We present a methodology for establishing meaningful multivariate specification regions on incoming materials or components. The approach uses multivariate PLS regression models to extract information from databases and to relate the properties of incoming materials, and the process variables, to the quality measures on the customer's product. The specification regions are multivariate in nature and are defined in the latent variable space of the PLS model. However, they are easy to implement in practice, and they can provide much insight into what constitutes acceptable material. The approach is illustrated using a simulated process, and is then used to establish multivariate specification regions for polymer resin properties in an industrial film process.

A rapid and non‐intrusive on‐line NIR imaging sensor is developed for monitoring spatio‐temporal crystallinity variations across the surface of polymer films. A multivariate image analysis and regression (MIA/MIR) approach is proposed and compared with standard NIR calibration techniques using averaged spectra or second order derivatives combined with PLS regression. Predictions of both the local and global crystallinity variations of HDPE, LDPE, and PP polymer samples were obtained with each approach. Our results show that small variations in crystallinity introduced by changes in cooling rates can be predicted within experimental errors. Crystallinity spatial distributions were also validated and found consistent with processing conditions.

Acquiring and processing phase-contrast microscopy images in wide-field long-term live-cell imaging and high-throughput screening applications is still a challenge as the methodology and algorithms used must be fast, simple to use and tune, and as minimally intrusive as possible. In this paper, we developed a simple and fast algorithm to compute the cell-covered surface (degree of confluence) in phase-contrast microscopy images. This segmentation algorithm is based on a range filter of a specified size, a minimum range threshold, and a minimum object size threshold. These parameters were adjusted in order to maximize the F-measure function on a calibration set of 200 hand-segmented images, and its performance was compared with other algorithms proposed in the literature. A set of one million images from 37 myoblast cell cultures under different conditions were processed to obtain their cell-covered surface against time. The data were used to fit exponential and logistic models, and the analysis showed a linear relationship between the kinetic parameters and passage number and highlighted the effect of culture medium quality on cell growth kinetics. This algorithm could be used for real-time monitoring of cell cultures and for high-throughput screening experiments upon adequate tuning.