A Data-Driven Approach Based on Deep Neural Network Regression for Predicting the Compressive Strength of Steel Fiber Reinforced Concrete by Nhat-Duc Hoang, Van-Duc Tran

“…Experimental results show that the L1 regularization helps achieve the most desired performance, with a coefficient of determination (R2) of roughly 0.96. Notably, an asymmetric loss function is used along with Nadam to decrease the percentage of overestimated cases from 50.83% to 27.08%. …”
Get full text

Estimativa das temperaturas máximas e mínimas do ar para a região do Circuito das Frutas, SP Estimation of maximum and minimum air temperatures for the "Circuito das Frutas" region... by Ludmila Bardin, Mário J. Pedro Júnior, Jener F. L. de Moraes

“…Also, maps with the spacial variability of the maximum and minimum mean monthly and annual temperatures are presented for the region.…”
Get full text

The Effect of Vocal Rehabilitation on Patients with Vocal Cord Paralysis by Mila Bunijevac, Andrijana Mikić, Maša Đurišić

“…Measures of central tendency, measures of variability, one-factor analysis of variance, t-test for independent samples, chi-square test and interclass correlation coefficient were applied in statistical data processing. …”
Get full text

Arterial hypertension and myocardial electric heterogeneity in patients with coronary heart disease by L. A. Leshchinsky, B. L. Multanovsky, A. G. Petrov, S. B. Ponomarev

“…Myocardial electric heterogeneity, especially in PS, correlated with left ventricular (LV) hypertrophy, LV diastolic function, and the overall functional status of cardiovascular system. …”
Get full text

Rapid global fitting of large fluorescence lifetime imaging microscopy datasets. by Sean C Warren, Anca Margineanu, Dominic Alibhai, Douglas J Kelly, Clifford Talbot, Yuriy Alexandrov, Ian Munro, Matilda Katan, Chris Dunsby, Paul M W French

“…This approach is often considered to be prohibitively slow and/or computationally expensive but we present here a computationally efficient global analysis algorithm for the analysis of time-correlated single photon counting (TCSPC) or time-gated FLIM data based on variable projection. …”
Get full text

Explainable AI-driven assessment of hydro climatic interactions shaping river discharge dynamics in a monsoonal basin by Prashant Parasar, Akhouri Pramod Krishna

“…The main findings of this study are (1) KAN demonstrated high predictive performance with root mean squared error (RMSE) values ranging from 42.7 to 58.3 m3/s, Nash–Sutcliffe efficiency (NSE) between 0.80 and 0.87, mean absolute error (MAE) between 28.9 to 52.7 and R2 values between 0.84 and 0.90 across stations. (2) SHAP based feature contribution analysis identified Relative humidity (hurs), specific humidity (huss), and temperature (tas) as key predictors, while (pr) showed limited contribution due to spatial inherent inconsistencies in GCM precipitation data. (3) The bootstrapped SHAP distributions highlighted substantial variability in feature importance, particularly for humidity variables, revealing station specific uncertainty patterns in model interpretation. (4) The KAN framework results indicate strong temporal alignment and physical realism, confirming KAN’s robustness in capturing seasonal discharge dynamics and extreme flow events under monsoon influence environments. (5) In this study KAN with SHAP (SHapley additive exPlanations) is implemented for hydrological modeling under monsoon-influenced and data-limited regions such as SRB, offering improved accuracy, functional precision and efficiency compared to traditional models. …”
Get full text

Exploring restoration efforts from a social lens: statistical models reveal relationships between salmon habitat restoration efforts and ecological and social characteristics of th... by Brittany D King, Robert Fonner

“…We specified statistical models to explain the variation in the number of restoration worksites undertaken in subwatersheds as a function of environmental and social variables. Using a common set of explanatory variables, we fit four models to examine the distribution of worksites associated with particular types of restoration actions (instream, riparian, land acquisition, and fish passage) and a fifth model to examine the distribution of all aquatic-based restoration worksites across action types. …”
Get full text

Evaluation of the Characteristics of Short Acquisition Times Using the Clear Adaptive Low-Noise Method and Advanced Intelligent Clear-IQ Engine by Ryosuke Ogasawara, Akiko Irikawa, Yuya Watanabe, Tomoya Harada, Shota Hosokawa, Kazuya Koyama, Keisuke Tsuda, Toru Kimura, Koichi Okuda, Yasuyuki Takahashi

“…The images were evaluated based on the coefficient of variation, recovery coefficient, % background variability (N_10mm), % contrast-to-% background variability ratio (Q_H10mm/N_10mm), and contrast-to-noise ratio. …”
Get full text

Optimization of the Fc-fusion protein refolding method produced from the bacterial expression system by P. S. Astrelina, S. A. Ishchuk, A. V. Kabanova, R. V. Drai

