Generalized cross-entropy for learning from crowds based on correlated chained Gaussian processes by J. Gil-González, G. Daza-Santacoloma, D. Cárdenas-Peña, A. Orozco-Gutiérrez, A. Álvarez-Meza

“…Machine learning applications heavily depend on labeled data provided by domain experts to train accurate models. …”
Get full text

Evaluation of Measurement Uncertainty for the Wave Buoy Calibration Device Using a Vertical Lifting Method by Yafei Huang, Donglei Zhao, Chenhao Gao, Tian Yan, Lijun He

“…Additionally, a high-precision time calibration method synchronizes the time of the motor’s upper computer software and a frequency meter, minimizing indication error. Key uncertainty sources, including repeatability, environmental temperature effects, and the smallest division measure of instrument, were systematically analyzed. …”
Get full text

Cuff-less blood pressure monitoring via PPG signals using a hybrid CNN-BiLSTM deep learning model with attention mechanism by Hanieh Mohammadi, Bahram Tarvirdizadeh, Khalil Alipour, Mohammad Ghamari

“…Through meticulous preprocessing steps, the model achieved an impressive mean absolute error (MAE) of 1.88 for systolic blood pressure (SBP) and 1.34 for diastolic blood pressure (DBP) across 5-fold cross-validation. …”
Get full text

Predicting medication wastage using machine learning based on patient beliefs by Firdaus Aziz, Sorayya Malek, Shubathira Sooriamoorthy, Ilham Asyilah Mahamood, Chong Wei Wen, Sharifah M. Syed Ahmad, Putri Nur Fatin Amir Rudin, Adliah Mhd Ali

“…Multiple ML regression models were evaluated to predict medication wastage, with performance assessed based on root mean squared error (RMSE). Results The XGBoost model achieved the best performance with the lowest RMSE of 4.67, outperforming other models (RMSE range:4.68–5.10). …”
Get full text

Estimation of Peak Junction Hotspot Temperature in Three-Level TNPC-IGBT Modules for Traction Inverters Through Chip-Level Modeling and Experimental Validation by Ahmed H. Okilly, Peter Nkwocha Harmony, Cheolgyu Kim, Do-Wan Kim, Jeihoon Baek

“…The outcomes show a relative estimation error of less than 1% when compared to experimental data and approximately 1.15% for the analytical model. …”
Get full text

UV Hyperspectral Imaging and Chemometrics for Honeydew Detection: Enhancing Cotton Fiber Quality by Mohammad Al Ktash, Mona Knoblich, Frank Wackenhut, Marc Brecht

“…Additionally, partial least squares regression (PLS-R) was utilized to predict the honeydew content for each pixel in hyperspectral images, achieving a cross-validation coefficient of determination <i>R</i>² = 0.75 and root mean square error of RMSE = 0.8 for the honey model. By employing a realistic spraying method that closely mimics natural contamination, this study refines sample preparation techniques for improved evaluation of honeydew levels. …”
Get full text

Data-Driven Prediction Methods for Lithium-Ion Battery State of Health Based on Elbow Rule by Liu Zhang, Bo Xing, Yanbing Gao, Lei Yao, Dengfeng Zhao, Jinquan Ding, Yanyan Li

“…The findings reveal a relative error of approximately 4% when maintaining lithium-ion battery SOH at 80%, affirming the GPR model&#x2019;s high accuracy and robust adaptability for SOH prediction.…”
Get full text

A physics-informed neural network-based method for predicting degradation trajectories and remaining useful life of supercapacitors by Lixin E, Jun Wang, Ruixin Yang, Chenxu Wang, Hailong Li, Rui Xiong

“…Validation results show a root mean square error (RMSE) of 3 ​mF (the rated capacity is 1 F) in the degradation trajectory prediction and a RMSE of 269 cycles (the average cycle life is 5180 cycles) for the RUL. …”
Get full text

Investigation on the Bearing Characteristics and Bearing Capacity Calculation Method of the Interface of Reinforced Soil with Waste Tire Grid by Jie Sun, Yuchen Tao, Zhikun Liu, Xiuguang Song, Wentong Wang, Hongbo Zhang

“…The average discrepancy between the calculated values of the established model and the theoretical values was merely 2.38% (maximum error < 5%). Overall, this research offers technical assistance for ensuring the safety of subgrade design and promoting environmental sustainability in engineering, enabling the effective utilization of waste tire grids in sustainable reinforcement applications.…”
Get full text

Steady-State Model Enabled Dynamic PEMFC Performance Degradation Prediction via Recurrent Neural Network by Qiang Liu, Weihong Zang, Wentao Zhang, Yang Zhang, Yuqi Tong, Yanbiao Feng

“…Comparative analysis of multiple RNN variants revealed that the hybrid methodology achieved superior prediction fidelity, demonstrating a root mean square error of 0.6228%. Notably, the integration of steady-state physics could reduce the RNN structural complexity while maintaining equivalent prediction accuracy. …”
Get full text

