scholarly journals Fault Classification of Nonlinear Small Sample Data through Feature Sub-Space Neighbor Vote

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1952
Author(s):  
Xian Du ◽  
Jingyang Yan ◽  
Rui Ma
Keyword(s):  
Manufacturing Process ◽  
Fractal Dimensionality ◽  
Small Sample ◽  
High Order ◽  
Fault Classification ◽  
Series Data ◽  
Spectral Features ◽  
Fault Type ◽  
Feature Subspace

The fault classification of a small sample of high dimension is challenging, especially for a nonlinear and non-Gaussian manufacturing process. In this paper, a similarity-based feature selection and sub-space neighbor vote method is proposed to solve this problem. To capture the dynamics, nonlinearity, and non-Gaussianity in the irregular time series data, high order spectral features, and fractal dimension features are extracted, selected, and stacked in a regular matrix. To address the problem of a small sample, all labeled fault data are used for similarity decisions for a specific fault type. The distances between the new data and all fault types are calculated in their feature subspaces. The new data are classified to the nearest fault type by majority probability voting of the distances. Meanwhile, the selected features, from respective measured variables, indicate the cause of the fault. The proposed method is evaluated on a publicly available benchmark of a real semiconductor etching dataset. It is demonstrated that by using the high order spectral features and fractal dimensionality features, the proposed method can achieve more than 84% fault recognition accuracy. The resulting feature subspace can be used to match any new fault data to the fingerprint feature subspace of each fault type, and hence can pinpoint the root cause of a fault in a manufacturing process.

scholarly journals Learning Deep Hierarchical Spatial–Spectral Features for Hyperspectral Image Classification Based on Residual 3D-2D CNN

Sensors ◽  
2019 ◽  
Vol 19 (23) ◽  
pp. 5276 ◽  
Author(s):  
Fan Feng ◽  
Shuangting Wang ◽  
Chunyang Wang ◽  
Jin Zhang
Keyword(s):  
Hyperspectral Image ◽  
Image Annotation ◽  
Small Sample ◽  
Training Data ◽  
Spectral Features ◽  
Training Samples ◽  
Small Sample Problem ◽  
Hyperspectral Classification ◽  
Organic Combination

Every pixel in a hyperspectral image contains detailed spectral information in hundreds of narrow bands captured by hyperspectral sensors. Pixel-wise classification of a hyperspectral image is the cornerstone of various hyperspectral applications. Nowadays, deep learning models represented by the convolutional neural network (CNN) provides an ideal solution for feature extraction, and has made remarkable achievements in supervised hyperspectral classification. However, hyperspectral image annotation is time-consuming and laborious, and available training data is usually limited. Due to the “small-sample problem”, CNN-based hyperspectral classification is still challenging. Focused on the limited sample-based hyperspectral classification, we designed an 11-layer CNN model called R-HybridSN (Residual-HybridSN) from the perspective of network optimization. With an organic combination of 3D-2D-CNN, residual learning, and depth-separable convolutions, R-HybridSN can better learn deep hierarchical spatial–spectral features with very few training data. The performance of R-HybridSN is evaluated over three public available hyperspectral datasets on different amounts of training samples. Using only 5%, 1%, and 1% labeled data for training in Indian Pines, Salinas, and University of Pavia, respectively, the classification accuracy of R-HybridSN is 96.46%, 98.25%, 96.59%, respectively, which is far better than the contrast models.

STUDY OF DECORATIVE VARIETY IN GORONTALO KARAWO FABRIC IN AESTHETIC AND SYMBOLIC ELEMENTS

ARTic ◽  
2019 ◽  
Vol 3 ◽  
pp. 121-134
Author(s):  
Apsari Dj Hasan
Keyword(s):  
Manufacturing Process ◽  
The Philippines ◽  
Aesthetic Theory ◽  
Cultural Meanings ◽  
Aesthetic Value ◽  
Aesthetic Form ◽  
Decorative Motifs ◽  
Symbolic Meanings ◽  
The Aesthetic

This study aims to examine the decorative types of Gorontalo karawo fabrics in aesthetic and symbolic elements. Researchers want to know as made in the research design, aspects that are present in the decoration of fabrics in aesthetic and symbolic elements. This study uses a number of related theories to get results, and as a determinant, the authors use aesthetic theory, as well as historical approaches. With this theoretical basis, the author seeks to describe the aesthetic aspects and symbolic meanings that exist in Gorontalo karawo fabric. Through the data collection of the chosen motif and provide a classification of motives, the part is used as a reference for research material. The results showed that Gorontalo filigree had an aesthetic value consisting of unity formed from the overall decorative motifs displayed, complexity formed by complexity in the manufacturing process, and intensity of seriousness in the manufacturing process or the impression displayed on the filigree motif. The aesthetic form also reflects the diversity of meanings for communication, such as the symbol of a leader with his noble instincts, a symbol of cultural cooperation, which is worth maintaining, and ideas about nature conservation. This research proves that the decoration in Gorontalo filigree cloth (karawo) does not only act as a visual value, but also as a communication of cultural meanings and social status. Of all these distinctive motifs show a relationship between humans and humans and humans with nature. The influence of culture from the Philippines is also known to have a strong influence on the emergence of the Gorontalo filigree namely manila filigree.