“…Increasing the buffer pH led to improved refolding efficiency.…”
Get full text

The Hydrodynamic Performance of a Vertical-Axis Hydro Turbine with an Airfoil Designed Based on the Outline of a Sailfish by Aiping Wu, Shiming Wang, Chenglin Ding

“…Transient numerical simulations employing dynamic mesh techniques and user-defined functions within the Fluent environment were conducted to analyze rotor interactions. …”
Get full text

A Comparative Study of Deep Reinforcement Learning Algorithms for Urban Autonomous Driving: Addressing the Geographic and Regulatory Challenges in CARLA by Yechan Park, Woomin Jun, Sungjin Lee

“…To evaluate the adaptability of each algorithm to geographical variability and complex traffic laws, scenario-specific reward and penalty functions were carefully designed and incorporated. …”
Get full text

Finite Difference/Fractional Pertrov–Galerkin Spectral Method for Linear Time-Space Fractional Reaction–Diffusion Equation by Mahmoud A. Zaky

“…The Pertrov–Galerkin spectral method is adapted using non-smooth generalized basis functions to discretize the spatial variable, and the L1 scheme on a non-uniform graded mesh is used to approximate the Caputo fractional derivative. …”
Get full text

Frequency Stability Analysis Based on Full State Model in Autonomous-Synchronization Voltage Source Interfaced Power System by Zhenyao LI, Deqiang GAN, Moude LUAN, Guoqing HE

“…Then, the parameters of the autonomous-synchronization voltage source model are compared with those of the synchronous machine model, and it is proved that the function of the governor is equivalent to increasing the system damping, which can reduce the steady-state error of the system frequency after being disturbed. …”
Get full text

MANAGING FRAUD IN CONTEMPORARY BUSINESS ENVIRONMENT, THE ROLE OF INFORMATION SECURITY MANAGEMENT: A STUDY OF QUOTED DEPOSIT MONEY BANKS (DMBs) IN NIGERIA by Onajero Kensington OHWO

“…Cronbach’s alpha reliability coefficients for the constructs ranged from 0.864 to 0.952. …”

Strain-specific properties and T cells regulate the susceptibility to papilloma induction by Mus musculus papillomavirus 1. by Alessandra Handisurya, Patricia M Day, Cynthia D Thompson, Michael Bonelli, Douglas R Lowy, John T Schiller

“…Thus, the functional cooperation of CD4+ and CD8+ T cells is required to protect this strain. …”
Get full text

Flexible imputation toolkit for electronic health records by Alireza Vafaei Sadr, Jiang Li, Wenke Hwang, Mohammed Yeasin, Ming Wang, Harold Lehmann, Ramin Zand, Vida Abedi

“…Pympute’s core algorithm, Flexible, intelligently selects the optimal imputation method for each variable based on its characteristics. Pympute offers a comprehensive suite of functionalities. …”
Get full text

Application of machine learning and neural network models based on experimental evaluation of dissimilar resistance spot-welded joints between grade 2 titanium alloy and AISI 304 s... by Marwan T. Mezher, Alejandro Pereira, Rusul Ahmed Shakir, Tomasz Trzepieciński

“…The best prediction model was found to be the ANN model when training the conjugate gradient with the Polak-Ribiere updates (Traincgp) training function with the hyperbolic tangent sigmoid transfer function (Tansig) with the mean squared error (MSE) and correlation coefficient (R2) values recorded as 0.01886 and 0.94973, respectively. …”
Get full text

Artificial Neural Network (ANN) Modeling of Plasma and Ultrasound-assisted Air Drying of Cumin Seeds by M. Namjoo, M. Moradi, M. A. Nematollahi, H. Golbakhshi

“…Therefore, the wavelet-based neural network (WNN), the multilayer perceptron neural network (MLPNN), and the radial-basis function neural network (RBFNN), as three well-known artificial neural networks models, were used to map the inputs and output data and the results were compared with the Multiple Quadratic Regression (MQR) analysis. …”
Get full text

Reconstructing Equatorial Electron Flux Measurements From Low‐Earth‐Orbit: A Conjunction Based Framework by D. L. Stumbaugh, J. Bortnik, S. G. Claudepierre

“…For each conjunction, we fit the equatorial pitch angle distribution (PAD) parameterized by the function JD=C⋅sinNα. The resulting conjunction data set contains the POES electron flux measurements, L and magnetic local time coordinates, geomagnetic activity Auroral Electrojet index, and C and N coefficients from the PAD fit for each conjunction. …”
Get full text

RP-18 HPLC Analysis of Drugs’ Ability to Cross the Blood-Brain Barrier by Anna W. Sobańska, Adam Hekner, Elżbieta Brzezińska

“…On the other hand, discriminant function analyses involving log k and (log k)/PSA as discriminating variables separated the CNS+ and CNS− compounds with the success rate ca. 90%. …”
Get full text