Filters
Predictive assessment of mycological state of bulk-stored barley using B-splines in conjunction with genetic algorithms
Postharvest grain preservation and storage can significantly affect the safety and nutritional value of cereal-based products. Negligence at this stage of the food processing chain can lead to mold development and mycotoxin accumulation, which pose considerable threats to the quality of harvested grain and, thus, to consumer health. Predictive models evaluating the risk associated with fungal activity constitute a promising solution for decision-making modules in advanced preservation management systems. In this study, an attempt was made to combine genetic algorithms and B-spline curves in order to develop a predictive model to assess the mycological state of malting barley grain stored at various temperatures (T = 12–30 °C) and water activity in grain (aw = 0.78–0.96). It was found that the B-spline curves consisting of four second-order polynomials were sufficient to approximate the datasets describing fungal growth in barley ecosystems stored under steady temperature and humidity conditions. Based on the designated structures of B-spline curves, a universal parameterized model covering the entire range of tested conditions was developed. In the model, the coordinates of the control points of B-spline curves were modulated by genetic algorithms using values of storage parameters (aw and T). A statistical assessment of model performance showed its high efficiency (R2 = 0.94, MAE = 0.21, RMSE = 0.28). As the proposed model is based on easily measurable on-line storage parameters, it could be used as an effective tool supporting modern systems of postharvest grain treatment.
Methodology for Quantifying Volatile Compounds in a Liquid Mixture Using an Algorithm Combining B-Splines and Artificial Neural Networks to Process Responses of a Thermally Modulated Metal-Oxide Semiconductor Gas Sensor
Metal oxide semiconductor (MOS) gas sensors have many advantages, but the main obstacle to their widespread use is the cross-sensitivity observed when using this type of detector to analyze gas mixtures. Thermal modulation of the heater integrated with a MOS gas sensor reduced this problem and is a promising solution for applications requiring the selective detection of volatile compounds. Nevertheless, the interpretation of the sensor output signals, which take the form of complex, unique patterns, is difficult and requires advanced signal processing techniques. The study focuses on the development of a methodology to measure and process the output signal of a thermally modulated MOS gas sensor based on a B-spline curve and artificial neural networks (ANNs), which enable the quantitative analysis of volatile components (ethanol and acetone) coexisting in mixtures. B-spline approximation applied in the first stage allowed for the extraction of relevant information from the gas sensor output voltage and reduced the size of the measurement dataset while maintaining the most vital features contained in it. Then, the determined parameters of the curve were used as the input vector for the ANN model based on the multilayer perceptron structure. The results show great usefulness of the combination of B-spline and ANN modeling techniques to improve response selectivity of a thermally modulated MOS gas sensor.
Machine and Deep Learning in the Evaluation of Selected Qualitative Characteristics of Sweet Potatoes Obtained under Different Convective Drying Conditions
This paper discusses the use of various methods to distinguish between slices of sweet potato dried in different conditions. The drying conditions varied in terms of temperature, the values were: 60 °C, 70 °C, 80 °C, and 90 °C. Examination methods included instrumental texture analysis using a texturometer and digital texture analysis based on macroscopic images. Classification of acquired data involved the use of machine learning techniques using various types of artificial neural networks, such as convolutional neural networks (CNNs) and multi-layer perceptron (MLP). As a result, in the convective drying, changes in color darkening were found in products with the following temperature values: 60 °C (L = 83.41), 70 °C (L = 81.11), 80 °C (L = 79.02), and 90 °C (L = 75.53). The best-generated model achieved an overall classification efficiency of 77%. Sweet potato dried at 90 °C proved to be completely distinguishable from other classes, among which classification efficiency varied between 61–83% depending on the class. This means that image analysis using deep convolutional artificial neural networks is a valuable tool in the context of assessing the quality of convective-dried sweet potato slices.