Personalized machine learning models for noninvasive hypoglycemia detection in people with type 1 diabetes using a smartwatch: Insights into feature importance during waking and sl... by Yasmine M Mohamed, José Mancera, Andreas Brandenberg, Stefan Fischli, Michael M Havranek

“…Machine learning (ML) models were built using a tree-based ensemble algorithm to detect hypoglycemic events registered by CGMS. …”
Get full text

Neighborhood socioeconomic inequality and sarcopenia in community-dwelling older adults: a cross-sectional study by Xiangyu Zhai, Doris S. F. Yu

“…Background Individual-level socioeconomic characteristics are known to predict sarcopenia, but little is known about how the neighborhood context shapes this debilitating problem among older adults. …”
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

A Framework to Calibrate Ecosystem Demography Models Within Earth System Models Using Parallel Surrogate Global Optimization by Yanyan Cheng, Wei Xia, Matteo Detto, Christine A. Shoemaker

“…The calibration for tropical forests has important implications for predicting land‐atmospheric interactions and responses of tropical forests to environmental changes.…”
Get full text

Identification of potential diagnostic markers and molecular mechanisms of asthma and ulcerative colitis based on bioinformatics and machine learning by Chenxuyu Zhang, Chenxuyu Zhang, Zheng Luo, Liang Ji

“…Gene Set Enrichment Analysis (GSEA) explored pathway alterations, while immune infiltration patterns were analyzed using the CIBERSORT algorithm. Molecular docking (MD) was performed to predict therapeutic compounds, followed by molecular dynamics simulations on the top-ranked docked complex to assess its binding stability.ResultsA total of 41 shared genes were identified, linked to inflammatory and immune pathways, including TNF, IL-17, and chemokine signaling. …”
Get full text

Smart indoor monitoring for disabled individuals using an ensemble of deep learning models in an IoT environment by Faisal S. Alsubaei, Abdulrahman A. Alshdadi, Mohammed Rizwanullah

“…Besides, the Improved Osprey Optimization Algorithm (IOOA)-based feature selection is employed to classify the most relevant features, enhancing the efficiency of the system by reducing dimensionality. …”
Get full text

Convolutional neural network for maxillary sinus segmentation based on the U-Net architecture at different planes in the Chinese population: a semantic segmentation study by Jiayi Chen

“…The best model was retained for predicting MS in the test set and calculating the model parameters. …”
Get full text

Analyzing the applicability of psychometric QoE modeling for projection-based point cloud video quality assessment by Sam Van Damme, Jeroen van der Hooft, Filip De Turck, Maria Torres Vega

“…Thus, real-time quality monitoring and prediction mechanisms are key to allow for fast countermeasures in case of QoE decrease. …”
Get full text

Mathematical solutions for coupled nonlinear equations based on bioconvection in MHD Casson nanofluid flow by Khalil Ur Rehman, Nosheen Fatima, Wasfi Shatanawi, Nabeela Kousar

“…ODEs were then numerically solved in MATLAB software using the built-in solver bvp4c algorithm. We established an artificial neural network (ANN) model, incorporating Tan-Sig and Purelin transfer functions, to enhance the accuracy of predicting skin friction coefficient (SFC) values along the surface. …”
Get full text

Analysis and Application of Grey-Markov Chain Model in Tax Forecasting by Huidi Zhang, Yimao Chen

“…The key to correct tax forecasting is the choice of forecasting algorithm. Traditional tax forecasting methods, such as factor scoring method, factor regression method, and system adjustment method, have a certain guiding role in actual work, but there are still many shortcomings, such as the limitation from the distribution and size of sample data and difficulty of grasping the nonlinear phenomena in economic system. …”
Get full text

Comprehensive analysis of IRF8-related genes and immune characteristics in lupus nephritis by Zhibin Yu, Chenghui Zheng, Yilun Wang

“…To bridge our findings with potential therapeutic implications, we used the drug-gene interaction database to predict drugs targeting the identified genes.ResultsTwenty co-differentially expressed genes (DEGs) were identified, with IRF8 exhibiting significant expression differences and potential as a biomarker. …”
Get full text

Exploration of the Prognostic Markers of Multiple Myeloma Based on Cuproptosis‐Related Genes by Xiao‐Han Gao, Jun Yuan, Xiao‐Xia Zhang, Rui‐Cang Wang, Jie Yang, Yan Li, Jie Li

“…Conclusion As a result of this investigation, a set of six biomarkers associated with cuproptosis (PARP1, EDEM3, SEC23A, RSL24D1, TTC37, and SRP72) were screened to provide a basis for predicting the prognosis of MM.…”
Get full text

Graph-Based Radiomics Feature Extraction From 2D Retina Images by Ofelio Jorreia, Nuno Goncalves, Rui Cortesao

“…The trained model achieved an accuracy of 94.95% in correctly identifying bifurcation points. Based on predicted bifurcation points and blood vessel segments, we use the Graph-Based Radiomics Feature Extraction Algorithm (Graph-BRFExtract) to extract the adjacency matrix. …”
Get full text

Radar versus optical: The impact of cloud cover when mapping seasonal surface water for health applications in monsoon-affected India. by Gowri Uday, Bethan V Purse, Douglas I Kelley, Abi Vanak, Abhishek Samrat, Anusha Chaudhary, Mujeeb Rahman, France F Gerard

“…Backscatter thresholds were identified manually, and our Bayesian algorithm found these thresholds were very likely (>97%). …”
Get full text

Application of Internet marketing tools for management decision-making by logistics enterprises by O.A., T.O., O.P., H.Yu.

“…The direct influence of the size of the advertising budget on the predicted indicators of targeted advertising has been proven. …”
Get full text

GEOECOLOGICAL DIAGNOSTICS OF THE REGIONS IN THE CENTRALBLACK SOIL REGION by S. A. Kurolap, N. V. Yakovenko, V. I. Fedotov, V. B. Mikhno, L. N. Kostyleva

“…The authors propose an algorithm to perform geoecological diagnostics of the large region. …”
Get full text

Comprehensive bioinformatics analysis uncover molecular pathways shared between osteoarthritis and atherosclerosis by Yingchao Jin, Hua Zhang

“…In addition, the immune infiltration of OA and AS was analyzed and compared based on the ssGSEA algorithm, and the correlation between hub genes and infiltrating immune cells was evaluated in OA and AS, respectively. …”
Get full text

Forecasting water quality indices using generalized ridge model, regularized weighted kernel ridge model, and optimized multivariate variational mode decomposition by Marjan Kordani, Mohsen Bagheritabar, Iman Ahmadianfar, Arvin Samadi-Koucheksaraee

“…For this reason, the suggested OMVMD-GRKR model serves as a valuable framework for predicting IWQI parameters.…”
Get full text

ISEE: Industrial Internet of Things perception in solar cell detection based on edge computing by Meiya Dong, Jumin Zhao, Deng-ao Li, Biaokai Zhu, Sihai An, Zhaobin Liu

“…Then it uses the powerful neural network processing unit module of the edge computing unit, combined with the convolutional neural network algorithm transplanted to the edge, to detect the defects of solar panels in real time. …”
Get full text

The Application of Artificial Digital Models in X-Ray Computed Tomography (CT) of the Core in Solving the Problem of Binarization of the Void Space of Reservoir Rocks by O. A. Melkishev, Y. V. Savitsky, S. V. Galkin

“…The use of the proposed model for predicting boundary values on obtained tomograms demonstrated a high degree of consistency with actual data.…”
Get full text