-
1
A Clustering Ensemble Framework with Integration of Data Characteristics and Structure Information: A Graph Neural Networks Approach
Published 2022-05-01“…Experimental results on six synthetic benchmark data sets and six real world data sets show that the proposed framework yields a better performance compared to 12 reference algorithms that are developed based on either clustering ensemble architecture or a deep clustering strategy.…”
Get full text
Article -
2
Comparison of Bagging and Sparcity Methods for Connectivity Reduction in Spiking Neural Networks with Memristive Plasticity
Published 2024-02-01“…In this work, we compare two methods of connectivity reduction that are applicable to spiking networks with local plasticity; instead of a large fully-connected network (which is used as the baseline for comparison), we employ either an ensemble of independent small networks or a network with probabilistic sparse connectivity. …”
Get full text
Article -
3
Reduced Order Modeling for Stochastic Prediction and Data Assimilation Onboard Autonomous Platforms At Sea
Published 2022“…Three new approaches that combine uncertainty with DMD are also investigated and found to produce practical and accurate results, especially if we employ either an ensemble of DMD forecasts or the DMD of an ensemble of forecasts. …”
Get full text
Thesis -
4
Developing and evaluating week 2 and weeks 3-4 outlook tools for extratropical storminess
Published 2022-10-01“…Our results show that the GEFSv12 and CFSv2 combined ensemble has higher skill than either individual ensemble. The combined ensemble shows some skill in predicting cyclone amplitude and frequency out to weeks 3-4, with highest skill in winter, and lowest skill in summer. …”
Get full text
Article -
5
CMEMS-LSCE: a global, 0.25°, monthly reconstruction of the surface ocean carbonate system
Published 2024-01-01“…Here, <span class="inline-formula"><i>σ</i></span> stands for either the ensemble standard deviation of <span class="inline-formula"><i>p</i>CO<sub>2</sub></span> estimates or the total uncertainty for each of the five other variables propagated through the processing chain with input data uncertainty. …”
Get full text
Article -
6
From climate model ensembles to climate change impacts and adaptation: a case study of water resource management in the southwest of England
Published 2009“…Large ensembles of climate models are increasingly available either as ensembles of opportunity or perturbed physics ensembles, providing a wealth of additional data that is potentially useful for improving adaptation strategies to climate change. …”
Journal article -
7
TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks
Published 2022-12-01“…Additionally, we adapted the models to take as input either all Ensembl genes (60,483) or protein coding genes only (19,758). …”
Get full text
Article -
8
Evapotranspiration Response to Climate Change in Semi-Arid Areas: Using Random Forest as Multi-Model Ensemble Method
Published 2021-01-01“…Large ensembles of climate models are increasingly available either as ensembles of opportunity or perturbed physics ensembles, providing a wealth of additional data that is potentially useful for improving adaptation strategies to climate change. …”
Get full text
Article -
9
Comparative proteomic analysis of tail regeneration in the green anole lizard, Anolis carolinensis
Published 2024-01-01“…For over 90% of these proteins in these tissues, we were able to assign a clear orthology to gene models in either the Ensembl or NCBI databases. For 13 proteins in the tail base, 9 proteins in the tail tip, and 10 proteins in both regions, the gene model in Ensembl and NCBI matched an uncharacterized protein, confirming that these predictions are present in the proteome. …”
Get full text
Article