Search

The demand for smart automation systems in postharvest technology, particularly in the postharvest process of garlic production, is high. In this study, we introduce an artificial intelligence (AI)-integrated robot system for grading and sorting of garlics after root trimming. We developed a robot system that automatically grades and sorts root-trimmed garlics based on image analysis using a deep learning model, which is equipped with a deep convolutional neural network (CNN). The robot system consists of three main modules: image acquisition module (IAM), image processing module (IPM), and garlic sorting module (GSM). The IAM captures a live video of garlic roots using an independent light-emitting diode (LED) and a web camera connected to a computer. The IPM consists of garlic image processing software (GIPS) installed on a Windows 10 computer. GIPS imports videos, detects the shape of garlic bulbs, and predicts the garlic class using the deep learning model. When a garlic bulb shape is detected, the image is preprocessed, and the deep learning model is automatically activated to predict the garlic class. The GSM physically separates garlics into three containers for good, bad, and scratched classes based on a previous predicted result. A total of 800 root-trimmed garlics were tested and evaluated in nine experiments. The processing time to predict classes from a garlic image on a regular laptop computer (Intel® core™ i7-8650U 1.9 GHz CPU, with 16 Gb RAM) was 0.19–0.58 s. The median time to trim and sort one garlic was 11 s (in a setting with three prediction replications), and the overall grading accuracy for the three classes was 89%. The individual predicted precision for the good, bad, and scratched classes was 95%, 68%, and 100%, respectively. Given that the robot system was robust and inexpensive, it has the potential to be integrated into a garlic root trimming machine to develop a fully automatic garlic root trimming and sorting robot.

We examined three types of ensiling container and two storage periods with respect to the fermentation quality of rice grain silage, and our findings confirmed that a method previously identified as optimal for silage production at the laboratory scale was also appropriate for farm-scale production. Crushed rice grain was adjusted to 30% moisture content, inoculated with lactic acid bacteria and ensiled in plastic pouches (200 g), plastic drums (15 kg) and flexible containers (100 kg). Samples of silage from the surface layer in the flexible containers had the pH value >5 and fungal growth was observed, but all internal samples had low pH (

To identify the best ensiling process and moisture content for rice grain silage, we determined the effects of additive (i.e. no additive, glucose additive or lactic acid bacteria [LAB] inoculation), crushing process (non-crushing or crushing) and moisture control (none [13.6%], 20.0, 27.5, 35.0, 42.5 or 50.0% moisture content [in fresh matter, FM]) on rough rice and brown rice. Forage rice harvested at the fully ripe stage was ensiled in small-scale experiments, and the silage was stored for 60 days. Regardless of the use of additives or LAB inoculation, the pH values tended to decrease with increasing moisture content. LAB inoculation and crushing resulted in low pH values, low butyric acid contents, low ethanol contents and high lactic acid contents, and the lactic acid content increased to more than 2.0% in FM at moisture contents of 27.5% and higher. The parameters of fermentation quality (pH, lactic acid, butyric acid, volatile basic nitrogen and ethanol content) were affected by not only the main effect of additive, crushing process and moisture control but also two-way or three-way interaction effects. LAB inoculation and crushing improved the lactic acid fermentation under lower moisture conditions, that is, 27.5% moisture content. In both rough rice and brown rice, we suggest that the appropriate pretreatment is the combined use of LAB inoculation, crushing process and controlling 27.5% moisture content.

Some anthocyanins have been reported to exhibit antioxidant activity and to enhance antioxidant enzyme activity. The aim of this study was to determine the fermentative quality of purple rice, which is abundant in anthocyanin, and its effects on digestibility, ruminal fermentation and oxidative status markers in sheep. The whole crop silages of purple and control rice were prepared in drum silos after the materials were chopped and lactic acid bacteria was inoculated. These were followed by a feeding trial using eight wethers in a 2 × 2 crossover design. Both the purple and control rice silages showed excellent fermentative qualities. Although the purple rice silage contained abundant anthocyanin, it had inadequate nutritional values in comparison to the control rice silage, including higher levels of fiber fractions, lower nutrient digestibility and lower production of ruminal volatile fatty acids. The feeding of the purple rice silages led to an elevation in plasma activity of superoxide dismutase, which is an important antioxidant enzyme. The results of this study suggest that purple rice may become a source of anthocyanin to improve oxidative status in ruminants. To achieve that, however, a new variety of purple rice with good nutritional value is needed for practical use as a ruminant feed.