A deep one-dimensional convolutional neural network for microplastics classification using Raman spectroscopy

Zhang, Wei; Feng, Wen; Cai, Zhuang; Wang, Huanqing; Yan, Qi; Wang, Qing

doi:10.1016/j.vibspec.2022.103487

Cited by 22 publications

(9 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The undifferentiated spectra and the differentiated spectra were separately input into the CNN model for feature extraction and were subsequently concatenated for classification. Previously studied methods ,, only utilized raw Raman spectrum in the input layer. In contrast, the differentiated data of the spectrum offer an intuitive representation of the peak location, even in the presence of low signal-to-noise ratio (SNR).…”

Section: Resultsmentioning

confidence: 99%

“…Recent efforts have aimed to advance microplastic detection by combining machine learning (ML) with Raman spectroscopy. − Convolution neural network (CNN), a deep learning method, has shown superiority in classifying new data without information loss. , CNN also demonstrates high accuracy in analyzing Raman spectra compared to other ML techniques . Previous attempts to differentiate microplastics by combining Raman spectroscopy and CNN have been made. , However, these CNNs may experience reduced accuracy or compatibility issues when using charge-coupled devices (CCDs) with different pixel counts or when the Raman shift varies due to calibration.…”

Section: Introductionmentioning

confidence: 99%

“…26 Previous attempts to differentiate microplastics by combining Raman spectroscopy and CNN have been made. 27,28 However, these CNNs may experience reduced accuracy or compatibility issues when using charge- coupled devices (CCDs) with different pixel counts or when the Raman shift varies due to calibration.…”

Section: ■ Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fast Detection and Classification of Microplastics below 10 μm Using CNN with Raman Spectroscopy

Lim,

Shin,

Shin

2024

Anal. Chem.

View full text Add to dashboard Cite

In light of the growing awareness regarding the ubiquitous presence of microplastics (MPs) in our environment, recent efforts have been made to integrate Artificial Intelligence (AI) technology into MP detection. Among spectroscopic techniques, Raman spectroscopy is preferred for the detection of MP particles measuring less than 10 μm, as it overcomes the diffraction limitations encountered in Fourier transform infrared (FTIR). However, Raman spectroscopy’s inherent limitation is its low scattering cross section, which often results in prolonged data collection times during practical sample measurements. In this study, we implemented a convolutional neural network (CNN) model alongside a tailored data interpolation strategy to expedite data collection for MP particles within the 1–10 μm range. Remarkably, we achieved the classification of plastic types for individual particles with a mere 0.4 s of exposure time, reaching an approximate confidence level of 85.47(±5.00)%. We postulate that the result significantly accelerates the aggregation of microplastic distribution data in diverse scenarios, contributing to the development of a comprehensive global microplastic map.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fast Detection and Classification of Microplastics below 10 μm Using CNN with Raman Spectroscopy

Lim,

Shin,

Shin

2024

Anal. Chem.

View full text Add to dashboard Cite

show abstract

“…54 MLP-ANN is a supervised learning-based artificial neural network that distinguishes nonlinearly separable data. 55,56 RBF-ANN consists of an input neuron, a hidden neuron, and an output neuron. The hidden layer is a Gaussian function centered on points with the same dimensions as the predictor variable.…”

Section: Methodsmentioning

confidence: 99%

Collaborative estimation of heavy metal stress in wheat seedlings based on LIBS-Raman spectroscopy coupled with machine learning

Yang,

Li,

Zuo

et al. 2023

J. Anal. At. Spectrom.

View full text Add to dashboard Cite

show abstract

“…Presently, prevalent spectral classification methodologies involve the utilization of one-dimensional feedforward neural networks for the extraction and categorization of Raman spectral features. Building upon this foundation, researchers such as Zhang et al [10] have effectively employed one-dimensional convolutional neural networks (1D-CNN) to achieve discrimination among ten types of plastic microparticles, achieving an impressive classification accuracy of up to 96.4%. Concurrently, scholars such as Song et al [11] have devised a one-dimensional VGG neural network model, attaining a classification accuracy of 87.91% in the analysis of Raman spectra from thousands of mineral samples.…”

Section: Introductionmentioning

confidence: 99%

RepDwNet: Lightweight Deep Learning Model for Spectral blood Raman spectra classification

He,

Zhou,

Ren

et al. 2023

Preprint

View full text Add to dashboard Cite

The Raman spectroscopy analysis technique has found extensive applications across various disciplines due to its exceptional convenience and efficiency, facilitating the analysis and identification of diverse substances. In recent years, owing to the escalating demand for high-efficiency analytical methods, deep learning models have progressively been introduced into the realm of Raman spectroscopy. However, the application of these models to portable Raman spectrometers has posed a series of challenges due to the computational intensity inherent to deep learning approaches. This research addresses this challenge by introducing a lightweight Raman spectroscopy classification model named RepDwNet. This model not only maintains high accuracy but also exhibits relatively lower computational overhead. Its design integrates advanced techniques, including multi-scale convolutional kernels, depthwise separable convolutions, and residual connections. These modules effectively capture features across varying scales while maximizing the coherence between them.To validate the feasibility and efficacy of the proposed model, a series of experiments were conducted utilizing an augmented Raman spectroscopy dataset from blood samples for species identification tasks. The experimental outcomes demonstrate that the model achieved remarkable accuracy rates of 98.24% and 97.37% on the reflectance and transmittance Raman blood data subsets, respectively. Furthermore, structural reparameterization techniques were employed to compress the model, thereby significantly enhancing inference speed and reducing model parameter size while preserving high classification accuracy. This optimization renders the model more suitable for deployment in portable device scenarios.

show abstract

A deep one-dimensional convolutional neural network for microplastics classification using Raman spectroscopy

Cited by 22 publications

References 56 publications

Fast Detection and Classification of Microplastics below 10 μm Using CNN with Raman Spectroscopy

Fast Detection and Classification of Microplastics below 10 μm Using CNN with Raman Spectroscopy

Collaborative estimation of heavy metal stress in wheat seedlings based on LIBS-Raman spectroscopy coupled with machine learning

RepDwNet: Lightweight Deep Learning Model for Spectral blood Raman spectra classification

Contact Info

Product

Resources

About