Structure dependent weather normalization

Data-Dependent Path Normalization in Neural Networks

We propose a unified framework for neural net normalization, regularization and optimization, which includes Path-SGD and Batch-Normalization and interpolates between them across two different dimensions. Through this framework we investigate issue of invariance of the optimization, data dependence and the connection with natural gradients.

Content Normalization for Text-Dependent Speaker Verification

Subspace based techniques, such as i-vector and Joint Factor Analysis (JFA) have shown to provide state-of-the-art performance for fixed phrase based text-dependent speaker verification. However, the error rates of such systems on the random digit task of RSR dataset are higher than that of Gaussian Mixture Model-Universal Background Model (GMM-UBM). In this paper, we aim at improving i-vector ...

Illumination Normalization Using Local Graph Structure

The problem associated with Illumination variation is one of the major problems in image processing, pattern recognition, medical image, etc; hence there is a need to handle and deal with such variations. This paper presents a novel and efficient algorithm for images illumination correction call local graph structure (LGS). LGS features are derived from a general definition of texture in a loca...

cDNA Microarray Data Normalization

Modeling and Weather-normalization of Wholehouse Metered Data for Residential End-use

A methodology is presented for modeling load shapes in the residential sector by using hourly whole-house metered data and temperature. Individual household-level load data are analyzed to achieve data smoothing (noise rejection) and comprcssiOn (in the ratio of approximately WA), and to disaggregate the weatherdependent and weather-independent components of the load. The weather-independent (l...