Study on Correlation-based Feature Selection in an Automatic Quality Inspection System using Support Vector Machine (SVM)

Song, DongHwan; Oh, Yeong Gwang; Kim, Namhun

doi:10.7232/jkiie.2016.42.6.370

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If you need to smooth and sharpen the picture, you can perform block operations and it can also smooth the outline of the image. ere are many methods for image smoothing; the most commonly used is the median and mean filtering methods, and of course, there are many other methods [29,30].…”

Section: Filter Processingmentioning

confidence: 99%

Image-Based Precision Measurement Technology for the Quality Inspection of Crane Boom Materials

Liu

Tan

Cao

et al. 2022

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

With the slow rise of the construction industry, cranes, as indispensable mechanical equipment in construction projects, are widely used in the lifting and handling of specific space ranges of construction projects. The quality of crane booms is particularly important for safety. This paper uses image measurement methods including filter processing, mean filtering, and Gaussian filtering to detect the quality of the crane boom material. The image is processed by the wavelet transform and Fourier transform. The grayscale transformation stretching method is applied to the surface image analysis of the boom material to obtain the final inspection. The research results show that the use of image measurement methods can effectively measure the thickness of the crane boom material, the geometric information of the boom material, and the surface roughness of the material and obtain effective image information. The detection accuracy reaches 98.1%. The error can be controlled better. The inspection and research on the quality of crane jib materials can ensure the quality and performance of crane jib materials, reduce the potential safety hazards of cranes during operation, and improve safety. This article organically combines workpiece surface roughness detection with digital image processing technology to preprocess the surface picture of the arm tube material. On this basis, the texture features in the image are extracted and programmed to calculate, and the final workpiece is obtained by the surface roughness value, which proves the feasibility of this method. The research results have very important practical significance for the detection of the quality of the arm tube material and the improvement of the quality level of the arm tube material.

show abstract

Section: Filter Processingmentioning

confidence: 99%

Image-Based Precision Measurement Technology for the Quality Inspection of Crane Boom Materials

Liu

Tan

Cao

et al. 2022

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

show abstract

“…이러한 특징 집합 구성 과정을 특징 선택(feature selection)이라 한다. 데이터의 분석의 효율성을 높이는 특징 선택 방법 (Song et al, 2016) (Yu and Liu, 2004). 여기서 각 특징이 반응 변수를 설명하는 정도를 클래스 관련성(class-relevance)이라 하고 각 특징이 다른 특징 과 얼마나 중복되었는지를 특징 간 중복(feature redundancy)이 라 한다.…”

Section: 안길승․이환철․허 선unclassified

Feature Selection Method for Multivariate Time Series Data Classification

안길승¹,

이환철²,

허선³

2017

JKIIE

View full text Add to dashboard Cite

Multivariate time series data classification has recently attracted interests from both industry and academia, as sensors used in various industries produce a lot of multivariate time series data. Having a lot of features, feature selection from those time series is essential to efficiently construct a classifier. In this paper, we propose a feature selection method to efficiently select features from the multivariate time series data considering variation. The candidate feature set is too large to efficiently select features and there are some feature redundancies. The proposed method can efficiently resolve these problems, and is validated by real datasets obtained from UCI Machine Learning Repository. Experiments show that the proposed method outperforms the typical feature selection methods in terms of accuracy and precision.

show abstract

Study on Correlation-based Feature Selection in an Automatic Quality Inspection System using Support Vector Machine (SVM)

Cited by 2 publications

References 10 publications

Image-Based Precision Measurement Technology for the Quality Inspection of Crane Boom Materials

Image-Based Precision Measurement Technology for the Quality Inspection of Crane Boom Materials

Feature Selection Method for Multivariate Time Series Data Classification

Contact Info

Product

Resources

About