Recurrent neural networks for aerodynamic parameter estimation with Lyapunov stability analysis by Sara Mohan George, S. S. Selvi, J. R. Raol

“…RNN-Gradient computes direct gradients and applies non-linearity to the error. Simulated flight data is employed in MATLAB implementations to assess estimation results, considering both performance metrics and computation time. …”
Get full text

Evaluating Sparse Inertial Measurement Unit Configurations for Inferring Treadmill Running Motion by Mackenzie N. Pitts, Megan R. Ebers, Cristine E. Agresta, Katherine M. Steele

“…We varied the type of input to reflect experimental parameters that are important in running studies—sensor location, sensor type, sampling rate, and running speed—and compared the error of inferred signals from each input type. Sensor location and type did not impact SHRED inference accuracy, while decreasing the sampling rate affected the accuracy of ankle measurements. …”
Get full text

Sample Size for Agreement Studies on Quantitative Variables by Bruno Mario Cesana, Paolo Antonelli

“…We generalized a restricted null hypothesis that constitutes a particular case in finding the supremum of the probability of rejecting the equivalence under the null hypothesis (H0) and which, obviously, limits its applicability. Particularly, we devise and propose an exact procedure for calculating the sample sizes for individual equivalence, as an expression of the agreement between two measurement methods, by using a size a test (that is, with adequate control of Type I error), based on the non-central bivariate t distribution with correlation equal to 1 and to the related functions for calculating a and 1-b probabilities. …”
Get full text

Direct 3-D printing of complex optical phantoms using dynamic filament mixing by Rahul Ragunathan, Miguel Mireles, Edward Xu, Aiden Lewis, Morris Vanegas, Qianqian Fang

“…We have characterized the printed phantoms and observed an average error between 12%–15% compared to our linear-mixing model-predicted values. …”
Get full text

Temporal-Sequence Offline Reinforcement Learning for Transition Control of a Novel Tilt-Wing Unmanned Aerial Vehicle by Shiji Jin, Wenjie Zhao

“…The policy is further constrained within an offline dataset collected via hardware-in-the-loop simulation using a variational autoencoder, and a sequence-level prediction mechanism is introduced to ensure temporal consistency across action trajectories, thereby mitigating extrapolation error while preserving data fidelity. Experimental results demonstrate that TSCQ significantly outperforms gain scheduling, Model Predictive Control (MPC), and Batch-Constrained Q-learning (BCQ), reducing the RMSE of pitch angle by up to 53.3% and vertical velocity RMSE by approximately 33%. …”
Get full text

Histopathology Grading of Breast Cancer Using Visual Geometry Group Method by A. Santika Hyperastuty, Fachruddin Ari Setiawan, Dio Alif Pradana, Rahma Ajeng Puspitasari, Lailatul Inayah, Eko Winarti

“…Although histopathological image analysis is still the gold standard for evaluating malignancy, it is prone to inconsistencies and human error. The objective of this research is to use the Visual Geometry Group's (VGG16) deep learning technique to automate the evaluation of breast cancer histology. …”
Get full text

Influence of Rice Husk Ash on Crystalline Phases and Mechanical Characteristics of Sustainable Bricks by F. Booth, M.B. Carranza, G. Novak, N. Okulik, A. Mocciaro, N. Rendtorff

“…Several models were analyzed to predict the elastic modulus, and the DEM model provided the best predictions, with a relative error of 1.43% for 15% RHA. The analysis of mechanical properties of porosity was conducted using various theoretical models, which allowed for a better understanding of the relationship between the porous structure of the bricks and their mechanical behavior. …”
Get full text

Time-Series Interval Forecasting with Dual-Output Monte Carlo Dropout: A Case Study on Durian Exports by Unyamanee Kummaraka, Patchanok Srisuradetchai

“…The dual-output architecture employs a custom loss function, combining mean squared error with Softplus-derived predictive variance, ensuring non-negative variance values. …”
Get full text

Logging Components Extraction Method and Anisotropy Recognition Based on 3D Holographic LWD Instrument by Shuyu Guo, Jie Wang, Xiangyu Xing, Jiaqi Xiao, Xiao Liu

