scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Supervised classification of wood species during milling based on extracted cut events from ultrasonic air-borne acoustic signals

22 May 2023-Wood Material Science and Engineering (Wood Material Science and Engineering)-pp 1-9
TL;DR: In this paper , an analysis framework for monitoring wood milling, an optical microphone with a sensitivity range from 10 Hz to 1 MHz was used, the gathered sound signals were segmented into individual cuts and transformed to the frequency domain by using the Fast Fourier Transformation.
Abstract: Novel monitoring techniques are a prerequisite for adaptive manufacturing processes, which are of increasing importance to allow an efficient processing of heterogeneous raw materials such as wood. To establish an analysis framework for monitoring wood milling, an optical microphone with a sensitivity range from 10 Hz to 1 MHz was used. The gathered sound signals were segmented into individual cuts and transformed to the frequency domain by using the Fast Fourier Transformation. The spectral data were then labelled according to wood species and analysed with Principle Component Analysis. Finally, it was possible to obtain a Machine Learning classification model based on Linear Discriminant Analysis to distinguish between wood species with an average accuracy of 93.1% in validation and 91.9% in testing.
References
More filters
Journal ArticleDOI
TL;DR: The Scree Test for the Number Of Factors this paper was first proposed in 1966 and has been used extensively in the field of behavioral analysis since then, e.g., in this paper.
Abstract: (1966). The Scree Test For The Number Of Factors. Multivariate Behavioral Research: Vol. 1, No. 2, pp. 245-276.

12,228 citations

Journal ArticleDOI
TL;DR: In this paper, a procedure for determining statistically whether the highest observation, lowest observation, highest and lowest observations, or more of the observations in the sample are statistical outliers is given.
Abstract: Procedures are given for determining statistically whether the highest observation, the lowest observation, the highest and lowest observations, the two highest observations, the two lowest observations, or more of the observations in the sample are statistical outliers. Both the statistical formulae and the application of the procedures to examples are given, thus representing a rather complete treatment of tests for outliers in single samples. This paper has been prepared primarily as an expository and tutorial article on the problem of detecting outlying observations in much experimental work. We cover only tests of significance in thii paper.

3,551 citations

Journal ArticleDOI
TL;DR: The paper focuses on the use of principal component analysis in typical chemometric areas but the results are generally applicable.
Abstract: Principal component analysis is one of the most important and powerful methods in chemometrics as well as in a wealth of other areas. This paper provides a description of how to understand, use, and interpret principal component analysis. The paper focuses on the use of principal component analysis in typical chemometric areas but the results are generally applicable.

1,622 citations

Journal ArticleDOI
TL;DR: In this article, best current expressions for the vibrational relaxation times of oxygen and nitrogen in the atmosphere are used to compute total absorption, and the resulting graphs of total absorption as a function of frequency for different humidities should be used in lieu of the graph published earlier by Evans et al.
Abstract: Best current expressions for the vibrational relaxation times of oxygen and nitrogen in the atmosphere are used to compute total absorption. The resulting graphs of total absorption as a function of frequency for different humidities should be used in lieu of the graph published earlier by Evans et al (1972).

158 citations

Book ChapterDOI
01 Jan 2013
TL;DR: This chapter discusses another popular data mining algorithm that can be used for supervised or unsupervised learning, Linear Discriminant Analysis, and presents the robust counterpart scheme originally proposed by Kim and Boyd.
Abstract: In this chapter we discuss another popular data mining algorithm that can be used for supervised or unsupervised learning. Linear Discriminant Analysis (LDA) was proposed by R. Fischer in 1936. It consists in finding the projection hyperplane that minimizes the interclass variance and maximizes the distance between the projected means of the classes. Similarly to PCA, these two objectives can be solved by solving an eigenvalue problem with the corresponding eigenvector defining the hyperplane of interest. This hyperplane can be used for classification, dimensionality reduction and for interpretation of the importance of the given features. In the first part of the chapter we discuss the generic formulation of LDA whereas in the second we present the robust counterpart scheme originally proposed by Kim and Boyd. We also discuss the non linear extension of LDA through the kernel transformation.

137 citations