PURPOSES : This study uses deep learning image classification models and vehicle-mounted cameras to detect types of pavement distress — such as potholes, spalling, punch-outs, and patching damage — which require urgent maintenance. METHODS : For the automatic detection of pavement distress, the optimal mount location on a vehicle for a regular action camera was first determined. Using the orthogonal projection of obliquely captured surface images, morphological operations, and multi-blob image processing, candidate distressed pavement images were extracted from road surface images of a 16,036 km in-lane distance. Next, the distressed pavement images classified by experts were trained and tested for evaluation by three deep learning convolutional neural network (CNN) models: GoogLeNet, AlexNet, and VGGNet. The CNN models were image classification tools used to identify and extract the combined features of the target images via deep layers. Here, a data augmentation technique was applied to produce big distress data for training. Third, the dimensions of the detected distressed pavement patches were computed to estimate the quantity of repair materials needed. RESULTS : It was found that installing cameras 1.8 m above the ground on the exterior rear of the vehicle could provide clear pavement surface images with a resolution of 1 cm per pixel. The sensitivity analysis results of the trained GoogLeNet, AlexNet, and VGGNet models were 93 %, 86 %, and 72 %, respectively, compared to 62.7 % for the dimensional computation. Following readjustment of the image categories in the GoogLeNet model, distress detection sensitivity increased to 94.6 %. CONCLUSIONS : These findings support urgent maintenance by sending the detected distressed pavement images with the dimensions of the distressed patches and GPS coordinates to local maintenance offices in real-time.

Clear cell odontogenic carcinoma (CCOC) is an extremely rare odontogenic neoplasm; Only a few cases have been reported in the English literatures. It displays a propensity for the mandible, most commonly presenting in the fifth to seventh decades, with a female predilection. The clinical and radiological manifestations are multiple and the diagnosis is histological. Histological feature is of large islands and strands of uniform cells with round or ovoid nuclei and clear cytoplasm. Clinically, painless swelling is the most common symptom, followed by pain, teeth mobility, and paresthesia. CCOC has a good prognosis after surgery. This case report presents the histopathological and clinical features of CCOC excised from the mandible.

The red imported fire ant (RIFA, Solenopsis invicta Buren) is defined as invasive species and one of 100 most threaten alien species in world by IUCN. In Korea, RIFA has been first detected at September 28th, 2017 in Busan Port during surveillance by Animal and Plant Quarantine Agency (APQA). The RIFA colony was revealed as a polygyne and H5 type through epidemiological analysis on Gp-9 gene and mt-DNA haplotype. APQA has developed eradication program for RIFA with enhanced surveillance in all nationwide Ports and Internal Container Depots. There are subsequently 7 times more invasions of RIFA in Ports (Busan, Pyongeaek, and Incheon) including 2 times of inlands (Daegu and Ansan) and completely eradicated so far. International trade and climate change increases possibility of establishment and spreading of RIFA in Korea. Therefore, it must be required an international cooperation for prevention of global spreading of RIFA between countries.

Two infamous ant species, red imported fire ant (RIFA, Solenopsis invicta) and tropical fire ant (TFA, S. geminata), originated from South America are invading and harming many countries around the world. Among them, RIFA, known as one of the 100 world’s worst invasive alien species, has been discovered in South Korea; in Busan (Gamman CT) in 2017, and subsequently in Busan (Hutchison CT), Pyongtaek, Incheon and Daegu in 2018. With these relentless introduction of RIFA, South Korea is not safe no more from these ants and faces a risk of settlement. Our research goal is tracing the country origin of invasive populations of RIFA and TFA based on molecular epidemiological approach. We are conducting both microsatellite and genome-wide SNP analyses in order to derive a complementary interpretation. These two methodologies are expected to result in improved resolution in population genetics analysis. Nevertheless, this work needs collaboration of many countries belonging to the range of origin and invasion of RIFA and TFA. We will briefly introduce our research project and progress of collaboration research.

Coke aggregates and carbon artifacts were produced to investigate the interactions of coke and pitch during the kneading process. In addition, the kneading ratio of the coke and binder pitch for the coke aggregates was controlled to identify the formation of voids and pores during carbonization at 900°C. Experiments and thermogravimetric analysis revealed that carbon yields were improved over the theoretical yield calculated by the weight loss of the coke and binder pitch; the improvement was due to the binding interactions between the coke particles and binder pitch by the kneading process. The true, apparent, and bulk densities fluctuated according to the kneading ratio. This study confirmed that an excessive or insufficient kneading ratio decreases the density with degradation of the packing characteristics. The porosity analysis indicated that formation of voids and pores by the binder pitch increased the porosity after carbonization. Image analysis confirmed that the kneading ratio affected the formation of the coke domains and the voids and pores, which revealed the relations among the carbon yields, density, and porosity.