The study determined the optimum process conditions to produce batuan fruit powder using combined Response Surface Methodology (RSM) and desirability function. The factors considered were sodium metabisulfite (SMS) concentration and drying temperature. Two-factor ANOVA revealed the significant responses among the physicochemical (bulk density, titratable acidity, total soluble solids, whiteness index) and functional (antioxidant activity, total phenolics, water absorption index, water solubility index) characteristics. The response that was not significant in the model was also identified (pH). Based on the results, the optimum drying temperature and SMS concentration were found to be 50.0 °C and 106 ppm, respectively. The powder was produced using the predicted optimum conditions and was analyzed for its physicochemical, functional, and sensory properties.
The real-time object detection system You Only Look Once (specifically YOLOv3) has recently shown remarkable speed, making it potentially suitable for Unmanned Aerial Vehicle (UAV) precision spraying. In this study, YOLO-WEED, a weed detection system based on YOLOv3, was developed. The dataset, derived from a five-minute UAV video, was split into a 69 : 17 : 13 ratio for training, validation, and testing, respectively. YOLO-WEED demonstrated a real-time detection speed (up to 24.4 FPS) and high performance using NVIDIA GeForce GTX 1060, with a mean average precision of 93.81 % and an F1 score of 0.94. These results successfully show the effectiveness of the YOLO-WEED system for real-time UAV weed detection, given its high speed and high accuracy in detection.
Trust influenced the attractiveness of ergonomic programs to Small Medium-sized Enterprises (SMEs) workers as individuals and groups as the collective. A framework of Kansei Engineering-based System for Agro-industry (KESAN) was proposed for worker trust assessment using a platform of Kansei engineering and artificial intelligence. A fuzzy inference model was used to process worker trust based on an input of ergonomic status against their mentality constraints of prior knowledge, familiarity, agreement, and preference. The research result indicated that fuzzy inference could simulate worker trust which was influenced by ergonomic status, mentality constraint, benefit agreement, and preference. This result indicated the possibility of using Kansei engineering and fuzzy inference to assess worker trust.
Heating in hot water (at 60, 65, and 70 °C) under pasteurization conditions was applied to mung bean sprout samples. The values of initial elastic modulus decreased significantly compared to that in unpasteurized samples. Tissue conditions of the sprout samples were evaluated based on electrical properties by electrical impedance spectroscopy. The electrical parameters were found to change significantly with the pasteurization conditions, even for a short treatment duration (within 60 s). Furthermore, these parameters exhibited a moderate correlation with mechanical properties. The property of the extracellular region was found to be particularly important for mechanical properties. Additionally, a decrease in pores on short-term heating was confirmed. Taken together, our results highlight the sensitivity of mung bean sprout tissues to pasteurization.