Development and validation of machine learning models for predicting post-cesarean pain and individualized pain management strategies: a multicenter study by Shenjuan Lv, Ning Sun, Chunhui Hao, Junqing Li, Yun Li

“…Performance metrics such as Root Mean Squared Error (RMSE) and Coefficient of Determination (R²) were evaluated through internal and external validations. …”
Get full text

Multi-objective optimization on thermo-structural performance of honeycomb absorbers for concentrated solar power systems by Masoud Behzad, Sébastien Poncet, Cristóbal Sarmiento-Laurel

“…Honeycomb volumetric solar receivers have emerged as promising candidates for concentrating solar power applications because of their thermal and mechanical properties, enabling the efficient heating of fluids. …”
Get full text

Development and psychometric evaluation of E-Learning Assessment Scale in Higher Education by Sevil Çiçek Özdemir, Ayten Şentürk Erenel, Şengül Yaman Sözbir, Sıdıka Pelit Aksu, Canan Uçakcı Asalıoğlu

“…CFA showed favourable results for Chi forecourt/ degrees of freedom (χ2/df), comparative fit indicator (CFI) and root mean square error of approximation (RMSEA). The Cronbach alpha of the scale was 0.96. …”
Get full text

Nearshore Depth Inversion Bathymetry from Coastal Webcam: A Novel Technique Based on Wave Celerity Estimation by Umberto Andriolo, Alberto Azevedo, Gil Gonçalves, Rui Taborda

“…The results were corroborated in comparison to ground-truth data available up to a depth of 10 m, yielding a mean bias of 0.05 m and a mean root mean square error (RMSE) of 0.43 m. In particular, RMSE was lower than 15% in the outer surf zone, where breaking processes occur. …”
Get full text

AI-Driven Adaptive Communications for Energy-Efficient Underwater Acoustic Sensor Networks by A. Ur Rehman, Laura Galluccio, Giacomo Morabito

“…GNU Radio simulations evaluate the framework effectiveness using metrics like energy consumption, bit error rate, throughput, and delay. Adaptive transmission strategies implicitly ensure reduced energy usage as compared to non-adaptive transmission solutions employing fixed communication parameters. …”
Get full text

View-Aware Contrastive Learning for Incomplete Tabular Data with Low-Label Regimes by Yingqiu Yang, Qianye Lin, Zeyue Li, Yakui Wang, Siyu Liang, Siyuan Zhang, Yiyan Wang, Chunli Lv

“…The model achieves an accuracy of 0.87, F1-score of 0.83, and AUC of 0.90 while reducing the normalized mean squared error to 0.066. These results significantly outperform mainstream baseline models such as XGBoost, TabTransformer, and VIME, demonstrating the proposed method’s robustness and broad applicability across diverse real-world tasks. …”
Get full text

Whole-Body 3D Pose Estimation Based on Body Mass Distribution and Center of Gravity Constraints by Fan Wei, Guanghua Xu, Qingqiang Wu, Penglin Qin, Leijun Pan, Yihua Zhao

“…Estimating the 3D pose of a human body from monocular images is crucial for computer vision applications, but the technique remains challenging due to depth ambiguity and self-occlusion. …”
Get full text

Improving Localization in Wireless Sensor Networks for the Internet of Things Using Data Replication-Based Deep Neural Networks by Jehan Esheh, Sofiene Affes

“…By combining the modified datasets with the original training data, we significantly increase the dataset size, which leads to a substantial reduction in normalized root mean square error (NRMSE). The experimental results demonstrate that this data augmentation technique significantly improves the performance of DNNs compared to the traditional Dv-hop algorithm at a low number of nodes while maintaining an efficient computational cost for data augmentation. …”
Get full text

Thermo-Mechanical Behavior Simulation and Experimental Validation of Segmented Tire Molds Based on Multi-Physics Coupling by Wenkang Xiao, Fang Cao, Jianghai Lin, Hao Wang, Chongyi Liu

“…Molding forces play a secondary role in total stress. The error between multi-field coupling simulation results and experimental results is controlled within 6%, verifying the model’s reliability. …”
Get full text

FirnLearn: A neural network-based approach to firn density modeling in Antarctica by Ayobami Ogunmolasuyi, Colin R. Meyer, Ian McDowell, Megan Thompson-Munson, Ian Baker

“…Our model, FirnLearn, evaluated on 225 cores, shows an average root-mean-square error of 31 kg m−3 and explained variance of 91%. …”
Get full text

