Rapid identification of ore minerals using multi-scale dilated convolutional attention network associated with portable Raman spectroscopy

Cai, Yaoyi; Xu, Degang; Shi, Hong

doi:10.1016/j.saa.2021.120607

Cited by 28 publications

(21 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Batch normalization (BN) is performed after each convolution layer to standardize the output maps of a training mini-batch to subsequent layers. This operation improves the training speed and reduces overfitting 22 , 31 . Following each BN layer, the rectified linear unit (ReLU) activation function is applied to the convolution feature maps to add nonlinear modelling ability to the neural network 32 .…”

Section: Methodsmentioning

confidence: 99%

“…The final output map is fed into fully connected layers to learn non-linear combinations of the extracted features. A dropout layer with inactivation probability of 0.1 is applied after the first fully connected layer to reduce overfitting by temporarily removing randomly selected neurons 22 , 33 . Finally, the output layer takes the features learnt by the model to calculate the input’s classification scores for each possible category.…”

Section: Methodsmentioning

confidence: 99%

“…The generated features can then be employed for specific tasks, such as classification. This end-to-end learning approach eliminates the need for manual feature extraction (i.e., dimensionality reduction), exceeding the classification efficiency of other machine learning methods 22 . Furthermore, CNNs consider the spatial correlation of elements of the input data by enforcing a local connectivity pattern between neurons of adjacent layers, called receptive fields.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Raman spectroscopy and convolutional neural networks for monitoring biochemical radiation response in breast tumour xenografts

Fuentes

Narayan

Milligan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Tumour cells exhibit altered metabolic pathways that lead to radiation resistance and disease progression. Raman spectroscopy (RS) is a label-free optical modality that can monitor post-irradiation biomolecular signatures in tumour cells and tissues. Convolutional Neural Networks (CNN) perform automated feature extraction directly from data, with classification accuracy exceeding that of traditional machine learning, in cases where data is abundant and feature extraction is challenging. We are interested in developing a CNN-based predictive model to characterize clinical tumour response to radiation therapy based on their degree of radiosensitivity or radioresistance. In this work, a CNN architecture is built for identifying post-irradiation spectral changes in Raman spectra of tumour tissue. The model was trained to classify irradiated versus non-irradiated tissue using Raman spectra of breast tumour xenografts. The CNN effectively classified the tissue spectra, with accuracies exceeding 92.1% for data collected 3 days post-irradiation, and 85.0% at day 1 post-irradiation. Furthermore, the CNN was evaluated using a leave-one-out- (mouse, section or Raman map) validation approach to investigate its generalization to new test subjects. The CNN retained good predictive accuracy (average accuracies 83.7%, 91.4%, and 92.7%, respectively) when little to no information for a specific subject was given during training. Finally, the classification performance of the CNN was compared to that of a previously developed model based on group and basis restricted non-negative matrix factorization and random forest (GBR-NMF-RF) classification. We found that CNN yielded higher classification accuracy, sensitivity, and specificity in mice assessed 3 days post-irradiation, as compared with the GBR-NMF-RF approach. Overall, the CNN can detect biochemical spectral changes in tumour tissue at an early time point following irradiation, without the need for previous manual feature extraction. This study lays the foundation for developing a predictive framework for patient radiation response monitoring.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Raman spectroscopy and convolutional neural networks for monitoring biochemical radiation response in breast tumour xenografts

Fuentes

Narayan

Milligan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning (DL) methods have been favored by many researchers in the field of spectroscopy, mainly because DL has obvious advantages in solving high-dimensional spectral data as a deep non-linear network mapping structure model ( Cai et al., 2022 ). There are hundreds or thousands of characteristic wavelengths in a spectrum, and spectral features can be excavated and learned from superficial to in-depth and layer-by-layer by DL, which is similar to imitating the thinking mode of the brain ( Ghosh et al., 2019 ).…”

Section: Introductionmentioning

confidence: 99%

Prediction approach of larch wood density from visible–near-infrared spectroscopy based on parameter calibrating and transfer learning

Zhang

Liu

2022

Front. Plant Sci.

