scholarly journals Predicting the tripartite network of mosquito-borne disease

2021 ◽  
Author(s):  
Tad Dallas ◽  
Sadie Jane Ryan ◽  
Ben Bellekom ◽  
Anna Claire Fagre ◽  
Rebecca Christofferson ◽  
...  
Keyword(s):  
North America ◽  
Predictive Models ◽  
Model Development ◽  
Model Performance ◽  
Vector Biology ◽  
Vector Transmission ◽  
Geographic Scope ◽  
Complex Interactions ◽  
Virus Interactions ◽  
Intermediate Vector

The potential for a pathogen to infect a host is mediated by traits of both the host and pathogen, as well as the complex interactions between them. Arthropod-borne viruses (arboviruses) require an intermediate vector, introducing an additional compatibility layer. Existing predictive models of host-virus networks rarely incorporate the unique aspects of vector transmission, instead treating vector biology as a hidden, unobserved layer. We explore two possible extensions to address this: first, we added vector traits into predictions of the bipartite host-virus network; and second, we used host, vector, and virus traits to predict the tripartite host-vector-virus network. We tested both approaches on mosquito-borne flaviviruses of mammals. Using host-virus models, we find that the inclusion of vector traits may improve inference in some cases, while viral traits proved to be the most important for model performance. Further, we found that it was possible, though quite difficult, to predict full tripartite (host-vector-virus) links. Both approaches are interesting avenues for further model development, but our results keenly underscore a need to collect more comprehensive datasets to characterize arbovirus ecology, across a wide and less biased geographic scope, especially outside of North America, and to better identify molecular traits that underpin host-vector-virus interactions.

scholarly journals Using GOME NO<sub>2</sub> satellite data to examine regional differences in TOMCAT model performance

2004 ◽  
Vol 4 (3) ◽  
pp. 2569-2613
Author(s):  
N. H. Savage ◽  
K. S. Law ◽  
J. A. Pyle ◽  
A. Richter ◽  
H. Nüß ◽  
...  
Keyword(s):  
North America ◽  
Case Studies ◽  
Biomass Burning ◽  
Satellite Data ◽  
Atmospheric Chemistry ◽  
Regional Differences ◽  
Model Development ◽  
Vertical Mixing ◽  
Model Performance ◽  
Model Treatment

Abstract. This paper compares column measurements of NO2 made by the GOME instrument on ERS-2 to model results from the TOMCAT global CTM. The overall correlation between the model and observations is good (0.79 for the whole world, and 0.89 for north America) but the modelled columns are too large over polluted areas (gradient of 1.4 for North America and 1.9 for Europe). NO2 columns in the region of outflow from North America into the Atlantic seem too high in winter in the model compared to the GOME results, whereas the modelled columns are too small off the coast of Africa where there appear to be biomass burning plumes in the satellite data. Several hypotheses are presented to explain these discrepancies. Weaknesses in the model treatment of vertical mixing and chemistry appear to be the most likely explanations. It is shown that GOME and other satellite data will be of great value in furthering our understanding of atmospheric chemistry and in targeting and testing future model development and case studies.

scholarly journals Climate drivers of plague epidemiology in British India, 1898–1949

2020 ◽  
Vol 287 (1928) ◽  
pp. 20200538
Author(s):  
Warren S. D. Tennant ◽  
Mike J. Tildesley ◽  
Simon E. F. Spencer ◽  
Matt J. Keeling
Keyword(s):  
Predictive Models ◽  
Control Measures ◽  
Climate Data ◽  
British India ◽  
Middle Income ◽  
Middle Income Countries ◽  
Complex Interactions ◽  
The World ◽  
Spatio Temporal

Plague, caused by Yersinia pestis infection, continues to threaten low- and middle-income countries throughout the world. The complex interactions between rodents and fleas with their respective environments challenge our understanding of human plague epidemiology. Historical long-term datasets of reported plague cases offer a unique opportunity to elucidate the effects of climate on plague outbreaks in detail. Here, we analyse monthly plague deaths and climate data from 25 provinces in British India from 1898 to 1949 to generate insights into the influence of temperature, rainfall and humidity on the occurrence, severity and timing of plague outbreaks. We find that moderate relative humidity levels of between 60% and 80% were strongly associated with outbreaks. Using wavelet analysis, we determine that the nationwide spread of plague was driven by changes in humidity, where, on average, a one-month delay in the onset of rising humidity translated into a one-month delay in the timing of plague outbreaks. This work can inform modern spatio-temporal predictive models for the disease and aid in the development of early-warning strategies for the deployment of prophylactic treatments and other control measures.

scholarly journals Towards scalable and reusable predictive models for cyber twins in manufacturing systems