Laser Phase Noise Compensation Method Based on Dual Reference Channels in Inverse Synthetic Aperture Lidar by Dengfeng Liu, Chen Xu, Yutang Li, Anpeng Song, Jian Li, Kai Jin, Xi Luo, Kai Wei

“…Compared to prior methods based on residual error linear estimation, the DRC method enhances compensation speed tenfold while maintaining accuracy. …”
Get full text

A Multihierarchy Flow Field Prediction Network for Multimodal Remote Sensing Image Registration by Wenqing Wang, Kunpeng Mu, Han Liu

“…At the same time, the photometric error loss is introduced to optimize the entire network from both the feature and original image levels. …”
Get full text

LET-SE2-VINS: A Hybrid Optical Flow Framework for Robust Visual–Inertial SLAM by Wei Zhao, Hongyang Sun, Songsong Ma, Haitao Wang

“…In no-loop scenarios, the method also achieves error reductions of 29.7%, 21.8%, and 24.1% on the MH_04, MH_05, and V2_03 sequences, respectively. …”
Get full text

Ionospheric Time Series Prediction Method Based on Spatio-Temporal Graph Neural Network by Yifei Chen, Yang Liu, Kunlin Yang, Lanhao Li, Chao Xiong, Jinling Wang

“…For the one-week (84 step) prediction test, the STGNN shows a 27.0% lower error compared to the MLPMultivariate model. The model’s self-adaptive spatial learning and multiscale temporal modeling uniquely enable TEC forecasting under diverse geophysical conditions.…”
Get full text

Temperature Correction for FWD Deflection in Cement Pavement Void Detection by Bei Zhang, Xiaoliang Wang, Yanhui Zhong, Xiaolong Li, Meimei Hao, Yuanhao Ding, Jianyang Liu, Xu Zhang

“…The results showed that, within the ranges of positive and negative temperature differences, the fitting degree of the temperature correction coefficient for the cement pavement exceeded 0.99, which was consistent with the variation trend of the temperature correction coefficient obtained through field tests. The error was lower than 7%, which verified the applicability of the temperature correction coefficient for the dynamic deflection of cement pavements based on FWD. …”
Get full text

Being confident in confidence scores: calibration in deep learning models for camera trap image sequences by Gaspard Dussert, Simon Chamaillé‐Jammes, Stéphane Dray, Vincent Miele

“…Our findings have clear implication for, for instance, the calculation of error rates or the selection of confidence score thresholds in ecological studies making use of artificial intelligence models.…”
Get full text

Recent Advancements in Artificial Intelligence in Battery Recycling by Subin Antony Jose, Connor Andrew Dennis Cook, Joseph Palacios, Hyundeok Seo, Christian Eduardo Torres Ramirez, Jinhong Wu, Pradeep L. Menezes

“…This paper reviews the latest developments in AI applications for battery recycling, focusing on methodologies, challenges, and future directions. …”
Get full text

A High‐Performance Miniaturized Frequency Shift Detection System for QCM‐Based Gravimetric Sensing by Chenyang Gao, Shuyu Fan, Wei Li, Yongbing Wang, Qianwen Xia, Dibo Hou, Yunqi Cao

“…As a result, compared with a commercial frequency counter, the superior linearity and accuracy of over 98.4% were confirmed with a mean relative error (MRE) of less than 0.92%.…”
Get full text

Accuracy Testing of Torque Limit Determination Algorithm Intended for Smart Bone Screwdrivers by Jack A. Wilkie, Alberto Battistel, Paul D. Docherty, Niklaus F. Friederich, Georg Rauter, Knut Möller

“…A good relationship was found between the estimated/predicted and true stripping torques (r = 0.926, 95% confidence interval (C.I.) [0.886, 0.952]), with a mean error of 18%. Additionally, the intermediate identified strength values were found to be highly correlated with the data-sheet values for the materials (r = 0.977, 95% C.I. [0.964, 0.985]). …”
Get full text

Paying attention to distortion: improving the accuracy of multistep-ahead carbon price forecasting with shape and temporal criteria by Tong Niu, Yuan Chen, Tao Li, Shaolong Sun, Weigang Zhao, Mingjian Cui, Jiakang Wang, Shiyu Han, Jiujiang Li, Yunkai Zhai

“…However, current state-of-the-art carbon price forecasting models, which are trained primarily via the mean squared error loss function, struggle to deliver precise and timely forecasts. …”
Get full text