Uterine wall tension is thought to be an important determinant of the onset of labor in pregnant women. We characterize human uterine wall tension using ultrasound from the second trimester of pregnancy until parturition and compare preterm, term and twin pregnancies. A total of 320 pregnant women were followed from first antenatal visit to delivery during the period 2000–2004 at the John Hunter Hospital, NSW, Australia. The uterine wall thickness, length, anterior-posterior diameter and transverse diameter were determined by serial ultrasounds. Subjects were divided into three groups: women with singleton pregnancies and spontaneous labor onset, either preterm or term and women with twin pregnancies. Intrauterine pressure results from the literature were combined with our data to form trajectories for uterine wall thickness, volume and tension for each woman using the prolate ellipsoid method and the groups were compared at 20, 25 and 30 weeks gestation. Uterine wall tension followed an exponential curve, with results increasing throughout pregnancy with the site of maximum tension on the anterior wall. For those delivering preterm, uterine wall thickness was increased compared with term. For twin pregnancies intrauterine volume was increased compared to singletons (), but wall thickness was not. There was no evidence for increased tension in those delivering preterm or those with twin gestations. These data are not consistent with a role for high uterine wall tension as a causal factor in preterm spontaneous labor in singleton or twin gestations. It seems likely that hormonal differences in multiple gestations are responsible for increased rates of preterm birth in this group rather than increased tension.
The smart metering infrastructure has changed how electricity is measured in both residential and industrial application. The large amount of data collected by smart meter per day provides a huge potential for analytics to support the operation of a smart grid, an example of which is energy demand forecasting. Short term energy forecasting can be used by utilities to assess if any forecasted peak energy demand would have an adverse effect on the power system transmission and distribution infrastructure. It can also help in load scheduling and demand side management. Many techniques have been proposed to forecast time series including Support Vector Machine, Artificial Neural Network and Deep Learning. In this work we use Long Short Term Memory architecture to forecast 3-day ahead energy demand across each month in the year. The results show that 3-day ahead demand can be accurately forecasted with a Mean Absolute Percentage Error of 3.15%. In addition to that, the paper proposes way to quantify the time as a feature to be used in the training phase which is shown to affect the network performance.
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.