Application of Even Span Greenhouse Solar Dryer (ESGSD) for drying Persian shallot; Kinetic analysis, machine learning modeling and quality evaluation

Case Studies in Thermal Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 105880 - 105880

Published: Feb. 1, 2025

Language: Английский

---

Prediction of Student Academic Performance Utilizing a Multi-Model Fusion Approach in the Realm of Machine Learning

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(7), P. 3550 - 3550

Published: March 24, 2025

The digitization of college student management is a crucial approach for training institutions to decrease costs while enhancing the quality students’ development. In this study, we focused on students majoring in Computer Science certain university and conducted an exploration using their scores multiple undergraduate courses. Initially, selected basic core academic courses based program identified four groups course combinations with strong positive correlations through correlation cluster analysis. This finding helped optimize arrangement structure major’s system. Next, organized overall performance data sequential format semester order. Multiple machine learning models were utilized perform regression prediction classification tasks determine student’s level. Finally, integrated create practical framework predicting performance, which can be applied digital management. also provide effective decision support early warning guide

Language: Английский

---

Recommendation Model of Additional Fuel Based on Feature Optimization and Machine Learning

Lecture notes in mechanical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 155 - 163

Published: Jan. 1, 2025

Language: Английский

---

Are the same parameters measured at admission and in the ICU comparable in their predictive values for complication and mortality in severely injured patients?

European journal of medical research, Journal Year: 2025, Volume and Issue: 30(1)

Published: April 2, 2025

Numerous studies have investigated variables that predict mortality and complications following severe trauma. These studies, however, mainly focus on admission values or a single variable. The aim of this study was to investigate the predictive quality multiple routine clinical measurements (at in ICU). Retrospective cohort severely injured patients treated at one Level 1 academic trauma centre. injury (ISS ≥ 16 points), primary complete data set. Exclusion criteria end-of-life treatment based advanced directive, secondary transferred patients. mortality, pneumonia, sepsis. Routine parameters were stratified measurement timepoint into Group TB (Trauma Bay, admission) intensive care unit (ICU, 72 h after admission). Prediction calculated using two prediction methods: adaptive boosting (AdaBoost, artificial intelligence, AI) LASSO regression analysis. Inclusion 3668 cases. Overall mean age 45.5 ± 20 years, ISS 28.2 15.1 points, incidence pneumonia 19.0%, sepsis 14.9%, death from haemorrhagic shock 4.1%, organ failure 1.9%, overall rate 26.8%. Highest value for include abbreviated scale (AIS), new severity score (NISS) systemic Inflammatory Response Syndrome (SIRS) score. ICU late lactate values, haematocrit, leukocytes, CRP. Sensitivity specificity models 25% cutoff 73.61% 76.24%, respectively. strongly depends measurement. Upon admission, affected anatomical regions are more predictive, while during stay, laboratory better predictor adverse outcomes. Therefore, dynamics pathophysiologic responses should be taken consideration, especially decision making definitive surgical interventions. III (retrospective study).

Language: Английский

---

Supervised Machine learning and Molecular docking modeling to Identify Potential Anti-Parkinson’s Agents

Journal of Molecular Graphics and Modelling, Journal Year: 2025, Volume and Issue: 139, P. 109073 - 109073

Published: May 9, 2025

Language: Английский

---