Independent component analysis and feature extraction techniques for NDT data

被引：0
|
作者：
Morabito, CF [1 ]
机构：
[1] Univ Reggio Calabria, Fac Engn, DIMET, I-89100 Reggio Di Calabria, Italy
来源：
MATERIALS EVALUATION | 2000年 / 58卷 / 01期
关键词：
piezopolymer; sensors; extraction techniques; eddy current testing; independent component analysis;
D O I：
暂无
中图分类号：
TB3 [工程材料学];
学科分类号：
0805 ; 080502 ;
摘要：
The challenge of obtaining relevant information about a specimen containing anomalies using external, noninvasive measurements is barely feasible without recent advances in signal processing. The usual two step nondestructive testing (NDT) problem (detection and reconstruction of the discontinuity) can indeed be interpreted as a pattern recognition task in which the feature extraction aspect is by far the most interesting from a scientific viewpoint. Various relevant feature extraction techniques are compared in this work, with the aim to find the most advantageous mapping that reduces the dimensionality of the input patterns while preserving the relevant information content about the discontinuity. The paper proposes a combination of various types of features to cope with different aspects of the problem.
引用
收藏
页码：85 / 92
页数：8
相关论文
共 50 条
  • [21] Independent component analysis with learning algorithm for electrocardiogram feature extraction and classification
    Jayasanthi, M.
    Rajendran, G.
    Vidhyakar, R. B.
    SIGNAL IMAGE AND VIDEO PROCESSING, 2021, 15 (02) : 391 - 399
  • [22] Face recognition using feature extraction based on independent component analysis
    Kwak, N
    Choi, CH
    Ahuja, N
    2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL II, PROCEEDINGS, 2002, : 337 - 340
  • [23] Independent component analysis with learning algorithm for electrocardiogram feature extraction and classification
    M. Jayasanthi
    G. Rajendran
    R. B. Vidhyakar
    Signal, Image and Video Processing, 2021, 15 : 391 - 399
  • [24] A novel feature extraction approach based on ensemble feature selection and modified discriminant independent component analysis for microarray data classification
    Mollaee, Maryam
    Moattar, Mohammad Hossein
    BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2016, 36 (03) : 521 - 529
  • [25] Data partitioning and independent component analysis techniques applied to fMRI
    Wismüller, A
    Meyer-Bäse, A
    Lange, O
    Otto, T
    Auer, D
    INDEPENDENT COMPONENT ANALYSES, WAVELETS, UNSUPERVISED SMART SENSORS, AND NEURAL NETWORKS II, 2004, 5439 : 104 - 115
  • [26] Robust techniques for independent component analysis (ICA) with noisy data
    Cichocki, A
    Douglas, SC
    Amari, S
    NEUROCOMPUTING, 1998, 22 (1-3) : 113 - 129
  • [27] Optimization techniques for independent component analysis with applications to EEG data
    Georgiev, P
    Cichocki, A
    Bakardjian, H
    QUANTITATIVE NEUROSCIENCE: MODELS, ALGORITHMS, DIAGNOSTICS, AND THERAPEUTIC APPLICATIONS, 2004, 2 : 53 - 68
  • [28] Feature extraction for heartbeat classification using independent component analysis and matching pursuits
    Herrero, GG
    Gotchev, A
    Christov, I
    Egiazarian, K
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 725 - 728
  • [29] Aquaculture feature extraction from satellite image using independent component analysis
    Han, J
    Chi, K
    Yeon, Y
    MACHINE LEARNING AND DATA MINING IN PATTERN RECOGNITION, PROCEEDINDS, 2005, 3587 : 660 - 666
  • [30] Independent component analysis applied to feature extraction for robust automatic speech recognition
    Potamitis, L
    Fakotakis, N
    Kokkinakis, G
    ELECTRONICS LETTERS, 2000, 36 (23) : 1977 - 1978
12345