Selection of industrial tomatoes using TD-NMR data and computational classification methods

Rapid estimation approach for glycosylated serum protein of human serum based on the combination of deep learning and TD-NMR technology

Rapid and precise estimation of glycosylated serum protein (GSP) of human serum is of great importance for the treatment and diagnosis of diabetes mellitus. In this study, we propose a novel method for estimation of GSP level based on the combination of deep learning and time domain nuclear magnetic resonance (TD-NMR) transverse relaxation signal of human serum. Specifically, a principal component analysis (PCA)-enhanced one-dimensional convolutional neural network (1D-CNN) is proposed to analyze the TD-NMR transverse relaxation signal of human serum. The proposed algorithm is proved by accurate estimation of GSP level for the collected serum samples. Furthermore, the proposed algorithm is compared with 1D-CNN without PCA, long short-term memory network (LSTM) and some conventional machine learning algorithms. The results indicate that PCA-enhanced 1D-CNN (PC-1D-CNN) has the minimum error. This study proves that proposed method is feasible and superior to estimate GSP level of human serum using TD-NMR transverse relaxation signals.

The use of time domain 1 H NMR to study proton dynamics in starch-rich foods: A review

Starch is a major contributor to the carbohydrate portion of our diet. When it is present with water, it undergoes several transformations during heating and/or cooling making it an essential structure-forming component in starch-rich food systems (e.g., bread and cake). Time domain proton nuclear magnetic resonance (TD ¹ H NMR) is a useful technique to study starch-water interactions by evaluation of molecular mobility and water distribution. The data obtained correspond to changes in starch structure and the state of water during or resulting from processing. When this technique was first applied to starch(-rich) foods, significant challenges were encountered during data interpretation of complex food systems (e.g., cake or biscuit) due to the presence of multiple constituents (proteins, carbohydrates, lipids, etc.). This article discusses the principles of TD ¹ H NMR and the tools applied that improved characterization and interpretation of TD NMR data. More in particular, the major differences in proton distribution of various dough and cooked/baked food systems are examined. The application of variable-temperature TD ¹ H NMR is also discussed as it demonstrates exceptional ability to elucidate the molecular dynamics of starch transitions (e.g., gelatinization, gelation) in dough/batter systems during heating/cooling. In conclusion, TD NMR is considered a valuable tool to understand the behavior of starch and water that relate to the characteristics and/or quality of starchy food products. Such insights are crucial for food product optimization and development in response to the needs of the food industry.