The outbreaks of Coronavirus Disease 2019 (COVID-19) have impacted the world significantly. Modeling the
trend of infection and real-time forecasting of cases can help decision making and control of the disease spread.
However, data-driven methods such as recurrent neural networks (RNN) can perform poorly due to limited
daily samples in time. In this work, we develop an integrated spatiotemporal model based on the epidemic
differential equations (SIR) and RNN. The former after simplification and discretization is a compact model
of temporal infection trend of a region while the latter models the effect of nearest neighboring regions. The
latter captures latent spatial information. We trained and tested our model on COVID-19 data in Italy, and
show that it out-performs existing temporal models (fully connected NN, SIR, ARIMA) in 1-day, 3-day, and
1-week ahead forecasting especially in the regime of limited training data.
more »
« less
An Integrated Recurrent Neural Network and Regression Model with Spatial and Climatic Couplings for Vector-borne Disease Dynamics
We developed an integrated recurrent neural network and nonlinear regression spatio-temporal model for vector-borne disease evolution. We take into account climate data and seasonality as external factors that correlate with disease transmitting insects (e.g. flies), also spill-over infections from neighboring regions surrounding a region of interest. The climate data is encoded to the model through a quadratic embedding scheme
motivated by recommendation systems. The neighboring regions’ influence is modeled by a long short-term memory neural network. The integrated model is trained by stochastic gradient descent and tested on leishmaniasis data in Sri Lanka from 2013-2018 where infection outbreaks occurred. Our model out-performed
ARIMA models across a number of regions with high infections, and an associated ablation study renders support to our modeling hypothesis and ideas.
more »
« less
- NSF-PAR ID:
- 10339405
- Date Published:
- Journal Name:
- International Conference on Pattern Recognition Applications and Methods
- Page Range / eLocation ID:
- 505 to 510
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The outbreaks of Coronavirus Disease 2019 (COVID-19) have impacted the world significantly. Modeling the trend of infection and realtime forecasting of cases can help decision making and control of the disease spread. However, data-driven methods such as recurrent neural networks (RNN) can perform poorly due to limited daily samples in time. In this work, we develop an integrated spatiotemporal model based on the epidemic differential equations (SIR) and RNN. The former after simplification and discretization is a compact model of temporal infection trend of a region while the latter models the effect of nearest neighboring regions. The latter captures latent spatial information. We trained and tested our model on COVID-19 data in Italy, and show that it out-performs existing temporal models (fully connected NN, SIR, ARIMA) in 1-day, 3-day, and 1-week ahead forecasting especially in the regime of limited training data.more » « less
-
more » « less
Abstract A dramatic increase in the number of outbreaks of dengue has recently been reported, and climate change is likely to extend the geographical spread of the disease. In this context, this paper shows how a neural network approach can incorporate dengue and COVID-19 data as well as external factors (such as social behaviour or climate variables), to develop predictive models that could improve our knowledge and provide useful tools for health policy makers. Through the use of neural networks with different social and natural parameters, in this paper we define a
Correlation Model through which we show that the number of cases of COVID-19 and dengue have very similar trends. We then illustrate the relevance of our model by extending it to a Long short-term memory model (LSTM) that incorporates both diseases, and using this to estimate dengue infections via COVID-19 data in countries that lack sufficient dengue data. -
more » « less
Abstract Disease dynamics are governed by variation of individuals, species, and environmental conditions across space and time. In some cases, an alternate reservoir host amplifies pathogen loads and drives disease transmission to less competent hosts in a process called pathogen spillover. Spillover is frequently associated with multi‐host disease systems where a single species is more tolerant of infection and more competent in pathogen transmission compared to other hosts. Pathogen spillover must be driven by biotic factors, including host and community characteristics, yet biotic factors interact with the abiotic environment (e.g., temperature) to create disease. Despite its fundamental role in disease dynamics, the influence of the abiotic environment on pathogen spillover has seldom been examined. Improving our understanding of disease processes such as pathogen spillover hinges on disentangling the effects of interrelated biotic and abiotic factors over space and time. We applied 10 yr of fine‐scale microclimate, disease, and tree community data in a path analysis to investigate the relative influence of biotic and abiotic factors on pathogen spillover for the emerging infectious forest disease sudden oak death (
SOD ). Disease transmission inSOD is primarily driven by the reservoir host California bay laurel, which supports high foliar pathogen loads that spillover onto neighboring oak trees and create lethal canker infections. The foliar pathogen load and susceptibility of oaks is expected to be sensitive to forest microclimate conditions. We found that biotic factors of pathogen load and tree diversity had relatively stronger effects on pathogen spillover compared to abiotic microclimate factors, with pathogen load increasing oak infection and tree diversity reducing oak infection. Abiotic factors still had significant effects, with greater heat exposure during summer months reducing pathogen loads and optimal pathogen conditions during the wet season increasing oak infection. Our results offer clues to possible disease dynamics under future climate change where hotter and drier or warmer and wetter conditions could have opposing effects on pathogen spillover in theSOD system. Disentangling direct and indirect effects of biotic and abiotic factors affecting disease processes can provide key insights into disease dynamics including potential avenues for reducing disease spread and predicting future epidemics. -
more » « less
During the 1950s, the Gros Michel species of bananas were nearly wiped out by the incurable Fusarium Wilt, also known as Panama Disease. Originating in Southeast Asia, Fusarium Wilt is a banana pandemic that has been threatening the multi-billion-dollar banana industry worldwide. The disease is caused by a fungus that spreads rapidly throughout the soil and into the roots of banana plants. Currently, the only way to stop the spread of this disease is for farmers to manually inspect and remove infected plants as quickly as possible, which is a time-consuming process. The main purpose of this study is to build a deep Convolutional Neural Network (CNN) using a transfer learning approach to rapidly identify Fusarium wilt infections on banana crop leaves. We chose to use the ResNet50 architecture as the base CNN model for our transfer learning approach owing to its remarkable performance in image classification, which was demonstrated through its victory in the ImageNet competition. After its initial training and fine-tuning on a data set consisting of 600 healthy and diseased images, the CNN model achieved near-perfect accuracy of 0.99 along with a loss of 0.46 and was fine-tuned to adapt the ResNet base model. ResNet50’s distinctive residual block structure could be the reason behind these results. To evaluate this CNN model, 500 test images, consisting of 250 diseased and healthy banana leaf images, were classified by the model. The deep CNN model was able to achieve an accuracy of 0.98 and an F-1 score of 0.98 by correctly identifying the class of 492 of the 500 images. These results show that this DCNN model outperforms existing models such as Sangeetha et al., 2023’s deep CNN model by at least 0.07 in accuracy and is a viable option for identifying Fusarium Wilt in banana crops.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.5220/0010762700003122
