An ensemble learning model to predict lymph node metastasis in early gastric cancer by Kaiqing Song, Jiaming Wu, Muchen Xu, Mengying Li, Yuqi Chen, Yi Zhang, Hong Chen, Caifeng Jiang

“…The optimal feature combination for each algorithm model was determined by combining the six highest weight features from all five models along with the independent risk factors. …”
Get full text

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

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

Nonlinear Stability Analysis of Shallow-Buried Bias Tunnel Based on Failure Mode Improvement by Wei Luo, Gequan Xiao, Zhi Tao, Jingyu Chen, Xi Lu, Haifeng Wang

“…Based on the improvement of the Karl Terzaghi failure mode for calculating the surrounding rock pressure of loose rock mass, combined with the upper bound theorem of limit analysis, the formula for calculating the surrounding rock pressure of shallow-buried tunnel in a slope area under a nonlinear failure criterion is derived. The SQP algorithm in MATLAB (R2022a) software was used to optimize the solution, and the influence of slope top load, buried depth ratio, cohesion, and axial tensile stress on the surrounding rock pressure and the failure mode of shallow-buried tunnel was analyzed through examples. …”
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

Occlusion mapping reveals the impact of flight and sensing parameters on vertical forest structure exploration with cost-effective UAV based laser scanning by Matthias Gassilloud, Barbara Koch, Anna Göritz

“…Using sensor position reconstruction and a ray tracing algorithm to quantify occlusion, we found that: (1) A larger sensor tilt angle up to 15° increased total occlusion, enhancing exploration in the upper canopy, while decreasing it below due to reduced canopy penetration. (2) Flying multiple azimuthal directions with a linear scanning mode reduced vertical occlusion by up to 15.0% due to improved coverage from diverse perspectives. (3) Lissajous scanning patterns resulted in 10.1% less vertical occlusion compared to linear patterns, underscoring the importance of additional viewing angles. …”
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

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

ASHM-YOLOv9: A Detection Model for Strawberry in Greenhouses at Multiple Stages by Yan Mo, Shaowei Bai, Wei Chen

“…Haar wavelet downsampling (HWD) was applied to optimize the Adaptive Downsampling module (Adown) of the initial model, thereby increasing the precision of object detection. …”
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

Development and validation of machine learning models to predict unplanned hospitalizations of patients with diabetes within the next 12 months by A. E. Andreychenko, A. D. Ermak, D. V. Gavrilov, R. E. Novitskiy, A. V. Gusev

“…The creation and inference of a machine learning model for predicting hospitalizations of patients with DM to an inpatient medical facility will make it possible to personalize the provision of medical care and optimize the load on the entire healthcare system.AIM: Development and validation of models for predicting unplanned hospitalizations of patients with diabetes due to the disease itself and its complications using machine learning algorithms and data from real clinical practice.MATERIALS AND METHODS: 170,141 depersonalized electronic health records of 23,742 diabetic patients were included in the study. …”
Get full text