{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/data-augmentation-of-spectral-data-for","title":"Data Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics","arxiv_id":"1710.01927","date":"2017-10-05","proceeding":null,"authors":["Esben Jannik Bjerrum","Mads Glahder","Thomas Skov"],"abstract":"Deep learning methods are used on spectroscopic data to predict drug content\nin tablets from near infrared (NIR) spectra. Using convolutional neural\nnetworks (CNNs), features are ex- tracted from the spectroscopic data. Extended\nmultiplicative scatter correction (EMSC) and a novel spectral data augmentation\nmethod are benchmarked as preprocessing steps. The learned models perform\nbetter or on par with hypothetical optimal partial least squares (PLS) models\nfor all combinations of preprocessing. Data augmentation with subsequent EMSC\nin combination gave the best results. The deep learning model CNNs also\noutperform the PLS models in an extrapolation chal- lenge created using data\nfrom a second instrument and from an analyte concentration not covered by the\ntraining data. Qualitative investigations of the CNNs kernel activations show\ntheir resemblance to wellknown data processing methods such as smoothing,\nslope/derivative, thresholds and spectral region selection.","url_abs":"http://arxiv.org/abs/1710.01927v1","url_pdf":"http://arxiv.org/pdf/1710.01927v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"data-augmentation-of-spectral-data-for","repo_url":"https://github.com/EBjerrum/Deep-Chemometrics","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"data-augmentation-of-spectral-data-for","repo_url":"https://github.com/dario-passos/deeplearning_for_vis-nir_spectra","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}