Search

Pressure injuries pose significant health risks, especially for the elderly, immobile individuals, and those with sensory impairments. These injuries can rapidly become chronic, making initial diagnosis important. Due to the difficulty of transporting patients from local health facilities to higher-level general hospitals for treatment, it is essential to utilize telemedicine tools, such as chatbots, to ensure rapid initial diagnosis. Recent advances in artificial intelligence have demonstrated potential for medical imaging and disease classification. Ongoing research in the field of dermatological diseases focuses on disease classification. However, the assessment accuracy of artificial intelligence is often limited by unequal class distributions and insufficient dataset quantities. In this study, we aim to enhance the accuracy of artificial intelligence models by generating synthetic datasets. Specifically, we focused on training models for Pressure Injury assessment using both real and synthetic datasets. We used PI data at a domestic medical university. As part of our supplementary research, we established a chatbot system to facilitate the assessment of pressure injuries. Using both constructed and synthetic data, we achieved a top-1 accuracy of 92.03%. The experimental results demonstrate that combining real and synthetic data significantly improves model accuracy. These findings suggest that synthetic datasets can be effectively utilized to address the limitations of small-scale datasets in medical applications. Future research should explore the use of diverse synthetic data generation methods and validate model performance on a variety of datasets to enhance the generalization and robustness of AI models for Pressure Injury assessment. [ABSTRACT FROM AUTHOR]

Cloud computing has recently gained widespread attention owing to its use in applications involving the Internet of Things (IoT). However, the transmission of massive volumes of data to a cloud server often results in overhead. Fog computing has emerged as a viable solution to address this issue. This study implements an Artificial Intelligence of Things (AIoT) system based on fog computing on a smart farm. Three experiments are conducted to evaluate the performance of the AIoT system. First, network traffic volumes between systems employing and not employing fog computing are compared. Second, the performance of the communication protocols—hypertext transport protocol (HTTP), message queuing telemetry transport protocol (MQTT), and constrained application protocol (CoAP)—commonly used in IoT applications is assessed. Finally, a convolutional neural network-based algorithm is introduced to determine the maturity level of coffee tree images. Experimental data are collected over ten days from a coffee tree farm in the Republic of Korea. Notably, the fog computing system demonstrates a 26% reduction in the cumulative data volume compared with a non-fog system. MQTT exhibits stable results in terms of the data volume and loss rate. Additionally, the maturity level determination algorithm performed on coffee fruits provides reliable results. [ABSTRACT FROM AUTHOR]

Worldwide, the increase in impervious surfaces due to urbanization has led to significant water cycle issues such as groundwater depletion, urban heat islands, and flooding. To address these challenges, Low-Impact Development (LID) techniques are increasingly being applied in stormwater management. This study focuses on Ulsan, designated as a water cycle model city in South Korea, with a particular emphasis on the highly urbanized Okgyo drainage watershed. Using the Stormwater Management Model (SWMM) version 5.1, long-term runoff simulations were conducted to evaluate the effects of LID implementation on water cycle change rates and recovery rates. The model incorporates detailed hydrological and hydraulic parameters, including inflow, runoff, infiltration, and evapotranspiration for six subcatchments within the watershed. The SWMM was calibrated and validated using 30 years of historical rainfall data (1987–2016) from the Ulsan weather station. Calibration and validation processes used the NRCS-CN (Curve Number) method to ensure accuracy in simulating runoff patterns and water balance. The study specifically evaluated the effectiveness of two LID techniques: bioretention and permeable pavements. Three scenarios were modeled: bioretention applied to 5% of the area, permeable pavements applied to 5% of the area, and a combined application of both techniques. The results showed that the combined scenario provided the best outcome, with a 7.80% reduction in surface runoff and a 14.56% improvement in water cycle health. The LID application scenario confirmed the potential to achieve the water cycle management target of handling 25.5 mm of rainfall. These findings demonstrate that the introduction of LID techniques in public spaces can significantly enhance water management. This research provides insights into effective water cycle management methods tailored to specific urban land uses, laying a foundation for future urban planning and sustainable development. [ABSTRACT FROM AUTHOR]

Vergence and accommodation responses of human vision are very important factors when a 3D image is observed, and a vergence-accommodation conflict (VAC) causes perceptual distortion, visual discomfort, and fatigue for an observer. Theoretically, a hologram is expected to provide a 3D image without such a conflict. In this article, natural focusing was verified by human accommodation response (A-R) measurement during on-axis analog reflection Denisyuk hologram observation. The A-R of a group of participants were measured for a real marker and its Denisyuk hologram at various visualization distances using an Nvision K5001 autorefractor. The experimental results statistically confirmed the equivalence of the responses to the Denisyuk hologram and its real counterpart, as well as the absence of a VAC.

Recent advancements in text-to-image models have been substantial, generating new images based on personalized datasets. However, even within a single category, such as furniture, where the structures vary and the patterns are not uniform, the ability of the generated images to preserve the detailed information of the input images remains unsatisfactory. This study introduces a novel method to enhance the quality of the results produced by text-image models. The method utilizes mask preprocessing with an image pyramid-based salient object detection model, incorporates visual information into input prompts using concept image embeddings and a CNN local feature extractor, and includes a filtering process based on similarity measures. When using this approach, we observed both visual and quantitative improvements in CLIP text alignment and DINO metrics, suggesting that the generated images more closely follow the text prompts and more accurately reflect the input image's details. The significance of this research lies in addressing one of the prevailing challenges in the field of personalized image generation: enhancing the capability to consistently and accurately represent the detailed characteristics of input images in the output. This method enables more realistic visualizations through textual prompts enhanced with visual information, additional local features, and unnecessary area removal using a SOD mask; it can also be beneficial in fields that prioritize the accuracy of visual data. [ABSTRACT FROM AUTHOR]

Deep learning technology is generally applied to analyze periodic data, such as the data of electromyography (EMG) and acoustic signals. Conversely, its accuracy is compromised when applied to the anomalous and irregular nature of the data obtained using a magneto-impedance (MI) sensor. Thus, we propose and analyze a deep learning model based on recurrent neural networks (RNNs) optimized for the MI sensor, such that it can detect and classify data that are relatively irregular and diverse compared to the EMG and acoustic signals. Our proposed method combines the long short-term memory (LSTM) and gated recurrent unit (GRU) models to detect and classify metal objects from signals acquired by an MI sensor. First, we configured various layers used in RNN with a basic model structure and tested the performance of each layer type. In addition, we succeeded in increasing the accuracy by processing the sequence length of the input data and performing additional work in the prediction process. An MI sensor acquires data in a non-contact mode; therefore, the proposed deep learning approach can be applied to drone control, electronic maps, geomagnetic measurement, autonomous driving, and foreign object detection. [ABSTRACT FROM AUTHOR]