• Korean Journal of Heritage: History & Science
• /
• v.54 no.1
• /
• pp.206-219
• /
• 2021

The warming of the climate is increasing the damage caused by termites to wooden buildings, cultural properties and houses. A group removal system can be installed around the building to detect and remove termite damage; however, if the site is not visited regularly, every one to two months, you cannot observe whether termites have spread within, and it is difficult to take prompt effective action. In addition, since the system is installed and operated in an exposed state for a long period of time, it may be ineffective or damaged, resulting in a loss of function. Furthermore if the system is installed near a cultural site, it may affect the aesthetic environment of the site. In this study, we created a detection system that uses wood, cellulose, magnets, and magnetic sensors to determine whether termites have entered the area. The data was then transferred to a low power LoRa Network which displayed the results without the necessity of visiting the site. The wood was made in the shape of a pile, and holes were made from the top to the bottom to make it easier for termites to enter and produce a cellulose sample. The cellulose sample was made in a cylindrical shape with a magnet wrapped in cellulose and inserted into the top of a hole in the wood. Then, the upper part of the wood pile was covered with a stopper to prevent foreign matter from entering. It also served to block external factors such as light and rainfall, and to create an environment where termites could add cellulose samples. When the cellulose was added by the termites, a space was created around the magnet, causing the magnet to either fall or tilt. The magnetic sensor inside the stopper was fixed on the top of the cellulose sample and measured the change in the distance between the magnet and the sensor according to the movement of the magnet. In outdoor experiments, 11 cellulose samples were inserted into the wood detection system and the termite inflow was confirmed through the movement of the magnet without visiting the site within 5 to 17 days. When making further improvements to the function and operation of the system it in the future, it is possible to confirm that termites have invaded without visiting the site. Then it is also possible to reduce damage and fruiting due to product exposure, and which would improve the condition and appearance of cultural properties.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.66 no.2
• /
• pp.105-111
• /
• 2021

Rice lodging is an annual occurrence caused by typhoons accompanied by strong winds and strong rainfall, resulting in damage relating to pre-harvest sprouting during the ripening period. Thus, rapid estimations of the area of lodged rice are necessary to enable timely responses to damage. To this end, we obtained images related to rice lodging using a drone in Gimje, Buan, and Gunsan, which were converted to 128 × 128 pixels images. A convolutional neural network (CNN) model, a deep learning model based on these images, was used to predict rice lodging, which was classified into two types (lodging and non-lodging), and the images were divided in a 8:2 ratio into a training set and a validation set. The CNN model was layered and trained using three optimizers (Adam, Rmsprop, and SGD). The area of rice lodging was evaluated for the three fields using the obtained data, with the exception of the training set and validation set. The images were combined to give composites images of the entire fields using Metashape, and these images were divided into 128 × 128 pixels. Lodging in the divided images was predicted using the trained CNN model, and the extent of lodging was calculated by multiplying the ratio of the total number of field images by the number of lodging images by the area of the entire field. The results for the training and validation sets showed that accuracy increased with a progression in learning and eventually reached a level greater than 0.919. The results obtained for each of the three fields showed high accuracy with respect to all optimizers, among which, Adam showed the highest accuracy (normalized root mean square error: 2.73%). On the basis of the findings of this study, it is anticipated that the area of lodged rice can be rapidly predicted using deep learning.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.1B
• /
• pp.41-51
• /
• 2010

In this study, runoff simulation was carried out in the area of Bisan 7-dong, Seo-gu, Daegu as drainage basin and the effects of the installation of underground storage facilities were analyzed during heavy rainfall. SWMM model was used for the runoff and pipe network analysis on Typhoon Maemi, 2003. 2-D inundation analysis model based on diffusion wave was employed for inundation analysis and to verify computed inundation areas with observed inundation trace map. The simulation results agree with observed in terms of inundation area and depth. Also, the effects of flood damage mitigation were analyzed through the overflow discharge and 2-D inundation analysis, depending upon whether the underground storage facility is installed or not. When the underground storage facility ($W:120m{\times}L:180m{\times}H:1.7m$) is installed, volume of overflow could be reduced by 72% and flooding area could be reduced by 40.1%. When the underground storage facility ($W:120m{\times}L:180 m{\times}H:2.0m$) is installed, volume of overflow could be reduced by 84.8% and flooding area could be reduced by 50.6%. When the underground storage facility ($W:120m{\times}L:180m{\times}H:2.2m$) is installed, volume of overflow could be reduced by 94% and flooding area could be reduced by 91.2%. There is no overflow of manhole, when the height of storage facility is 2.5 m. It is expected that the study results presented through quantitative analysis on the effects of underground facilities can be used as base data for socially and economically effective installation of underground facilities to prevent flood damage.