This paper presents a detailed analysis of the relation between physical characteristics and defects of green coffee beans and the sensory profile that influence the sensory notes of fragrance, aroma, flavor, and aftertaste of coffee. Machine learning models were used to identify the variables of importance and identify the ways in which these variables affect the sensory note of coffee, to determine which algorithm and its hyperparameters have greater precision in determining the sensory values of coffee such as floral, fruity, herbal, nutty, caramel, chocolate, spicy, resinous, pyrolytic, earthy, fermented, and phenolic. The result indicates the relationship and importance that exist between the physical variables, defects, and size of the green coffee bean, with respect to their respective sensory notes. The data of the proposed system demonstrate that by combining the scores of several experts, a precision can be achieved analogously to that obtained by cupping experts; therefore, the possibility of errors induced by human concerns such as fatigue or subjectivity is reduced.

Sugarcane is one of the main agro-industrial products consumed worldwide, and, therefore, the use of suitable soils is a key factor to maximize its production. As a result, the need to evaluate soil matrices, including many physical, chemical, and biological parameters, to determine the soil’s aptitude for growing food crops increases. Machine learning techniques were used to perform an in-depth analysis of the physicochemical indicators of vertisol-type soils used in sugarcane production. The importance of the relationship between each of the indicators was studied. Furthermore, and the main objective of the present work, was the determination of the minimum number of the most important physicochemical indicators necessary to evaluate the agricultural suitability of the soils, with a view to reducing the number of analyses in terms of physicochemical indicators required for the evaluation. The results obtained relating to the estimation of agricultural capability using different numbers of parameters showed accuracy results of up to 91% when implementing three parameters: Potassium (K), Calcium (Ca) and Cation Exchange Capacity (CEC). The reported results, relating to the estimation of the physicochemical parameters, indicated that it was possible to estimate eleven physicochemical parameters with an average accuracy of 73% using only the data of K, Ca and CEC as input parameters in the Machine Learning models. Knowledge of these three parameters enables determination of the values of soil potential in regard to Hydrogen (pH), organic matter (OM), Phosphorus (P), Magnesium (Mg), Sulfur (S), Boron (B), Copper (Cu), Manganese (Mn), and Zinc (Zn), the Calcium/Magnesium ratio (Ca/Mg), and also the texture of the soil.

This paper presents a novel biomechatronic device that resolves the necessities of mobility for people with spinal cord trauma (SCI) and disability. The proposed device features a safe and reliable mobility mechanism that withstands daily use without premature mechanical wear, facilitating the activities of daily living (ADL) for people affected by SCI, integrating them to a social and workforce environment that allows them, on one hand, to move in a standing upright position in complex situations of the urban architecture, and on the other hand, provides them a mechatronic system to assist them to stand up and sit down.

This study investigates the energy recovery potential of bio-oil derived from hydrothermal carbonization (HTC) of citrus waste through anaerobic digestion (AD). The bio-oil, a complex mixture containing 30-50% of the original carbon from biomass, serves as a valuable substrate for AD. Leveraging the HTC pretreatment, the hydrolysis step in AD becomes more efficient, facilitating faster degradation rates. Anaerobic digestion of the bio-oil was conducted in a high-loading hybrid anaerobic reactor. The reactor underwent stabilization using tomato liquid fraction, followed by bio-oil feeding with an applied volumetric loading of 5 g COD/L-d under mesophilic conditions. Remarkably, COD removals exceeded 90% when utilizing the tomato fraction and surpassed 80% in the bio-oil feed. Additionally, methane yield approached theoretical levels, highlighting the effectiveness of combining HTC and AD technologies. The study demonstrates that the integration of HTC and AD offers a promising alternative for the sustainable utilization of citrus industry wastes, showcasing high removal efficiencies and methane production. This approach aligns with circular economy principles, providing a pathway for efficient waste valorization and renewable energy generation.

Rice is a widely consumed food product worldwide, and it generates an agro-industrial waste product called rice husk, which currently lacks economic value and is poorly managed due to its difficult handling. Therefore, the objective of this work was to carry out the hydrothermal carbonization of rice husk to produce hydrochar as a biofuel using different reaction conditions. The hydrothermal carbonization of the rice husk was performed in a 1 L stainless steel reactor, model CF-1, using temperatures of 180, 190, and 200 °C and reaction times of 1, 2, and 3 h, respectively. The rice husk and the hydrochars were analyzed for pH, moisture content, total solids, volatile solids, ash content, electrical conductivity, elemental analysis, and higher heating value (HHV). The main results showed that the hydrochars had acidic pH values, moisture content below 10%, TS and VS values above 90% and 74%, respectively, high ash content and electrical conductivity, and HHV values greater than 15 MJ/kg. The thermochemical conversion of rice husks helps reduce the volume of a difficult-to-manage agro-industrial waste product and, in turn, provides a biofuel with a higher HHV than the initial biomass (14.34 MJ/kg). At the end of the study, it was observed that one hour was sufficient to improve the HHV compared to uncarbonized rice husks, due to the increase in C (> 38%) and low moisture (< 8%).

Quality control in green coffee bean production is critical for food safety and economic sustainability. A persistent gap in existing automated inspection systems is their inability to capture both sides of each bean, which leads to systematic under-detection of surface defects. This work presents three contributions: (i) a novel mechatronic apparatus that mechanically guarantees dual-sided imaging of every bean, (ii) a public 12-class dataset of green coffee bean defects, and (iii) an embedded, real-time inspection pipeline validated on low-cost hardware. The apparatus sequentially presents each bean, from a standard 350 g sample, to two 16-megapixel cameras under controlled LED illumination. A dataset of 9600 images spanning 12 classes (11 defects and 1 normal) was generated from expert-classified samples and enriched through data augmentation. Four convolutional neural network (CNN) architectures, VGG-16, VGG-19, ResNet-50 and YOLOv8, were trained and benchmarked using precision, recall, F1-score and mean average precision. YOLOv8 achieved the best overall performance, with a precision of 97.4%, a recall of 99.6%, an F1-score of 0.930 and a mean average precision of 96.5%, outperforming VGG-16 (accuracy 86.07%), VGG-19 (accuracy 67.03%) and ResNet-50 (accuracy 87.76%). Dual-sided acquisition raised mean per-class detection accuracy from 0.727 to 0.908, a relative gain of 25.7% over an equivalent single-sided configuration. Deployed in real-time “track” mode on a Raspberry Pi 4, the system simultaneously classifies defects and counts beans by category, processing a 350 g sample in approximately 38 min. Combining mechanical innovation with lightweight deep learning enables practical, scalable, and cost-effective quality control for laboratories specialized in coffee analysis.