Support vector machine based classification of seafloor rock types measured underwater using Laser Induced Breakdown Spectroscopy

Yelameli, Mallikarjun; Thornton, Blair; Takahashi, Tomoko; Weerkoon, Tharindu; Takemura, Yasunori; Ishii, Kazuo

doi:10.1109/oceansap.2016.7485507

Cited by 7 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sirven et al [ 8 ] adopted principal component analysis (PCA), soft independent modeling of class analogy (SIMCA), and partial least-squares discriminant analysis (PLS-DA) for rock classification. Yelameli et al [ 9 ] used a support vector machine (SVM) to distinguish ten different rock samples. Li et al [ 10 ] applied k-nearest neighbors (kNN) and an SVM to discriminate soft tissues.…”

Section: Introductionmentioning

confidence: 99%

Convolution Neural Network with Laser-Induced Breakdown Spectroscopy as a Monitoring Tool for Laser Cleaning Process

Choi

Park

2022

Sensors

View full text Add to dashboard Cite

In this study, eight different painted stainless steel 304L specimens were laser-cleaned using different process parameters, such as laser power, scan speed, and the number of repetitions. Laser-induced breakdown spectroscopy (LIBS) was adopted as the monitoring tool for laser cleaning. Identification of LIBS spectra with similar chemical compositions is challenging. A convolutional neural network (CNN)-based deep learning method was developed for accurate and rapid analysis of LIBS spectra. By applying the LIBS-coupled CNN method, the classification CNN model accuracy of laser-cleaned specimens was 94.55%. Moreover, the LIBS spectrum analysis time was 0.09 s. The results verified the possibility of using the LIBS-coupled CNN method as an in-line tool for the laser cleaning process.

show abstract

Section: Introductionmentioning

confidence: 99%

Convolution Neural Network with Laser-Induced Breakdown Spectroscopy as a Monitoring Tool for Laser Cleaning Process

Choi

Park

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…This study investigates the use of machine learning techniques to classify the underwater LIBS spectra of hydrothermal rocks according to their label and geological group. Interest in the hydrothermal rocks lies in the fact that they contain various industrially important metals like copper, lead, and zinc . Grouping of the rocks based on their constituent metals and reactivity plays a vital role in separation and purification of metals from the mineral ores .…”

Section: Introductionmentioning

confidence: 99%

“…Interest in the hydrothermal rocks lies in the fact that they contain various industrially important metals like copper, lead, and zinc. 23 Grouping of the rocks based on their constituent metals and reactivity plays a vital role in separation and purification of metals from the mineral ores. 24 Thirty rocks were used in this experiment, and every rock was labeled from 1 to 30.…”

mentioning

confidence: 99%

Classification and statistical analysis of hydrothermal seafloor rocks measured underwater using laser‐induced breakdown spectroscopy

Yelameli

Thornton

Takahashi

et al. 2018

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

This study investigates the use of statistical methods for the classification of laser‐induced breakdown spectroscopy (LIBS) measurements of water‐immersed rocks with respect to their labels and geological groups. The analysis is performed on deep‐sea hydrothermal deposit rocks. These rocks are categorized on the basis of the relative ratio of Zn‐Pb‐Cu on a ternary diagram. The proposed method demonstrates that the accurate classification of rocks with respect to their labels and geological group from the LIBS data can be successfully achieved by combining principal component analysis (PCA), which reduces the dimensionality of the data, with classification algorithms such as the support vector machine (SVM), k‐nearest neighbor search (KNN), and artificial neural network (ANN) methods. The performance of the classification algorithms depends on the size of the dataset. Additionally, removing the linear trend from the data enhances the performance of the classification in terms of sensitivity. The best classification performance concerning the rock label is obtained using an SVM linear kernel algorithm with 95% sensitivity. The best classification performance concerning the geological group is obtained using the SVM method with 98% accuracy. The one‐sided Wilcoxon signed rank test is applied to the classification results in the rock label and group cases, and the results indicate that the SVM algorithm has statistical significance over the other algorithms while classifying the rock labels and rock group.

show abstract

“…Several groups including Tsinghua University [31][32][33][34][35][36][37][38], South China University of Technology [39][40][41][42], Shanxi University [43][44][45][46] and Mitsubishi Heavy [47,48] have made a great contribution on the coal property analysis; groups such as Shenyang Institute of Automation [49][50][51], Huazhong University of Science and Technology [52,53], and Tohoku University [54,55] also made significant progress on the online and in situ LIBS applications on the metallurgical industry. In terms of applications for the extreme environment detection, groups such as University of Tokyo [56][57][58][59] and Ocean University of China [60][61][62][63] have successfully employed the in situ analysis of deep-sea mineral samples using LIBS, and groups such as Dalian University of Technology [64][65][66][67] and Japan Atomic Energy Agency [68,69] have proved that LIBS is an effective tool for in situ elemental analysis for nuclear reactors. A new collinear DP-LIBS method has been proposed by Tokushima University and Xi'an Jiaotong University.…”

mentioning

confidence: 99%

From big to strong: growth of the Asian laser-induced breakdown spectroscopy community

Hou

Deguchi

et al. 2019

Plasma Sci. Technol.

View full text Add to dashboard Cite

Support vector machine based classification of seafloor rock types measured underwater using Laser Induced Breakdown Spectroscopy

Cited by 7 publications

References 14 publications

Convolution Neural Network with Laser-Induced Breakdown Spectroscopy as a Monitoring Tool for Laser Cleaning Process

Convolution Neural Network with Laser-Induced Breakdown Spectroscopy as a Monitoring Tool for Laser Cleaning Process

Classification and statistical analysis of hydrothermal seafloor rocks measured underwater using laser‐induced breakdown spectroscopy

From big to strong: growth of the Asian laser-induced breakdown spectroscopy community

Contact Info

Product

Resources

About