Using spatio-temporal graph neural networks to estimate fleet-wide photovoltaic performance degradation patterns
Ontology highlight
ABSTRACT:
SUBMITTER: Fan Y
PROVIDER: S-EPMC10866472 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Spiking neural networks (SNNs) are potentially highly efficient models for inference on fully parallel neuromorphic hardware, but existing training methods that convert conventional artificial neural networks (ANNs) into SNNs are unable to exploit these advantages. Although ANN-to-SNN conversion has achieved state-of-the-art accuracy for static image classification tasks, the following subtle but important difference in the way SNNs and ANNs integrate information over time makes the direct application of conversion techniques for sequence processing tasks challenging. Whereas all connections in SNNs have a certain propagation delay larger than zero, ANNs assign different roles to feed-forward connections, which immediately update all neurons within the same time step, and recurrent connections, which have to be rolled out in time and are typically assigned a delay of one time step. Here, we present a novel method to obtain highly accurate SNNs for sequence processing by modifying the ANN training before conversion, such that delays induced by ANN rollouts match the propagation delays in the targeted SNN implementation. Our method builds on the recently introduced framework of streaming rollouts, which aims for fully parallel model execution of ANNs and inherently allows for temporal integration by merging paths of different delays between input and output of the network. The resulting networks achieve state-of-the-art accuracy for multiple event-based benchmark datasets, including N-MNIST, CIFAR10-DVS, N-CARS, and DvsGesture, and through the use of spatio-temporal shortcut connections yield low-latency approximate network responses that improve over time as more of the input sequence is processed. In addition, our converted SNNs are consistently more energy-efficient than their corresponding ANNs.
| S-EPMC7214871 | biostudies-literature
Project description:Cognitive functions produced by large-scale neural integrations are the most representative 'emergence phenomena' in complex systems. A novel approach focusing on the instantaneous phase difference of brain oscillations across brain regions has succeeded in detecting moment-to-moment dynamic functional connectivity. However, it is restricted to pairwise observations of two brain regions, contrary to large-scale spatial neural integration in the whole-brain. In this study, we introduce a microstate analysis to capture whole-brain instantaneous phase distributions instead of pairwise differences. Upon applying this method to electroencephalography signals of Alzheimer's disease (AD), which is characterised by progressive cognitive decline, the AD-specific state transition among the four states defined as the leading phase location due to the loss of brain regional interactions could be promptly characterised. In conclusion, our synthetic analysis approach, focusing on the microstate and instantaneous phase, enables the capture of the instantaneous spatiotemporal neural dynamics of brain activity and characterises its pathological conditions.
| S-EPMC10761722 | biostudies-literature
Project description:The Compact Muon Solenoid (CMS) experiment is a general-purpose detector for high-energy collision at the Large Hadron Collider (LHC) at CERN. It employs an online data quality monitoring (DQM) system to promptly spot and diagnose particle data acquisition problems to avoid data quality loss. In this study, we present a semi-supervised spatio-temporal anomaly detection (AD) monitoring system for the physics particle reading channels of the Hadron Calorimeter (HCAL) of the CMS using three-dimensional digi-occupancy map data of the DQM. We propose the GraphSTAD system, which employs convolutional and graph neural networks to learn local spatial characteristics induced by particles traversing the detector and the global behavior owing to shared backend circuit connections and housing boxes of the channels, respectively. Recurrent neural networks capture the temporal evolution of the extracted spatial features. We validate the accuracy of the proposed AD system in capturing diverse channel fault types using the LHC collision data sets. The GraphSTAD system achieves production-level accuracy and is being integrated into the CMS core production system for real-time monitoring of the HCAL. We provide a quantitative performance comparison with alternative benchmark models to demonstrate the promising leverage of the presented system.
