搜索结果: 1-7 共查到“科学技术统计学 classification”相关记录7条 . 查询时间(0.137 秒)
Vanilla Lasso for sparse classification under single index models
Vanilla Lasso sparse classification single index models
2016/1/20
This paper study sparse classification problems. We show that under single-index models, vanilla Lasso could give good estimate of unknown parameters. With this result, we see that even if the model i...
Classification of Segments in PolSAR Imagery by Minimum Stochastic Distances Between Wishart Distributions
Region-Based Classification Stochastic Distances Hypothesis Tests Polarimetry Wishart distribution
2013/4/28
A new classifier for Polarimetric SAR (PolSAR) images is proposed and assessed in this paper. Its input consists of segments, and each one is assigned the class which minimizes a stochastic distance. ...
Hybrid Maximum Likelihood Modulation Classification Using Multiple Radios
Modulation classification data fusion ML esti-mation EM algorithm
2013/4/28
The performance of a modulation classifier is highly sensitive to channel signal-to-noise ratio (SNR). In this paper, we focus on amplitude-phase modulations and propose a modulation classification fr...
Inverse Signal Classification for Financial Instruments
time-series classification signal analysis decision tree learning
2013/4/28
The paper presents new machine learning methods: signal composition, which classifies time-series regardless of length, type, and quantity; and self-labeling, a supervised-learning enhancement. The pa...
On false discovery rate thresholding for classification under sparsity
false discovery rate thresholding classification under sparsity
2011/7/6
We study the properties of false discovery rate (FDR) thresholding, viewed as a classification procedure. The "0"-class (null) is assumed to have a known, symmetric log-concave density while the "1"-c...
Improving the precision of classification trees
Bagging kernel density discrimination nearest neighbor pre-diction random forest
2010/11/8
Besides serving as prediction models, classification trees are use-ful for finding important predictor variables and identifying inter-esting subgroups in the data. These functions can be compromised ...
Statistical Classification Techniques for Photometric Supernova Typing
photometric sn typing boosting KDE
2010/10/19
Future photometric supernova surveys will produce vastly more candidates than can be followed up spectroscopically, highlighting the need for effective classification methods based on lightcurves alo...