The sensing needs for the fresh produce industry can be split into two primary stages: during maturation in the field, also referred to as Precision Farming, and during storage and transport of the produce, or Postharvest Storage. This work seeks to improve the accuracy and reliability of commercially available electrochemical and spectroscopic sensors tailored to the sensing needs of the fresh produce industry. For electrochemical
One of six IDRC 17 Student award recipients, Ryan Lerud is in the PhD programme at Portland State University, being co-advised by Peter Moeck of the Physics Department and Shankar Rananavare of the Chemistry Department. Ryan has been using multivariate statistics to develop a NIR/Vis Portable Fruit Quality Meter as part of his Masters thesis and on-going internship with Felix Instruments, Camas, WA. In this article, Ryan discusses instrument design, the impact that design has on fluctuating temperature and voltage and the effect of the latter on model performance.
The author has spent the last three years as part of a team developing a handheld near infrared (NIR) fruit spectrometer for use across the agricultural supply chain. In this article, Ryan provides examples of calibrations and discusses some of the finer issues of good analytical technique to answer some of the most common questions asked by users of NIR spectroscopy in developing robust and reliable models.A s near infrared (NIR) spectroscopy moves from the laboratory to field-ready, handheld spectrometer units, the NIR community needs to develop simple examples and language suitable for farmers, QA technicians and other layperson operators. As I interact with people new to the use of NIR for agriculture, one question that always arises is: "how good a model can I make?". As practitioners of NIR, we know the answer to this question depends on many factors; the largest being the cost and time for the level of effort they are willing to put into the calibration process. Yet, we as a community have stock answers such as "the model can only be as good as the reference method", or "the model can be better than the reference method, if you keep only the well-predicted values". As accurate as these statements might be they are less than useful for someone without a background in NIR.To help customers visualise the importance of the reference method accuracy and why it is important not to cut corners while developing a model, we discuss the transflection sugar water data in Table 1. By taking a set of 18 spectra, shown in Figure 1, and inputting either the estimated sugar concentration or the actual sugar concentration into a partial least squares regression (PLSR), we can directly see the impact of error in the reference values. From the results shown in Figure 2, it becomes obvious that the error of estimation in the reference is carried over to the model. Specifically, that the root mean square error of cross-validation (RMSECV ), for the model built using the estimated sugar concentration is nearly double that of the model developed on the basis of the actual sugar concentration. Both models were built using the
Near infrared spectroscopy is a routine measurement and analysis tool for both liquid and solid samples in a wide variety of industries and locations, both process and laboratory. For process measurements analyzer, validation is a key component of a complete measurement system. This short article will describe an automated validation system suitable for near infrared process analyzers.
Transfer methods were compared for the porting of partial least squares models for intact mango dry matter content between short wave near infrared silicon photodiode array instruments. Methods included bias adjustment using average difference spectrum, new pixel-to-wavelength assignments, piecewise direct standardisation (PDS), global models, model updating (MU) and combinations of these. Best results (R 2 > 0.84 and bias < 0.2) were obtained by PDS using the same variety of fruit in calibration and transfer sets. The use of an apple spectra transfer set was also successful, if the wavelength accuracy of the slave unit(s) is satisfactory. Alternatively, a field practical solution that gave acceptable prediction results involved development of a global model across units or model updating by inclusion of spectra of the new population, using reference values estimated using the master unit.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.