OTFS: A Potential Waveform for Space–Air–Ground Integrated Networks in 6G and Beyond by Obinna Okoyeigbo, Xutao Deng, Agbotiname Lucky Imoize, Olamilekan Shobayo

“…Using 6G exploration library in MATLAB, this study compares the bit error rate (BER) performance of OTFS and OFDM under static and multipath channels with varying mobility scenarios from 20 km/h to 2000 km/h, and varying modulation orders (BPSK, QPSK, and 8-PSK). …”
Get full text

Advanced beamforming and reflection control in intelligent reflecting surfaces with integrated channel estimation by Sakhshra Monga, Anmol Rattan Singh, Nitin Saluja, Chander Prabha, Shivani Malhotra, Asif Karim, Md. Mehedi Hassan

“…Specifically, the sum rate for GDNNet (GNN + DNN) improves by 12.57% over linear minimum mean square error (LMMSE) and by 12.42% over perfect CSI concerning the number of users, and by 28.57% over LMMSE and by 14.28% over perfect CSI concerning pilot length. …”
Get full text

Integrating IoT With Adaptive Beamforming for Enhanced Urban Sensing in Smart Cities by Sunday Enahoro, Sunday C. Ekpo, Mfonobong Uko, Fanuel Elias, Stephen Alabi

“…SmartBeam+ dynamically adjusts the beamforming weights using real-time Channel State Information (CSI) to maximize the Signal-to-Interference-and-Noise Ratio (SINR), minimize the bit error rate (BER), and suppress interference effectively. …”
Get full text

Numerical insights into enhanced heat transfer mechanisms in TiO2-Au ethylene glycol nanofluids within Darcy porous media using fractional calculus by Mumtaz Khan, Dianchen Lu, Mudassar Imran, Muhammad Shoaib Anwar

“…To confirm the validity of our approach, we conducted an error analysis by comparing the solutions with exact solutions to verify the accuracy of our results. …”
Get full text

Energy Consumption Modeling and Flight Time Analysis of Micro Drones by Nusin Akram, Mina Khoshrangbaf, Moharram Challenger, Orhan Dagdeviren

“…In this paper, we propose a voltage-based regression model to estimate the energy consumption and flight time of micro drones, using sampled voltage data obtained from experimental evaluations in ground, take-off, hovering, and flying modes. The mean absolute error of the proposed regression models is less than 0.3 V for all flying modes. …”
Get full text

A novel pressure control method for nonlinear shell-and-tube steam condenser system via electric eel foraging optimizer by Serdar Ekinci, Cebrail Turkeri, Davut Izci, Laith Abualigah, Mohit Bajaj, Vojtech Blazek, Lukas Prokop

“…Simulation results confirm that EEFO reduces settling time by 22.7%, overshoot by 78.7%, steady-state error by three orders of magnitude, and ITAE by 81.2% compared to metaheuristic based methods. …”
Get full text

Audio Watermarking Algorithm Against Speed Attack based on Amplitude Rearrangement by WANG Xin, HUANG Ying, NIU Baoning, WU Shiqiang, LAN Fangpeng, GUAN Hu

“…This technology has important applications in copyright protection, content authentication, and secure communication. …”
Get full text

Data-Driven Battery Remaining Life Prediction Based on ResNet with GA Optimization by Jixiang Zhou, Weijian Huang, Haiyan Dai, Chuang Wang, Yuhua Zhong

“…In order to reduce the usage of the dataset, only the first 100 cycles of the battery data were used, and the prediction error was about 9%. Secondly, the deep feature extraction capability of ResNet is utilized to effectively capture the complex patterns and subtle changes during battery decline to alleviate the problem of gradient disappearance. …”
Get full text

Adsorption Performance of La(III) and Y(III) on Orange Peel: Impact of Experimental Variables, Isotherms, and Kinetics by Li Liu, Yunzhang Rao, Changshun Tian, Tao Huang, Jiacheng Lu, Meidao Zhang, Min Han

“…The experimental data is well fitted by the Langmuir isotherm model with correlation coefficient R2>0.9 and the minimum standard error values. Equilibrium results show that Langmuir monolayer adsorption capacity of La(III) and Y(III) onto orange peel is up to 37.61 and 31.10 mg/g. …”
Get full text

Development and Psychometric Properties of a Scale of Teachers’ Coping Strategies Towards the Evaluation of Performance in Public Schools by Jocabeth Nohemi Chambilla-Apaza, Ailyn Yicela Merchan-Fuentes, Denis Frank Cunza-Aranzábal, Carlos D. Abanto-Ramírez

“…Internal reliability was high for the full scale and dimensions (α and ω > 0.8), indicating that it was free of random error, yielding the same results across multiple applications for the same sample. …”
Get full text