Online Feature Selection for Robust Classification of the Microbiological Quality of Traditional Vanilla Cream by Means of Multispectral Imaging

A pH-sensitive intelligent packaging film harnessing Dioscorea zingiberensis starch and anthocyanin for meat freshness monitoring

Abundant starch was isolated from Dioscorea zingiberensis C.H. Wright, a novel and underutilized industrial crop resource. In this study, an intelligent packaging film able to indicate food freshness was developed and characterized. D. zingiberensis starch (DZS) was bleached first, and its particle size, total starch content, amylose content, and gelatinization temperature were then measured. Butterfly pea (Clitoria ternatea Linn.) flowers were selected as the source of polyphenols, which rendered the prepared film intelligent and progressively blue-violet. SEM and FT-IR analyses showed the homogeneous dispersion of butterfly pea flower extract (BPE) in the film. The BPE-loaded film showed improved flexibility and resistance to UV and oxidation while maintaining sufficient mechanical strength and physical properties. Moreover, the film underwent a distinguishable color change from red to blue-violet and finally to green-yellow with increasing pH from 2 to 13. Similar color alteration also occurred when the film was exposed to ammonia. When the film was used to monitor the freshness of chicken stored at room temperature, it exhibited an obvious color change, implying its deterioration. Therefore, the newly developed BPE-DZS film, which was produced from readily accessible natural substances, can serve as an intelligent packaging material, indicating food freshness and prolonging shelf life.

Spectroscopy and imaging technologies coupled with machine learning for the assessment of the microbiological spoilage associated to ready-to-eat leafy vegetables

Based on both new and previously utilized experimental data, the present study provides a comparative assessment of sensors and machine learning approaches for evaluating the microbiological spoilage of ready-to-eat leafy vegetables (baby spinach and rocket). Fourier-transform infrared (FTIR), near-infrared (NIR), visible (VIS) spectroscopy and multispectral imaging (MSI) were used. Two data partitioning approaches and two algorithms, namely partial least squares regression and support vector regression (SVR), were evaluated. Concerning baby spinach, when model testing was performed on samples randomly selected, the performance was better than or similar to the one attained when testing was performed based on dynamic temperatures data, depending on the applied analytical technology. The two applied algorithms yielded similar model performances for the majority of baby spinach cases. Regarding rocket, the random data partitioning approach performed considerably better results in almost all cases of sensor/algorithm combination. Furthermore, SVR algorithm resulted in considerably or slightly better model performances for the FTIR, VIS and NIR sensors, depending on the data partitioning approach. However, PLSR algorithm provided better models for the MSI sensor. Overall, the microbiological spoilage of baby spinach was better assessed by models derived mainly from the VIS sensor, while FTIR and MSI were more suitable in rocket. According to the findings of this study, a distinct sensor and computational analysis application is needed for each vegetable type, suggesting that there is not a single combination of analytical approach/algorithm that could be applied successfully in all food products and throughout the food supply chain.

Spoilage potential of Bacillus subtilis in a neutral-pH dairy dessert

The objective of this study was the characterization of the microbiota associated with spoilage of vanilla cream pudding during storage at different temperatures. Commercial cream samples were stored aerobically at 4, 8, 12 and 15 °C for a maximum time period of 40 days. At appropriate time intervals, cream samples were subjected to: (i) microbiological analyses, and (ii) high-performance liquid chromatography (HPLC). Furthermore, the spoilage microbiota was identified through repetitive extragenic palindrome-PCR, while selected isolates were further characterized based on sequencing of the V1-V3 region of the 16S rRNA gene. Microbial growth was observed only during storage of cream samples at 12 and 15 °C, with the applied genotypic analysis demonstrating that Bacillus subtilis subsp. subtilis was the dominant spoilage microorganism of this product. Based on the HPLC analysis results, citric acid and sucrose were the most abundant organic acid and sugar, respectively throughout storage of cream pudding, whereas notable changes mainly included: (i) increase in the concentration of lactic acid and to a lesser extent of formic and acetic acids, and (ii) increase in the concentration of glucose and fructose at the expense of sucrose and lactose. The results of this study should be useful for the dairy industry in detecting and controlling microbiological spoilage in cream pudding and other chilled, neutral-pH dairy desserts.

Deciphering Cancer Cell Behavior From Motility and Shape Features: Peer Prediction and Dynamic Selection to Support Cancer Diagnosis and Therapy

Cell motility varies according to intrinsic features and microenvironmental stimuli, being a signature of underlying biological phenomena. The heterogeneity in cell response, due to multilevel cell diversity especially relevant in cancer, poses a challenge in identifying the biological scenario from cell trajectories. We propose here a novel peer prediction strategy among cell trajectories, deciphering cell state (tumor vs. nontumor), tumor stage, and response to the anticancer drug etoposide, based on morphology and motility features, solving the strong heterogeneity of individual cell properties. The proposed approach first barcodes cell trajectories, then automatically selects the good ones for optimal model construction (good teacher and test sample selection), and finally extracts a collective response from the heterogeneous populations via cooperative learning approaches, discriminating with high accuracy prostate noncancer vs. cancer cells of high vs. low malignancy. Comparison with standard classification methods validates our approach, which therefore represents a promising tool for addressing clinically relevant issues in cancer diagnosis and therapy, e.g., detection of potentially metastatic cells and anticancer drug screening.