Search

In this article, a new approach to short-term load forecasting is proposed using a multicolumn radial basis function neural network (MCRN). The advantage of this new approach over similar models in speed and accuracy is also discussed, especially in regards to renewable generation forecasting. Because weather and seasonal effects have a direct impact not only on load demand but also on renewable energy production, it follows that as the penetration rate of renewable DG increases, the grid will become even more sensitive to weather impacts in the long term. In our approach, we use a k-d tree algorithm to split our feature-rich dataset into dense specialized subsets. These subsets are then trained in parallel as multiple artificial neural networks using a modified error correction algorithm to form the MCRN. This approach reduces the number of hidden neurons, increases the speed of convergence, and improves generalization over similar alternative forecasting methods.

Epicardial adipose tissue volume (EAT) has been linked to coronary artery disease and the risk of major adverse cardiac events. As manual quantification of EAT is time-consuming, requires specialized training, and is prone to human error, we developed a method (DeepFat) for the automatic assessment of EAT on non-contrast low-dose CT calcium score images using deep learning. We segmented the tissue enclosed by the pericardial sac on axial slices, using two innovations. First, we applied a HU‑attention-window with a window/level 350/40-HU to draw attention to the sac and reduce numerical errors. Second, we applied look ahead slab-of-slices with bisection (“bisect”) in which we split the heart into halves and sequenced the lower half from bottom-to-middle and the upper half from top-to-middle, thereby presenting an always increasing curvature of the sac to the network. EAT volume was obtained by thresholding voxels within the sac in the fat window (-190/-30-HU). Compared to manual segmentation, our algorithm gave excellent results with volume Dice=88.52%±3.3, slice Dice=87.70%±7.5, EAT error=0.5%±8.1, and R=98.52%(p

Our ultimate goal is to predict adverse cardiovascular events from CT calcium score exams using radiomics. Unlike the traditional whole heart Agatston score, our approach analyzes individual calcifications, creating a challenge for accurate/reproducible assessments. Optional preprocessing consisted of 3D blind deconvolution optimized on masked sharp structures, giving PSFs similar to measured ones, followed by noise reduction. In our experiment, we found that blind deconvolution improves the accuracy and reproducibility of CT calcium score evaluation. It is beneficial to use this to predict adverse cardiovascular event since it provides a robust and accurate evaluation of clinically relevant and pre-clinical calcifications. We conclude that for archived images where PSFs are unavailable, 3D blind deconvolution is a useful preprocessing step for improved radiomics assessments of CT-calcium-score images.

This paper proposes the multicolumn RBF network (MCRN) as a method to improve the accuracy and speed of a traditional radial basis function network (RBFN). The RBFN, as a fully connected artificial neural network (ANN), suffers from costly kernel inner-product calculations due to the use of many instances as the centers of hidden units. This issue is not critical for small datasets, as adding more hidden units will not burden the computation time. However, for larger datasets, the RBFN requires many hidden units with several kernel computations to generalize the problem. The MCRN mechanism is constructed based on dividing a dataset into smaller subsets using the k-d tree algorithm. $N$ resultant subsets are considered as separate training datasets to train $N$ individual RBFNs. Those small RBFNs are stacked in parallel and bulged into the MCRN structure during testing. The MCRN is considered as a well-developed and easy-to-use parallel structure, because each individual ANN has been trained on its own subsets and is completely separate from the other ANNs. This parallelized structure reduces the testing time compared with that of a single but larger RBFN, which cannot be easily parallelized due to its fully connected structure. Small informative subsets provide the MCRN with a regional experience to specify the problem instead of generalizing it. The MCRN has been tested on many benchmark datasets and has shown better accuracy and great improvements in training and testing times compared with a single RBFN. The MCRN also shows good results compared with those of some machine learning techniques, such as the support vector machine and k-nearest neighbors.