Short-term results of treatment of non-epithelial gastro-intestinal tumors complicated by bleeding by S. G. Shapovalyants, A. I. Mikhalev, Ye. D. Fedorov, R. V. Plakhov, L. M. Mikhaleva, Z. V. Galkova, Ye. V. Ivanova, A. E. Sergeyenko

“…According to suggested diagnostic algorithm detailed characteristic of patients with bleeding tumor was given, the optimal method of surgical intervention was chosen. …”
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

Detection Model for Cotton Picker Fire Recognition Based on Lightweight Improved YOLOv11 by Zhai Shi, Fangwei Wu, Changjie Han, Dongdong Song, Yi Wu

“…The improved detection algorithm maintains high accuracy while achieving faster inference speed and fewer model parameters. …”
Get full text

OR-FCOS: an enhanced fully convolutional one-stage approach for growth stage identification of Oudemansiella raphanipes by Runze Fang, Huamao Huang, Nuoyan Guo, Haichuan Wei, Shiyi Wang, Haiying Hu, Ming Liu

“…Channel pruning further reduces the decoder’s parameters, decreasing model size and computational requirements while maintaining precision. The enhanced algorithm achieved a mean average precision (mAP) of 89.4% ( $$\hbox {mAP}_{50}$$ ) and 78.3% ( $$\hbox {mAP}_{50:95}$$ ), while the number of model parameters was reduced to 9.9 M, the model size was reduced to 40.1 MB, and the number of floating point operations per second (FLOPs) was reduced to 31.2 G. …”
Get full text

New Heuristic Local Search Method for University Course Timetabling by Mohammad Sadegh Shiri, Mostafa Khorramizadeh, Vahid Ahmadi

“…In the second phase, several new neighbourhood functions are used to improve the quality of computed feasible solutions. While the fitness function of the first phase is based on the violation of hard constraints, the fitness function of the second phase is based on the penalty of the feasible solution.Findings: The numerical results indicate that the required computing time increases with the size of instances, and the algorithm tends to converge towards the optimal solution after a few minutes.Originality/Value: The presented algorithm enables us to deal with extensive university course timetabling problems in practice. …”
Get full text

Rail surface identification and adhesion control based on dynamic adhesion characteristics by Wen Liu, Hongfeng Qi, Jingchun Huang, Yiyuan Chen, Sheng He, Haoxiang Feng

“…Therefore, to achieve stable tracking of the optimal adhesion state while adopting the feedback dynamic adhesion characteristic model, this study utilizes a machine learning algorithm to perform classification training on discrete points of the simulated adhesion characteristic model under various rail conditions. …”
Get full text

PP-QADMM: A Dual-Driven Perturbation and Quantized ADMM for Privacy Preserving and Communication-Efficient Federated Learning by Anis Elgabli

“…We provide a rigorous theoretical proof of convergence, showing that PP-QADMM converges to the optimal solution for convex problems while achieving a convergence rate comparable to standard ADMM, but with significantly lower communication and energy costs, and robust privacy protection. …”
Get full text

NLP-Driven Analysis of Pneumothorax Incidence Following Central Venous Catheter Procedures: A Data-Driven Re-Evaluation of Routine Imaging in Value-Based Medicine by Martin Breitwieser, Vanessa Moore, Teresa Wiesner, Florian Wichlas, Christian Deininger

“…<b>Methods:</b> We analyzed electronic health records from four university hospitals in Salzburg, Austria, focusing on X-rays performed between 2012 and 2021 following CVC procedures. A custom-built NLP algorithm identified cases of pneumothorax from radiologists’ reports and clinician requests, while excluding cases with contraindications such as chest injuries, prior pneumothorax, or missing data. …”
Get full text

Improved RT-DETR Framework for Railway Obstacle Detection by Peng Li, Yanhui Peng, Su-Mei Wang, Cheng Zhong