| S-EPMC10747755 | biostudies-literature
Project description:Magnetic resonance imaging (MRI) plays a critical role in the planning and monitoring of hepatocellular carcinomas (HCC) treated with locoregional therapies, in order to assess disease progression or recurrence. Dynamic contrast-enhanced (DCE)-MRI sequences offer temporal data on tumor enhancement characteristics which has strong prognostic value. Yet, predicting follow-up DCE-MR images from which tumor enhancement and viability can be measured, before treatment of HCC actually begins, remains an unsolved problem given the complexity of spatial and temporal information. We propose an approach to predict future DCE-MRI examinations following transarterial chemoembolization (TACE) by learning the spatio-temporal features related to HCC response from pre-TACE images. A novel Spatial-Temporal Discriminant Graph Neural Network (STDGNN) based on graph convolutional networks is presented. First, embeddings of viable, equivocal and non-viable HCCs are separated within a joint low-dimensional latent space, which is created using a discriminant neural network representing tumor-specific features. Spatial tumoral features from independent MRI volumes are then extracted with a structural branch, while dynamic features are extracted from the multi-phase sequence with a separate temporal branch. The model extracts spatio-temporal features by a joint minimization of the network branches. At testing, a pre-TACE diagnostic DCE-MRI is embedded on the discriminant spatio-temporal latent space, which is then translated to the follow-up domain space, thus allowing to predict the post-TACE DCE-MRI describing HCC treatment response. A dataset of 366 HCC's from liver cancer patients was used to train and test the model using DCE-MRI examinations with associated pathological outcomes, with the spatio-temporal framework yielding 93.5% classification accuracy in response identification, and generating follow-up images yielding insignificant differences in perfusion parameters compared to ground-truth post-TACE examinations.
| S-EPMC8651128 | biostudies-literature
Project description:BackgroundIt is often the case that only a portion of the underlying network structure is observed in real-world settings. However, as most network analysis methods are built on a complete network structure, the natural questions to ask are: (a) how well these methods perform with incomplete network structure, (b) which structural observation and network analysis method to choose for a specific task, and (c) is it beneficial to complete the missing structure.MethodsIn this paper, we consider the incomplete network structure as one random sampling instance from a complete graph, and we choose graph neural networks (GNNs), which have achieved promising results on various graph learning tasks, as the representative of network analysis methods. To identify the robustness of GNNs under graph sampling scenarios, we systemically evaluated six state-of-the-art GNNs under four commonly used graph sampling methods.ResultsWe show that GNNs can still be applied on single static networks under graph sampling scenarios, and simpler GNN models are able to outperform more sophisticated ones in a fairly experimental procedure. More importantly, we find that completing the sampled subgraph does improve the performance of downstream tasks in most cases; however, completion is not always effective and needs to be evaluated for a specific dataset. Our code is available at https://github.com/weiqianglg/evaluate-GNNs-under-graph-sampling.
| S-EPMC9044246 | biostudies-literature
Project description:Recent advances in spatial and temporal networks have enabled researchers to more-accurately describe many real-world systems such as urban transport networks. In this paper, we study the response of real-world spatio-temporal networks to random error and systematic attack, taking a unified view of their spatial and temporal performance. We propose a model of spatio-temporal paths in time-varying spatially embedded networks which captures the property that, as in many real-world systems, interaction between nodes is non-instantaneous and governed by the space in which they are embedded. Through numerical experiments on three real-world urban transport systems, we study the effect of node failure on a network's topological, temporal and spatial structure. We also demonstrate the broader applicability of this framework to three other classes of network. To identify weaknesses specific to the behaviour of a spatio-temporal system, we introduce centrality measures that evaluate the importance of a node as a structural bridge and its role in supporting spatio-temporally efficient flows through the network. This exposes the complex nature of fragility in a spatio-temporal system, showing that there is a variety of failure modes when a network is subject to systematic attacks.
| S-EPMC4929911 | biostudies-literature
Project description:Learning ultimately relies on changes in the flow of activity in neural microcircuits. The plasticity of neural dynamics is particularly relevant for the processing of temporal information. Chronic stimulation of cultured rat cortical networks revealed experience-dependent plasticity in neural dynamics. We observed changes in the temporal structure of activity that reflected the intervals used during training, suggesting that cortical circuits are inherently capable of temporal processing on short timescales.
