Explore the vast range of titles available.

Recently, autonomous flight has emerged as a key technology in the aerospace and defense sectors; however, traditional code-based autonomous flight systems face limitations in complex environments. Although reinforcement learning offers an alternative, its practical application in real-world settings is hindered by the substantial data requirements. In this study, we develop a framework that integrates a Generative Adversarial Network (GAN) and Hindsight Experience Replay (HER) into model-based reinforcement learning to enhance data efficiency and accuracy. We compared the proposed framework against existing algorithms in actual quadcopter control. In the comparative experiment, we demonstrated an improvement of up to 70.59% in learning speed, clearly highlighting the impact of the environmental model. To the best of our knowledge, this study is the first where a GAN and HER are combined with model-based reinforcement learning, and it is expected to contribute significantly to the practical application of reinforcement learning in autonomous flight.

This study examines the dynamic relationship between changes in construction contract amounts across the diversified business areas within the portfolios of Korean construction firms and their overall business performance using a vector error correction model. It aims to provide a detailed evaluation of the effectiveness and characteristics of diversification strategies in the construction industry. This analysis employs key variables, including the debt ratio, return on total assets, diversification index, and construction contract amounts in domestic and overseas building, civil engineering, and plant construction projects. Two distinct models are used: Model A investigates the relationship between the debt ratio and diversification while Model B explores the relationship between the return on total assets and diversification. The time series data for the analysis spans from Q1 2002 to Q4 2021 on a quarterly basis. The results indicate that Korean construction firms have actively expanded into overseas markets to enhance their financial soundness. However, while such diversification efforts facilitate short-term capital acquisition, they have a negative impact on long-term business performance. When technological capabilities remain constant, lowering prices to increase contract volume may ultimately erode long-term profitability. Therefore, rather than focusing solely on expanding contract volumes through diversification, it is essential to first objectively assess the strengths of each business sector and focus on strengthening core competencies and expertise before pursuing further diversification.

We analyzed fundus images to identify whether convolutional neural networks (CNNs) can discriminate between right and left fundus images. We gathered 98,038 fundus photographs from the Gyeongsang National University Changwon Hospital, South Korea, and augmented these with the Ocular Disease Intelligent Recognition dataset. We created eight combinations of image sets to train CNNs. Class activation mapping was used to identify the discriminative image regions used by the CNNs. CNNs identified right and left fundus images with high accuracy (more than 99.3% in the Gyeongsang National University Changwon Hospital dataset and 91.1% in the Ocular Disease Intelligent Recognition dataset) regardless of whether the images were flipped horizontally. The depth and complexity of the CNN affected the accuracy (DenseNet121: 99.91%, ResNet50: 99.86%, and VGG19: 99.37%). DenseNet121 did not discriminate images composed of only left eyes (55.1%, p = 0.548). Class activation mapping identified the macula as the discriminative region used by the CNNs. Several previous studies used the flipping method to augment data in fundus photographs. However, such photographs are distinct from non-flipped images. This asymmetry could result in undesired bias in machine learning. Therefore, when developing a CNN with fundus photographs, care should be taken when applying data augmentation with flipping.

This study proposes an automated three-dimensional (3D)-modeling method that combines convolutional neural networks (CNNs) with unmanned aerial vehicle (UAV) technology for the efficient management of thermal anomalies in building exteriors. Conventional 3D-modeling methods for thermal imaging management either require the processing of large volumes of data due to the use of thermal distribution information from entire image regions or involve increased processing time when architectural drawings are unavailable. In this study, RGB and infrared (IR) thermal images collected via UAVs were used to automatically detect windows and thermal anomalies using a CNN-based object detection model (YOLOv5). Subsequently, Global Navigation Satellite System (GNSS)-based coordinate data and image metadata were used to convert the resolution coordinates into actual spatial coordinates, which were then vectorized to automatically generate a 3D model. The resulting 3D model demonstrated high similarity to the actual building, accurately representing the locations of thermal anomalies. This method enabled faster, more objective, and more cost-effective maintenance compared to conventional methods, making it especially beneficial for efficiently managing difficult-to-access high-rise buildings.

Building maintenance plays an increasingly important role as buildings age. During maintenance, it is necessary to analyze building defects and record their locations when performing exterior inspections. Hence, this study proposes an automatic three-dimensional (3D) modeling method based on image analysis using unmanned aerial vehicle (UAV) flights and convolutional neural networks. A geographic information system is used to acquire geographic coordinate points (GCPs) for the geometry of the building, and a UAV is flown to collect the GCPs and images, which provide location information on the building elements and defects. Comparisons revealed that the generated 3D models were similar to the actual buildings. Next, the recorded locations of the building defects and the actual locations were examined, and the results confirmed that the defects were generated correctly. Our findings indicated that the proposed method can improve building maintenance. However, it has several limitations, which provide directions for future research.