“…Building upon the RT-DETR framework, this study proposes a Multiscale Separable Deformable (MSD) module that integrates depthwise convolution with deformable convolution to enhance feature extraction capabilities while reducing computational load. Additionally, a Deformable Agent Attention (DAA) mechanism is designed to optimize attention weights through sparse queries, effectively improving detection accuracy for small targets and enhancing inference speed in complex scenarios. …”
Get full text

Research on Credit Risk Prevention in Supply Chain Finance Driven by Blockchain by Lin Kejing

“…Distributed ledger technology is utilized through blockchain to ensure the transparency and traceability of information, while smart contracts optimize the credit execution and supervision process, playing a key role in preventing and controlling credit risks. …”
Get full text

A Collaborative Transit Signal Priority Method Considering Gaming among Traffic Participants by Bing Wu, Haishan Wang, Yanli Wang, Ben Zhai, TanXing Xue

“…Different from previous studies, Co-TSP uses game theory to realize collaborative optimization, instead of transforming the problem into a single objective optimization problem by weighting. …”
Get full text

Efficient Context-Preserving Encoding and Decoding of Compositional Structures Using Sparse Binary Representations by Roman Malits, Avi Mendelson

“…In addition, the proposed algorithms allow to optimize the amount of compute and memory needed to achieve the desired encoding/decoding performance.…”
Get full text

User preference–based QoS-aware service function placement in IoT-Edge cloud by Briytone Mutichiro, Younghan Kim

“…The proposed solutions are evaluated based on different metrics and the obtained results show the gap between the heuristic user preference placement algorithm and the optimal solution to be minimal.…”
Get full text

An improved lightweight method based on EfficientNet for birdsong recognition by Haolun He, Hui Luo

“…Finally, we employ the Adam optimization algorithm to improve network convergence speed. …”
Get full text

Analytical Designing of Optimum Controller for Linear-Quadratic Functional with the Given Limiting Restrictions by V. I. Timoshpolskii, V. B. Kovalevskii, G. Romadan, P. V. Ilyusenko

“…This methodology may be used in resource saving technologies while soaking metal in the furnace. The paper reveals new methods of optimization that do not have analogues.…”
Get full text

Investigating the Machining Behavior of the Additively Manufactured Polymer-Based Composite Using Adaptive Neuro-Fuzzy Learning by Anastasios Tzotzis, Dumitru Nedelcu, Simona-Nicoleta Mazurchevici, Panagiotis Kyratsis

“…Multi-objective optimization using the Non-Dominated Sorting Genetic Algorithm 2 (NSGA-II) algorithm was employed to minimize both <i>Ra</i> and <i>T</i> simultaneously. …”
Get full text

Rate of penetration prediction in drilling operations: a comparative study of AI models and meta-heuristic approaches by Fatemeh Mohammadinia, Ali Ranjbar, Fatemeh Ghazi, Seyyed Taha Hosseini

“…To further enhance model performance, metaheuristic optimization strategies such as the Crow Search Algorithm (CSA), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) are integrated. …”
Get full text

Rolling Bearing Fault Diagnosis Based on Adaptive Multiparameter-Adjusting Bistable Stochastic Resonance by Z. H. Lai, S. B. Wang, G. Q. Zhang, C. L. Zhang, J. W. Zhang

“…Furthermore, the influence of algorithm parameters on the optimization results is discussed, and the optimization results of the Langevin system and the Duffing system are compared. …”
Get full text

Iterative approach for photonic crystal devices design by Pavel V. Mokshin, Dimitriy L. Golovashkin, Vladimir S. Pavelyev

“…The proposed approach differs from known general-purpose optimization methods (e.g., genetic algorithm or gradient procedures) by using diffraction pattern information at different frequencies while optimizing an element designed to operate at the selected wavelength. …”
Get full text

A Knowledge-Driven Smart System Based on Reinforcement Learning for Pork Supply-Demand Regulation by Haohao Song, Jiquan Wang

“…By harnessing dynamic decision-making capabilities of reinforcement learning (RL), we design an optimization architecture centered on the Q-learning mechanism and dual-strategy pools, which is integrated into the honey badger algorithm to form the RL-enhanced honey badger algorithm (RLEHBA). …”
Get full text