With the widespread adoption of smart farms and continuous advancements in IoT (Internet of Things) technology, acquiring diverse additional data has become increasingly convenient. Consequently, studies relevant to deep learning models that leverage multimodal data for crop disease diagnosis and associated data augmentation methods are significantly growing. We propose a comprehensive deep learning model that predicts crop type, detects disease presence, and assesses disease severity at the same time. We utilize multimodal data comprising crop images and environmental variables such as temperature, humidity, and dew points. We confirmed that the results of diagnosing crop diseases using multimodal data improved 2.58%p performance compared to using crop images only. We also propose a multimodal-based mixup augmentation method capable of utilizing both image and environmental data. In this study, multimodal data refer to data from multiple sources, and multimodal mixup is a data augmentation technique that combines multimodal data for training. This expands the conventional mixup technique that was originally applied solely to image data. Our multimodal mixup augmentation method showcases a performance improvement of 1.33%p compared to the original mixup method.

Colorectal cancer is one of the most common cancers with a high mortality rate. The determination of microsatellite instability (MSI) status in resected cancer tissue is vital because it helps diagnose the related disease and determine the relevant treatment. This paper presents a two-stage classification method for predicting the MSI status based on a deep learning approach. The proposed pipeline includes the serial connection of the segmentation network and the classification network. In the first stage, the tumor area is segmented from the given pathological image using the Feature Pyramid Network (FPN). In the second stage, the segmented tumor is classified as MSI-L or MSI-H using Inception-Resnet-V2. We examined the performance of the proposed method using pathological images with 10× and 20× magnifications, in comparison with that of the conventional multiclass classification method where the tissue type is identified in one stage. The F1-score of the proposed method was higher than that of the conventional method at both 10× and 20× magnifications. Furthermore, we verified that the F1-score for 20× magnification was better than that for 10× magnification.

The deterioration of power generation facilities built during the early stages of plant operation is becoming increasingly severe, raising concerns about potential socioeconomic harm from pipe leaks. Consequently, there is a pressing need for rapid leak detection and proactive responses. Prior research primarily relied on various signal processing techniques and supervised learning for leak detection. However, these approaches struggle with accurate detection amid environments with diverse background noises and weak leak signals, exacerbated by challenges in gathering sufficient real-world leakage data, which can lead to overfitting during model learning. Therefore, in this paper, an adaptable leak detection model suitable for various environments was proposed to ensure precise leak detection. Frequency spectrum feature extraction and transfer learning were utilized to achieve accurate leak detection, even with limited data. In addition, an unsupervised learning–based autoencoder model is employed to identify leaks accurately by learning general patterns, even when leakage data is limited. Experimental results demonstrate that the proposed model, integrating feature extraction techniques using the Uniform Manifold Approximation and Projection (UMAP) algorithm and employing transfer learning, achieved a higher accuracy performance with 6.35 percentage points (%p) compared to the model lacking these techniques. In addition, these findings confirm a slight decrease in accuracy performance even when using minimal learning data. Moreover, the leak detection performance was superior to the existing models considered in this study, achieving a high accuracy rate of 99.19%.

This paper introduces the novel design and implementation of a low-power wireless monitoring system designed for nuclear power plants, aiming to enhance safety and operational efficiency. By utilizing advanced signal-processing techniques and energy-efficient technologies, the system supports real-time, continuous monitoring without the need for frequent battery replacements. This addresses the high costs and risks associated with traditional wired monitoring methods. The system focuses on acoustic and ultrasonic analysis, capturing sound using microphones and processing these signals through heterodyne frequency conversion for effective signal management, accommodating low-power consumption through down-conversion. Integrated with edge computing, the system processes data locally at the sensor level, optimizing response times to anomalies and reducing network load. Practical implementation shows significant reductions in maintenance overheads and environmental impact, thereby enhancing the reliability and safety of nuclear power plant operations. The study also sets the groundwork for future integration of sophisticated machine learning algorithms to advance predictive maintenance capabilities in nuclear energy management.

Leak detection in nuclear reactor coolant systems is crucial for maintaining the safety and operational integrity of nuclear power plants. Traditional leak detection methods, such as acoustic emission sensors and spectroscopy, face challenges in sensitivity, response time, and accurate leak localization, particularly in complex piping systems. In this study, we propose a novel leak detection approach that incorporates a rigid guide tube into the insulation layer surrounding reactor coolant pipes and combines this with an advanced detection criterion based on Frequency Center of Gravity shifts and Signal-to-Noise Ratio analysis. This dual-method strategy significantly improves the sensitivity and accuracy of leak detection by providing a stable transmission path for ultrasonic signals and enabling robust signal analysis. The rigid guide tube-based system, along with the integrated criteria, addresses several limitations of existing technologies, including the detection of minor leaks and the complexity of installation and maintenance. By enhancing the early detection of leaks and enabling precise localization, this approach contributes to increased reactor safety, reduced downtime, and lower operational costs. Experimental evaluations demonstrate the system’s effectiveness, focusing on its potential as a valuable addition to the current array of nuclear power plant maintenance technologies. Future research will focus on optimizing key parameters, such as the threshold frequency shift (Δf) and the number of randomly selected frequencies (N), using machine learning techniques to further enhance the system’s accuracy and reliability in various reactor environments.