English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With noisy environment caused by fluoresence and additive white noise as wellas complicated spectrum fingerprints, the identification of complex mixturematerials remains a major challenge in Raman spectroscopy application. In thispaper, we propose a new scheme based on a constant wavelet transform (CWT) anda deep network for classifying complex mixture. The scheme first transforms thenoisy Raman spectrum to a two-dimensional scale map using CWT. A multi-labeldeep neural network model (MDNN) is then applied for classifying material. Theproposed model accelerates the feature extraction and expands the feature graphusing the global averaging pooling layer. The Sigmoid function is implementedin the last layer of the model. The MDNN model was trained, validated andtested with data collected from the samples prepared from substances in palmoil. During training and validating process, data augmentation is applied toovercome the imbalance of data and enrich the diversity of Raman spectra. Fromthe test results, it is found that the MDNN model outperforms previouslyproposed deep neural network models in terms of Hamming loss, one error,coverage, ranking loss, average precision, F1 macro averaging and F1 microaveraging, respectively. The average detection time obtained from our model is5.31 s, which is much faster than the detection time of the previously proposedmodels.

Identification of complex mixtures for Raman spectroscopy using a novel scheme based on a new multi-label deep neural network