Spectral Classification and Particular Spectra Identification Based on Data Mining

Yang, Peng; Yang, Guowei; Zhang, Fanlong; Jiang, Bin; Wang, Mengxin

doi:10.1007/s11831-020-09401-9

Cited by 8 publications

(4 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML techniques have demonstrated significant improvements in the analysis of luminescence, near-infrared, and other spectral data [5][6][7][8][9][10][11][12][13][14][15]. Furthermore, ML methods have shown promise in enhancing the analysis of laser-induced breakdown spectroscopy data [16][17][18][19][20][21]. Notably, a study [5] has demonstrated the utility of ML learning in achieving spectroscopy calibration invariance.…”

Section: Introductionmentioning

confidence: 99%

Time resolved study of temperature sensing using Gd₂O₃:Er,Yb: deep learning approach

Rabasovic,

Savic-Sevic,

Križan

et al. 2023

Phys. Scr.

View full text Add to dashboard Cite

This paper examines the potential applications of machine learning algorithms in the analysis of optical spectra from Gd2O3:Er,Yb thermophosphor. The material was synthesized using the solution combustion method. For data acquisition, we employed pulsed laser diode excitation at 980 nm and utilized a streak camera with a spectrograph to obtain time-resolved spectral data of the optical emission from Gd2O3:Er,Yb. To ensure data consistency and facilitate visualization, we employed principal component analysis and Uniform Manifold Approximation and Projection clustering. Our findings demonstrate that, instead of the conventional approach of identifying spectral peaks and calculating intensity ratios, it is feasible to train computer software to recognize time-resolved spectra associated with different temperatures of the thermophosphor. Through our analysis, we have successfully devised a technique for remote temperature estimation by leveraging deep learning artificial neural networks.

show abstract

Section: Introductionmentioning

confidence: 99%

Time resolved study of temperature sensing using Gd₂O₃:Er,Yb: deep learning approach

Rabasovic,

Savic-Sevic,

Križan

et al. 2023

Phys. Scr.

View full text Add to dashboard Cite

show abstract

“…We found that stellar astrometry is astrometry with a greater investigative perspective, which became evident in the background information from aspects such as the identification of stars and consolidation of highprecision stellar catalogues (Apellániz et al, 2020;Luhman, 2021;Luhman & Esplin, 2020), spectral classifications to recognise characteristics such as real brightness, age, temperature, and chemical composition of stars (Kyritsis et al, 2022;Yang et al, 2020), measurement of stellar distances (Gehan et al, 2021;Guo et al, 2021), reduction of data obtained in probes and satellites to determine own movements, stellar occultations and parallaxes (Bowler et al, 2021;Gomes et al, 2022;Marchetti, 2021;Zari et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Didactic Intervention for the Teaching of Stellar Astrometry in Field Educational Contexts

Pineda Caro,

Valderrama,

Torres Merchán

2023

Acta Sci.

View full text Add to dashboard Cite

Background: Astrometry is a field of study that integrates the procedures necessary to determine the position and movements of celestial bodies, which is why it uses concepts typical of the natural sciences that could be used in scientific education. Objective: To identify scientific concepts related to astrometry in rural secondary basic education contexts. Design: The sequence of activities consisted of Diagnosis of Prior Knowledge, Didactic Intervention, and Assessment. Setting and Participants: 65 students from three rural educational institutions (field schools) of the Department of Boyacá in Colombia participated. Data Collection and Analysis: Two questionnaires were implemented to assess students' prior concepts and strengthened concepts, which were validated by the judgment of experts in the area. The data was grouped into two categories of analysis: Astrometric Concepts and Astrometric Techniques and Methods.Results: The learning of astrometric concepts such as stellar evolution, parallax, classification, and principles of spectroscopy was favoured, in addition to concepts from physics such as electromagnetic spectrum, brightness, luminosity, temperaturecolour ratio, and mathematical concepts, some trigonometric relationships and astronomical units. However, difficulties were evidenced in relation to knowledge of the celestial vault, movements of the stars, and management of astronomical models. Conclusions: The students had little previous knowledge about astrometry, strengthened through didactic intervention, enabling the association of physics, mathematical, and astronomical concepts in the classroom.

show abstract

“…The key point of feature selection is to pick the representative bands from the full-range spectra by projection calculation or heuristic algorithms [20]. So far, many feature selection methods have been proposed and applied [21]. The core idea of feature extraction is to transform the spectra matrix and pick out the eigenvectors with the biggest eigenvalues or information weights [22].…”

Section: Introductionmentioning

confidence: 99%

Classification for GM and Non-GM Maize Kernels Based on NIR Spectra and Deep Learning

Wei

Liu

et al. 2023

Processes

View full text Add to dashboard Cite

The classification of GM and non-GM maize kernels is fundamental for further analysis of the gene action in maize. Therefore, a complete and novel detection scheme based on near-infrared spectra was designed to distinguish GM and non-GM maize kernels. Hyperspectral images (935–1720 nm) of 777 maize kernels from 3 kinds were captured, and the average spectra of the maize kernels were extracted for modeling analysis. The classical modeling methods based on feature engineering were first studied, and the backpropagation neural network–genetic algorithm model showed the best performance with a prediction accuracy of 0.861. Then, novel modeling methods based on deep learning were developed. To dig out the interactive information between different bands and match the application scenarios, the original spectra were transformed into two-dimensional matrices before establishing the deep learning models. A modified convolution neural network (i.e., VGG net) with dilated convolution was finally constructed to classify the maize kernels, and the prediction accuracy reached 0.961. This research provides a referential and novel way to detect GM maize kernels. Future research will improve the detection scheme for monitoring unauthorized GM organisms by introducing the visualization technology of deep learning.

show abstract

Spectral Classification and Particular Spectra Identification Based on Data Mining

Cited by 8 publications

References 59 publications

Time resolved study of temperature sensing using Gd₂O₃:Er,Yb: deep learning approach

Time resolved study of temperature sensing using Gd₂O₃:Er,Yb: deep learning approach

Didactic Intervention for the Teaching of Stellar Astrometry in Field Educational Contexts

Classification for GM and Non-GM Maize Kernels Based on NIR Spectra and Deep Learning

Contact Info

Product

Resources

About

Spectral Classification and Particular Spectra Identification Based on Data Mining

Cited by 8 publications

References 59 publications

Time resolved study of temperature sensing using Gd2O3:Er,Yb: deep learning approach

Time resolved study of temperature sensing using Gd2O3:Er,Yb: deep learning approach

Didactic Intervention for the Teaching of Stellar Astrometry in Field Educational Contexts

Classification for GM and Non-GM Maize Kernels Based on NIR Spectra and Deep Learning

Contact Info

Product

Resources

About

Time resolved study of temperature sensing using Gd₂O₃:Er,Yb: deep learning approach

Time resolved study of temperature sensing using Gd₂O₃:Er,Yb: deep learning approach