Influence of Data Splitting on Performance of Machine Learning Models in Prediction of Shear Strength of Soil

Mathematical Problems in Engineering, Год журнала: 2021, Номер 2021, С. 1 - 15

Опубликована: Фев. 5, 2021

The main objective of this study is to evaluate and compare the performance different machine learning (ML) algorithms, namely, Artificial Neural Network (ANN), Extreme Learning Machine (ELM), Boosting Trees (Boosted) considering influence various training testing ratios in predicting soil shear strength, one most critical geotechnical engineering properties civil design construction. For aim, a database 538 samples collected from Long Phu 1 power plant project, Vietnam, was utilized generate datasets for modeling process. Different (i.e., 10/90, 20/80, 30/70, 40/60, 50/50, 60/40, 70/30, 80/20, 90/10) were used divide into assessment models. Popular statistical indicators, such as Root Mean Squared Error (RMSE), Absolute (MAE), Correlation Coefficient (R), employed predictive capability models under ratios. Besides, Monte Carlo simulation simultaneously carried out proposed models, taking account random sampling effect. results showed that although all three ML performed well, ANN accurate statistically stable model after 1000 simulations (Mean R = 0.9348) compared with other Boosted 0.9192) ELM 0.8703). Investigation on greatly affected by training/testing ratios, where 70/30 presented best Concisely, herein an effective manner selecting appropriate predict strength accurately, which would be helpful phases construction projects.

Язык: Английский

---

Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models

Cement and Concrete Research, Год журнала: 2021, Номер 145, С. 106449 - 106449

Опубликована: Апрель 17, 2021

Язык: Английский

---

High-performance concrete strength prediction based on ensemble learning

Construction and Building Materials, Год журнала: 2022, Номер 324, С. 126694 - 126694

Опубликована: Фев. 4, 2022

Язык: Английский

---

Revealing the nature of metakaolin-based concrete materials using artificial intelligence techniques

Construction and Building Materials, Год журнала: 2022, Номер 322, С. 126500 - 126500

Опубликована: Янв. 22, 2022

Язык: Английский

---

Introducing stacking machine learning approaches for the prediction of rock deformation

Transportation Geotechnics, Год журнала: 2022, Номер 34, С. 100756 - 100756

Опубликована: Март 22, 2022

Язык: Английский

---

Prediction of axial load capacity of rectangular concrete-filled steel tube columns using machine learning techniques

Engineering With Computers, Год журнала: 2021, Номер 38(S4), С. 3283 - 3316

Опубликована: Июль 4, 2021

Язык: Английский

---

Soft computing-based models for the prediction of masonry compressive strength

Engineering Structures, Год журнала: 2021, Номер 248, С. 113276 - 113276

Опубликована: Окт. 5, 2021

Язык: Английский

---

Metamodel techniques to estimate the compressive strength of UHPFRC using various mix proportions and a high range of curing temperatures

Construction and Building Materials, Год журнала: 2022, Номер 349, С. 128737 - 128737

Опубликована: Авг. 18, 2022

Язык: Английский

---

Fault diagnosis in industrial rotating equipment based on permutation entropy, signal processing and multi-output neuro-fuzzy classifier

Expert Systems with Applications, Год журнала: 2022, Номер 206, С. 117754 - 117754

Опубликована: Июнь 11, 2022

Rotating equipment is considered as a key component in several industrial sectors. In fact, the continuous operation of many machines such sub-sea pumps and gas turbines relies on correct performance their rotating equipment. order to reduce probability malfunctions this equipment, condition monitoring, fault diagnosis systems are essential. work, novel approach proposed perform based permutation entropy, signal processing, artificial intelligence. To that aim, vibration signals employed for an indication bearing performance. facilitate diagnosis, detection isolation performed two separate steps. As first, once received, faulty state determined by entropy. case detected, type using processing Wavelet packet transform envelope analysis utilized extract frequency components fault. The allows automatic selection band includes characteristic resonance fault, which subject change different operational conditions. method works extracting proper features used decide about bearing's multi-output adaptive neuro-fuzzy inference system classifier. effectiveness assessed Case Western Reserve University dataset: demonstrates method's capabilities accurately diagnosing faults compared existing approaches.

Язык: Английский

---

Data-Driven Compressive Strength Prediction of Fly Ash Concrete Using Ensemble Learner Algorithms

Buildings, Год журнала: 2022, Номер 12(2), С. 132 - 132

Опубликована: Янв. 27, 2022

Concrete is one of the most popular materials for building all types structures, and it has a wide range applications in construction industry. Cement production use have significant environmental impact due to emission different gases. The fly ash concrete (FAC) crucial eliminating this defect. However, varied features cementitious composites exist, understanding their mechanical characteristics critical safety. On other hand, forecasting concrete, machine learning approaches are extensively employed algorithms. goal work compare ensemble deep neural network models, i.e., super learner algorithm, simple averaging, weighted integrated stacking, as well separate stacking order develop an accurate approach estimating compressive strength FAC reducing high variance predictive models. Separate with random forest meta-learner received predictions (97.6%) highest coefficient determination lowest mean square error variance.

Язык: Английский

---