Food Cooking Process Modeling With Neural Networks by Javier Fananas-Anaya, Gonzalo Lopez-Nicolas, Carlos Sagues, Sergio Llorente

“…The main novelty is that we define a novel training algorithm adapted to the modeling of real-time dynamical systems, allowing a NARX-NN with a simple structure to obtain a negligible error compared to the results of the original FEM model. …”
Get full text

Neural-enhanced motion-to-EMG: refining simulated muscle activity from musculoskeletal models using a Seq2Seq approach by Tatsuya Teramae, Takamitsu Matsubara, Takamitsu Matsubara, Tomoyuki Noda, Jun Morimoto, Jun Morimoto

“…Previous efforts to optimize the parameters in musculoskeletal model simulators have yielded limited improvements in estimation accuracy. A key source of error that is identified in this study is the spatio-temporal distortion between the estimated and actual muscle activity, which has been inadequately addressed in previous research. …”
Get full text

LightHand99K: A Synthetic Dataset for Hand Pose Estimation With Wrist-Worn Cameras by Jeongho Lee, Changho Kim, Jaeyun Kim, Seon Ho Kim, Younggeun Choi, Sang-Il Choi

“…Incorporating three data augmentation techniques, LightHand99K demonstrated a 36% increase in area under the curve (AUC) and a 6.2-mm reduction in average endpoint error (EPE) compared to existing datasets. These results underscore the value of LightHand99K in advancing hand-pose estimation, particularly in wrist-worn camera applications. …”
Get full text

Supervised machine learning prediction and investigation of nonlinear optical rectification in Ge/Si0.15Ge0.85 asymmetric coupled triangle quantum wells by A. Cherni, N. Yahyaoui, N. Zeiri, M.L. Bouazizi, M.Al. Zahrani

“…Among the three ML models, the DT model yields the most accurate predictions, with RMSE values between 0.0038 and 0.0053 and MAE values between 0.0020 and 0.0027 across all considered LR values. These low error values demonstrate a strong agreement with the theoretical calculation, validating the reliability of the proposed ML-based approach. …”
Get full text

Axial compressive behavior of partial CFRP-jacketed coal samples: Effects of CFRP layers and strip coverage ratio by Qingwen Li, Yuqi Zhong, Mengjiao Xu, Chuangchuang Pan, Fanfan Nie, Hao Yang

“…A modified strength model for partial CFRP-jacketed coal samples was developed, and its validation through the integral absolute error index demonstrated strong performance and high precision.…”
Get full text

CMACGSA: Improved Gravitational Search Algorithm Based on Cerebellar Model Articulation Controller for Optimization by Nazmiye Ebru Bulut, Emre Dandil, Ugur Yuzgec, Alpaslan Duysak

“…Additional enhancements include Lévy mutation, boundary control methods and an error handling mechanism, which together improve the robustness and adaptability of the algorithm. …”
Get full text

Neural network quantification for solar radiation prediction: An approach for low power devices by Brenda Alejandra Villamizar-Medina, Angelo Joseph Soto Vergel, Byron Medina-Delgado, Darwin Orlando Cardozo-Sarmiento, Dinael Guevara-Ibarra, Oriana Alexandra Lopez-Bustamante

“…Metrics such as root mean square error (RMSE) of 44.24 and R² of 0.96 indicate that the selected quantized model differs from the original non-quantized model by less than 0.5% in RMSE and 0.04% in R². …”
Get full text

Machine Learning-Driven Optimization of Transport Layers in MAPbI₃ Perovskite Solar Cells for Enhanced Performance by Velpuri Leela Devi, Piyush Kuchhal, Debasis de, Abhinav Sharma, Neeraj Kumar Shukla, Mona Aggarwal

“…In this research work, among those eight ML models, the XGBoost algorithm shows high accuracy for predicting the power conversion efficiency (PCE) of the cell, achieving root mean square error (RMSE) of 0.052 and a coefficient of determination (R2) of 0.999. …”
Get full text

SMOTE vs. SMOTEENN: A Study on the Performance of Resampling Algorithms for Addressing Class Imbalance in Regression Models by Gazi Husain, Daniel Nasef, Rejath Jose, Jonathan Mayer, Molly Bekbolatova, Timothy Devine, Milan Toma

“…The results indicate that SMOTEENN consistently outperforms SMOTE in terms of accuracy and mean squared error across all sample sizes and models. SMOTEENN also demonstrates healthier learning curves, suggesting improved generalization capabilities, particularly for a sampling strategy with a given number of instances. …”
Get full text

Deformation and migration characteristics of bubbles moving in gas-liquid countercurrent flow in annulus by Bangtang YIN, Tianbao DING, Shulong WANG, Zhiyuan WANG, Baojiang SUN, Wei ZHANG, Xuliang ZHANG

