• Publications
  • Influence
Learning from partially supervised data using mixture models and belief functions
TLDR
This paper addresses classification problems in which the class membership of training data are only partially known. Expand
  • 115
  • 8
  • PDF
Fault diagnosis in railway track circuits using Dempster-Shafer classifier fusion
TLDR
This paper addresses the problem of fault detection and isolation in railway track circuits. Expand
  • 95
  • 4
  • PDF
A hidden process regression model for functional data description. Application to curve discrimination
TLDR
A new approach for functional data description is proposed in this paper. Expand
  • 48
  • 4
  • PDF
Model-based clustering and segmentation of time series with changes in regime
TLDR
Mixture model-based clustering, usually applied to multidimensional data, has become a popular approach in many data analysis problems, both for its good statistical properties and for the simplicity of implementation. Expand
  • 64
  • 3
  • PDF
Time series modeling by a regression approach based on a latent process
TLDR
We propose a new method for modeling and classifying time series representing the condition measurements acquired during switch operations. Expand
  • 52
  • 3
  • PDF
A dynamic Bayesian network to represent discrete duration models
TLDR
In this paper, the description of a specific dynamic Bayesian network, referred to as Graphical Duration Model (GDM), is given to represent a wide range of duration models. Expand
  • 33
  • 3
B-scan ultrasonic image analysis for internal rail defect detection
A multi-fiber linear array laser catheter for use in irradiation of biological tissue where a circular laser beam is optically transformed to coincide with the cross-section of a linear array ofExpand
  • 15
  • 3
Mixture-model-based signal denoising
TLDR
This paper proposes a new signal denoising methodology for dealing with asymmetrical noises. Expand
  • 8
  • 3
  • PDF
Mixture Model Estimation with Soft Labels
TLDR
This paper addresses classification problems in which the class membership of training data is only partially known. Expand
  • 17
  • 1
A new decision criterion for feature selection application to the classification of non destructive testing signatures
TLDR
This paper describes a new decision criterion for feature selection (or descriptor selection) and its application to a classification problem. Expand
  • 11
  • 1
  • PDF