Scalable reinforcement learning for large-scale coordination of electric vehicles using graph neural networks by Stavros Orfanoudakis, Valentin Robu, E. Mauricio Salazar, Peter Palensky, Pedro P. Vergara

“…Extensive experimental evaluations show that EV-GNN significantly outperforms state-of-the-art RL algorithms in scalability and generalization across diverse EV charging scenarios, delivering notable improvements in both small- and large-scale problems.…”
Get full text

A Clinically Interpretable Approach for Early Detection of Autism Using Machine Learning With Explainable AI by Oishi Jyoti, Hafsa Binte Kibria, Zareen Tasnim Pear, Md Nahiduzzaman, Md. Faysal Ahamed, Khandaker Reajul Islam, Jaya Kumar, Muhammad E. H. Chowdhury

“…SHAP are also illustrated to improve model interpretability by highlighting the most influential features, thereby aiding physician understanding. …”
Get full text

IHML: Incremental Heuristic Meta-Learner by Onur Karadeli, Kıymet Kaya, Şule Gündüz Öğüdücü

“…The results show that the proposed model achieves more accuracy (in average % 10 and at most % 71 improvements) compared to the baseline machine learning models in the literature.…”
Get full text

Predicting the Remaining Useful Life of an Aircraft Engine Using a Stacked Sparse Autoencoder with Multilayer Self-Learning by Jian Ma, Hua Su, Wan-lin Zhao, Bin Liu

“…However, the hyperparameters of the deep learning, which significantly impact the feature extraction and prediction performance, are determined based on expert experience in most cases. The grid search method is introduced in this paper to optimize the hyperparameters of the proposed aircraft engine RUL prediction model. …”
Get full text

Exploring Machine Learning Models for Vault Safety in ICL Implantation: A Comparative Analysis of Regression and Classification Models by Qing Zhang, Qi Li, Zhilong Yu, Ruibo Yang, Emmanuel Eric Pazo, Yue Huang, Hui Liu, Chen Zhang, Salissou Moutari, Shaozhen Zhao

“…In the task of predicting vault > 750 µm vs. ≤ 750 µm, random forest emerged as the most effective classifier, achieving accuracy of 86 ± 9% and an AUC of 0.88. …”
Get full text

Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-Dimensional Tokens by Vittorio Erba, Emanuele Troiani, Luca Biggio, Antoine Maillard, Lenka Zdeborová

“…We quantify the improvement that optimal learning brings with respect to vectorizing the sequence of tokens and learning via simple linear regression. …”
Get full text

Developing advanced datadriven framework to predict the bearing capacity of piles on rock by Kennedy C. Onyelowe, Shadi Hanandeh, Viroon Kamchoom, Ahmed M. Ebid, Fabián Danilo Reyes Silva, José Luis Allauca Palta, José Luis Llamuca Llamuca, Siva Avudaiappan

“…The developed framework provides engineers and practitioners with a powerful tool for improving pile design accuracy, reducing uncertainties, and optimizing construction practices. …”
Get full text

Machine learning discovery of the dielectric properties of strontium-containing condensed matter by Dongyang Huang, Jiaxing Fu, Chenghao Yu

“…In this work, machine learning models were successfully developed to capture the relationship between composition and dielectric properties of strontium-containing dielectrics using different algorithms, with hyperparameter optimization performed via grid search. …”
Get full text

Intelligent deep learning for human activity recognition in individuals with disabilities using sensor based IoT and edge cloud continuum by Mohammed Maray

“…Finally, the deep belief network (DBN) model is employed for HAR. To exhibit the improved performance of the existing IDLTHAR-PDST model, a comprehensive simulation study is accomplished. …”
Get full text

Validation of Sea Surface Temperature From GK-2A Geostationary Satellite and Error Reduction Considering Impact of Satellite Zenith Angle by Kyung-Ae Park, Hye-Jin Woo, Stephane Saux Picart, Anne O'Carroll, Eunha Sohn, HuiTae Joo, Joon-Soo Lee, Joon-Yong Yang

