Parts-per-quadrillion level gas molecule detection: CO-LITES sensing by Haiyue Sun, Shunda Qiao, Ying He, Xiaorong Sun, Yufei Ma

“…The obtained MPC, with a long optical path length (OPL) of 25.8 m and a small volume of 165.8 ml, is beneficial for increasing gas absorption while keeping the sensor compact. The novel QTF was structurally optimized to obtain low f 0 (~9.5 kHz) and modified by polydimethylsiloxane (PDMS) to reduce heat diffusion and enhance vibration amplitude. …”
Get full text

Development of an interpretable machine learning model based on CT radiomics for the prediction of post acute pancreatitis diabetes mellitus by Xiyao Wan, Yuan Wang, Ziyi Liu, Ziyan Liu, Shuting Zhong, Xiaohua Huang

“…The radiomics model was developed based on the optimal features retained after dimensionality reduction, utilizing the extreme gradient boosting (XGBoost) algorithm. …”
Get full text

Continuous Sign Language Recognition With Multi-Scale Spatial-Temporal Feature Enhancement by Zhen Wang, Dongyuan Li, Renhe Jiang, Manabu Okumura

“…Firstly, for better continuous frame information exploration, based on the optimal transport algorithm, we first propose a spatial resonance module, which is used to extract the global common spatial features of two adjacent frames along the frame sequence. …”
Get full text

Enhancing and Generalizing Position-Velocity Tracking in Imperfect <italic>mm</italic>Wave Systems Using a Low-Complexity Neural Network by Deeb Assad Tubail, Mohammed Zourob, Salama Ikki

“…To manage the computational demands of the training phase, we employ a low-complexity algorithm, the Extreme Learning Machine (ELM), which calculates weights and biases through closed-form solution, avoiding complex optimization processes. …”
Get full text

Evaluation of the quality of depression-related information on Chinese websites and video platforms: a cross-sectional comparative analysis by YueDong Chen, Jia Yin, YuKe Ding, ChangYu Wang, JiaXin Zhu, Lu Niu

“…In addition, the platform needs to prioritize optimizing the algorithm of recommendations and present real high-quality health information to the audience.…”
Get full text

Water quality prediction and carbon reduction mechanisms in wastewater treatment in Northwest cities using Random Forest Regression model by Jingjing Sun, Xin Guan, Xiaojun Sun, Xiaojing Cao, Yepei Tan, Jiarong Liao

“…For example, the R2 for COD prediction is 0.99954, while the R2 values for NH4 +-N, TP, and TN predictions reach 0.99989. …”
Get full text

Physicochemical profiling and ranking of parkinson’s disease drugs through QSPR and Fuzzy TOPSIS analysis by YuLan Chen, Abdul Rauf, Aqsa Shafique, Fairouz Tchier, Adnan Aslam, Keneni Abera Tola

“…Molecular structures were encoded as adjacency matrices using MATLAB 2017, and six Sombor index variants—computed via a custom Maple 2020 algorithm—served as topological descriptors for QSPR modeling. …”
Get full text

Fully-Gated Denoising Auto-Encoder for Artifact Reduction in ECG Signals by Ahmed Shaheen, Liang Ye, Chrishni Karunaratne, Tapio Seppänen

“…While our model performs best compared with other models tested in this study, more improvements are needed for optimal morphological preservation, especially in the presence of electrode motion artifacts.…”
Get full text

Utilization of Neural Network in the Diagnosis of Pes Planus and Pes Cavus with a Smartphone Camera by Samir Ghandour MD, Anton Lebedev BS, Wei Shao Tung BS, Konstantin Semianov BS, Artem Semyanov MS, Daniel Guss MD, MBA, Gregory R. Waryasz MD, John Y. Kwon MD, Christopher W. DiGiovanni MD, Soheil Ashkani-Esfahani MD, Lorena Bejarano-Pineda MD

“…Category: Midfoot/Forefoot Introduction/Purpose: Pes Planus (flatfoot) and Pes Cavus (high arch) are common foot deformities requiring clinical assessment and radiographic imaging for diagnosis and subsequent management. While effective, traditional diagnostic methods pose limitations such as cost, radiation exposure, and accessibility, particularly in underserved areas. …”
Get full text

