Search

Missing data is a prevailing problem in predictive analytics. In this paper, a winner‐take‐all (WTA) autoencoder‐based piecewise linear model is developed to solve the nonlinear regression problem under the missing value scenario, which consists of two parts: an overcomplete WTA autoencoder and a gated linear network. The overcomplete WTA autoencoder is a stacked denoising autoencoder (SDAE) designed to play two roles: (1) to estimate the missing values; (2) to realize a sophisticated partitioning by generating a broad set of binary gate control sequences. Besides, an iterative algorithm with renewed teacher signals is developed to train the SDAE. On the other hand, the gated linear network with the generated binary gate control sequences implements a flexible piecewise linear model for nonlinear regression. By composing a quasi‐linear kernel based on the gate control sequences, the piecewise linear model is then identified in the same way as a support vector regression. Experimental results have shown that our proposed hybrid model has a better performance than traditional models. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

In both the research and engineering fields, missing data is a serious problem that cannot be overlooked. Therefore, available datasets with missing data are a challenge to be modeled by conventional global prediction models. In this paper, we propose a hybrid model consisting of an autoencoder and a gated linear network for solving the regression problem under missing value scenario. A sophisticated modeling and identifying algorithm is developed. First, an extended affinity propagation (AP) clustering algorithm is applied to obtain a self‐organized competitive net dividing the datasets into several clusters. Second, a multiple imputation tool with top p% winner‐take‐all denoising autoencoders (DAE) is introduced to realize better predictions of missing values, in which rough estimates of missing values by using the mean imputation and similarity method within the clusters are used as teacher signals of DAE. Finally, a gated linear network is designed to construct a piecewise linear regression model with interpolations in the exact same way as a support vector regression with a quasilinear kernel composed using the cluster information obtained in the AP clustering step. Based on the experiments of five datasets, our proposed method demonstrates its effectiveness and robustness compared with other traditional kernels and state‐of‐the‐art methods, even on datasets with a large percentage of missing values. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Summary: Areal BMD (aBMD) from DXA is not a sufficiently accurate predictor of fracture. Novel volumetric BMD derived from 3D modeling of the hip from DXA images significantly improved the predictive ability for hip fracture relative to aBMD at the femoral neck, but not aBMD at the total hip. Introduction: To clarify whether volumetric and geometric indices derived from novel three-dimensional (3D) modeling of the hip using dual-energy X-ray absorptiometric (DXA) images improve hip fracture prediction relative to areal bone mineral density (aBMD). Methods: We examined 1331 women who had completed the baseline survey and at least one follow-up survey over 20 years (age 40–79 years at baseline). Each survey included aBMD measurement at the hip by DXA. Volumetric and geometric indices of the hip at baseline and the 10-year follow-up were estimated from DXA images using a 3D modeling algorithm. Incident hip fractures during the 20-year follow-up period were identified through self-report. Cox proportional hazards regression models allowing for repeated measurements of predictors and outcomes were constructed, and their predictive ability for hip fracture was evaluated using areas under receiver operating characteristic curves (AUCs) and net reclassification improvement (NRI) over aBMD at the femoral neck (FN) and total hip (TH) as references. Results: During a median follow-up of 19.8 years, 68 incident hip fractures were identified (2.22/1000 person-years). A significantly larger AUC of trabecular volumetric BMD (vBMD) at the total hip (AUC = 0.741), femoral neck (AUC = 0.748), and intertrochanter (AUC = 0.738) and significant NRI (0.177, 0.149, and 0.195, respectively) were observed compared with FN-aBMD (AUC = 0.701), but not TH-aBMD. Conclusions: vBMD obtained from 3D modeling using routinely obtained hip DXA images significantly improved hip fracture risk prediction over conventional FN-aBMD, but not TH-aBMD. Trial registration: The Japanese Population-Based Osteoporosis (JPOS) Cohort Study was retrospectively registered as UMIN000032869 in the UMIN Clinical Trials Registry on July 1, 2018. [ABSTRACT FROM AUTHOR]

The article focuses on a study which examines large-scale observational evidence of cross-cultural differences in facial behavior using advanced in computer science. Topics discussed include the automated facial coding used, the reliability of the facial action unit detection algorithms across different testing subsets, multilevel regression estimates predicting each facial action's base rate percentage.

Traffic forecasting is used for circuit dimensions and income prediction. Traffic forecasting in Japan has been carried out mainly by multiple regression models. However, recently, a traffic forecasting method using the Kalman filter for a state space model was proposed by David and Pack. When such a forecasting method is used, it is necessary to cope with outliers correspond to the outliers of noises in the state space model, an algorithm for detecting and discriminating outliers considering the noise distributions is developed. A new traffic forecasting method with a state space model including this algorithm is proposed. This method detects and discriminates changes in traffic patterns, and applies the necessary dispositions. The validity of this method is confirmed by applying it to field data [ABSTRACT FROM AUTHOR]