Optical coherence tomography (OCT) is a noninvasive method that can quickly and accurately examine the eye at the cellular level. Several studies have used OCT for analysis of anterior chamber cells. However, these studies have several limitations. This study was performed to supplement existing reports of automated analysis of anterior chamber cell images using spectral domain OCT (SD-OCT) and to compare this method with the Standardization of Uveitis Nomenclature (SUN) grading system. We analyzed 2398 anterior segment SD-OCT images from 34 patients using code written in Python. Cell density, size, and eccentricity were measured automatically. Increases in SUN grade were associated with significant cell density increases at all stages (p < 0.001). Significant differences were observed in eccentricity in uveitis, post-surgical inflammation, and vitreous hemorrhage (p < 0.001). Anterior segment SD-OCT is reliable, fast, and accurate means of anterior chamber cell analysis. This method showed a strong correlation with the SUN grade system. Also, eccentricity could be helpful as a supplementary evaluation tool.

Continuous inspections and observations are required to preserve the safety and condition of buildings. Although the number of deteriorated buildings has increased over the years, traditional inspection methods are still used. However, this approach is time-consuming, costly, and carries the risk of poor inspection owing to the subjective intervention of the inspector. To overcome these limitations, many recent studies have developed advanced inspection methods by integrating unmanned aerial vehicles (UAVs) and artificial intelligence (AI) methods during the visual inspection stage. However, the inspection approach using UAV and AI can vary in operation and data acquisition methods depending on the building structures. Notably, in the case of residential buildings, it is necessary to consider how to operate UAVs and how to apply AI due to privacy issues of residents and various exterior contour shapes. Thus, an empirical case study was adopted in this study to explore the integration of UAVs and artificial intelligence (AI) technology to inspect the condition of structures, focusing on residential buildings. As a result, this study proposed the field-adopted UAV operation method and AI-based defect detection model for adopting the residential buildings. Moreover, the lessons learned from holistic and descriptive analyses, which include drone application limitations, points of improvement of data collection, and items to be considered when AI and UAV based inspection for residential buildings, are summarized in this paper. The discussed problems and results derived from this study can contribute to future AI- and UAV-based building inspections.

In this study, we investigated a convolutional neural network (CNN)-based framework for the estimation of the best-corrected visual acuity (BCVA) from fundus images. First, we collected 53,318 fundus photographs from the Gyeongsang National University Changwon Hospital, where each fundus photograph is categorized into 11 levels by retrospective medical chart review. Then, we designed 4 BCVA estimation schemes using transfer learning with pre-trained ResNet-18 and EfficientNet-B0 models where both regression and classification-based prediction are taken into account. According to the results of the study, the predicted BCVA by CNN-based schemes is close to the actual value such that 94.37% of prediction accuracy can be achieved when 3 levels of difference can be tolerated during prediction. The mean squared error and R 2 score were measured as 0.028 and 0.654, respectively. These results indicate that the BCVA can be predicted accurately for extreme cases, i.e., the level of BCVA is close to either 0.0 or 1.0. Moreover, using the Guided Grad-CAM, we confirmed that the macula and the blood vessel surrounding the macula are mainly utilized in the prediction of BCVA, which validates the rationality of the CNN-based BCVA estimation schemes since the same area is also exploited during the retrospective medical chart review. Finally, we applied the t-distributed stochastic neighbor embedding to examine the characteristics of CNN-based BCVA estimation schemes. The developed BCVA estimation schemes can be employed to obtain the objective measurement of BVCA as well as the medical screening of people with poor access to medical care through smartphone-based fundus imaging.

Activities on Unmanned Aerial Vehicle (UAV) have increased over the last years and there are many fields in which UAVs can be used. One of the basic applications is reconnaissance of a given area using multiple UAVs. To perform reconnaissance mission, there are two methods: (i) path planning to navigate the pre-determined route; and (ii) random mobility method to explore without prior knowledge. In this paper, we indicate the imbalance problem of existing random mobility models for reconnaissance and propose a new model considering reconnaissance balance based on the number of visits. We divide the scanning area into N zones and then select a zone stochastically in which the search is insufficient. We evaluated the performance of the model by focusing on the coverage rate and average inter-visiting time. The proposed model shows that the 90%-coverage reaching time is improved by about 25% and the average inter-visiting time is improved by up to 15% compared to the previous approach.