Mechanical Properties and Fracture Surface Morphology of Quartz Sandstone Under Triaxial Shear by Zhinan LIN, Shihong FENG, Jiaquan WANG, Qiang ZHANG, Haifeng LONG

“…Also, based on the Delaunay point–cloud discretization algorithm, the failure fracture surface of quartz sandstone was reconstructed, and the variation characteristics of its potential contact part with the effective inclination threshold of the surface were analyzed. …”
Get full text

YOLO-RDM: Innovative Detection Methods for Eggplants and Stems in Complex Natural Environment by Qin Liu, Zhibin Zhou, Lu Xiong, Meilian Lu, Jingwen Ouyang

“…Finally, the loss function is substituted with the MPDIoU loss, optimizing the bounding box regression algorithm and enhancing convergence speed and regression accuracy. …”
Get full text

Determining Planetary Boundary Layer Height by Micro-pulse Lidar with Validation by UAV Measurements by Yueh-Chen Wang, Sheng-Hsiang Wang, Jasper R. Lewis, Shuenn-Chin Chang, Stephen M. Griffith

“…Furthermore, the Haar wavelet and the Hybrid image processing can detect the PBL development comparably well, but both methods are dependent on their initial conditions and optimized algorithm settings. In addition, the accompanying UAV observations are conclusively shown to have a high degree of efficacy for validating the lidar data. …”
Get full text

Predicting the permeability and compressive strength of pervious concrete using a stacking ensemble machine learning approach by Fan Yu, Wei Chu, Rui Zhang, Zhang Gao, Yunan Yang

“…Firstly, six independent models, the multiple linear regression and the Stacking algorithm were applied to construct the ensemble model. …”
Get full text

Mechanistic insights into synergistic effects using coupled PK-PD modeling by Jinzhou Sun, Qianqian Chen, Chumeng Zhuang, Xiaohong Li, Li Yu, Weifeng Jin

“…The model also showed that CA had a larger apparent volume of distribution and clearance in rats, while HSYA had a shorter mean retention time and elimination half-life. …”
Get full text

Data-driven robust outpatient physician scheduling with medical visiting information by Qingyun He, Shuqun Shen, Zhiyu Lv, Shixin Yang

“…In this study, we develop a data-driven optimization framework for a mid-term period spanning several weeks within the outpatient department of a dermatology hospital. …”
Get full text

Controversies in treating nutcracker syndrome by Vitorio Perić, Thomas Ferenc, Tomica Bratić, Jana Bebek, Ivan Antun Mašić, Filip Ferega, Vid Vrčić, Danko Milošević, Helga Sertić Milić, Vinko Vidjak

“…Moreover, due to the lack of standardized treatment guidelines, the optimal management of anterior NCS remains a topic of debate. …”
Get full text

Proposal of Low-Speed Sensorless Control of IPMSM Using a Two-Interval Six-Segment High-Frequency Injection Method with DC-Link Current Sensing by Daniel Konvicny, Pavol Makys, Alex Franko

“…The dual-period structure, termed the two-interval six-segment high-frequency injection, allows for more precise current measurement during the signal injection period while maintaining optimal motor control during the field-oriented control period. …”
Get full text

Externally bonded reinforcement side extended (EBRSE) technique to postpone debonding of FRP laminates in strengthened concrete elements by Mehdi Aghabagloo, Laura Carreras, Cristina Barris, Alba Codina, Marta Baena

“…Additionally, a numerical approach was applied, combining the finite difference method with a metaheuristic optimization algorithm, to derive the bond-slip law governing the constitutive behavior of both systems. …”
Get full text

Potential effects of climate change on the threatened Malagasy poison frogs: A multispecies approach by Albert Carné, David R. Vieites, Neftalí Sillero

“…Range shifts tracking their optimal niche conditions are expected for nearly all species, but the receptor areas are not always suitable. …”
Get full text

Arrears behavior prediction of power users based on BP neural network and multi-scale feature learning: a refined risk assessment framework by Liang Yu, Yuanshen Hong, Hua Lin, Xu Jiang, Ziming Song

“…The BP neural network algorithm adjusts weights to minimize prediction errors, while multi-scale feature learning captures the diversity and regularity of user behavior by extracting data from various time dimensions, such as daily, weekly, and monthly intervals. …”
Get full text