Supervised machine learning statistical models for visual outcome prediction in macular hole surgery: a single-surgeon, standardized surgery study by Kanika Godani, Vishma Prabhu, Priyanka Gandhi, Ayushi Choudhary, Shubham Darade, Rupal Kathare, Prathiba Hande, Ramesh Venkatesh

“…Clinical trial registration number Not applicable.…”
Get full text

Soil moisture estimation underneath crop cover using high incidence angle C-band Sentinel-1 SAR data by Hari Shanker Srivastava, Thota Sivasankar, Madhuri Dilip Gavali, Parul Patel

Get full text

Experimentally profiling dielectric properties of Escherichia coli and Staphylococcus aureus by movement velocity and force by Akmal Suhaimi, Arash Zulkarnain, Noraziah Mohamad Zin, Abdullah Abdulhameed, Aminuddin Ahmad Kayani, Ramdzan Buyong

“…The benefits of AI integration into DEP systems include improving position and accuracy, faster processing and decision-making, enhancing particle classification, reducing human error, and many others. On the other hand, DEP research often focuses on CMF values of the particles. …”
Get full text

Precision forecasting for hybrid energy systems using five deep learning algorithms for meteorological parameter prediction by Ceren Ceylan, Zehra Yumurtacı

“…Most significantly, our framework successfully forecasted sixth year (2023) energy production with 1.55 % error, validating its real-world applicability. This research contributes to the methodological advancement of renewable energy forecasting by systematically identifying optimal algorithmic approaches for different meteorological parameters in hybrid systems, thereby supporting the integration of intermittent renewable sources into sustainable energy infrastructures.…”
Get full text

Predicting the Robustness of Large Real-World Social Networks Using a Machine Learning Model by Ngoc-Kim-Khanh Nguyen, Quang Nguyen, Hai-Ha Pham, Thi-Trang Le, Tuan-Minh Nguyen, Davide Cassi, Francesco Scotognella, Roberto Alfieri, Michele Bellingeri

“…We found that the RF model can predict network robustness with a mean squared error (RMSE) of 0.03 and is 30% better than the MLR model. …”
Get full text

Spatial correlation guided cross scale feature fusion for age and gender estimation by Shiyi Jiang, Qing Ji, Hukui Shi, Che Chen, Yang Xu

“…Comprehensive experiments demonstrate that SCGNet achieves state-of-the-art performance with minimum Mean Absolute Error (MAE) 4.01% for age estimation on IMDB-Clean (2.9% improvement over VOLO-D1) and highest gender classification accuracy on IMDB-Clean, UTKFace, and Lagenda datasets, showing improvements in cross-scene adaptability compared to VOLO and MiVOLO models respectively. …”
Get full text

Active RIS-NOMA Uplink in URLLC, Jamming Mitigation via Surrogate and Deep Learning by Ghazal Asemian, Mohammadreza Amini, Burak Kantarci

“…The deep regression model converges to a weighted mean square error (WMSE) of 10.6 for RIS with 25 elements and 15.8 for larger RIS size, highlighting the effectiveness of the deep regression model and RIS configuration’s importance.…”
Get full text

NEW ROLE FOR THE TEACHER: PREVENT STUDENTS FROM COMPLETELY ABANDONING THEMSELVES TO AI AND RELINQUISHING CONTROL OVER THEIR LEARNING. Illustration for foreign languages for specifi... by Felicia CONSTANTIN

“…the incalculable benefits of the use of AI by students, in terms of speed, number of variants generated, productions with a high level of language, the generation of suggestive images through free and high-performance applications, the creation or self-creation of evaluation exercises; (b). the double valence - positive and negative - of some aspects: respect and nuance of the workload, originality in the context of a large number of users, error correction, management in solving the assignments, emotional involvement; (c). the disadvantages about the inability to perform some work tasks, the deviations from the defined work task, the hallucinations produced, and the limitations in the context of a common collaborative activity platform. …”
Get full text

Exothermic thermosolutal convection in a nanofluid-filled square cavity with a rotating Z-Fin: ISPH and AI integration by Kuiyu Cheng, Abdelraheem M. Aly, Nghia Nguyen Ho, Sang-Wook Lee, Andaç Batur Çolak, Weaam Alhejaili

“…The ANN model, employing the Levenberg–Marquardt algorithm, achieved a coefficient of determination $ R = 0.99994 $ and a mean squared error $ \text{MSE} = 4.21\times {10}^{-6} $, demonstrating its reliability in predicting thermal performance. …”
Get full text

Plasmonic Mode Interference Effect Based Sensors by Neha Ahlawat, Awanish Pandey, Saurabh Mani Tripathi

