-
15901
Energy-efficient outdoor air flow control in ventilation systems
Published 2021-06-01“…The expected microclimate parameters predicted assessment in real time opens up the possibility of using such elements and algorithms for controlling the ventilation and air conditioning system, which provide the required air quality with minimal energy consumption. …”
Get full text
Article -
15902
RETRACTED ARTICLE: Construction and validation of a machine learning-based immune-related prognostic model for glioma
Published 2024-10-01“…Subsequently, a consensus prognostic model was developed through the application of machine learning algorithms. In which the Lasso + plsRcox algorithm demonstrated the best predictive performance. …”
Get full text
Article -
15903
Short- to Medium-Term Weather Forecast Skill of the AI-Based Pangu-Weather Model Using Automatic Weather Stations in China
Published 2025-01-01“…Furthermore, the iteration precision of Pangu’s 1 h forecast model is significantly lower than that of the other models, but this discrepancy in precision may not be prominently reflected in Pangu’s actual forecasting process due to the greedy algorithm employed. In the case study on typhoon forecasting, Pangu, along with FuXi and FengWu, demonstrates comparable performance in predicting Bebinca’s track compared to ECMWF and outperforms GFS in its track predictions. …”
Get full text
Article -
15904
Continuously relapsing (for two years) course of diarrheal variant of IBS (<i>Clinical case</i>)
Published 2013-10-01“…By the example of clinical case to show modern algorithm of diagnostics and choice of pathogenically proved treatment for patient with continuously relapsing course of irritable bowel syndrome (IBS).Key points. …”
Get full text
Article -
15905
A Centralized Multi-Agent DRL-Based Trajectory Control Strategy for Unmanned Aerial Vehicle-Enabled Wireless Communications
Published 2024-01-01“…Numerical results demonstrate that the proposed method significantly enhances both communication coverage and network throughput in comparison to the base line algorithms.…”
Get full text
Article -
15906
MATHEMATICAL RATIONALE FOR CREATING AN APPLICATION FOR CONDUCTING RANDOM MEETINGS «COFFEE BREAK»
Published 2024-12-01“…Specifically, the study has defined the concept of the CoffeeBreak mobile application, outlined the system model with detailed subsystems and environment interactions, and formulated mathematical models to form the basis of the candidate selection algorithm. The model ensures that users are matched in a way that promotes engagement, as each participant can be assured that their matched partner is equally motivated for the encounter. …”
Get full text
Article -
15907
Integrated Analysis and Validation of Ferroptosis-Related Genes Associated with Ischemia/Reperfusion Injury in Lung Transplantation
Published 2025-01-01“…Weighted gene co-expression network analysis (WGCNA) was used to identify module genes, and overlapping genes were further analyzed using two machine learning algorithms. The CIBERSORT algorithm was applied to assess immune cell infiltration, while Mendelian randomization (MR) analysis was used to investigate causal relationships between candidate genes and PGD. …”
Get full text
Article -
15908
Complex Cloud-Sea Background Simulation for Space-Based Infrared Payload Digital Twin
Published 2025-01-01“…Static cloud-sea scenes are generated using Qilu-2 and New Technology satellite images, while dynamic scenarios are simulated with our iterative fractal dimension optimization algorithm. Next, we propose a high-precision infrared cloud-sea simulation method based on these simulate scenarios. …”
Get full text
Article -
15909
IMU Sensor-Based Worker Behavior Recognition and Construction of a Cyber–Physical System Environment
Published 2025-01-01“…The collected sensor data are preprocessed using Kalman and extended Kalman filters, among others, and an algorithm was proposed to evaluate workers’ safety status and update health-related data in real time. …”
Get full text
Article -
15910
Identification of microsatellite loci according to BAC sequencing data and their physical mapping to the bread wheat 5B chromosome
Published 2016-01-01“…The assembly characteristics (N50 = 4 136 bp) are comparable to the recently obtained data for wheat and relative species and acceptable for identification of microsatellite loci. An algorithm utilizing the properties of complexity decompositions in he sliding-window mode was used to detect DNA sequences with a repeat unit of 2–4 bp. …”
Get full text
Article -
15911
Identification of Parkinson’s disease using MRI and genetic data from the PPMI cohort: an improved machine learning fusion approach
Published 2025-02-01“…Two multi-modal fusion strategies were used: feature-level fusion, where we employed a hybrid feature selection algorithm combining Fisher discriminant analysis, an ensemble Lasso (EnLasso) method, and partial least squares (PLS) regression to identify and integrate the most informative features from neuroimaging and genetic data; and decision-level fusion, where we developed an adaptive ensemble stacking (AE_Stacking) model to synergistically integrate the predictions from multiple base classifiers trained on individual modalities.ResultsThe AE_Stacking model achieving the highest average balanced accuracy of 95.36% and an area under the receiver operating characteristic curve (AUC) of 0.974, significantly outperforming feature-level fusion and single-modal models (p < 0.05). …”
Get full text
Article -
15912
Optimasi Klasifikasi Sentimen Komentar Pengguna Game Bergerak Menggunakan Svm, Grid Search Dan Kombinasi N-Gram
Published 2024-08-01“…In this study, sentiment classification was performed using the Support Vector Machine (SVM) algorithm, employing N-Gram techniques for feature selection. …”
Get full text
Article -
15913
Assessing the Impact of Social Media Usage and Performance of the Selected Small and Medium Businesses in Ntungamo District.