“…By proposing optimal algorithms for SST retrievals from geostationary satellites, this study is anticipated to improve the monitoring of SSTs in regions covered by GK-2A. …”
Get full text

A Full-Life-Cycle Modeling Framework for Cropland Abandonment Detection Based on Dense Time Series of Landsat-Derived Vegetation and Soil Fractions by Qiangqiang Sun, Zhijun You, Ping Zhang, Hao Wu, Zhonghai Yu, Lu Wang

“…Compared to the traditional yearly land cover-based approach (with an overall accuracy of 77.39%), this algorithm can overcome the propagation of classification errors (with product accuracy from 74.47% to 85.11%), especially in terms of improving the ability to capture changes at finer spatial scales. …”
Get full text

A novel method for soil organic carbon prediction using integrated ‘ground-air-space’ multimodal remote sensing data by Yilin Bao, Xiangtian Meng, Huanjun Liu, Mengyuan Xu, Mingchang Wang

“…The SOC prediction experiments conducted in Youyi, the largest state farm in China, demonstrate that Model (iii) achieves the highest accuracy with the GNN model. This model improves coefficient of determination (R2) and ratio of performance to interquartile distance (RPIQ) by 0.09 and 0.28, respectively, and reduces root mean square error (RMSE) by 0.52 g kg−1 compared to Model (ii). …”
Get full text

Predictive model for determining the indications for automated 3D ultrasound for screening patients at low risk of developing breast tumors by A. E. Garanina, A. V. Kholin

“…The developed algorithms will help optimize screening and referral for additional examinations, which is of practical importance for improving diagnostics and optimizing healthcare resources.…”
Get full text

Research Progress and Prospect of Green Infrastructure with Public Health Promotion Function by Tongyu LI, Junyi LIXU, Binxia XUE, Yan (USA) SONG

“…Such a framework could significantly enhance urban planning and policy-making by optimizing GI interventions to provide the most significant public health benefits. …”
Get full text

ON THE SIMULATION OF MODES ОF ELECTRIC POWER SYSTEMS WITH FACTS by E. D. Halilov

“…It is necessary to reduce the power loss, improve the reliability and quality of power supply and increase the power transmission. …”
Get full text

Implementation of XGBoost Models for Predicting CO₂ Emission and Specific Tractor Fuel Consumption by Nebojša Balać, Zoran Mileusnić, Aleksandra Dragičević, Mihailo Milanović, Andrija Rajković, Rajko Miodragović, Olivera Ećim-Đurić

“…The CO₂ prediction model achieved an accuracy exceeding 80%, while the model for fuel consumption reached over 65%. Although not optimized for high precision, these models offer a valuable basis for preliminary assessments and highlight the potential of data-driven approaches for improving energy efficiency and environmental sustainability in agricultural mechanization.…”
Get full text

Deep learning-based prediction of individualized Real-time FSH doses in GnRH agonist long protocols by Na Kong, Yu Xia, Zhilong Wang, Hui Zhang, Liyan Duan, Yingchun Zhu, Chenyang Huang, Guijun Yan, Jie Mei, Wujun Li, Haixiang Sun

“…Most existing models are limited to static predictions of initial doses and do not support real-time adjustments throughout stimulation. …”
Get full text

Intelligent resource allocation in internet of things using random forest and clustering techniques by Nahideh Derakhshanfard, Lida Hosseinzadeh, Fahimeh Rashid Jafari, Ali Ghaffari

“…A Random Forest model is then trained to accurately predict the resource needs of each cluster, enabling optimal allocation. Simulation results show that the proposed approach improves prediction accuracy to 94%, reduces energy consumption by 20%, and decreases response time by 10% compared to existing methods. …”
Get full text

Elastic regularization networks for enhanced UAV visual tracking by Qingjiao Meng, Ji Li, Yan Jin, Zhaotian Deng

“…On the DTB70 dataset, the proposed method achieves a precision of 0.747 and a success rate of 0.789, representing improvements of 1% and 2.9%, respectively, over the STRCF algorithm. …”
Get full text

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

“…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