Jiwon Ryu

Growers need to assess fruit growth and harvest timing, and monitoring individual fruit volume informs both. However, this remains challenging on the plant because leaves occlude the fruit and a single viewpoint reveals only part of its surface. Three-dimensional (3D) shape completion can recover fruit geometry, and thereby volume, from partial point clouds. Most methods treat each observation independently and ignore the temporal continuity of repeated visits to the same fruit, so the estimated volume trajectories become noisy and unstable. We present SCoRe (Sequential CoRe), which extends a single-frame DeepSDF-based encoder with temporal latent fusion. The fusion averages the shape code across visits, favoring the latest observation as gaps grow, and keeps that code from moving backward along a growth axis found in the data, since a healthy fruit does not shrink before harvest. It introduces no learned parameters and runs at inference time. We evaluate SCoRe on 2,513 RGB-D frames of Korean melon (Cucumis melo L. var. makuwa, 210 fruits) imaged across two seasons and three greenhouses, using post-harvest photogrammetric meshes as ground truth and caliper measurements as an intermediate-frame reference. Against an identical single-frame encoder, SCoRe reduces the last-frame volume root mean squared error (RMSE) from 87.4 to 50.6 mL, a 42% reduction, and raises F1 at 5 mm from 66.1% to 83.0%. It surpasses established single-frame shape completion baselines, with the largest gains under heavy occlusion, and remains robust under irregular revisit intervals, as repeated crop monitoring requires. Code, trained weights, and data are publicly available.

The external quality of high-value crops like the Oriental melon (Cucumis melo L. var. makuwa) directly determines market value, yet conventional manual inspection suffers from subjectivity, labor intensity, and inconsistency. Unlike existing single-factor automated systems, this study developed an integrated sorting system that simultaneously and quantitatively evaluates morphology, color, and surface defects, addressing the critical gap in comprehensive external quality assessment. The proposed hybrid model integrates digital image processing for morphological and color analysis with a state-of-the-art semantic segmentation model for defect evaluation. To specifically address the severe data imbalance inherent in Oriental melon defect datasets, the framework incorporates a Denoising Diffusion Probabilistic Model for targeted data augmentation. This approach enabled the generation of high-fidelity images of rare critical defects (e.g., cracks, damage) even with sparse training data, significantly enhancing overall performance. The Mask2Former (Swin-T) model, fine-tuned with the augmented dataset, achieved a superior mDice score of 81.5. The fully integrated system demonstrated a final grading accuracy of 86.3-96.5% on a test set. Field deployment in a commercial sorting facility validated the system's robustness, achieving 85.4-99.0% grading accuracy on independently collected samples and processing speeds of 43 fps (14 samples/second), substantially exceeding typical facility requirements (4-5 samples/second). This research demonstrates the first comprehensive automated grading system for Oriental melons, establishing a transferable framework applicable to other high-value crops facing class imbalance and addressing labor shortage challenges in modern agriculture.

This study developed non-destructive technology for predicting apple size to determine optimal harvest timing of field-grown apples. RGBD images were collected in field environments with fluctuating light conditions, and deep learning techniques were integrated to analyze morphometric parameters. After training various models, the EfficientDet D4 and Mask R-CNN ResNet101 models demonstrated the highest detection accuracy. Morphometric metrics were measured by linking boundary box information with 3D depth information to determine horizontal and vertical diameters. Without occlusion, mean absolute percentage error (MAPE) using boundary box-based methods was 6.201% and 5.164% for horizontal and vertical diameters, respectively, while mask-based methods achieved improved accuracy with MAPE of 5.667% and 4.921%. Volume and weight predictions showed MAPE of 7.183% and 6.571%, respectively. For partially occluded apples, amodal segmentation was applied to analyze morphometric parameters according to occlusion rates. While conventional models showed increasing MAPE with higher occlusion rates, the amodal segmentation-based model maintained consistent accuracy regardless of occlusion rate, demonstrating potential for automated harvest systems where fruits are frequently partially obscured by leaves and branches.

Food Science of Animal Resources (Food Sci. Anim. Resour.) is an international, peer-reviewed bimonthly journal publishing original research and reviews on basic and applied aspects of the use of animal resources including the meat, egg, dairy, and edible insect/worm products. Food Sci. Anim. Resour. is published and distributed by the Korean Society for Food Science of Animal Resources.

The demand for safe and edible meat has led to the advancement of freeze-storage techniques, but falsely labeled thawed meat remains an issue. Many methods have been proposed for this purpose, but they all destroy the sample and can only be performed in the laboratory by skilled personnel. In this study, hyperspectral image data were used to construct a machine learning (ML) model to discriminate between freshly refrigerated, long-term refrigerated, and thawed beef meat samples. With four pre-processing methods, a total of five datasets were prepared to construct an ML model. The PLS-DA and SVM techniques were used to construct the models, and the performance was highest for the SVM model applying scatter correction and the RBF kernel function. These results suggest that it is possible to construct a prediction model to distinguish between fresh and non-fresh meat using the spectra obtained by purifying hyperspectral image data cubes, which can be a rapid and non-invasive method for routine analyses of the meat storage state.

A laparoscopic approach is widely used in abdominal surgery. Although several studies have compared surgical and oncological outcomes between laparoscopic surgery (LS) and open surgery (OS) in rectal cancer patients, there have been few studies on postoperative renal outcomes. We conducted a retrospective cohort study involving 1,633 patients who underwent rectal cancer surgery between 2003 and 2017. Postoperative acute kidney injury (AKI) was diagnosed according to the serum creatinine criteria of the Kidney Disease: Improving Global Outcomes classification. Among the 1,633 patients, 1,072 (65.6%) underwent LS. After matching propensity scores, 395 patients were included in each group. The incidence of postoperative AKI in the LS group was significantly lower than in the OS group (9.9% vs. 15.9%; p = 0.01). Operation time, estimated blood loss, and incidence of transfusion in the LS group were significantly lower than those in the OS group. Cox proportional hazard models revealed that LS was associated with decreased risk of postoperative AKI (hazard ratio [HR], 0.599; 95% confidence interval [CI], 0.402–0.893; p = 0.01) and postoperative transfusion was associated with increased risk of AKI (HR, 2.495; 95% CI, 1.529–4.072; p < 0.001). In the subgroup analysis, the incidence of postoperative AKI in patients with middle or high rectal cancer who underwent LS was much lower than in those who underwent OS (HR, 0.373; 95% CI, 0.197–0.705; p = 0.002). This study showed that LS may have a favorable effect on the development of postoperative AKI in patients with rectal cancer.

The size of a device and its adaptability to human properties are important factors in developing a wearable device. In wearable robot research, therefore, soft materials and tendon transmissions have been utilized to make robots compact and adaptable to the human body. However, when used for wearable robots, these methods sometimes cause uncertainties that originate from elongation of the soft material or from undefined human properties. In this research, to consider these uncertainties, we propose a data-driven method that identifies both kinematic and stiffness parameters using tension and wire stroke of the actuators. Through kinematic identification, a method is proposed to find the exact joint position as a function of the joint angle. Through stiffness identification, the relationship between the actuation force and the joint angle is obtained using Gaussian Process Regression (GPR). As a result, by applying the proposed method to a specific robot, the research outlined in this paper verifies how the proposed method can be used in wearable robot applications. This work examines a novel wearable robot named Exo-Index, which assists a human’s index finger through the use of three actuators. The proposed identification methods enable control of the wearable robot to result in appropriate postures for grasping objects of different shapes and sizes.