Tae-Sung Shin

Firmness is an important quality indicator of blueberries. Firmness loss (or softening) of postharvest blueberries has posed a challenge in its shelf-life quality control and can be delineated with its microstructural changes. To investigate spatial and spectral characteristics of microstructures based on firmness, hyperspectral microscope imaging (HMI) was employed for this study. The mesocarp area with 20× magnification of blueberries was selectively imaged with a Fabry–Perot interferometer HMI system of 400–1000 nm wavelengths, resulting in 281 hypercubes of parenchyma cells in a resolution of 968 × 608 × 300 pixels. After properly processing each hypercube of parenchyma cells in a blueberry, the cell image with different firmness was examined based on parenchyma cell shape, cell wall segment, cell-to-cell adhesion, and size of intercellular spaces. Spectral cell characteristics of firmness were also sought based on the spectral profile of cell walls with different image preprocessing methods. The study found that softer blueberries (1.96–3.92 N) had more irregular cell shapes, lost cell-to-cell adhesion, loosened and round cell wall segments, large intercellular spaces, and cell wall colors that were more red than the firm blueberries (6.86–8.83 N). Even though berry-to-berry (or image-to-image) variations of the characteristics turned out large, the deep learning model with spatial and spectral features of blueberry cells demonstrated the potential for blueberry firmness classification with Matthew’s correlation coefficient of 73.4% and accuracy of 85% for test set.

This paper reports the results of a feasibility study for the development of a hyperspectral image recovery (reconstruction) technique using a RGB color camera and regression analysis in order to detect and classify colonies of foodborne pathogens. The target bacterial pathogens were the six representative non-O157 Shiga-toxin producing Escherichia coli (STEC) serogroups (O26, O45, O103, O111, O121, and O145) grown in Petri dishes of Rainbow agar. The purpose of the feasibility study was to evaluate whether a DSLR camera (Nikon D700) could be used to predict hyperspectral images in the wavelength range from 400 to 1,000 nm and even to predict the types of pathogens using a hyperspectral STEC classification algorithm that was previously developed. Unlike many other studies using color charts with known and noise-free spectra for training reconstruction models, this work used hyperspectral and color images, separately measured by a hyperspectral imaging spectrometer and the DSLR color camera. The color images were calibrated (i.e. normalized) to relative reflectance, subsampled and spatially registered to match with counterpart pixels in hyperspectral images that were also calibrated to relative reflectance. Polynomial multivariate least-squares regression (PMLR) was previously developed with simulated color images. In this study, partial least squares regression (PLSR) was also evaluated as a spectral recovery technique to minimize multicollinearity and overfitting. The two spectral recovery models (PMLR and PLSR) and their parameters were evaluated by cross-validation. The QR decomposition was used to find a numerically more stable solution of the regression equation. The preliminary results showed that PLSR was more effective especially with higher order polynomial regressions than PMLR. The best classification accuracy measured with an independent test set was about 90%. The results suggest the potential of cost-effective color imaging using hyperspectral image classification algorithms for rapidly differentiating pathogens in agar plates.

This paper reports the latest development of a color vision technique for detecting colonies of foodborne pathogens grown on agar plates with a hyperspectral image classification model that was developed using full hyperspectral data. The hyperspectral classification model depended on reflectance spectra measured in the visible and near-infrared spectral range from 400 and 1,000 nm (473 narrow spectral bands). Multivariate regression methods were used to estimate and predict hyperspectral data from RGB color values. The six representative non-O157 Shiga-toxin producing Eschetichia coli (STEC) serogroups (O26, O45, O103, O111, O121, and O145) were grown on Rainbow agar plates. A line-scan pushbroom hyperspectral image sensor was used to scan 36 agar plates grown with pure STEC colonies at each plate. The 36 hyperspectral images of the agar plates were divided in half to create training and test sets. The mean Rsquared value for hyperspectral image estimation was about 0.98 in the spectral range between 400 and 700 nm for linear, quadratic and cubic polynomial regression models and the detection accuracy of the hyperspectral image classification model with the principal component analysis and k-nearest neighbors for the test set was up to 92% (99% with the original hyperspectral images). Thus, the results of the study suggested that color-based detection may be viable as a multispectral imaging solution without much loss of prediction accuracy compared to hyperspectral imaging.

This paper extends work on the construction of instructional modules that use graphical and simulation techniques for teaching statistical concepts ( Marasinghe, et al. 1996 Marasinghe, M. G. , Meeker, W. Q. , Cook, D. , and Shin, T. (1996), “UsingGraphics and Simulation to Teach Statistical Concepts,” TheAmerican Statistician, 50(4), 342–351. [Taylor & Francis Online], [Web of Science ®] [Google Scholar] ; Iversen and Marasinghe 2001 Iversen, P. , and Marasinghe, M. G. (2001), “DynamicGraphical Tools for Teaching Experimental Design and AnalysisConcepts,” The American Statistician, 55(4), 345–351. [Taylor & Francis Online], [Web of Science ®] [Google Scholar] ). These modules consist of two components: a software part and a lesson part. A computer program written in LISP-STAT with a highly interactive user interface that the instructor and the students can use for exploring various ideas and concepts comprises the software part. The lesson part is a prototype document providing guidance for instructors for creating their own lessons using the software module. This includes a description of concepts to be covered, instructions on how to use the module and some exercises. The regression modules described here are designed to illustrate various concepts associated with regression model fitting such as the use of residuals and other case diagnostics to check for model adequacy, the assessment of the effects of transforming the response variable on the regression fit using well-known diagnostic plots and the use of statistics to measure effects of collinearity on model selection.

The value to students of active learning has been recognized. This has led to the wide use of assignments in statistical methods courses where students use statistical software and computing equipment to analyze data. These assignments enable most students to master the mechanics of data analysis. The amount of experience that a student can get with such assignments is, however, limited. A sizable proportion of students have difficulty grasping some of the many concepts that are introduced in these courses. Nevertheless, these concepts are important for effective modeling and data analysis, and instructors should focus on them. By using current computing technology, it is possible to supplement standard data analysis assignments and algebraic derivations and have students become actively involved in the learning of important statistical concepts. The learning experience can be enhanced by giving students additional statistical “experiences” by using combinations of carefully designed and implemented multiple simulations and dynamic graphics to illustrate key ideas. In this article we describe and illustrate several instructional modules and corresponding software that have been designed to assist instructors in teaching introductory statistics courses.