View full text Add to dashboard Cite

Wood density, as a key indicator to measure wood properties, is of weighty significance in enhancing wood utilization and modifying wood properties in sustainable forest management. Visible–near-infrared (Vis-NIR) spectroscopy provides a feasible and efficient solution for obtaining wood density by the advantages of its efficiency and non-destructiveness. However, the spectral responses are different in wood products with different moisture content conditions, and changes in external factors may cause the regression model to fail. Although some calibration transfer methods and convolutional neural network (CNN)-based deep transfer learning methods have been proposed, the generalization ability and prediction accuracy of the models still need to be improved. For the prediction problem of Vis-NIR wood density in different moisture contents, a deep transfer learning hybrid method with automatic calibration capability (Resnet1D-SVR-TrAdaBoost.R2) was proposed in this study. The disadvantage of overfitting was avoided when CNN processes small sample data, which considered the complex exterior factors in actual production to enhance feature extraction and migration between samples. Density prediction of the method was performed on a larch dataset with different moisture content conditions, and the hybrid method was found to achieve the best prediction results under the calibration samples with different target domain calibration samples and moisture contents, and the performance of models was better than that of the traditional calibration transfer and migration learning methods. In particular, the hybrid model has achieved an improvement of about 0.1 in both R2 and root mean square error (RMSE) values compared to the support vector regression model transferred by piecewise direct standardization method (SVR+PDS), which has the best performance among traditional calibration methods. To further ascertain the generalizability of the hybrid model, the model was validated with samples collected from mixed moisture contents as the target domain. Various experiments demonstrated that the Resnet1D-SVR-TrAdaBoost.R2 model could predict larch wood density with a high generalization ability and accuracy effectively but was computation consuming. It showed the potential to be extended to predict other metrics of wood.

show abstract

“…The intervention of professionals in ore separation is reduced, which not only improves the beneficiation capacity, but also reduces the process abnormality and equipment failure rate. The combination of convolution neural network and spectral technology [8][9][10], ore image segmentation [11], ABC-BP (Artificial Bee Colony-Back Propagation) neural network [12], and other improved methods [13][14][15] are used to realize the ore classification of image recognition and effectively solve the problem of manual separation in the process of ore production.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Sorting Method of Bauxite Based on SE-Enhanced Network

Zhao

Luo

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

A fast and accurate bauxite recognition method combining an attention module and a clustering algorithm is proposed in this paper. By introducing the K-means clustering algorithm into the YOLOv4 network and embedding the SE attention module, we calculate the corresponding anchor box value, enhance the feature learning ability of the network to bauxite, automatically learn the importance of different channel features, and improve the accuracy of bauxite target detection. In the experiment, 2189 bauxite photos were taken and screened as the target detection datasets, and the targets were divided into four categories: No. 55, No. 65, No. 70, and Nos. 72–73. By selecting the category volume balanced datasets, the optimal YOLOv4 network model was obtained after training 7000 times, so that the average accuracy of bauxite sorting reached 99%, and the reasoning speed was better than 0.05 s. Realizing the high-speed and high-precision sorting of bauxite greatly improves the mining efficiency and accuracy of the bauxite industry. At the same time, the model provides key technical support for the practical application of the same type of engineering.

show abstract

Rapid identification of ore minerals using multi-scale dilated convolutional attention network associated with portable Raman spectroscopy

Cited by 28 publications

References 28 publications

Raman spectroscopy and convolutional neural networks for monitoring biochemical radiation response in breast tumour xenografts

Raman spectroscopy and convolutional neural networks for monitoring biochemical radiation response in breast tumour xenografts

Prediction approach of larch wood density from visible–near-infrared spectroscopy based on parameter calibrating and transfer learning

Machine Learning Sorting Method of Bauxite Based on SE-Enhanced Network

Contact Info

Product

Resources

About