• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.525-538
• /
• 2020

A practical animal face classification system that classifies animals in image and video data is considered as a pivotal topic in machine learning. In this research, we are proposing a novel method of fully connected dual Deep Convolutional Neural Network (DCNN), which extracts and analyzes image features on a large scale. With the inclusion of the state of the art Batch Normalization layer and Exponential Linear Unit (ELU) layer, our proposed DCNN has gained the capability of analyzing a large amount of dataset as well as extracting more features than before. For this research, we have built our dataset containing ten thousand animal faces of ten animal classes and a dual DCNN. The significance of our network is that it has four sets of convolutional functions that work laterally with each other. We used a relatively small amount of batch size and a large number of iteration to mitigate overfitting during the training session. We have also used image augmentation to vary the shapes of the training images for the better learning process. The results demonstrate that, with an accuracy rate of 92.0%, the proposed DCNN outruns its counterparts while causing less computing costs.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.2
• /
• pp.96-109
• /
• 2024

The purpose of this study is to propose a method for evaluating the similarity of Show gardens using Deep Learning models, specifically VGG-16 and ResNet50. A model for judging the similarity of show gardens based on VGG-16 and ResNet50 models was developed, and was referred to as DRG (Deep Recognition of similarity in show Garden design). An algorithm utilizing GAP and Pearson correlation coefficient was employed to construct the model, and the accuracy of similarity was analyzed by comparing the total number of similar images derived at 1st (Top1), 3rd (Top3), and 5th (Top5) ranks with the original images. The image data used for the DRG model consisted of a total of 278 works from the Le Festival International des Jardins de Chaumont-sur-Loire, 27 works from the Seoul International Garden Show, and 17 works from the Korea Garden Show. Image analysis was conducted using the DRG model for both the same group and different groups, resulting in the establishment of guidelines for assessing show garden similarity. First, overall image similarity analysis was best suited for applying data augmentation techniques based on the ResNet50 model. Second, for image analysis focusing on internal structure and outer form, it was effective to apply a certain size filter (16cm × 16cm) to generate images emphasizing form and then compare similarity using the VGG-16 model. It was suggested that an image size of 448 × 448 pixels and the original image in full color are the optimal settings. Based on these research findings, a quantitative method for assessing show gardens is proposed and it is expected to contribute to the continuous development of garden culture through interdisciplinary research moving forward.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.143-156
• /
• 2023

To precisely and reliably analyze the contents of the satellite imagery, recognizing the clouds which are the obstacle to gathering the useful information is essential. In recent times, deep learning yielded satisfactory results in various tasks, so many studies using deep neural networks have been conducted to improve the performance of cloud detection. However, existing methods for cloud detection have the limitation on increasing the performance due to the adopting the network models for semantic image segmentation without modification. To tackle this problem, we introduced the multi-branch neural architecture search to find optimal network structure for cloud detection. Additionally, the proposed method adopts the soft intersection over union (IoU) as loss function to mitigate the disagreement between the loss function and the evaluation metric and uses the various data augmentation methods. The experiments are conducted using the cloud detection dataset acquired by Arirang-3/3A satellite imagery. The experimental results showed that the proposed network which are searched network architecture using cloud dataset is 4% higher than the existing network model which are searched network structure using urban street scenes with regard to the IoU. Also, the experimental results showed that the soft IoU exhibits the best performance on cloud detection among the various loss functions. When comparing the proposed method with the state-of-the-art (SOTA) models in the field of semantic segmentation, the proposed method showed better performance than the SOTA models with regard to the mean IoU and overall accuracy.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.3
• /
• pp.166-178
• /
• 2023

This study aims to introduce and assess CNN Deep Learning methods to analyze visual landscape images on social media with embedded user perceptions and experiences. This study analyzed visual landscape images by focusing on a healing place. For the study, seven adjectives related to healing were selected through text mining and consideration of previous studies. Subsequently, 50 evaluators were recruited to build a Deep Learning image. Evaluators were asked to collect three images most suitable for 'healing', 'healing landscape', and 'healing place' on portal sites. The collected images were refined and a data augmentation process was applied to build a CNN model. After that, 15,097 images of 'healing' and 'healing landscape' on portal sites were collected and classified to analyze the visual landscape of a healing place. As a result of the study, 'quiet' was the highest in the category except 'other' and 'indoor' with 2,093 (22%), followed by 'open', 'joyful', 'comfortable', 'clean', 'natural', and 'beautiful'. It was found through research that CNN Deep Learning is an analysis method that can derive results from visual landscape image analysis. It also suggested that it is one way to supplement the existing visual landscape analysis method, and suggests in-depth and diverse visual landscape analysis in the future by establishing a landscape image learning dataset.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.397-418
• /
• 2024

