Predicting the Tensile Strength of Plant Leaves Based on GA-SVM by Wei Chang, Meihong Liu, Yayu Huang, Junjie Lei, Kai Wu

“…A comparative analysis with other predictive algorithms demonstrates that the GA-SVM model achieves the lowest prediction error and highest accuracy, with mean absolute error and root mean squared error values of 0.0774 and 0.0745, respectively. …”
Get full text

INVARIANT SYSTEM OF AUTOMATIC WATER-LEVEL REGULATING IN THE BOILER SHELL by G. T. Kulakov, A. N. Kuchorenko

“…The comparative analysis of the modeling results of the Cascade-System Automatic Regulation (CSAR) with PID-regulator adjusted according to the foreign  methods  and  of  the  proposed  invariant  system  shows  considerable  improvement in regulation quality of the latter, viz. : system performance grows 2,5 times when working through the task jump, the peak value of overcorrection lowers from 42,5 to 10,0 %; while working through the internal disturbance, the regulating time reduces by 33 %, the maximum dynamic error of the regulation lowers by 65 %; the time of external combustion disturbance workout completion reduces two times, the maximum dynamic error of regulating – by 63 %; the maximum dynamic error of regulation while working through external disturbance with overheated steam rate diminishes by 71 %, the regulating time reduces by 1,5 times.…”
Get full text

Enhancing Human–Computer Interaction With Cultural Nuance: A Deep Reinforcement Learning Perspective by Xiaohui Wang

“…The results of the studies show that adding cultural backgrounds to temperament recognition can result in significant gains, as demonstrated by a 4.6% reduction in detection error over previous models. …”
Get full text

The Neural Correlates and Behavioral Impact of Peripheral Noise Electrical Stimulation on Motor Learning by Li-Wei Chou, Man-Wai Kou, Hui-Min Lee, Felipe Fregni, Vincent Chen, Chung-Lan Kao

“…The differences (force error) between the actual and the targeted force were calculated, and motor learning was achieved by reducing the force error to a plateau. …”
Get full text

Testing the role of online group-based supervision for local humanitarian workers following a crisis: A mixed-methods longitudinal study. by Gülşah Kurt, Fatema Almeamari, Hafsa El-Dardery, Aya Kardouh, Scarlett Wong, Michael McGrath, Louis Klein, Ammar Beetar, Salah Lekkeh, Ahmed El-Vecih, Wael Yasaki, Ceren Acarturk, Dusan Hadzi-Pavlovic, Zachary Steel, Simon Rosenbaum, Ruth Wells

“…Quantitative findings showed a significant reduction in psychological distress and an increase in compassion satisfaction during the post-earthquake supervision period (b = -0.18, error = 0.06, CrI = -0.29, -0.07, b = 0.26, error = 0.04, CrI = 0.18, 0.35, respectively). …”
Get full text

Intelligence data acquisition based on embedded system in Chinese cuisine cooker (CCICR V1.0) by Jianbao Zhang, Deyi Wang, Shiping Bao, Xin Chang, Yi Liang

“…The weighing module demonstrates a maximum relative error of only 0.288%, while the attitude sensor experiment shows an attitude information error of just 0.22°C. …”
Get full text

Convolutional neural network-based deep learning for landslide susceptibility mapping in the Bakhtegan watershed by Li Feng, Maosheng Zhang, Yimin Mao, Hao Liu, Chuanbo Yang, Ying Dong, Yaser A. Nanehkaran

“…The CNN model outperformed other classification approaches, achieving an accuracy of 95.76% and a precision of 95.11%. Additionally, error metrics confirmed its reliability, with a mean absolute error (MAE) of 0.11864, mean squared error (MSE) of 0.18796, and root mean squared error (RMSE) of 0.18632. …”
Get full text

Uncertainty-Guided Prediction Horizon of Phase-Resolved Ocean Wave Forecasting Under Data Sparsity: Experimental and Numerical Evaluation by Yuksel Rudy Alkarem, Kimberly Huguenard, Richard W. Kimball, Stephan T. Grilli

“…Results show under a 50% probability of upstream data loss, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>τ</mi></semantics></math></inline-formula>-trimmed TiDE model achieves a 46% reduction in error at the most upstream target, compared to 22% for LSTM. …”
Get full text

Methodology for Determining the Effective Thickness of the Cemented Layer of Steel by S. G. Sandomirski, A. L. Val’ko, S. P. Rudenko

“…The technique provides a significant reduction in the influence of the structural banding of the metal and the inevitable error in measuring hardness on the result of determining the hef . …”
Get full text

Model-Free Predictive Current Controller for Common Mode Voltage Stabilization by Finite odd Virtual Vector set by Majid Akbari, S. Alireza Davari, Reza Ghandehari, Freddy Flores-Bahamonde, Jose Rodriguez

“…The modulation modification-based methods inherently increase the steady-state error of the compared currents due to the reduced number of voltage vectors. …”
Get full text

Sidewalk thermal comfort in street canyon and role of pavements under perpendicular sun rays during summer by D. Jareemit, M. Srivanit

