Robust Cross-Validation of Predictive Models Used in Credit Default Risk by Jose Vicente Alonso, Lorenzo Escot

“…Model validation is a challenging Machine Learning task, usually more difficult for consumer credit default models because of the availability of small datasets, the modeling of low-frequency events (imbalanced data), and the bias in the explanatory variables induced by the train/test sets split of the validation techniques (covariate shift). While many methodologies have been developed, cross-validation is perhaps the most widely accepted, often being part of the model development process by optimizing the hyperparameters of predictive algorithms. …”
Get full text

Emergent behaviors in multiagent pursuit evasion games within a bounded 2D grid world by Sihan Xu, Zhaohui Dang

“…After training with MARL algorithms, pursuers achieved a 99.9% success rate in 1,000 randomized pursuit-evasion trials, demonstrating the effectiveness of the learned strategies. …”
Get full text

Efficient topology control for time-varying spacecraft networks with unreliable links by Wei Zhang, Hong Ma, Tao Wu, Xueshu Shi, Yiwen Jiao

“…We prove that such an optimization problem is NP-hard. Then, we provide five heuristic algorithms, which can significantly maintain low topology cost efficiency ratio while achieving high reliable connectivity. …”
Get full text

Enhancing network slice security with Deep Reinforcement Learning and Moving Target Defense strategies by Andreas Andreou, Constandinos X. Mavromoustakis, Evangelos Markakis, Athina Bourdena, George Mastorakis

“…By modelling the problem as a Markov Decision Process (MDP), the proposed framework leverages advanced DRL algorithms to learn optimal policies for deploying MTD mechanisms across network slices by continuously adapting defences to counter evolving cyber threats. …”
Get full text

A practical study of artificial intelligence-based real-time feedback in online physical education teaching by Jiewei Ma, Lianzhen Ma, Shilong Qi, Bo Zhang, Wenpian Ruan

“…Future research should focus on optimizing algorithms and integrating adaptive learning to create more effective OLPE strategies.…”
Get full text

Quantum Edge Detection and Convolution Using Paired Transform-Based Image Representation by Artyom Grigoryan, Alexis Gomez, Sos Agaian, Karen Panetta

“…We demonstrate that our approach achieves improved processing speed compared to classical methods while maintaining comparable accuracy. The successful implementation of real-world images highlights the potential of this research for large-scale quantum image processing, architecture-specific optimizations, and applications beyond edge detection.…”
Get full text

Tomographic SAR imaging via generative adversarial neural network with cascaded U‐Net architecture by Jie Li, Kun Wang, Zhiyuan Li, Bingchen Zhang, Yirong Wu

“…It can be regarded as an inherently sparse reconstruction problem and can be solved using compressive sensing algorithms. However, the performances are limited by the number of acquisitions and suffer from computational burdens in practice. …”
Get full text

Variant Design of Girder-Slab Structure with Different Geometric Cells Under Flexural Vibrations by Andrey A. Chernyaev, Kirill V. Marfin

“…Therefore, the development of methods and algorithms for searching of the most rational and optimal design solutions is of great significance. …”
Get full text

Evaluating Material Parameter Influence on Drapability Using VStitcher by Malin Schiller, Soraya Flohr, Jeanne Marisol Delmas, Anja Krüger, Anne-Marie Miene, Patrizia Zimmermann, Lena Wolf, Miriam Seffers, Michelle-Sophie Ruchay-Drammeh, Ulrike Reinhardt, Lilia Sabantina

“…The most significant effect on the drape coefficient (DC) is seen with increased bending stiffness, while changes in thickness, elongation, and shear stiffness have a minimal effect. …”
Get full text

Advances and challenges in neoantigen prediction for cancer immunotherapy by Yi Zhang, Ting-Ting Chen, Xiong Li, Ai-Lin Lan, Peng-Fei Ji, Ya-Juan Zhu, Xue-Yao Ma

“…Future advancements will focus on dynamic tumor microenvironment monitoring, multi-omics integration, improved computational models and algorithms to refine neoantigen prediction, and developing optimized personalized vaccines.…”
Get full text

A multi-functional simulation platform for on-demand ride service operations by Siyuan Feng, Taijie Chen, Yuhao Zhang, Jintao Ke, Zhengfei Zheng, Hai Yang