The Land Surface Temperature (LST) is a crucial parameter in identifying drought. It is essential to identify how LST can increase its accuracy, particularly in mountainous and hill areas. Increasing the LST accuracy can be achieved by applying early data processing in the correction phase, specifically in the context of topographic correction on the Lambertian model. Empirical evidence has demonstrated that this particular stage effectively enhances the process of identifying objects, especially within areas that lack direct illumination. Therefore, this research aims to examine the application of the Lambertian model in estimating LST using the Multi-Channel Method (MCM) across various physiographic regions. Lambertian model is a method that utilizes Lambertian reflectance and specifically addresses the radiance value obtained from Sun-Canopy-Sensor(SCS) and Cosine Correction measurements. Applying topographical adjustment to the LST outcome results in a notable augmentation in the dispersion of LST values. Nevertheless, the area physiography is also significant as the plains terrain tends to have an extreme LST value of ≥ 350 K. In mountainous and hilly terrains, the LST value often falls within the range of 310-325 K. The absence of topographic correction in LST results in varying values: 22 K for the plains area, 12-21 K for hilly and mountainous terrain, and 7-9 K for both plains and mountainous terrains. Furthermore, validation results indicate that employing the Lambertian model with SCS and Cosine Correction methods yields superior outcomes compared to processing without the Lambertian model, particularly in hilly and mountainous terrain. Conversely, in plain areas, the Lambertian model's application proves suboptimal. Additionally, the relationship between physiography and LST derived using the Lambertian model shows a high average R² value of 0.99. The lowest errors(K) and root mean square error values, approximately ±2 K and 0.54, respectively, were achieved using the Lambertian model with the SCS method. Based on the findings, this research concluded that the Lambertian model could increase LST values. These corrected values are often higher than the LST values obtained without the Lambertian model.

• Journal of the Society of Disaster Information
• /
• v.15 no.4
• /
• pp.479-492
• /
• 2019

Purpose: The purpose of this study is to accurately analyze the damage of bridges in order to determine whether fire bridges can be used continuously or to provide information on maintenance augmentation data. Method: XRD, SEM and EDS analyzes of concrete were carried out to estimate the fire temperature transferred to the structure, and analyzed by depth and area from PSCI beam and bottom plate concrete surface. Results: Test results G_12,11 for the fire zone concrete were confirmed to be affected by heat up to depth of 60mm and the temperature of the hydrothermal heat was above 1000℃. Also, the girder G_10,9,8 was relatively weakly damaged compared to G_12,11, and the degree of damage was confirmed to be affected by heat up to a depth of 40 mm. Conclusion: Based on the analyzed data, it is considered that if the repair / reinforcement and periodic inspection are carried out, the bridge can secure sufficient safety even considering the damage caused by the fire.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• The Journal of Korean Academy of Prosthodontics
• /
• v.45 no.2
• /
• pp.228-239
• /
• 2007