2021 ◽  
Author(s):  
Cinzia Giannetti ◽  
Aniekan Essien
Keyword(s):  
Data Streams ◽  
Predictive Models ◽  
Manufacturing Systems ◽  
Model Building ◽  
Model Performance ◽  
Cyberphysical Systems ◽  
Pragmatic Approach ◽  
Analyse Data ◽  
Fully Connected ◽  
Smart Factories

AbstractSmart factories are intelligent, fully-connected and flexible systems that can continuously monitor and analyse data streams from interconnected systems to make decisions and dynamically adapt to new circumstances. The implementation of smart factories represents a leap forward compared to traditional automation. It is underpinned by the deployment of cyberphysical systems that, through the application of Artificial Intelligence, integrate predictive capabilities and foster rapid decision-making. Deep Learning (DL) is a key enabler for the development of smart factories. However, the implementation of DL in smart factories is hindered by its reliance on large amounts of data and extreme computational demand. To address this challenge, Transfer Learning (TL) has been proposed to promote the efficient training of models by enabling the reuse of previously trained models. In this paper, by means of a specific example in aluminium can manufacturing, an empirical study is presented, which demonstrates the potential of TL to achieve fast deployment of scalable and reusable predictive models for Cyber Manufacturing Systems. Through extensive experiments, the value of TL is demonstrated to achieve better generalisation and model performance, especially with limited datasets. This research provides a pragmatic approach towards predictive model building for cyber twins, paving the way towards the realisation of smart factories.

Abstract 223: Non-Cardiac Comorbidities in Predictive Models for Valvular Heart Disease Interventions

2016 ◽  
Vol 9 (suppl_2) ◽  
Author(s):  
Benjamin Wessler ◽  
Christine Lundquist ◽  
Gowri Raman ◽  
Jennifer Lutz ◽  
Jessica Paulus ◽  
...  
Keyword(s):  
Heart Disease ◽  
Predictive Models ◽  
Valvular Heart Disease ◽  
De Novo ◽  
Predictive Analytics ◽  
Model Performance ◽  
Median Number ◽  
Valve Surgery ◽  
Comorbid Condition ◽  
Comorbid Conditions

Background: Interventions for patients with valvular heart disease (VHD) now include both surgical and percutaneous procedures. As a result, treatments are being offered to increasingly complex patients with a significant burden of non-cardiac comorbid conditions. There is a major gap in our understanding of how various comorbidities relate to prognosis following interventions for VHD. Here we describe how comorbidities are handled in clinical predictive models for patients undergoing interventions for VHD. Methods: We queried the Tufts Predictive Analytics and Comparative Effectiveness (PACE) Clinical Prediction Model (CPM) Registry to identify de novo CPMs for patients undergoing VHD interventions. We systematically extracted information on the non-cardiac comorbidities contained in the CPMs and also measures of model performance. Results: From January 1990- May 2012 there were 12 CPMs predicting measures of morbidity or mortality for patients undergoing interventions for VHD. There were 2 CPMs predicting outcomes for isolated aortic valve replacement, 3 CPMs predicting outcomes for isolated mitral valve surgery, and 7 models predicting outcomes for a combination of valve surgery subtypes. Ten out of twelve (83%) of the CPMs for patients undergoing interventions for VHD predicted mortality. The median number of non-cardiac comorbidities included in the CPMs was 4 (range 0-7). All of the CPMs predicting mortality included at least 1 comorbid condition. The top 3 most common comorbidities included in these CPMs were, renal dysfunction (10/12, 83%), prior CVA (7/12, 58%) and measures of BMI/BSA (7/12, 58%). Diabetes was present in only 25% (3/12) of the models and chronic lung disease in only 17% (2/12). Conclusions: Non-cardiac comorbidities are frequently found in CPMs predicting morbidity and mortality following interventions for VHD. There is significant variation in the number and type of specific comorbid conditions included in these CPMs. More work is needed to understand the directionality, magnitude, and consistency of effect of these non-cardiac comorbid conditions for patients undergoing interventions for VHD.

scholarly journals IDENTIFYING KEY FACTORS OF COMMUTER TRAIN SERVICE QUALITY:AN EMPIRICAL ANALYSIS FOR DHAKA CITY

2019 ◽  
Vol 31 (2) ◽  
Author(s):  
Anika Nowshin Mowrin ◽  
Md. Hadiuzzaman ◽  
Saurav Barua ◽  
Md. Mizanur Rahman
Keyword(s):  
Traffic Congestion ◽  
Fuzzy Inference ◽  
Confusion Matrix ◽  
Model Development ◽  
Model Performance ◽  
Total Sample ◽  
Dhaka City ◽  
Anfis Model ◽  
Regular User ◽  
Inference System

