Performance optimisation and predictive modelling of rice husk ash recycled concrete under the coupled action of freeze-thaw cycles and chloride erosion: Experimental study and machine learning

Construction and Building Materials, Journal Year: 2025, Volume and Issue: 481, P. 141467 - 141467

Published: May 4, 2025

Language: Английский

---

Prediction of split tensile strength of recycled aggregate concrete leveraging explainable hybrid XGB with optimization algorithm

Multiscale and Multidisciplinary Modeling Experiments and Design, Journal Year: 2024, Volume and Issue: 7(4), P. 4343 - 4359

Published: May 31, 2024

Language: Английский

---

Application of Nighttime Light Data Simulation Based on Multi-Indicator System and Machine Learning Model in Predicting Potentially Suitable Economic Development Areas: A Case Study of the Turpan–Hami Region

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(2), P. 240 - 240

Published: Jan. 11, 2025

In recent years, the accelerated urbanization process in China has led to increased land resource constraints and unregulated expansion, imposing significant pressure on ecosystems environment. As a critical node along Silk Road Economic Belt, Turpan–Hami region experienced rapid urban development under policy support but faces challenges utilization efficiency sustainable development. To address these challenges, this study innovatively combines nighttime light remote sensing data quantify economic intensity integrates socioeconomic natural environment indicators based previous research. Four tree-based ensemble learning models—Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Machine (LightGBM), Categorical (CatBoost)—were employed predict potential suitability zones their intensity. The results show that CatBoost model performed best prediction, revealing spatial disparities: high-suitability areas are concentrated regions with superior conditions well-developed infrastructure, whereas terrain inadequate infrastructure exhibit lower suitability. An analysis of changes over historical periods (2010, 2015, 2020) demonstrates gradual expansion time.

Language: Английский

---

Optimized Deep Learning Model for Predicting Liver Metastasis in Colorectal Cancer Patients

Symmetry, Journal Year: 2025, Volume and Issue: 17(1), P. 103 - 103

Published: Jan. 11, 2025

Colorectal cancer is a leading type of worldwide and major contributor to fatalities, liver metastasis the most likely distant in colorectal patients. Classifying predicting whether occurs patients can help doctors timely determine progress disease form more reasonable treatment plan, which results better prognosis for In this paper, using Surveillance, Epidemiology, End Results database, selecting both symmetric asymmetric features, we extracted disease-related data 40,870 who were pathologically diagnosed with from 2010 2015 classified modeled developed show symmetry study. A total six deep learning models utilized, hyperparameter optimization was performed on Crested Porcupine Optimizer. The best-performing model selected interpretation explore features that affect develop metastasis. Among selected, FT-Transformer model, optimized by Optimizer, best, an accuracy 0.945, 95% confidence interval (CI) [0.942, 0.952], AUC 0.949, CI 0.957]. This study make medical decisions, detect metastases earlier, monitor indicators have significant impact occurrence patients, use surgical treatment, radiotherapy, chemotherapy, other corresponding therapeutic interventions improve survival rate

Language: Английский

---

Low voltage user power internet of things monitoring system based on LoRa wireless technology

Energy Informatics, Journal Year: 2025, Volume and Issue: 8(1)

Published: Jan. 27, 2025

Language: Английский

---