Yulia R. Gel

Yulia R. Gel

Auto-generated profile, based on publicly available information

Yulia R. Gel

Virginia Tech, Blacksburg, Virginia, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 March 2020 in IEEE Access
Verified
Journal Article
Open access
A0Annalisa Appice 0000-0001-9840-844X
Annalisa Appice 0000-0001-9840-844X
YGYulia R. Gel
Yulia R. Gel
IIIliyan Iliev
Iliyan Iliev
VLVyacheslav Lyubchich
Vyacheslav Lyubchich
Donato MalerbaDonato Malerba
Donato Malerba
The mosquito-borne dengue fever is a major public health problem in tropical countries, where it is strongly conditioned by climate factors such as temperature. In this paper, we formulate a holistic machine learning strategy to analyze the temporal dynamics of temperature and dengue data and use this knowledge to produce accurate predictions of dengue, based on temperature on an annual scale. The temporal dynamics are extracted from historical data by utilizing a novel multi-stage combination of auto-encoding, window-based data representation and trend-based temporal clustering. The prediction is performed with a trend association-based nearest neighbour predictor. The effectiveness of the proposed strategy is evaluated in a case study that comprises the number of dengue and dengue hemorrhagic fever cases collected over the period 1985–2010 in 32 federal states of Mexico. The empirical study proves the viability of the proposed strategy and confirms that it outperforms various state-of-the-art competitor methods formulated both in regression and in time series forecasting analysis.

17 November 2021 in WIREs Data Mining and Knowledge Discovery
Verified
Journal Article
Open access
PDF file
CACuneyt Gurcan Akcora
Cuneyt Gurcan Akcora
YGYulia R. Gel
Yulia R. Gel
MKMurat Kantarcioglu
Murat Kantarcioglu
Blockchain is an emerging technology that has enabled many applications, from cryptocurrencies to digital asset management and supply chains. Due to this surge of popularity, analyzing the data stored on blockchains poses a new critical challenge in data science. To assist data scientists in various analytic tasks for a blockchain, in this tutorial, we provide a systematic and comprehensive overview of the fundamental elements of blockchain network models. We discuss how we can abstract blockchain data as various types of networks and further use such associated network abstractions to reap important insights on blockchains' structure, organization, and functionality.This article is categorized under: Technologies > Data Preprocessing Application Areas > Business and Industry Fundamental Concepts of Data and Knowledge > Data Concepts Fundamental Concepts of Data and Knowledge > Knowledge Representation

19 April 2023 in IEEE Transactions on Power Systems
Verified
Journal Article
Open access
YCYuzhou Chen
Yuzhou Chen
RJRoshni Anna Jacob
Roshni Anna Jacob
YGYulia R. Gel
Yulia R. Gel
JZJie Zhang
Jie Zhang
H. Vincent PoorH. Vincent Poor
H. Vincent Poor
With the increase in cyber-physical threats and extreme weather events, resilience of the power system has become a problem of utmost societal importance. In this paper, we propose a novel approach for resilience improvement of power distribution networks, based on the notions of persistent homology and simplicial neural networks (SNNs) which are new directions in graph learning. In particular, tools of persistent homology allow us to capture the most essential topological descriptors of the distribution network. In turn, extending the convolutional operation to simplicial complexes on the distribution network, using the Hodge-Laplacian analytics, enables us to describe complex interactions among multi-node higher order graph substructures. Such higher order graph substructures are of particular importance in distribution networks, since a change in power demand at a load bus (or the power supplied from a substation) will produce a corresponding perturbation in nodal variables (such as the bus voltages) and edge variables (such as branch currents). We validate our new Higher-Order Topological Neural Networks (HOT-Nets) model for contingency classification of three test distribution networks, the IEEE 37-bus feeder, IEEE 123-bus feeder, and the 342-bus low voltage network. Our experiment results on two case studies (i.e., (i) with sensors placed at all the buses alone in the networks and (ii) with partial observability in the networks) indicate that HOT-Nets substantially outperforms 9 state-of-the-art methods, yielding relative gains of up to 14.04% in terms of system resilience classification.

3 June 2021 in WIREs Computational Statistics
Verified
Journal Article
Closed access
PDF file
ADAsim K. Dey
Asim K. Dey
YTYahui Tian
Yahui Tian
YGYulia R. Gel
Yulia R. Gel

2 October 2019 in North American Actuarial Journal
Verified
Journal Article
Closed access
AGAzar Ghahari
Azar Ghahari
NNNathaniel K. Newlands
Nathaniel K. Newlands
VLVyacheslav Lyubchich
Vyacheslav Lyubchich
YGYulia R. Gel
Yulia R. Gel
Challenges in risk estimation for agricultural insurance bring to the fore statistical problems of modeling complex weather and climate dynamics, analyzing massive multi-resolution, multi-source data. Nonstationary space-time structure of such data also introduces greater complexity when assessing the highly nonlinear relationship between weather events and crop yields. In this setting, conventional parametric statistical and actuarial models may no longer be appropriate. In turn, modern machine learning and artificial intelligence procedures, which allow fast and automatic learning of hidden dependencies and structures, offer multiple operational benefits and now prove to deliver a highly competitive performance in a variety of applications, from credit card fraud detection to the next best product offer and customer segmentation. Yet their potential in actuarial sciences, and particularly agricultural insurance, remains largely untapped. In this project, we introduce a modern deep learning methodology into the assessment of climate-induced risks in agriculture and evaluate its potential to deliver a higher predictive accuracy, speed, and scalability. We present a pilot study of deep learning algorithms—specifically, deep belief networks—using historical crop yields, weather station–based records, and gridded weather reanalysis data for Manitoba, Canada from 1996 to 2011. Our findings show that deep learning can attain higher prediction accuracy, based on benchmarking its performance against more conventional approaches, especially in multiscale, heterogeneous data environments of agricultural risk management.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YCYuzhou Chen
Yuzhou Chen
JFJose Frias
Jose Frias
YGYulia R. Gel
Yulia R. Gel
Graph contrastive learning (GCL) has recently emerged as a new concept which allows for capitalizing on the strengths of graph neural networks (GNNs) to learn rich representations in a wide variety of applications which involve abundant unlabeled information. However, existing GCL approaches largely tend to overlook the important latent information on higher-order graph substructures. We address this limitation by introducing the concepts of topological invariance and extended persistence on graphs to GCL. In particular, we propose a new contrastive mode which targets topological representations of the two augmented views from the same graph, yielded by extracting latent shape properties of the graph at multiple resolutions. Along with the extended topological layer, we introduce a new extended persistence summary, namely, extended persistence landscapes (EPL) and derive its theoretical stability guarantees. Our extensive numerical results on biological, chemical, and social interaction graphs show that the new Topological Graph Contrastive Learning (TopoGCL) model delivers significant performance gains in unsupervised graph classification for 8 out of 12 considered datasets and also exhibits robustness under noisy scenarios.