“…On-demand ride services or ride-sourcing services have been experiencing fast development and steadily reshaping the way people travel in the past decade. Various optimization algorithms, including reinforcement learning approaches, have been developed to help ride-sourcing platforms design better operational strategies to achieve higher efficiency. …”
Get full text

STUDY OF ROBUST TOA DISCRIMINATORS FOR SPACE-BASED RADAR ALTIMETER by D. S. Borovitsky, A. E. Zhesterev, V. P. Ipatov, R. M. Mamchur

“…In the  robust  algorithms TOA-measuring  is performed without  using  any  echo  physical  model.  …”
Get full text

Treatment Strategies and Prognostic Outcomes in Acute Limb Ischemia: A Systematic Review and Meta-Analysis Comparing Thrombolytic Therapy and Open Surgical Interventions by Mircea Cătălin Coșarcă, Nicolae Alexandru Lazăr, Suzana Vasilica Șincaru, Bogdan Corneliu Bandici, Eduard Costin Argatu, Cosmin Carașca, Ráduly Gergő, Dorin Constantin Dorobanțu, Cristian Trâmbițaș, Adrian Vasile Mureșan

“…Future research should focus on refining treatment algorithms, investigating novel thrombolytic agents, and expanding the role of minimally invasive techniques to improve long-term outcomes while mitigating complications such as bleeding and reperfusion injuries.…”
Get full text

Stroke Risk Classification Using the Ensemble Learning Method of XGBoost and Random Forest by Gullam Almuzadid, Egia Rosi Subhiyakto

“…The dataset was split into 80% training and 20% testing data (hold-out test) to ensure objective evaluation. Hyperparameter optimization was performed using Bayesian optimization, while model evaluation employed stratified K-fold cross-validation to prevent overfitting. …”
Get full text

Research on the Stability of Express Delivery Supply Chain Based on Risk Propagation Model ------ Case Studies of SF Express and JD Logistics by Fan Yunhui

“…Based on the research results, optimization strategies such as dynamic path optimization algorithms and blockchain-based information isolation mechanisms are proposed, providing theoretical tools and practical references for risk prevention and control in the express delivery industry.…”
Get full text

Artificial Intelligence Applications in Pediatric Craniofacial Surgery by Lucas M. Harrison, Ragan L. Edison, Rami R. Hallac

“…AI-driven algorithms assist in preoperative planning by identifying anatomical abnormalities, predicting surgical outcomes, and guiding personalized treatment strategies. …”
Get full text

Advances in Numerical Modeling for Heat Transfer and Thermal Management: A Review of Computational Approaches and Environmental Impacts by Łukasz Łach, Dmytro Svyetlichnyy

“…Sustainable computing practices, including energy-efficient algorithms and renewable-powered data centers, offer potential solutions. …”
Get full text

Emerging generalization advantage of quantum-inspired machine learning in the diagnosis of hepatocellular carcinoma by Domenico Pomarico, Alfonso Monaco, Nicola Amoroso, Loredana Bellantuono, Antonio Lacalamita, Marianna La Rocca, Tommaso Maggipinto, Ester Pantaleo, Sabina Tangaro, Sebastiano Stramaglia, Roberto Bellotti

“…The variational optimization of PQCs achieves better accuracy than classical counterparts on the independent test set, reaching an advantage equal to $$11\%$$ 11 % in accuracy, while tensor networks offer equivalent performance with fewer parameters.…”
Get full text

AI‐Driven TENGs for Self‐Powered Smart Sensors and Intelligent Devices by Aiswarya Baburaj, Syamini Jayadevan, Akshaya Kumar Aliyana, Naveen Kumar SK, George K Stylios

“…This review explores the synergistic potential of AI‐driven TENG systems, from optimizing materials and fabrication to embedding machine learning and deep learning algorithms for intelligent real‐time sensing. …”
Get full text

Machine learning approaches for predicting the link of the global trade network of liquefied natural gas. by Pei Zhao, Hao Song, Guang Ling

“…This study demonstrates that machine learning algorithms-specifically random forest and decision tree-outperform in predicting links within the global LNG trade network based on local information proximity, while the graph attention network, a deep learning model, exhibits stable optimization and effective feature learning. …”
Get full text