Commuter train is a viable alternative to road transport to ease the traffic congestion which requires appropriate planning by concerned authorities. The research is aimed to assess passengers’ perception about commuter train service running in areas near Dhaka city. An Adaptive Neuro Fuzzy Inference System (ANFIS) model has been developed to evaluate service quality (SQ) of commuter train. Field survey data has been conducted among 802 respondents who were the regular user of commuter train and 12 attributes have been selected for model development. ANFIS was developed by the training and then tested by 80% and 20% of the total sample respectively. After that, model performance has been evaluated by (i) Confusion Matrix (ii) Root Mean Square Error (RMSE) and attributes are ranked based on their relative importance. The proposed ANFIS model has 61.50% accuracy in training and 47.80% accuracy in testing.  From the results, it is found that 'Bogie condition', 'Cleanliness', ‘Female harassment’, 'Behavior of staff' and 'Toilet facility' are the most significant attributes. This indicates that some necessary measures should be taken immediately to recover the effects of these attributes to improve the SQ of commuter train. 

scholarly journals Using Model Performance to Assess the Representativeness of Data for Model Development and Calibration in Financial Institutions

Risks ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 204
Author(s):  
Chamay Kruger ◽  
Willem Daniel Schutte ◽  
Tanja Verster
Keyword(s):  
Case Studies ◽  
Model Development ◽  
Model Performance ◽  
Data Set ◽  
Pooled Data ◽  
External Data ◽  
First Case ◽  
Multivariate Prediction ◽  
Credit Data

This paper proposes a methodology that utilises model performance as a metric to assess the representativeness of external or pooled data when it is used by banks in regulatory model development and calibration. There is currently no formal methodology to assess representativeness. The paper provides a review of existing regulatory literature on the requirements of assessing representativeness and emphasises that both qualitative and quantitative aspects need to be considered. We present a novel methodology and apply it to two case studies. We compared our methodology with the Multivariate Prediction Accuracy Index. The first case study investigates whether a pooled data source from Global Credit Data (GCD) is representative when considering the enrichment of internal data with pooled data in the development of a regulatory loss given default (LGD) model. The second case study differs from the first by illustrating which other countries in the pooled data set could be representative when enriching internal data during the development of a LGD model. Using these case studies as examples, our proposed methodology provides users with a generalised framework to identify subsets of the external data that are representative of their Country’s or bank’s data, making the results general and universally applicable.

scholarly journals MOSTWAS: Multi-Omic Strategies for Transcriptome-Wide Association Studies

2020 ◽  
Author(s):  
Arjun Bhattacharya ◽  
Yun Li ◽  
Michael I. Love
Keyword(s):  
Gene Expression ◽  
Transcription Factors ◽  
Brain Tissue ◽  
Predictive Models ◽  
Association Studies ◽  
Genetic Regulation ◽  
Breast Tumors ◽  
Risk Genes ◽  
Complex Interactions ◽  
Trait Associations

ABSTRACTTraditional predictive models for transcriptome-wide association studies (TWAS) consider only single nucleotide polymorphisms (SNPs) local to genes of interest and perform parameter shrinkage with a regularization process. These approaches ignore the effect of distal-SNPs or other molecular effects underlying the SNP-gene association. Here, we outline multi-omics strategies for transcriptome imputation from germline genetics to allow more powerful testing of gene-trait associations by prioritizing distal-SNPs to the gene of interest. In one extension, we identify mediating biomarkers (CpG sites, microRNAs, and transcription factors) highly associated with gene expression and train predictive models for these mediators using their local SNPs. Imputed values for mediators are then incorporated into the final predictive model of gene expression, along with local SNPs. In the second extension, we assess distal-eQTLs (SNPs associated with genes not in a local window around it) for their mediation effect through mediating biomarkers local to these distal-eSNPs. Distal-eSNPs with large indirect mediation effects are then included in the transcriptomic prediction model with the local SNPs around the gene of interest. Using simulations and real data from ROS/MAP brain tissue and TCGA breast tumors, we show considerable gains of percent variance explained (1-2% additive increase) of gene expression and TWAS power to detect gene-trait associations. This integrative approach to transcriptome-wide imputation and association studies aids in identifying the complex interactions underlying genetic regulation within a tissue and important risk genes for various traits and disorders.AUTHOR SUMMARYTranscriptome-wide association studies (TWAS) are a powerful strategy to study gene-trait associations by integrating genome-wide association studies (GWAS) with gene expression datasets. TWAS increases study power and interpretability by mapping genetic variants to genes. However, traditional TWAS consider only variants that are close to a gene and thus ignores important variants far away from the gene that may be involved in complex regulatory mechanisms. Here, we present MOSTWAS (Multi-Omic Strategies for TWAS), a suite of tools that extends the TWAS framework to include these distal variants. MOSTWAS leverages multi-omic data of regulatory biomarkers (transcription factors, microRNAs, epigenetics) and borrows from techniques in mediation analysis to prioritize distal variants that are around these regulatory biomarkers. Using simulations and real public data from brain tissue and breast tumors, we show that MOSTWAS improves upon traditional TWAS in both predictive performance and power to detect gene-trait associations. MOSTWAS also aids in identifying possible mechanisms for gene regulation using a novel added-last test that assesses the added information gained from the distal variants beyond the local association. In conclusion, our method aids in detecting important risk genes for traits and disorders and the possible complex interactions underlying genetic regulation within a tissue.

