A new data processing strategy combined with a convolutional neural network for rapid and accurate prediction of geographical classifications of natural products

Zhou, Bingwen; Jia, Mengke; Zhang, Fan; Jin, Qi; Yu, Boyang

doi:10.1016/j.chemolab.2022.104594

Cited by 3 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the activation function for the convolutional layers uses the most commonly used recti ed linear unit function (ReLU function), which is faster and more e cient than other activation functions, such as Tanh and Sigmoid, for non-saturated non-linear ReLU [23]. For the structure of the convolutional neural network model, the rst convolutional layer contains 32 lters with a kernel size of 3 and a step size of 2.…”

Section: Construction Of Cnn Modelsmentioning

confidence: 99%

Accurate felt-tip pen brands classification based on a convolutional neural network using data augmentation

Huang

Wang

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Ink analysis played an important role in document examination, but the limited dataset made it difficult for many algorithms to distinguish inks accurately. This paper aimed to evaluate the feasibility of two data augmentation(DA) methods, Gaussian noise data augmentation (GNDA) and extended multiplicative signal augmentation (EMSA), for the classification of felt-tip pen ink brands. Four brands of felt-tip pens were analysed using FTIR spectroscopy. Five classification models were used, convolutional neural network (CNN), K-nearest neighbor (KNN), support vector machine (SVM), random forest (RF), and partial least squares discriminant analysis (PLS-DA). The results showed that the datasets generated by GNDA and EMSA are similar to the original datasets and have some diversity. The EMSA method had optimal classification results when combined with CNN, with classification accuracy (ACC), precision (PRE), recall (REC) and F1 score reaching 99.86%, 99.87%, 99.86%, 99.86%, and 99.86%, compared with GNDA-CNN method(ACC = 80.90%, PRE = 87.34%, REC = 81.62%, F1 score = 79.23%). This study shows that when raw spectral data is small, DA methods can be combined with neural network models to identify ink brands effectively.

show abstract

Section: Construction Of Cnn Modelsmentioning

confidence: 99%