Support vector machine (SVM) is a popular classification method for analysis of high dimensional data such as genomics data. Recently a number of linear SVM methods have been developed to achieve feature selection through either frequentist regularization or Bayesian shrinkage, but the linear assumption may not be plausible for many real applications. In addition, recent work has demonstrated that incorporating known biological knowledge, such as those from functional genomics, into the statistical analysis of genomic data offers great promise of improved predictive accuracy and feature selection. Such biological knowledge can often be represented by graphs. In this article, we propose a novel knowledge-guided nonlinear Bayesian SVM approach for analysis of high-dimensional data. Our model uses graph information that represents the relationship among the features to guide feature selection. To achieve knowledge-guided feature selection, we assign an Ising prior to the indicators representing inclusion/exclusion of the features in the model. An efficient MCMC algorithm is developed for posterior inference. The performance of our method is evaluated and compared with several penalized linear SVM and the standard kernel SVM method in terms of prediction and feature selection in extensive simulation studies. Also, analyses of genomic data from a cancer study show that our method yields a more accurate prediction model for patient survival and reveals biologically more meaningful results than the existing methods.CCD photometric observations of four main-belt and one near-Earth asteroid were made in 2019. Of these, the Vestoid 2602 Moore and Hungaria (27568) 2000 PT6 were confirmed to be binary asteroids. The Hungaria 3880 Kaiserman is a suspected binary. Near-Earth asteroid (142040) 2002 QE15 was found to have a long period (46.4 h). Re-evaluation of data for the asteroid from two previous apparitions found a secondary period that is consistent with the system being a candidate for the rare class of very wide binary asteroids. New analysis of the data from 2016 for Phocaea member 2937 Gibbs found two periods (the second being ambiguous). It could not be determined if the asteroid is binary or in a tumbling state.We present lists of asteroid photometry opportunities for objects reaching a favorable apparition and have no or poorly-defined lightcurve parameters. Additional data on these objects will help with shape and spin axis modeling via lightcurve inversion. We also include lists of objects that will or might be radar targets. Lightcurves for these objects can help constrain pole solutions and/or remove rotation period ambiguities that might not come from using radar data alone.Lightcurves for four L5 Jovian Trojan asteroids were obtained at the Center for Solar System Studies (CS3) from 2019 January to March. The suspected binary Trojan, 2207 Antenor was observed again and a single attenuation event was detected.CCD photometric observations of 10 main-belt asteroids were obtained from the Center for Solar System Studies from 2019 January to March. In light of recent period analysis, images of 2120 Tyumenia obtained in 2004 were re-examined. The resulting analysis found a period of 17.515 h, which is consistent with the recent results.We present lists of asteroid photometry opportunities for objects reaching a favorable apparition and have no or poorly-defined lightcurve parameters. Additional data on these objects will help with shape and spin axis modeling via lightcurve inversion. We also include lists of objects that will or might be radar targets. Lightcurves for these objects can help constrain pole solutions and/or remove rotation period ambiguities that might not come from using radar data alone.CCD photometric observations of the inner main-belt asteroid (20882) 2000 VH57 were made from 2018 Sept. 15 through Oct. 20. Analysis of the data showed that the asteroid is binary with a primary rotational period of 2.5586 hr and a satellite orbital period of 32.81 hr. Mutual eclipse/occultation events indicate a lower limit on the secondary-to-primary mean diameter ratio (Ds/Dp) of 0.23. During the period of observations, the primary and secondary lightcurves evolved as the viewing aspect changed. In particular, the depth of the secondary event increased significantly towards the end of the observations.Lightcurves for four Hilda asteroids were obtained at the Center for Solar System Studies (CS3) from 2018 September-November 3514 Hooke, 3557 Sokolsky, 4495 Dassanowksy, and 10331 Peterbluhm. 4495 Dassanowksy appears to be a binary asteroid with a primary period of either 2.6314 hr or 5.263 hr and an orbital period of 18.516 hr. The secondary-to-primary ratio of the effective diameters is 0.26 ± 0.02.Lightcurves for 32 near-Earth asteroids (NEAs) obtained at the Center for Solar System Studies (CS3) from 2018 September-December were analyzed for rotation period and signs of satellites or tumbling.In the last five years, deep learning (DL) has become the state-of-the-art tool for solving various tasks in medical image analysis. Among the different methods that have been proposed to improve the performance of Convolutional Neural Networks (CNNs), one typical approach is the augmentation of the training data set through various transformations of the input image. Data augmentation is typically used in cases where a small amount of data is available, such as the majority of medical imaging problems, to present a more substantial amount of data to the network and improve the overall accuracy. However, the ability of the network to improve the accuracy of the results when a slightly modified version of the same input is presented is often overestimated. This overestimation is the result of the strong correlation between data samples when they are considered independently in the training phase. In this paper, we emphasize the importance of optimizing for accuracy as well as precision among multiple replicates of the same training data in the context of data augmentation. To this end, we propose a new approach that leverages the augmented data to help the network focus on the precision through a specifically-designed loss function, with the ultimate goal to improve both the overall performance and the network's precision at the same time. https://www.selleckchem.com/products/ots964.html We present two different applications of DL (regression and segmentation) to demonstrate the strength of the proposed strategy. We think that this work will pave the way to a explicit use of data augmentation within the loss function that helps the network to be invariant to small variations of the same input samples, a characteristic that is always required to every application in the medical imaging field.