“…By employing the same inversion method, the anisotropy coefficients calculated from the new signal will be more accurate than those derived from traditional signals, with the developed signal inversion average error controllable within 0.01.…”
Get full text

Improved Remote Photoplethysmography Using Machine Learning-Based Filter Bank by Jukyung Lee, Hyosung Joo, Jihwan Woo

“…., resulting in a mean absolute error of 2.5 beats per minute) higher accuracy than those of conventional methods. …”
Get full text

Improving Diacritical Arabic Speech Recognition: Transformer-Based Models with Transfer Learning and Hybrid Data Augmentation by Haifa Alaqel, Khalil El Hindi

“…Data augmentation techniques, including volume adjustment, pitch shift, speed alteration, and hybrid strategies, further mitigate data limitations, significantly reducing word error rates (WER). Our methods achieve a WER of 12.17%, outperforming traditional ASR systems and setting a new benchmark for DA ASR. …”
Get full text

Synergistic detection of E. coli using ultrathin film of functionalized graphene with impedance spectroscopy and machine learning by Amrit Kumar, Shweta Mishra, R. K. Gupta, V. Manjuladevi

“…The integration of ML significantly improves detection accuracy, reduces analysis time, and minimizes human error, paving the way for scalable, cost-effective diagnostic tools for diverse biological and environmental applications.…”
Get full text

Measuring the Dimension Accuracy of Products Created by 3D Printing Technology with the Designed Measuring System by Martin Pollák, Dominik Sabol, Karol Goryl

“…The result is the design of a measurement scanning system with precise motion control through a connected servo drive intended for industrial applications of object error detection and measurement of dimension accuracy.…”
Get full text

Stress-Strength Reliability of Two-Parameter Exponential Distribution Based on Progres- sively Type-II Censored Data by Sajad Rostamian

“…Methods: The maximum likelihood and the best linear unbiased estimates of  are obtained, and the Bayes estimates of  are computed under the squared error, linear-exponential, and Stein loss functions. …”
Get full text

A Multiparameter Coupled Prediction Model for Annular Cuttings Bed Height in Horizontal Wells by Zongyu Lu, Baocheng Wu, Jiangang Shi, Chuanming Xi, Kai Wei

“…The model provides convenience for engineering applications.…”
Get full text

Improved Ellipsoidal Intersection Method for 2D Data Fusion by Muhammed Mert Ulupinar, Gokhan Soysal

“…Monte Carlo simulations under various correlation cases demonstrate that Improved Ellipsoidal Intersection method calculates lower root mean square error compared to existing techniques, particularly in high-correlation cases. …”
Get full text

Video Analysis and Frame Prediction Based on Improved Object Detection and ConvGRU by Xijuan Wang, Ru Chen

“…The PSNR, structural similarity, and interpolation error of the frame prediction model were superior to existing advanced models. …”
Get full text

Precision-and-flexibility optimized wearable dual-channel EEG acquisition system by Fugui Qi, Chuantao Li, Yufei Jing, Fuming Chen

“…The classical experiments show that when the input voltage of the system is 10 μV–10 mV, the short-circuit noise is lower than 1.5 μV, the output error is smaller than 10%, the input impedance can reach 680 MΩ, and the dry electrode can obtain clear α waves in areas with hair. …”
Get full text

LITERATURE REVIEW: ADVANTAGES AND DISADVANTAGES OF BLACK BOX AND WHITE BOX TESTING METHODS by Asri Maspupah

“…Software testing methods play a crucial role in ensuring the quality, security, and performance of applications. The two main approaches often used are black box and white box testing. …”
Get full text

Artificial intelligence orchestration for text-based ultrasonic simulation via self-review by multi-large language model agents by Soyeon Kim, Yonggyun Yu, Hogeon Seo

“…In particular, when vectorized output lengths deviate from the standard, we regenerate outputs using multiple LLM agents, reducing the scenario generation error rate from 23.89 to 1.48% and enhancing reliability significantly. …”
Get full text