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

Hyperspectral Imaging (HSI) combines microscopy and spectroscopy to assessthe spatial distribution of spectroscopically active compounds in objects, andhas diverse applications in food quality control, pharmaceutical processes, andwaste sorting. However, due to the large size of HSI datasets, it can bechallenging to analyze and store them within a reasonable digitalinfrastructure, especially in waste sorting where speed and data storageresources are limited. Additionally, as with most spectroscopic data, there issignificant redundancy, making pixel and variable selection crucial forretaining chemical information. Recent high-tech developments in chemometricsenable automated and evidence-based data reduction, which can substantiallyenhance the speed and performance of Non-Negative Matrix Factorization (NMF), awidely used algorithm for chemical resolution of HSI data. By recovering thepure contribution maps and spectral profiles of distributed compounds, NMF canprovide evidence-based sorting decisions for efficient waste management. Toimprove the quality and efficiency of data analysis on hyperspectral imaging(HSI) data, we apply a convex-hull method to select essential pixels andwavelengths and remove uninformative and redundant information. This processminimizes computational strain and effectively eliminates highly mixed pixels.By reducing data redundancy, data investigation and analysis become morestraightforward, as demonstrated in both simulated and real HSI data forplastic sorting.

Systematic reduction of Hyperspectral Images for high-throughput Plastic Characterization