Abstract-Power companies can benefit from the use of knowledge discovery methods and statistical machine learning for preventive maintenance. We introduce a general process for transforming historical electrical grid data into models that aim to predict the risk of failures for components and systems. These models can be used directly by power companies to assist with prioritization of maintenance and repair work. Specialized versions of this process are used to produce 1) feeder failure rankings, 2) cable, joint, terminator and transformer rankings, 3) feeder MTBF (Mean Time Between Failure) estimates and 4) manhole events vulnerability rankings. The process in its most general form can handle diverse, noisy, sources that are historical (static), semi-real-time, or real-time, incorporates state-of-the-art machine learning algorithms for prioritization (supervised ranking or MTBF), and includes an evaluation of results via cross-validation and blind test. Above and beyond the ranked lists and MTBF estimates are business management interfaces that allow the prediction capability to be integrated directly into corporate planning and decision support; such interfaces rely on several important properties of our general modeling approach: that machine learning features are meaningful to domain experts, that the processing of data is transparent, and that prediction results are accurate enough to support sound decision making. We discuss the challenges in working with historical electrical grid data that were not designed for predictive purposes. The "rawness" of these data contrasts with the accuracy of the statistical models that can be obtained from the process; these models are sufficiently accurate to assist in maintaining New York City's electrical grid.Index Terms-applications of machine learning, electrical grid, smart grid, knowledge discovery, supervised ranking, computational sustainability, reliability !
BackgroundAdverse pregnancy outcomes (APOs) affect a large proportion of pregnancies and represent an important cause of morbidity and mortality worldwide. Yet, the pathophysiology of APOs is poorly understood, limiting our ability to prevent and treat these conditions.ObjectiveTo search for genetic risk markers for four APOs, we performed genome-wide association studies (GWAS) for preterm birth, preeclampsia, gestational diabetes, and pregnancy loss.Study DesignA total of 9,757 nulliparas from the nuMoM2b study were genotyped. We clustered participants by their genetic ancestry and focused our analyses on the three sub-cohorts with the largest sample sizes: European (EUR, n=6,082), African (AFR, n=1,425), and American (AMR, n=846). Association tests were carried out separately for each sub-cohort and brought together via meta-analysis. Four APOs were tested by GWAS: preeclampsia (n=7,909), gestational length (n=4,781), gestational diabetes (n=7,617), and pregnancy loss (n=7,809). Using the results of the genome-wide associations for each APO, SNP-based heritability of these traits was inferred using LDscore. Putative regulatory effects were inferred by transcriptome-wide association analysis.ResultsTwo variants were significantly associated with pregnancy loss (rs62021480: OR = 3.29, P = 7.83×10−11, and rs142795512: OR = 4.72, P = 9.64×10−9), implicating genes TRMU and RGMA in this APO. An intronic variant was significantly associated with gestational length (rs73842644: beta = -0.667, P = 4.9×10−8). Three loci were significantly associated with gestational diabetes (rs72956265: OR = 3.09, P = 2.98×10−8, rs10890563: OR = 1.88, P = 3.53×10−8, rs117689036: OR = 3.15, P = 1.46×10−8), located on or near ZBTB20, GUCY1A2, and MDGA2, respectively. Several loci previously correlated with preterm birth (in genes WNT4, EBF1, PER3, IL10, and ADCY5), gestational diabetes (in TCF7L2), and preeclampsia (in MTHFR) were found to be associated with these outcomes in our cohort as well.ConclusionOur study identified genetic associations with gestational diabetes, pregnancy loss, and gestational length. We also confirm correlations of several previously identified variants with these APOs.Disclosure StatementThe authors declare no conflict of interestSource of financial supportPrecision Health Initiative of Indiana University, National Institutes of Health award R01HD101246 to DMH and PR. Cooperative agreement funding from the National Heart, Lung, and Blood Institute and the Eunice Kennedy Shriver National Institute of Child Health and Human Development: grant U10-HL119991 to RTI International; grant U10-HL119989 to Case Western Reserve University; grants U10-HL120034 and R01LM013327 to Columbia University; grant U10-HL119990 to Indiana University; grant U10-HL120006 to the University of Pittsburgh; grant U10-HL119992 to Northwestern University; grant U10-HL120019 to the University of California, Irvine; grant U10-HL119993 to University of Pennsylvania; and grant U10-HL120018 to the University of Utah. National Center for Research Resources and the National Center for Advancing Translational Sciences, National Institutes of Health to Clinical and Translational Science Institutes at Indiana University (grant UL1TR001108) and University of California, Irvine (grant UL1TR000153).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.