, which is 11% higher than that of YOLOv7, and the model calculation amount and parameter amount are reduced by 75.6% and 60.3%, respectively. …”
Get full text

Research on optimization of vector control of an asynchronous motor using the analytical control system by A. N. Tsvetkov, Ngok Shi Doan, D. A. Yaroslavsky

“…The control algorithm based on determining the optimal value of the magnetic flux in the coordinates of the d - q axis to achieve low power losses, taking into account losses in the iron core and low magnetic saturations, helps to improve the efficiency of inverter control.RESULTS. …”
Get full text

Adaptive resource optimization mechanism for blockchain sharding in digital twin edge network by Li JIANG, Shengli XIE, Hui TIAN

“…To address the security and privacy issues for data sharing in digital twin edge networks, a new distributed and secure data sharing mechanism was developed by leveraging blockchain sharding.Considering dynamic and time varying features in digital twin edge networks and mapping errors of physic networks, an adaptive resource allocation model was formulated which jointly optimized cluster head selection, local base station (BS) consensus access selection, spectrum and computation consensus resources allocation, in order to maximize transactional throughput for the blockchain sharding.Moreover, a digital twin edge networks empowered two-layered proximal policy optimization (PPO) algorithm was designed to obtain the optimal solutions.Numerical results illustrate that the proposed algorithm can effectively improve the transactional throughput for the blockchain sharding.Meanwhile, it can well adapt to the mapping errors.…”
Get full text

Optimizing Fairness and Spectral Efficiency With Shapley-Based User Prioritization in Semantic Communication by Moirangthem Tiken Singh, Adnan Arif, Rabinder Kumar Prasad, Bikramjit Choudhury, Chandan Kalita, Sikdar Md. S. Askari

“…The Shapley-based approach outperforms established methods, including the Hungarian algorithm, reinforcement learning algorithms like Deep Q-Network (DQN) and Proximal Policy Optimization (PPO), as well as conventional 4G and 5G resource allocation strategies. …”
Get full text

Disturbance Observer-Based Optimal Active Suspension Control for Vehicle-Trailer Systems by Yonghwan Jeong

Get full text

A hybrid Bayesian network-based deep learning approach combining climatic and reliability factors to forecast electric vehicle charging capacity by David Chunhu Li

“…This architecture uses extensive transaction data and climate analysis to build a detailed model of EV charging pile reliability. Additionally, two algorithms are designed to assess the usage and reliability of charging stations. …”
Get full text

Improving meningitis surveillance and diagnosis with machine learning: Insights from São Paulo. by Audêncio Victor, Diego Augusto Medeiros Santos, Eduardo Koerich Nery, Danilo Pereira Mori, Pamella Cristina de Carvalho Lucas, Denise Cammarota, Guillermo Leonardo Florez Montero, Fabiano Novaes Barcellos Filho, Ana Lúcia Frugis Yu, Telma Regina Marques Pinto Carvalhanas

“…These techniques can be integrated into public health protocols to improve meningitis outbreak responses and optimize patient treatment.…”
Get full text

Point Data Registration With the Multi-Object, Cardinalized Optimal Linear Assignment Metric by Pablo A. Barrios, Vicente Guzman, Martin D. Adams, Claudio A. Perez

“…The Iterative Closest Point (ICP) algorithm and its variants were initially used to solve such problems and since then, various global methods have been proposed to improve registration when data outliers exist. …”
Get full text

Optimal relay selection for full duplex SWIPT-NOMA systems with maximal throughput by Taoshen LI, Anni SHI, Zhe WANG, Lu HE

“…To improve the performance of 5G communication system, a full duplex Internet of things (IoT) relay system model was built by introducing the non-orthogonal multi-access (NOMA) technology.For the relay system of simultaneous wireless information and power transfer (SWIPT), it was considered that the relay node can harvest the energy of the source node, the self-interference signal of the loop channel and the free energy access point (EAP), and NOMA technology was used to forward the source node signal and its own signal to different destination nodes.Based on the model, a power distribution collaboration SWIPT relay selection strategy was proposed to optimize system throughput.Firstly, the problem model was established based on the constraints of communication quality of service and transmission power of source nodes.And then, the original nonlinear 0-1 programming problem was converted into a pair of coupling optimization problem by mathematical transformation, and the optimal relay selection of outer optimization problem was solved based on the optimal solution of the internal optimization problem.Finally, an optimal relay selection algorithm was used to maximize system throughput.Simulation results show that the proposed model and strategy are superior to the traditional maximum-minimum relay selection schemes in terms of throughput gain, and the consideration of EAP can significantly improve the interrupt performance.…”
Get full text

Optimal relay selection for full duplex SWIPT-NOMA systems with maximal throughput by Taoshen LI, Anni SHI, Zhe WANG, Lu HE