Fault Classification of Hydroelectric Generating Unit Based on Improved Evidence Theory

2014 ◽  
Vol 7 (1) ◽  
pp. 78-83 ◽  
Author(s):  
Jiatang Cheng ◽  
Li Ai ◽  
Zhimei Duan ◽  
Yan Xiong
Keyword(s):  
Fault Diagnosis ◽  
Information Fusion ◽  
Evidence Theory ◽  
Fault Classification ◽  
Fusion Method ◽  
Inconsistent Result ◽  
High Conflict

Aiming at the problem of the conventional vibration fault diagnosis technology with inconsistent result of a hydroelectric generating unit, an information fusion method was proposed based on the improved evidence theory. In this algorithm, the original evidence was amended by the credibility factor, and then the synthesis rule of standard evidence theory was utilized to carry out information fusion. The results show that the proposed method can obtain any definitive conclusion even if there is high conflict evidence in the synthesis evidence process, and may avoid the divergent phenomenon when the consistent evidence is fused, and is suitable for the fault classification of hydroelectric generating unit.

scholarly journals Time–frequency time–space LSTM for robust classification of physiological signals

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tuan D. Pham
Keyword(s):  
Time Series ◽  
Network Architecture ◽  
Time Series Data ◽  
Short Term Memory ◽  
Physiological Signals ◽  
Series Data ◽  
Time Frequency ◽  
Time Space ◽  
Deep Recurrent Neural Network

AbstractAutomated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.

Nearest Neighbor-Based Strategy to Optimize Multi-View Triplet Network for Classification of Small-Sample Medical Imaging Data

2021 ◽  
pp. 1-15
Author(s):  
Phawis Thammasorn ◽  
Wanpracha A. Chaovalitwongse ◽  
Daniel S. Hippe ◽  
Landon S. Wootton ◽  
Eric C. Ford ◽  
...  
Keyword(s):  
Medical Imaging ◽  
Nearest Neighbor ◽  
Small Sample ◽  
Imaging Data ◽  
Medical Imaging Data

scholarly journals High-pass filtering artifacts in multivariate classification of neural time series data

2021 ◽  
Vol 352 ◽  
pp. 109080
Author(s):  
Joram van Driel ◽  
Christian N.L. Olivers ◽  
Johannes J. Fahrenfort
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Series Data ◽  
Multivariate Classification ◽  
High Pass

scholarly journals Classification of multiwavelength transients with Machine Learning

2020 ◽  
Author(s):  
K Sooknunan ◽  
M Lochner ◽  
Bruce A Bassett ◽  
H V Peiris ◽  
R Fender ◽  
...  
Keyword(s):  
Machine Learning ◽  
Small Sample ◽  
Light Curves ◽  
Machine Learning Techniques ◽  
Optical Data ◽  
Test Time ◽  
Test Accuracy ◽  
Training Set ◽  
The Impact

Abstract With the advent of powerful telescopes such as the Square Kilometer Array and the Vera C. Rubin Observatory, we are entering an era of multiwavelength transient astronomy that will lead to a dramatic increase in data volume. Machine learning techniques are well suited to address this data challenge and rapidly classify newly detected transients. We present a multiwavelength classification algorithm consisting of three steps: (1) interpolation and augmentation of the data using Gaussian processes; (2) feature extraction using wavelets; (3) classification with random forests. Augmentation provides improved performance at test time by balancing the classes and adding diversity into the training set. In the first application of machine learning to the classification of real radio transient data, we apply our technique to the Green Bank Interferometer and other radio light curves. We find we are able to accurately classify most of the eleven classes of radio variables and transients after just eight hours of observations, achieving an overall test accuracy of 78%. We fully investigate the impact of the small sample size of 82 publicly available light curves and use data augmentation techniques to mitigate the effect. We also show that on a significantly larger simulated representative training set that the algorithm achieves an overall accuracy of 97%, illustrating that the method is likely to provide excellent performance on future surveys. Finally, we demonstrate the effectiveness of simultaneous multiwavelength observations by showing how incorporating just one optical data point into the analysis improves the accuracy of the worst performing class by 19%.

Sign in / Sign up

Export Citation Format

Share Document