scholarly journals Modelling streamflow response to hydro-climatic variables in the Upper Mkomazi River, South Africa

2014 ◽  
Author(s):  
◽  
Oluwaseun Kunle Oyebode
Keyword(s):  
South Africa ◽  
Water Resources ◽  
Genetic Programming ◽  
Predictive Models ◽  
Model Development ◽  
De Algorithm ◽  
Planning And Management ◽  
Ann Models ◽  
Artificial Neural

Streamflow modelling remains crucial to decision-making especially when it concerns planning and management of water resources systems in water-stressed regions. This study proposes a suitable method for streamflow modelling irrespective of the limited availability of historical datasets. Two data-driven modelling techniques were applied comparatively so as to achieve this aim. Genetic programming (GP), an evolutionary algorithm approach and a differential evolution (DE)-trained artificial neural network (ANN) were used for streamflow prediction in the upper Mkomazi River, South Africa. Historical records of streamflow and meteorological variables for a 19-year period (1994- 2012) were used for model development and also in the selection of predictor variables into the input vector space of the models. In both approaches, individual monthly predictive models were developed for each month of the year using a 1-year lead time. Two case studies were considered in development of the ANN models. Case study 1 involved the use of correlation analysis in selecting input variables as employed during GP model development, while the DE algorithm was used for training and optimizing the model parameters. However in case study 2, genetic programming was incorporated as a screening tool for determining the dimensionality of the ANN models, while the learning process was further fine-tuned by subjecting the DE algorithm to sensitivity analysis. Altogether, the performance of the three sets of predictive models were evaluated comparatively using three statistical measures namely, Mean Absolute Percent Error (MAPE), Root Mean-Squared Error (RMSE) and coefficient of determination (R2). Results showed better predictive performance by the GP models both during the training and validation phases when compared with the ANNs. Although the ANN models developed in case study 1 gave satisfactory results during the training phase, they were unable to extensively replicate those results during the validation phase. It was found that results from case study 1 were considerably influenced by the problems of overfitting and memorization, which are typical of ANNs when subjected to small amount of datasets. However, results from case study 2 showed great improvement across the three evaluation criteria, as the overfitting and memorization problems were significantly minimized, thus leading to improved accuracy in the predictions of the ANN models. It was concluded that the conjunctive use of the two evolutionary computation methods (GP and DE) can be used to improve the performance of artificial neural networks models, especially when availability of datasets is limited. In addition, the GP models can be deployed as predictive tools for the purpose of planning and management of water resources within the Mkomazi region and KwaZulu-Natal province as a whole.

Communality from equal weight for GIS-based landslide susceptibility mapping

2020 ◽  
Author(s):  
Sandip Som ◽  
Saibal Ghosh ◽  
Soumitra Dasgupta ◽  
Thrideep Kumar ◽  
J. N. Hindayar ◽  
...  
Keyword(s):  
Land Use Planning ◽  
Landslide Susceptibility ◽  
Regional Scale ◽  
Model Development ◽  
Model Performance ◽  
Roc Curves ◽  
Landslide Inventory ◽  
Landslide Susceptibility Mapping ◽  
Equal Weight ◽  
Landslide Susceptibility Index

Abstract Modeling landslide susceptibility is one of the important aspects of land use planning and risk management. Several modeling methods are available based either on highly specialized knowledge on causative attributes or on good landslide inventory data to use as training and testing attribute on model development. Understandably, these two criteria are rarely available for local land regulators. This paper presents a new model methodology, which requires minimum knowledge of causative attributes and does not depend on landslide inventory. As landslide causes due to the combined effect of causative attributes, this model utilizes communality (common variance) of the attributes, extracted by exploratory factor analysis and used for calculation of landslide susceptibility index. The model can understand the inter-relationship of different geo-environmental attributes responsible for landslide along with identification and prioritization of attributes on model performance to delineate non-performing attributes. Finally, the model performance is compared with the well established AHP method (knowledge driven) and FRM method (data driven) by cut-off independent ROC curves along with cost-effectiveness. The model shows it’s performance almost at par with the established models, involving minimum modeling expertise. The findings and results of the present work will be helpful for the town planners and engineers on a regional scale for generalized planning and assessment.

Sign in / Sign up

Export Citation Format

Share Document