“…To improve the performance of 5G communication system, a full duplex Internet of things (IoT) relay system model was built by introducing the non-orthogonal multi-access (NOMA) technology.For the relay system of simultaneous wireless information and power transfer (SWIPT), it was considered that the relay node can harvest the energy of the source node, the self-interference signal of the loop channel and the free energy access point (EAP), and NOMA technology was used to forward the source node signal and its own signal to different destination nodes.Based on the model, a power distribution collaboration SWIPT relay selection strategy was proposed to optimize system throughput.Firstly, the problem model was established based on the constraints of communication quality of service and transmission power of source nodes.And then, the original nonlinear 0-1 programming problem was converted into a pair of coupling optimization problem by mathematical transformation, and the optimal relay selection of outer optimization problem was solved based on the optimal solution of the internal optimization problem.Finally, an optimal relay selection algorithm was used to maximize system throughput.Simulation results show that the proposed model and strategy are superior to the traditional maximum-minimum relay selection schemes in terms of throughput gain, and the consideration of EAP can significantly improve the interrupt performance.…”
Get full text

Stowage Plan Based Slot Optimal Allocation in Rail-Water Container Terminal by Yanjing Li, Xiaoning Zhu, Li Wang, Xi Chen

“…To obtain an efficient and reasonable solution for slot allocation in rail-water container terminals, this paper develops storage optimal allocation model 1 to improve the yard space utilization, which is solved by a heuristic algorithm based on Tabu search. …”
Get full text

Hybrid Optimization Machine Learning Framework for Enhancing Trust and Security in Cloud Network by Himani Saini, Gopal Singh, Amrinder Kaur, Sunil Saini, Niyaz Ahmad Wani, Vikram Chopra, Zahid Akhtar, Shahid Ahmad Bhat

“…To strengthen trust evaluation, the framework combines an optimized Levenberg algorithm with the Firefly Algorithm. …”
Get full text

Simulation Analysis of RES System Optimization Strategy of Range-extended Electric Vehicle by Xing Zhongyi

“…Based on the working modes of the transmission system of range-extended electric vehicle,the map of internal combustion engine and battery system characters are obtained through calculation,the main components of transmission are set up in Matlab on the basis of dynamics equation,and the model is analyzed,the genetic algorithm is combined into control strategy in order to optimize the start-close area of range extended system.The simulation results show that the optimized strategy can not only improve the fluctuation range of SOC,but also improve the fuel consumption of transmission system.…”
Get full text

Design optimization of university ideological and political education system based on deep learning by Shangle Ai, Huanhuan Ding

“…Firstly, this paper introduces the research methods in detail, including deep learning algorithm and model design, as well as the optimization design process of IPE system. …”
Get full text

Optimal sensor placement of bridge structure based on sensitivity‐effective independence method by Wenhao Chai, Yaxun Yang, Haibo Yu, Fuli Yang, Zhikui Yang

“…Abstract Taking the optimal sensor placement problem in bridge structural health monitoring as the study object and relying on the engineering example of a simply supported steel truss bridge, the improved optimal sensor placement method based on sensitivity‐effective independence method was proposed. …”
Get full text

Random Forest-Based Prediction of the Optimal Solid Ink Density in Offset Lithography by Laihu Peng, Hao Fan, Yubao Qi, Jianqiang Li

“…To improve the efficiency of determining the optimal solid ink density, the Random Forest algorithm was applied for the first time to the prediction task of solid ink density in offset printing. …”
Get full text

Improved Motion Correction in Dynamic Contrast-Enhanced MRI Using Low Rank With Soft Weighting by Jichang Zhang, Faisal Najeeb, Yulin Wang, Xinpei Wang, Pengfei Xu, Hammad Omer, Jianjun Zheng, Jingfeng Zhang, Sue Francis, Paul Glover, Richard Bowtell, Thomas Meersmann, Chengbo Wang

Get full text

An AI-based automatic leukemia classification system utilizing dimensional Archimedes optimization by Warda M. Shaban

“…The proposed method is called the Dimensional Archimedes Optimization Algorithm (DAOA). DAOA is based on the Archimedes Optimization Algorithm (AOA) and Dimensional Learning Strategy (DLS). …”
Get full text

Schur Complement Optimized Iterative EKF for Visual–Inertial Odometry in Autonomous Vehicles by Guo Ma, Cong Li, Hui Jing, Bing Kuang, Ming Li, Xiang Wang, Guangyu Jia

Get full text

Accuracy–Efficiency Trade-Off: Optimizing YOLOv8 for Structural Crack Detection by Jiahui Zhang, Zoia Vladimirovna Beliaeva, Yue Huang

“…To address the accuracy–efficiency trade-off faced by deep learning models in structural crack detection, this paper proposes an optimized version of the YOLOv8 model. …”
Get full text