“…The established bubble migration velocity prediction model yields errors within ± 15 %, and demonstrates broad applicability across a wide range of operating conditions.…”
Get full text

A Machine Learning-Based Real-Time Remaining Useful Life Estimation and Fair Pricing Strategy for Electric Vehicle Battery Swapping Stations by Seyit Alperen Celtek, Seda Kul, A. Ozgur Polat, Hamed Zeinoddini-Meymand, Farhad Shahnia

“…The results suggest that XGBoost provides the most suitable balance between accuracy and efficiency, making it an effective solution for real-world applications. Comparative analysis shows that the XGBoost model outperforms the second-best method (Random Forest) with a lower error (3.50 vs 3.79) while maintaining competitive computational efficiency (9.75 vs 8.52 seconds) and memory usage (2.12 vs 2.32 MB) when solving a typical numerical case study problem. …”
Get full text

Online Asynchronous Learning over Streaming Nominal Data by Hongrui Li, Shengda Zhuo, Lin Li, Jiale Chen, Tianbo Wang, Jun Tang, Shaorui Liu, Shuqiang Huang

“…We evaluate OALN on twelve real-world datasets; the average cumulative error rates are 23.31% and 28.28% under the missing rates of 10% and 50%, respectively, and the average AUC scores are 0.7895 and 0.7433, which are the best results among the compared algorithms. …”
Get full text

Fully Wireless Implantable Device Capable of Multichannel Neural Spike Recording and Stimulation for Long-Term Freely Moving Rodent Study by Minh Duc Hoang, Wonok Kang, Matthew Koh, Sung-Min Park

“…This study presents a fully wireless implantable device with a compact volume of 4.8 cm3, offering six-channel spike recording at 20 kHz which matches the performance of commercial benchtop systems and four-channel stimulation with <0.1% error for long-term freely moving rodent studies. …”
Get full text

Sugarcane acreage estimation using Sentinel-2A satellite data and time series approach by Yogesh Garde, Swaroop D. B, Vipul Shinde, Sagar Kolekar, V.S. Thorat, Jay Delvadiya, Alok Shrivastava

“…Additionally, it was compared the accuracy of combined approach with individual methods, signifying that the combined approach yielded superior results, the result stands at 141.961 (00'ha) with a lower absolute percent error of  6.57%. …”
Get full text

A neural networks technique for analysis of MHD nano-fluid flow over a rotating disk with heat generation/absorption by Yousef Jawarneh, Humaira Yasmin, Wajid Ullah Jan, Ajed Akbar, M. Mossa Al-Sawalha

“…A regression analysis, a mean squared error (MSE) assessment, and a histogram analysis were used to further evaluate the proposed NNB-LMS. …”
Get full text

The Time Difference of Arrival Estimation Method Utilizing an Inexact Reconstruction Within the Framework of Compressed Sensing by Shanhe Wang, Yu Xiang, Yuanyuan Gao, Yu Hua, Changjiang Huang, Xian Zhao

“…Simulation results demonstrate that when the signal-to-noise ratio (SNR) of the received signal is at least 0 dB and the compressed sampling length exceeds one-tenth of the original signal length, the TDOA estimation error of the proposed method is nearly identical to that of the cross-correlation method.…”
Get full text

Dynamic reconstruction of electroencephalogram data using RBF neural networks by Xuan Wang, Congcong Du, Xianjin Ke, Jian Zhang, Zheng Zheng, Yayan Yue, Ming Yu

“…Statistical analyses including ANOVA and Kruskal-Wallis tests were performed to assess age-related differences in fixed-point coordinates.ResultsThe RBF network demonstrated high accuracy in EEG signal reconstruction across different frequency a normalized root mean square error (NRMSE) of 0.0671 ± 0.0074 and a Pearson correlation coefficient ± 0.0678. …”
Get full text

Development of Quantitative Structure–Anti-Inflammatory Relationships of Alkaloids by Cristian Rojas, Doménica Muñoz, Ivanna Cordero, Belén Tenesaca, Davide Ballabio

“…The performance of the models was quantified by means of the non-error rate (<i>NER</i>) statistical parameter.…”
Get full text

A comparative study on trajectory tracking control methods for automated vehicles by Dequan Zeng, Shicong Pan, Yinquan Yu, Yiming Hu, Jinwen Yang, Peizhi Zhang, Lu Xiong, Giuseppe Carbone, Letian Gao

“…Finally, a lateral control method based on nonlinear integral sliding mode control (NISMC) is developed, which realizes zero steady-state error by substituting saturation function for symbolic function and introducing integral action. …”
Get full text

Transfer Learning for Photovoltaic Power Forecasting Across Regions Using Large-Scale Datasets by Seongho Bak, Sowon Choi, Donguk Yang, Doyoon Kim, Heeseon Rho, Kyoobin Lee

“…It reduces the mean absolute percentage error by up to 38.8% compared with models trained solely on the target data. …”
Get full text