Monitoring pH and acidity during yoghurt fermentation is essential for product quality and process efficiency. Conventional measurement methods, however, are invasive and labour-intensive. This study developed artificial neural network (ANN) models to predict pH and titratable acidity during yoghurt fermentation using CIELAB colour parameters (L, a*, b*). Reconstituted milk powder with 12% total solids was prepared with varying protein levels (4.2–4.8%), inoculum concentrations (1–3%), and fermentation temperatures (36–44 °C). Data were collected every 10 min until pH 4.6 was reached. Forty models were trained for each output variable, using 90% of the data for training and 10% for validation. The first two phases of the fermentation process were clearly distinguishable, lasting between 4.5 and 7 h and exceeding 0.6% lactic acid in all treatments evaluated. The best pH model used two hidden layers with 28 neurons (R² = 0.969; RMSE = 0.007), while the optimal acidity model had four hidden layers with 32 neurons (R² = 0.868; RMSE = 0.002). The strong correlation between colour and physicochemical changes confirms the feasibility of this non-destructive approach. Integrating ANN models and colourimetry offers a practical solution for real-time monitoring, helping improve process control in industrial yoghurt production.

Ultrasound is considered a physical technology that can be applied at various stages of food processing to optimise resources and reduce production time. In this study, the influence of ultrasonic treatments at different power levels (0 W, 100 W, 200 W, and 300 W) on three Isaño genotypes (yellow, yellow with purple eyes, and purple) during alcoholic fermentation was investigated. The main parameters assessed were yeast growth kinetics, ethanol production, and substrate consumption in an ultrasonic bath operating at a frequency of 50 kHz. The findings demonstrated enhanced yeast growth, accelerated substrate consumption, and increased ethanol production compared to the control (untreated sample). However, the impact of ultrasound on fermentation decreased as the power level increased. Notably, an ultrasonic power of 100 W applied over 84 h of fermentation resulted in the highest ethanol yield (10.36% v/v) in the purple Isaño genotype. In conclusion, ultrasonic treatment is a promising approach to improve the fermentation process of Isaño, potentially enabling its development as a functional beverage with both nutritional and therapeutic properties.

Native Andean potatoes (Solanum tuberosum subsp. andigenum) are a valuable phytogenetic resource due to their compositional diversity and adaptation to high-altitude environments. Their starch is a key functional polysaccharide widely used in food systems; however, information on the kinematic viscosity of dilute gels under moderate thermal conditions remains limited. This study evaluated the effects of temperature (26, 36, and 46 °C) and starch concentration (1–3% w/v) on the kinematic viscosity of gels from three Andean potato varieties: Imilla Negra, Compis, and Peruanita. Starch was extracted from fresh tubers (Puno, Peru) using a wet extraction method, and gels were prepared by heating dispersions at 85 °C for 5 min under controlled conditions. Viscosity (0.61–34.47 cSt) decreased with increasing temperature and increased with concentration, confirming the sensitivity of these systems to thermal and compositional factors. The Arrhenius model adequately described temperature dependence, with activation energies of 15.19–29.75 kJ·mol⁻¹, showing an increasing trend with concentration. At 3% and 26 °C, viscosity followed Compis > Imilla Negra > Peruanita, indicating varietal differences in thickening capacity. These results provide useful rheological data for the design and optimisation of food processes involving dilute Andean potato starch dispersions.

Black mashua (Tropaeolum tuberosum), also known as purple mashua, is an Andean plant with high nutritional and medicinal value. It has traditionally been used to treat prostate conditions. This study examined how the agroecological origin (Puno and Junín) and processing methods (extrusion and drum drying) affected the physicochemical, bioactive, and technofunctional properties of instant black mashua flour. Both factors were found to significantly influence the content of bioactive compounds and technofunctional behaviour of the flour. Although extrusion increased the content of total phenols, flavonoids, carotenoids, and total glucosinolates, it decreased the levels of vitamin C and anthocyanins, likely due to their thermal sensitivity. From a technological perspective, extrusion also resulted in higher bulk density, water absorption capacity, and swelling power. In contrast, drum drying produced higher water solubility and gelatinisation index values. Samples from Puno generally exhibited higher glucosinolate contents than those from Junín, while extrusion proved more effective in enhancing glucosinolate retention and improving functional properties. These findings suggest that the processing method should be chosen based on the specific bioactive compounds and technological functionalities that are prioritised in each agroecological zone.