“…Field data validation showed acceptable errors (R² = 0.91, normalized mean square error = 0.17).FINDINGS: For an east-west-oriented deep street canyon with direct overhead sunlight in summer, low-albedo materials for road and sidewalk surfaces are recommended to enhance thermal comfort. …”
Get full text

Operational cost savings: Blockchain-driven back-office automation and syndicated loan growth in U.S. banks by Maksym Ivasenko, Serhiy Frolov, Mykhaylo Heyenko, Nataliia Kolodnenko, Viktoriia Datsenko

“…Using the Autoregressive Distributed Lag Model (ARDL) bounds testing approach, evidence of cointegration is found and long-run elasticity is estimated: a steady 1% increase in the volume of syndicated loans reduces the operating expense ratio by 0.147%, which means that almost doubling the volume of loans in the resulting sample leads to approximately 15% structural reduction in the burden on banks’ back offices. The associated error correction model gives a short-run elasticity of –0.276 (i.e., a 1% quarterly shock to loan volume reduces expenses by 0.276 p.p.) and a 47% correction rate to a new equilibrium. …”
Get full text

A Hybrid RBF-PSO Framework for Real-Time Temperature Field Prediction and Hydration Heat Parameter Inversion in Mass Concrete Structures by Shi Zheng, Lifen Lin, Wufeng Mao, Yanhong Wang, Jinsong Liu, Yili Yuan

“…The hybrid F₃, incorporating Dynamic Time Warping (DTW) for elastic time alignment and feature penalties for engineering-critical metrics, achieved superior performance with a 74% reduction in the prediction error (mean MAE = 1.0 °C) and <2% parameter identification errors, resolving the phase mismatches inherent in F₂ and avoiding F₁’s prohibitive computational costs (498 FEM calls). …”
Get full text

Learning Curves in Laparoscopic Training: Comparative Analysis of Two Training Models by Layla Settaf-Cherif, Adam Ostrowski, Anmol Khan, Katarzyna Malinowska, Oliwia Kwiatkowska, Łukasz Paszylk, Jan Adamowicz, Tomasz Drewa

“…Conclusions: Distributed training demonstrated superiority in skill retention, error reduction, and consistent task performance, especially in tasks requiring precision. …”
Get full text

Classical and Quantum Algorithms for Characters of the Symmetric Group by Sergey Bravyi, David Gosset, Vojtech Havlicek, Louis Schatzki

“…To assess classical hardness of these problems, we present a general reduction from strong simulation (computing a given probability) to weak simulation (sampling with a small error). …”
Get full text

Improving stock price forecasting with M-A-BiLSTM: a novel approach by Zihan Liu

“…Evaluated on stock datasets from Apple, ExxonMobil, Tesla, and Snapchat, our model outperforms existing deep learning methods, achieving a 15.91% reduction in Mean Squared Error (MSE) for Tesla and a 5.95% increase in R-squared (R2) for Apple. …”
Get full text

A Nonlinear Hybrid Algorithm for Retrieving Land Surface Temperatures From Chinese Atmospheric Environment Monitoring Satellite Thermal Infrared Data by Yichao Li, Hang Zhao, Kun Li, Jian Zeng, Qiongqiong Lan, Qijin Han, You Wu, Yonggang Qian

“…Cross-validation with moderate-resolution imaging spectroradiometer (MODIS) LST products showed that the hybrid algorithm outperforms the SW and TES algorithms in retrieving LST, achieving reductions in LST error of 0.43 and 0.16 K at the Qinghai Lake site, and 0.67 and 0.06 K at the Dunhuang site, respectively. …”
Get full text

Accurate Wideband RCS Estimation from Limited Field Data Using Infinitesimal Dipole Modeling with Compressive Sensing by Jeong-Wan Lee, Ye Chan Jung, Sung-Jun Yang

“…Furthermore, compared to approaches without compressive sensing, the method shows a 55.1% and a 75.5% reduction in error in averaged RCS for VV-pol and HH-pol, respectively. …”
Get full text

WDM-PON Free Space Optical (FSO) System Utilizing LDPC Decoding for Enhanced Cellular C-RAN Fronthaul Networks by Dokhyl AlQahtani, Fady El-Nahal

“…Our system transmits 20 Gbps, 16-QAM intensity-modulated orthogonal frequency-division multiplexing (OFDM) signals, achieving a substantial reduction in bit error rate (BER). Numerical results show that the proposed WDM-PON-FSO architecture, augmented with LDPC decoding, maintains reliable transmission over 2 km under strong turbulence conditions.…”
Get full text

Prediction of Automotive Wire Harness Aging Based on CNN-biLSTM-Attention by Kun Xia, Qi Zhu, Qingqing Yuan, Jingxia Wang

“…The results show the system achieves a mean absolute error (MAE) of 0.02806, with 32.50% and 62.06% error reduction compared to LSTM and Random Forest models, respectively, demonstrating effective prediction performance.…”
Get full text