Statement of problem: Following tooth loss, the edentulous alveolar process of maxilla is affected by irreversible reabsorption process, with progressive sinus pneumatization leads to leaving inadquate bone height for placement of endosseous implants. Grafting the floor of maxillary sinus by sinus lifting surgery and augmentation of autologous bone or alternative bone material is a method of attaining sufficient bone height for maxillary implants placement and has proven to be a highty successful. Purpose: This study was undertaken to clarify the morphometric characteristics of inferior maxillary sinus and alveolar process for installation of implants. Material and method: Nineteen skulls (37 sinuses, 10M / 9F) obtained from the collection of the department of anatomy and cell biology of Hanyang medical school were studied. The mean age of the deceased was 69.9 years (range 44 to 88 years). The distance between alveolar border and inferior sinus margin at each tooth, the height of alveolar process and the thickness of cortical bone of the outer and inner table of alveolar process and the inferior wall of maxillary sinus were measured. Results and Conclusion: 1. The septum of inferior maxillary sinus were observe 28 sides (76.%) and located at the third molar (52.6%) and the second molar (26.3%). The deepest points of inferior border of maxillary sinus were located the first or second molar. The distance between alveolar margin and the deepest point of inferior maxillary sinus is $9.7{\pm}4.9mm$. 2. The length of the outer table of alveolar process were $4.9\sim28.2mm$ and the shortest point was between the first and the second molors. The thickness of them were $0.9\sim3.2mm$. The length of the inner table of alveolar process were $7.4\sim25.8mm$ and the shortest point was between the first and the second molars. The thickness of the were $0.9\sim4.6mm$. The results of this study are useful anatomical data for installing of maxillary implants.

• International Journal of High-Rise Buildings
• /
• v.12 no.3
• /
• pp.225-234
• /
• 2023

Even at this point in the era of digital transformation, we are still facing many problems in the safety sector that cannot prevent the occurrence or spread of human casualties. When you are in an unexpected emergency, it is often difficult to respond only with human physical ability. Human casualties continue to occur at construction sites, manufacturing plants, and multi-use facilities used by many people in everyday life. If you encounter a situation where normal judgment is impossible in the event of an emergency at a life site where there are still many safety blind spots, it is difficult to cope with the existing manual guidance method. New variable guidance technology, which combines artificial intelligence and digital twin, can make it possible to prevent casualties by processing large amounts of data needed to derive appropriate countermeasures in real time beyond identifying what safety accidents occurred in unexpected crisis situations. When a simple control method that divides and monitors several CCTVs is digitally converted and combined with artificial intelligence and 3D digital twin control technology, intelligence augmentation (IA) effect can be achieved that strengthens the safety decision-making ability required in real time. With the enforcement of the Serious Disaster Enterprise Punishment Act, the importance of distributing a smart location guidance system that urgently solves the decision-making delay that occurs in safety accidents at various industrial sites and strengthens the real-time decision-making ability of field workers and managers is highlighted. The smart location guidance system that combines artificial intelligence and digital twin consists of AIoT HW equipment, wireless communication NW equipment, and intelligent SW platform. The intelligent SW platform consists of Builder that supports digital twin modeling, Watch that meets real-time control based on synchronization between real objects and digital twin models, and Simulator that supports the development and verification of various safety management scenarios using intelligent agents. The smart location guidance system provides on-site monitoring using IoT equipment, CCTV-linked intelligent image analysis, intelligent operating procedures that support workflow modeling to immediately reflect the needs of the site, situational location guidance, and digital twin virtual fencing access control technology. This paper examines the limitations of traditional fixed passive guidance methods, analyzes global technology development trends to overcome them, identifies the digital transformation properties required to switch to intelligent variable smart location guidance methods, explains the characteristics and components of AI-based public facility smart fire safety integrated system (ISFS).

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.55-68
• /
• 2014

Some infrastructure these days is usually constructed under the ground for it to not interfere the foot-traffic of pedestrians, and thus, it is difficult to visually confirm the accurate location of the site where the establishments must be buried. These technical difficulties increase the magnitude of the problems that could arise from over-reliance on the experience of the worker or a mere blueprint. Such problems include exposure to flood and collapse. This paper proposes a constructor-oriented visualization system via mobile gadgets in general construction sites with occluded structures. This proposal is consisted with three stages. First, "Stage of detecting manhole and extracting features" detects and extracts the basis point of occluded structures which is unoccluded manhole. Next, "Stage of tracking features" tracks down the extracted features in the previous stage. Lastly, "Stage of visualizing occluded constructions" analyzes and synthesizes the GPS data and 3D objects obtained from mobile gadgets in the previous stages. This proposal implemented ideal method through parallel analysis of manhole detection, feature extraction, and tracking techniques in indoor environment, and confirmed the possibility through occluded water-pipe augmentation in real environment. Also, it offers a practical constructor-oriented environment derived from the augmented 3D results of occluded water-pipings.