Wind power is a rapidly growing source of clean energy. Accurate short-term forecasting of wind power is essential for reliable energy generation. In this study, we propose a novel wind power forecasting approach using spatiotemporal analysis to enhance forecasting performance. First, the wind power time-series data from the target turbine and adjacent neighboring turbines were utilized to form a graph structure using graph neural networks (GNN). The graph structure was used to compute the spatiotemporal correlation between the target turbine and adjacent turbines. Then, the prediction models were trained using a deep residual network (DRN) for short-term wind power prediction. Considering the wind speed, the historic wind power, air density, and historic wind power in adjacent wind turbines within the supervisory control and data acquisition (SCADA) system were utilized. A comparative analysis was performed using conventional machine-learning approaches. Industrial data collected from Hami County, Xinjiang, China, were used for the case study. The computational results validate the superiority of the proposed approach for short-term wind-power forecasting.

Short-Term Wind Power Prediction via Spatial Temporal Analysis and Deep Residual Networks

Time-Series Graph Network for Sea Surface Temperature Prediction

Deep Reinforcement Learning Guided Graph Neural Networks for Brain Network Analysis

Although functional connectivity and associated graph theory measures (e.g., centrality; how centrally important to the network a region is) are widely used in brain research, the full extent to which these functional measures are related to the underlying structural connectivity is not yet fully understood. Graph neural network deep learning methods have not yet been applied for this purpose, and offer an ideal model architecture for working with connectivity data given their ability to capture and maintain inherent network structure. Here, we applied this model to predict functional connectivity from structural connectivity in a sample of 998 participants from the Human Connectome Project. Our results showed that the graph neural network accounted for 89% of the variance in mean functional connectivity, 56% of the variance in individual-level functional connectivity, 99% of the variance in mean functional centrality, and 81% of the variance in individual-level functional centrality. These results represent an important finding that functional centrality can be robustly predicted from structural connectivity. Regions of particular importance to the model's performance as determined through lesioning are discussed, whereby regions with higher centrality have a higher impact on model performance. Future research on models of patient, demographic, or behavioural data can also benefit from this graph neural network method as it is ideally-suited for depicting connectivity and centrality in brain networks. These results have set a new benchmark for prediction of functional connectivity from structural connectivity, and models like this may ultimately lead to a way to predict functional connectivity in individuals who are unable to do fMRI tasks (e.g., non-responsive patients).

/pdf/structure-can-predict-function-in-the-human-brain-a-graph-26ac07gm5m.pdf

Structure can predict function in the human brain: a graph neural network deep learning model of functional connectivity and centrality based on structural connectivity

Few-shot learning presents a challenging paradigm for training discriminative models on a few training samples representing the target classes to discriminate. However, classification methods based on deep learning are ill-suited for such learning as they need large amounts of training data –let alone one-shot learning. Recently, graph neural networks (GNNs) have been introduced to the field of network neuroscience, where the brain connectivity is encoded in a graph. However, with scarce neuroimaging datasets particularly for rare diseases and low-resource clinical facilities, such data-devouring architectures might fail in learning the target task. In this paper, we take a very different approach in training GNNs, where we aim to learn with one sample and achieve the best performance –a formidable challenge to tackle. Specifically, we present the first one-shot paradigm where a GNN is trained on a single population-driven template –namely a connectional brain template (CBT). A CBT is a compact representation of a population of brain graphs capturing the unique connectivity patterns shared across individuals. It is analogous to brain image atlases for neuroimaging datasets. Using a one-representative CBT as a training sample, we alleviate the training load of GNN models while boosting their performance across a variety of classification and regression tasks. We demonstrate that our method significantly outperformed benchmark one-shot learning methods with downstream classification and time-dependent brain graph data forecasting tasks while competing with the “train on all” conventional training strategy. Our source code can be found at https://github.com/basiralab/one-representative-shot-learning.

One Representative-Shot Learning Using a Population-Driven Template with Application to Brain Connectivity Classification and Evolution Prediction

Brain networks provide essential insights into the diagnosis of functional brain disorders, such as Alzheimer’s disease (AD). Many machine learning methods have been applied to learn from brain images or networks in Euclidean space. However, it is still challenging to learn complex network structures and the connectivity of brain regions in non-Euclidean space. To address this problem, in this paper, we exploit the study of brain network classification from the perspective of graph learning. We propose an aggregator based on extreme learning machine (ELM) that boosts the aggregation ability and efficiency of graph convolution without iterative tuning. Then, we design a graph neural network named GNEA (Graph Neural Network with ELM Aggregator) for the graph classification task. Extensive experiments are conducted using a real-world AD detection dataset to evaluate and compare the graph learning performances of GNEA and state-of-the-art graph learning methods. The results indicate that GNEA achieves excellent learning performance with the best graph representation ability in brain network classification applications.

/pdf/gnea-a-graph-neural-network-with-elm-aggregator-for-brain-1tzuuawei9.pdf

GNEA: A Graph Neural Network with ELM Aggregator for Brain Network Classification

An Uncertainty-based Neural Network for Explainable Trajectory Segmentation

Electromagnetic inverse scattering is a nonlinear and ill-posed problem. Some traditional algorithms have been proposed to solve it, but they cannot perform well in both terms of efficiency and accuracy. In order to reconstruct high quality images in real time, this paper presents a hybrid method which combines the Born iterative Gaussian mixture model generalized approximate message passing (BI-GMM-GAMP) algorithm with a convolutional neural network (CNN). To be specific, BI-GMM-GAMP is first used for obtaining the preliminary images. Subsequently, these pictures are used for training U-Net. Experiments show the validity of this method.

A Hybrid Electromagnetic Inversion Method Based on BI-GMM-GAMP and Convolutional Neural Network

Ventricular fibrillation is the most lethal arrhythmia. At present, the treatment of ventricular fibrillation is commonly received after the onset of the disease, which mainly depends on external defibrillation and drug-assisted therapy. Although activity of heartbeats can be described and analyzed using the most popular technique ECG (electrocardiogram), there is still no widely recognized prediction methods for ventricular fibrillation. Therefore, in this paper, in order to realize warning of ventricular fibrillation, we focus on the detection of atrial fibrillation and ventricular flutter, which are the arrhythmias often occurring before ventricular fibrillation. We propose a frequency-domain LSTM (Long Short-Term Memory), which uses heartbeat waves transformed from the original time domain into the frequency domain as input. Furthermore, to address the problem of big ECG data training efficiency and scalability, we also provide an implementation of our method under the distributed computing framework MapReduce in the Spark cluster. Experimental results indicate that our method achieves excellent classification performance compared with rival methods.

Zhixun Liu

Papers

GNEA: A Graph Neural Network with ELM Aggregator for Brain Network Classification

An Uncertainty-based Neural Network for Explainable Trajectory Segmentation

A Hybrid Electromagnetic Inversion Method Based on BI-GMM-GAMP and Convolutional Neural Network

Efficient Learning of Big ECG Data for Ventricular Fibrillation Warning