Journal ArticleDOI
Distribution inference from early-stage stationary data streams by transfer learning
Kai Wang,Jian Li,Fugee Tsung +2 more
- pp 1-25
TLDR
An instance-based transfer learning approach which integrates a sufficient amount of auxiliary data from similar processes or products to aid the distribution inference in the authors' target task, and an efficient online algorithm with recursive formulas to update upon every incoming data point.Abstract:
Data streams are prevalent in current manufacturing and service systems where real-time data arrive progressively. A quick distribution inference from such data streams at their early stages is ext...read more
Citations
More filters
Change-Point Detection in Time-Series Data by Relative Density-Ratio Estimation (情報論的学習理論と機械学習)
TL;DR: This paper presents a novel statistical change-point detection algorithm based on non-parametric divergence estimation between time-series samples from two retrospective segments that is accurately and efficiently estimated by a method of direct density-ratio estimation.
Journal Article
Nonparametric monitoring of data strems for changes in location and scale
TL;DR: In this paper, a framework for detecting changes in data streams when the distributional form of the stream variables is unknown is developed, based on hypothesis tests which involve ranking data points and a method for calculating these ranks online in a manner which respects the constraints of data stream analysis.
Journal ArticleDOI
Multi-sensor based landslide monitoring via transfer learning
TL;DR: A regularized parameter-based transfer learning approach integrated with the ordered LASSO is first proposed to effectively transfer information from old sensors with sufficient historical data to new ones with limited data, as well as monitoring the newly deployed sensors sequentially based on the generalized likelihood ratio.
Journal ArticleDOI
A new approach to generating virtual samples to enhance classification accuracy with small data-a case of bladder cancer.
TL;DR: A distance-based mega-trend-diffusion (DB-MTD) technique is proposed to appropriately estimate the degree of data diffusion with less impacts from extreme values, and demonstrates that the proposed method outperforms other VSG techniques in classification and regression items for small bladder cancer datasets.
Journal ArticleDOI
A Transfer Learning-Based Multivariate Control Chart for Dengue Surveillance in Hong Kong
TL;DR: In this paper , a transfer learning-based estimator is proposed to increase parameter estimation accuracy for areas with limited historic data points for detecting dengue outbreaks, and a multivariate control chart based on transfer-learned parameters is developed for online monitoring.
References
More filters
Journal ArticleDOI
A Survey on Transfer Learning
Sinno Jialin Pan,Qiang Yang +1 more
TL;DR: The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.
The Matrix Cookbook
TL;DR: Theodorakopoulos et al. as mentioned in this paper used the Oticon Foundation for funding their PhD studies, and they would like to thank the following for contributions and suggestions: Bill Baxter, Brian Templeton, Christian Rishoj, Christian Schroppel Douglas L. Theobald, Esben Hoegh-Rasmussen, Glynne Casteel, Jan Larsen, Jun Bin Gao, Jurgen Struckmeier, Kamil Dedecius, Korbinian Strimmer, Lars Christiansen, Lars Kai Hansen, Leland Wilkinson, Lig
Proceedings ArticleDOI
Boosting for transfer learning
TL;DR: In this paper, the authors proposed a transfer learning framework called TrAdaBoost, which allows users to utilize a small amount of newly labeled data to leverage the old data to construct a high-quality classification model for the new data.
Journal ArticleDOI
Monte Carlo Strategies in Scientific Computing
TL;DR: The strength of this book is in bringing together advanced Monte Carlo methods developed in many disciplines, including the Ising model, molecular structure simulation, bioinformatics, target tracking, hypothesis testing for astronomical observations, Bayesian inference of multilevel models, missing-data problems.
Book Chapter
Correcting sample selection bias by unlabeled data
TL;DR: This paper proposed a nonparametric method which directly produces resampling weights without distribution estimation, which works by matching distributions between training and testing sets in feature space, and experimental results demonstrate that their method works well in practice.