An official website of the United States government
IntroductionThe objective of this study is to develop predictive models for rocking-induced permanent settlement in shallow foundations during earthquake loading using stacking, bagging and boosting ensemble machine learning (ML) and artificial neural network (ANN) models. MethodsThe ML models are developed using supervised learning technique and results obtained from rocking foundation experiments conducted on shaking tables and centrifuges. The overall performance of ML models are evaluated using k-fold cross validation tests and mean absolute percentage error (MAPE) and mean absolute error (MAE) in their predictions. ResultsThe performances of all six nonlinear ML models developed in this study are relatively consistent in terms of prediction accuracy with their average MAPE varying between 0.64 and 0.86 in final k-fold cross validation tests. DiscussionThe overall average MAE in predictions of all nonlinear ML models are smaller than 0.006, implying that the ML models developed in this study have the potential to predict permanent settlement of rocking foundations with reasonable accuracy in practical applications.
more »
« less
A Transfer Learning Approach to Correct the Temporal Performance Drift of Clinical Prediction Models: Retrospective Cohort Study
BackgroundClinical prediction models suffer from performance drift as the patient population shifts over time. There is a great need for model updating approaches or modeling frameworks that can effectively use the old and new data. ObjectiveBased on the paradigm of transfer learning, we aimed to develop a novel modeling framework that transfers old knowledge to the new environment for prediction tasks, and contributes to performance drift correction. MethodsThe proposed predictive modeling framework maintains a logistic regression–based stacking ensemble of 2 gradient boosting machine (GBM) models representing old and new knowledge learned from old and new data, respectively (referred to as transfer learning gradient boosting machine [TransferGBM]). The ensemble learning procedure can dynamically balance the old and new knowledge. Using 2010-2017 electronic health record data on a retrospective cohort of 141,696 patients, we validated TransferGBM for hospital-acquired acute kidney injury prediction. ResultsThe baseline models (ie, transported models) that were trained on 2010 and 2011 data showed significant performance drift in the temporal validation with 2012-2017 data. Refitting these models using updated samples resulted in performance gains in nearly all cases. The proposed TransferGBM model succeeded in achieving uniformly better performance than the refitted models. ConclusionsUnder the scenario of population shift, incorporating new knowledge while preserving old knowledge is essential for maintaining stable performance. Transfer learning combined with stacking ensemble learning can help achieve a balance of old and new knowledge in a flexible and adaptive way, even in the case of insufficient new data.
more »
« less
- Award ID(s):
- 2014554
- PAR ID:
- 10467165
- Publisher / Repository:
- JMIR Publications
- Date Published:
- Journal Name:
- JMIR Medical Informatics
- Volume:
- 10
- Issue:
- 11
- ISSN:
- 2291-9694
- Page Range / eLocation ID:
- e38053
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Learning nonlinear functions from input-output data pairs is one of the most fundamental problems in machine learning. Recent work has formulated the problem of learning a general nonlinear multivariate function of discrete inputs, as a tensor completion problem with smooth latent factors. We build upon this idea and utilize two ensemble learning techniques to enhance its prediction accuracy. Ensemble methods can be divided into two main groups, parallel and sequential. Bagging also known as bootstrap aggregation is a parallel ensemble method where multiple base models are trained in parallel on different subsets of the data that have been chosen randomly with replacement from the original training data. The output of these models is usually combined and a single prediction is computed using averaging. One of the most popular bagging techniques is random forests. Boosting is a sequential ensemble method where a sequence of base models are fit sequentially to modified versions of the data. Popular boosting algorithms include AdaBoost and Gradient Boosting. We develop two approaches based on these ensemble learning techniques for learning multivariate functions using the Canonical Polyadic Decomposition. We showcase the effectiveness of the proposed ensemble models on several regression tasks and report significant improvements compared to the single model.more » « less
-
Abstract This work explores the impacts of magnetogram projection effects on machine-learning-based solar flare forecasting models. Utilizing a methodology proposed by D. A. Falconer et al., we correct for projection effects present in Georgia State University’s Space Weather Analytics for Solar Flares benchmark data set. We then train and test a support vector machine classifier on the corrected and uncorrected data, comparing differences in performance. Additionally, we provide insight into several other methodologies that mitigate projection effects, such as stacking ensemble classifiers and active region location-informed models. Our analysis shows that data corrections slightly increase both the true-positive (correctly predicted flaring samples) and false-positive (nonflaring samples predicted as flaring) prediction rates, averaging a few percent. Similarly, changes in performance metrics are minimal for the stacking ensemble and location-based model. This suggests that a more complicated correction methodology may be needed to see improvements. It may also indicate inherent limitations when using magnetogram data for flare forecasting.more » « less
-
The objective of this study is to develop data-driven predictive models for seismic energy dissipation of rocking shallow foundations during earthquake loading using decision tree-based ensemble machine learning algorithms and supervised learning technique. Data from a rocking foundation’s database consisting of dynamic base shaking experiments conducted on centrifuges and shaking tables have been used for the development of a base decision tree regression (DTR) model and four ensemble models: bagging, random forest, adaptive boosting, and gradient boosting. Based on k-fold cross-validation tests of models and mean absolute percentage errors in predictions, it is found that the overall average accuracy of all four ensemble models is improved by about 25%–37% when compared to base DTR model. Among the four ensemble models, gradient boosting and adaptive boosting models perform better than the other two models in terms of accuracy and variance in predictions for the problem considered.more » « less
-
Abstract BackgroundRecently, machine learning techniques have been applied to data collected from inertial measurement units to automatically assess balance, but rely on hand-engineered features. We explore the utility of machine learning to automatically extract important features from inertial measurement unit data for balance assessment. FindingsTen participants with balance concerns performed multiple balance exercises in a laboratory setting while wearing an inertial measurement unit on their lower back. Physical therapists watched video recordings of participants performing the exercises and rated balance on a 5-point scale. We trained machine learning models using different representations of the unprocessed inertial measurement unit data to estimate physical therapist ratings. On a held-out test set, we compared these learned models to one another, to participants’ self-assessments of balance, and to models trained using hand-engineered features. Utilizing the unprocessed kinematic data from the inertial measurement unit provided significant improvements over both self-assessments and models using hand-engineered features (AUROC of 0.806 vs. 0.768, 0.665). ConclusionsUnprocessed data from an inertial measurement unit used as input to a machine learning model produced accurate estimates of balance performance. The ability to learn from unprocessed data presents a potentially generalizable approach for assessing balance without the need for labor-intensive feature engineering, while maintaining comparable model performance.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.2196/38053