Published 2024“…The study findings further assessed the challenges encountered when small business owner-managers in the Ntungamo district use social media in their business and these included time constraints, limited expertise, Negative feedback and online reputation management, and keeping up with algorithm changes. Based on the challenges, the study findings further examined the solutions to the challenges and these were; Monitoring social media channels regularly and responding promptly and professionally to customer feedback, whether positive or negative, Investing in social media training,g and Prioritizing social media management in the study area.…”
Get full text
Thesis -
15914
Principles of effective out-patient diagnostics of diffuse liver diseases
Published 2014-11-01“…In the case of abnormal liver tests preliminary diagnosis was determined according to certain algorithm and these patients were recruited for further investigation and specifications of diagnosis in department of hepatology, University clinical hospital N 2, State educational government-financed institution of higher professional education «Sechenov First Moscow state medical university». …”
Get full text
Article -
15915
Nutritional Profiles and Factors Associated with the Intake of Certain Food Types in Patients Undergoing Maxillofacial Prosthetic Rehabilitation: A Cross-Sectional Study
Published 2025-01-01“…Patients’ nutrient intakes were compared to the reference values from the BDHQ ad hoc computer algorithm based on the 2015 National Health and Nutrition Survey in Japan. …”
Get full text
Article -
15916
Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders
Published 2025-01-01“…Furthermore, the tracking accuracy was assessed through a comparative analysis with a validated semi-automatic algorithm (Movidea), obtaining a Pearson correlation (R) of 93.96% (88.61–96.60%) and a root mean square error (RMSE) of 9.52 pixels (7.29–12.37). …”
Get full text
Article -
15917
Identification of serum tRNA-derived small RNAs biosignature for diagnosis of tuberculosis
Published 2025-12-01“…By utilizing cross-validation with a random forest algorithm approach, the training cohort achieved a sensitivity of 100% and specificity of 100%. …”
Get full text
Article -
15918
Glu4: An open-source package for real-time forecasting and alerting post-bariatric hypoglycemia based on continuous glucose monitoring
Published 2025-12-01“…Methods: Glu4 employs a two-step approach to predict PBH. A run-to-run algorithm forecasts future glucose levels using past CGM data, identifying potential hypoglycemic events 30 min in advance. …”
Get full text
Article -
15919
Assessment of access and outcomes of kidney transplantation through the reforms of the Swiss organ allocation system
Published 2025-01-01“…Since the introduction of the transplantation law in 2007, which imposed organ allocation on a national level, the algorithm has been optimized. Initially based on waiting time, HLA compatibility, and crossmatch performed by cell complement-dependent cytotoxicity techniques, the system moved in 2012 to a score including HLA compatibility, waiting time, anti-HLA antibodies detected by the Luminex® technology, and a virtual crossmatch. …”
Get full text
Article -
15920
Soil organic carbon contents and their major influencing factors in mangrove tidal flats: a comparison between estuarine and non-estuarine areas
Published 2025-02-01“…We compared the SOC and soil physicochemical properties between estuarine and non-estuarine mangrove tidal flats. The Random Forest algorithm was employed to identify the main influencing factors affecting SOC. …”
Get full text
Article