Machine learning based multi-physical-model blending for enhancing renewable energy forecast - improvement via situation dependent error correction

Abstract

Background Given tongue features and basic features, this study aimed to develop and assess a non-invasive machine learning model to perform regression prediction on fasting plasma glucose and glycated haemoglobin which will help optimize diabetes risk warning. Methods We collected the basic features, tongue features and blood features of the subjects. Using machine learning algorithms to analyze these data, we built models to predict fasting plasma glucose and glycated haemoglobin. Then the performance of the models was evaluated through 5-fold crossvalidation results and test set results. Results The results of cross validation on the training set showed that given non-invasive input features, the minimum average mean square error of fasting plasma glucose and glycated haemoglobin prediction was 1.227 and 0.438. Our non-invasive fasting plasma glucose prediction model with tongue features and basic features combined achieved a minimum mean square error of 0.601 and a maximum coe cient of determination of 0.606 on the test set. The glycated haemoglobin prediction model product a minimum mean square error of 0.272 and a maximum coe cient of determination of 0.539 on the test set. The Clarke's Error Grid Analysis showed that the non-invasive blending model had 90.83% of points in zone A and 8.49% of points in zone B on the test set. Conclusions We developed an effective non-invasive method for estimating fasting plasma glucose and glycated haemoglobin from tongue features and basic features combined, which may help identify individuals at high risk for diabetes.

Baseline and target values for regional and point PV power forecasts: Toward improved solar forecasting

“…Indeed one pathway to enable such needed improvement in forecasting is via machine learning technology. Towards this end, as part of the project work performed under the SunShot Initiative's Improving the Accuracy of Solar Forecasting program, a system for improving solar forecast, Watt-sun, is being developed by this team (Lu et al, 2015a;2015b). Watt-sun uses big-data information processing technologies and applies machinelearnt, situation-dependent blending of multiple models to enhance system intelligence, adaptability and scalability.…”

“…Three PV plants were chosen among hundreds of sites available by the solar utilities in the Watt-sun (Lu et al, 2015a;2015b) research consortium as point test cases: Smyrna, Green Mountain Power (GMP), and Tucson Electric Power (TEP). The selection was based on the best quality, continuity, and variety of power production observations at the sites.…”

Prediction of fasting plasma glucose and glycated haemoglobin using machine learning based on tongue features

“…The machine learning based model blending approach is a very common fusion technique [30]. The idea of model fusion is to use many independent models to calculate the initial prediction, and then mix the initial prediction to achieve a better nal prediction result.…”

Electricity Market Empowered by Artificial Intelligence: A Platform Approach

“…Applications often involve the use of artificial neural network methods for solar modeling [51] in both single and hybrid approaches [53]. For instance, the use of machine learning can improve the solar forecasting accuracy with a range of 30% to 50% increase, e.g., [54,55] compared to conventional forecasting models.…”