“…We have shown that using this sensitivity-matrix approach, the error associated with the estimated variations in the perturbations is of the order of 10<inline-formula><tex-math notation="LaTeX">$^{-4}$</tex-math></inline-formula> to 10<inline-formula><tex-math notation="LaTeX">$^{-3}$</tex-math></inline-formula>, making it a powerful tool to estimate simultaneously varying perturbation parameters by tracking multiple resonances.…”
Get full text

Multi-Modal Deep Learning for Lung Cancer Detection Using Attention-Based Inception-ResNet by Mohamed Hosny, Ibrahim A. Elgendy, Mousa Ahmad Albashrawi

“…However, these methods are time-intensive and highly susceptible to human error. Deep learning (DL) has emerged as a powerful alternative to autonomously identify complex patterns within radiological and histopathological images. …”
Get full text

A reliable tool for assessment of acceptance of e-consultation service in hospitals: the modified e-consultation Technology Acceptance Model (TAM) questionnaire by Rasha Ashmawy, Sally Zeina, Ehab Kamal, Khaled Shelbaya, Nermeen Gawish, Sandy Sharaf, Elrashdy M. Redwan, Azza Mehanna

“…Confirmatory factor analysis (CFA) confirmed the two-factor model, with standardized factor loadings between 0.80 and 0.95, a Comparative Fit Index (CFI) of 0.95, and a Root Mean Square Error of Approximation (RMSEA) of 0.084. Conclusion The modified e-consultation TAM questionnaire proves to be a reliable and valid tool for evaluating physicians’ acceptance of and satisfaction with e-consultation service. …”
Get full text

Structural strength optimization design of ultra-high-pressure and ultra-wear-resistant pneumatic ball valve opened and closed at large explosion instantaneously using finite eleme... by Xianmei Liu, Mingcun Zhang

“…The experiment shows that after optimization, the maximum equivalent stress peak of the valve body is reduced by 32.7%, the leakage rate is reduced to 0.008%, and the dynamic fatigue life is increased to 1.5 × 105 cycles under the commonly used engineering stress amplitude. The stress error between the simulation and the test is always less than 5%. …”
Get full text

Reliability of the Tuck Jump Assessment Using Standardized Rater Training by Kevin Racine, Meghan Warren, Craig Smith, Monica R. Lininger

“…Although the TJA has broad clinical applicability, there is no standardized training to maximize the TJA measurement properties…”
Get full text

Improvement of SAM2 Algorithm Based on Kalman Filtering for Long-Term Video Object Segmentation by Jun Yin, Fei Wu, Hao Su, Peng Huang, Yuetong Qixuan

“…SAM 2’s fixed temporal window approach indiscriminately retains historical frames, failing to account for frame quality or dynamic motion patterns. This leads to error propagation and tracking instability in challenging scenarios involving fast-moving objects, partial occlusions, or crowded environments. …”
Get full text

Parametric study and optimisation of supercritical extraction of Chlorella Vulgaris microalgae using Response surface methodology by Milap G. Nayak, Reena D. Gamit

“…Sovová model with high R2 and low residual error showed a close agreement between predicted and observed values of oil extraction yield. …”
Get full text

Features of minimizing total electrical losses in high-voltage electromechanical systems for stationary industrial fan installations by A.V. Synetskyi, I.M. Kotsur

“…A methodology for determining the optimal switching frequency of the semiconductor elements in the converter, which is part of the high-voltage electromechanical system, has been proposed. The calculation error of the optimal switching frequency of the semiconductor elements, obtained analytically, does not exceed 3.5% compared to the results obtained through simulation. …”
Get full text

Assessment of Isometric Shoulder Strength in Swimmers: A Validation and Reliability Study of the ASH and iASH Tests by Hugo Ogando-Berea, Santiago Virgós-Abelleira, Pablo Hernandez-Lucas, Fernando Zarzosa-Alonso

“…The symmetry in strength between both sides supports their applicability in preventive programmes.…”
Get full text

Motion control and singular perturbation algorithms for lower limb rehabilitation robots by Yanchun Xie, Anna Wang, Xue Zhao, Yang Jiang, Yao Wu, Hailong Yu

“…Experimental results demonstrate significant improvements in tracking error and system response compared to traditional methods, providing patients with a more comfortable and safer rehabilitation experience.…”
Get full text

Comparison of lower limb kinematic and kinetic estimation during athlete jumping between markerless and marker-based motion capture systems by Changzhi Yang, Linyu Wei, Xi Huang, Lili Tu, Yanjia Xu, Xiaolong Li, Zhe Hu

“…Abstract Markerless motion capture (ML) systems, which utilize deep learning algorithms, have significantly expanded the applications of biomechanical analysis. Jump tests are now essential tools for athlete monitoring and injury prevention. …”
Get full text