Applied Machine Learning in NIR Technology

Dear Colleagues,

As you already know, since the 1980s, Near-Infrared Reflectance (NIR) scanners have been a common companion in laboratories. This technology allows the analysis of the electromagnetic spectrum in bands close to the visible spectrum. As a result, there is a large amount of information that can be analyzed in order to make predictions about a factor such as the quality of the sample.  This advantage of being able to quickly analyze the material without having to destroy the samples have made it so that, in recent times, this kind of equipment has been moved from the laboratory to portable devices in some cases as small as a credit card. Therefore, numerous applications have been developed under the umbrella of this technology, such as analysis of sewer water, determination of the food safety, diagnosis of construction material, support on medical and vet diagnosis; the number of applications are near endless.

However, this blossom of applications usually goes along with the requirement of a model which identifies and uses the information in the captured spectra. The relationship between both factors is usually non-linear and complex, so it is necessary to use machine learning techniques to obtain it. Although, it has usually been performed through an analytical process, currently, the application of machine learning has been a step forward in terms of the precision and adjustment of the results. As NIR and machine learning are multidisciplinary technologies, many fields of science and industry could benefit from their use.

Especially, if we focus on feature selection of the bands on the spectra that contain the information required to solve the problem, the application of machine learning needs a process of adjustment to optimize the performance. The aim of this Special Issue is to present the latest advances that have been made in this field, combining both techniques, as well as to show the remaining challenges and the future in this area of research. That is why this Special Issue solicits submissions in, but not limited to, the following areas:

• Selection of features or bands of the NIR spectra, with a special interest in those applications using nano-scale NIR scanners due to its limit operational range;
• Studies of different preprocessing techniques and comparison with automatic features extraction process, such as PCA, LDA, evolutionary computation;
• Developments combining cloud computing, fog computing or edge computing with the processing of NIR spectra in different industrial processes;
• Application and comparative of the latest approaches of machine learning techniques, such as deep learning or ensemble models;
• Works with a particular interest to cover the explainable artificial intelligence in the frame of decision-making using NIR data and machine learning.

Dr. Enrique Fernandez-Blanco
Dr. Daniel Rivero
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.