| S-EPMC2910842 | biostudies-literature
Project description:BackgroundWe investigate whether deep learning (DL) neural networks can reduce erroneous human "judgment calls" on bedside echocardiograms and help distinguish Takotsubo syndrome (TTS) from anterior wall ST segment elevation myocardial infarction (STEMI).MethodsWe developed a single-channel (DCNN[2D SCI]), a multi-channel (DCNN[2D MCI]), and a 3-dimensional (DCNN[2D+t]) deep convolution neural network, and a recurrent neural network (RNN) based on 17,280 still-frame images and 540 videos from 2-dimensional echocardiograms in 10 years (1 January 2008 to 1 January 2018) retrospective cohort in University of Iowa (UI) and eight other medical centers. Echocardiograms from 450 UI patients were randomly divided into training and testing sets for internal training, testing, and model construction. Echocardiograms of 90 patients from the other medical centers were used for external validation to evaluate the model generalizability. A total of 49 board-certified human readers performed human-side classification on the same echocardiography dataset to compare the diagnostic performance and help data visualization.FindingsThe DCNN (2D SCI), DCNN (2D MCI), DCNN(2D+t), and RNN models established based on UI dataset for TTS versus STEMI prediction showed mean diagnostic accuracy 73%, 75%, 80%, and 75% respectively, and mean diagnostic accuracy of 74%, 74%, 77%, and 73%, respectively, on the external validation. DCNN(2D+t) (area under the curve [AUC] 0·787 vs. 0·699, P = 0·015) and RNN models (AUC 0·774 vs. 0·699, P = 0·033) outperformed human readers in differentiating TTS and STEMI by reducing human erroneous judgement calls on TTS.InterpretationSpatio-temporal hybrid DL neural networks reduce erroneous human "judgement calls" in distinguishing TTS from anterior wall STEMI based on bedside echocardiographic videos.FundingUniversity of Iowa Obermann Center for Advanced Studies Interdisciplinary Research Grant, and Institute for Clinical and Translational Science Grant. National Institutes of Health Award (1R01EB025018-01).
| S-EPMC8426197 | biostudies-literature
Project description:As explanations are increasingly used to understand the behavior of graph neural networks (GNNs), evaluating the quality and reliability of GNN explanations is crucial. However, assessing the quality of GNN explanations is challenging as existing graph datasets have no or unreliable ground-truth explanations. Here, we introduce a synthetic graph data generator, SHAPEGGEN, which can generate a variety of benchmark datasets (e.g., varying graph sizes, degree distributions, homophilic vs. heterophilic graphs) accompanied by ground-truth explanations. The flexibility to generate diverse synthetic datasets and corresponding ground-truth explanations allows SHAPEGGEN to mimic the data in various real-world areas. We include SHAPEGGEN and several real-world graph datasets in a graph explainability library, GRAPHXAI. In addition to synthetic and real-world graph datasets with ground-truth explanations, GRAPHXAI provides data loaders, data processing functions, visualizers, GNN model implementations, and evaluation metrics to benchmark GNN explainability methods.
| S-EPMC10024712 | biostudies-literature
Project description:ObjectiveWe aimed to study the networks' mechanism of metabolic covariance networks in mesial temporal lobe epilepsy (mTLE), through examining the brain value of fluorine-18-fluorodeoxyglucose positron emission tomography (18 F-FDG-PET).Methods18 F-FDG-PET images from 16 patients with mTLE were analyzed using local and global metabolic covariance network (MCN) approaches, including whole metabolic pattern analysis (WMPA), hippocampus-based (h-) MCN, whole brain (w-) MCN, and edge-based connectivity analysis (EBCA).ResultsWMPA showed a typical ipsilateral hypometabolism and contralateral hypermetabolism pattern to epileptic zones in mTLE. h-MCN revealed decreased hippocampus-based synchronization in contralateral regions. w-MCN exhibited a disrupted metabolic network with globally increased small-world properties and regionally decreased nodal metrics in the ipsilateral hemisphere. Hippocampus (h)-EBCA and whole brain EBCA (w-EBCA) both detected a reduced-connectivity dominated metabolic covariant network. Moreover, the reduced interhemisphere connectivity seemingly played a major role in the aberrant epileptic topological pattern.ConclusionFrom a metabolic point of view, we demonstrated the damaging effects with reduced contralateral intranetwork metrics properties and the compensatory effects in contralateral intranetworks with increased network properties. However, the import role of significant reduced interhemisphere connection has rarely been reported in other mTLE studies. Taken together, 18 F-FDG-PET MCN analysis provides new evidence that the mTLE is a system neurological disorder with disrupted networks.
| S-EPMC6488969 | biostudies-literature