As a result of climate change and global warming, plant diseases and pests are drawing attention because they are dispersing more quickly than ever before. The tomato leaf miner destroys the growth structure of the tomato, resulting in 80 to 100 percent tomato loss. Despite extensive efforts to prevent its spread, the tomato leaf miner can be found on most continents. To protect tomatoes from the tomato leaf miner, inspections must be performed on a regular basis throughout the tomato life cycle. To find a better deep neural network (DNN) approach for detecting tomato leaf miner, we investigated two DNN models for classification and segmentation. The same RGB images of tomato leaves captured from real-world agricultural sites were used to train the two DNN models. Precision, recall, and F1-score were used to compare the performance of two DNN models. In terms of diagnosing the tomato leaf miner, the DNN model for segmentation outperformed the DNN model for classification, with higher precision, recall, and F1-score values. Furthermore, there were no false negative cases in the prediction of the DNN model for segmentation, indicating that it is adequate for detecting plant diseases and pests.

Spinal cord injury (SCI) is one of the most devastating conditions and many SCI patients suffer neurological sequelae. Stem cell therapies are expected to be beneficial for many patients with central nervous system injuries, including SCI. Adult stem cells (ASCs) are not associated with the risks which embryonic stem cells have such as malignant transformation, or ethical problems, and can be obtained relatively easily. Consequently, many researchers are currently studying the effects of ASCs in clinical trials. The environment of transplanted cells applied in the injured spinal cord differs between the phases of SCI; therefore, many researchers have investigated these phases to determine the optimal time window for stem cell therapy in animals. In addition, the results of clinical trials should be evaluated according to the phase in which stem cells are transplanted. In general, the subacute phase is considered to be optimal for stem cell transplantation. Among various candidates of transplantable ASCs, mesenchymal stem cells (MSCs) are most widely studied due to their clinical safety. MSCs are also less immunogenic than neural stem/progenitor cells and consequently immunosuppressants are rarely required. Attempts have been made to enhance the effects of stem cells using scaffolds, trophic factors, cytokines, and other drugs in animal and/or human clinical studies. Over the past decade, several clinical trials have suggested that transplantation of MSCs into the injured spinal cord elicits therapeutic effects on SCI and is safe; however, the clinical effects are limited at present. Therefore, new therapeutic agents, such as genetically enhanced stem cells which effectively secrete neurotrophic factors or cytokines, must be developed based on the safety of pure MSCs.

This paper presents a novel approach to enhance pose estimation accuracy and precision in mobile robotics using multiple graphical markers. While traditional single-marker methods using graphical markers such as ArUco offer simple implementation, their performance is susceptible to environmental variations and measurement errors. To address these limitations, we propose a robust pose estimation algorithm that leverages multiple markers simultaneously. Our approach incorporates two key mechanisms: spatial consistency verification to detect invalid markers within the marker array, and temporal stability analysis to identify and exclude outlier measurements. The algorithm enhances pose estimation accuracy by averaging measurements from valid markers while preventing any single marker from dominating the estimation process. The effectiveness of our approach was validated through experiments using both fixed and drone-mounted camera configurations. The results demonstrated that the pose estimation using multiple markers significantly improved both accuracy and precision compared with single-marker approaches. In fixed-camera experiments, the proposed method showed reduced mean errors and standard deviations in both position and orientation measurements across various camera poses. Similarly, in drone-mounted camera experiments, our approach exhibited superior stability with significantly lower measurement variations during hovering maneuvers. These improvements were particularly pronounced in challenging scenarios, such as when the camera was tilted at large angles relative to the marker plane. This research contributes to the advancement of reliable pose estimation methodologies in mobile robotics and autonomous systems, with potential applications across diverse environments where precise position and orientation measurements are crucial.

This study proposes the Weight-Incorporating A* (WIA*) algorithm for mobile robot path planning. The WIA* algorithm integrates three weight factors into the Conventional A* cost function: an Obstacle Collision (OC) weight factor for collision avoidance, a Path Distance (PD) weight factor for path length optimization, and a Driving Suitability (DS) weight factor for environmental considerations. Experimental validation was conducted using nine 2D grid maps and a 3D virtual environment. The results show that WIA* achieved zero obstacle collisions compared to an average of 9.11 collisions with Conventional A*. Although WIA* increased path length by 12.69%, it reduced driving suitability cost by 93.88%, achieving zero cost in six out of nine test environments. The algorithm demonstrates effective collision-free path generation while incorporating environmental factors for practical mobile robot navigation.

Original Article Deep learning model for the diagnosis of breast cancers smaller than 1 cm with ultrasonography: integration of ultrasonography and clinical factors Jae Hwan Bong, Tae Hee Kim, Seongkyun Jeong