• Convergence Security Journal
• /
• v.23 no.5
• /
• pp.73-79
• /
• 2023

Cyber threats are evolving and becoming more sophisticated with the development of new technologies, and consequently the number of service failures caused by DDoS attacks are continually increasing. Recently, DDoS attacks have numerous types of service failures by applying a large amount of traffic to the domain address of a specific service or server. In this paper, after generating the data of the Syn Flooding attack, which is the representative attack type of bandwidth exhaustion attack, the data were compared and analyzed using Random Forest, Decision Tree, Multi-Layer Perceptron, and KNN algorithms for the effective detection of attacks, and the optimal algorithm was derived. Based on this result, it will be useful to use as a technique for the detection policy of Syn Flooding attacks.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.11 no.4
• /
• pp.143-150
• /
• 2009

Deicing salt is used to melt snow and ice on the road for traffic safety during the winter season, which accumulates in the roadside vegetation and induces visible injuries. The damage may accelerate particularly when it coincides with early spring leaf out. In order to better understand the response mechanisms, C. kousa (3-year-old) was irrigated twice prior to leaf bud in a rhizosphere with solutions of 0.5, 1.0, and 3.0% calcium chloride ($CaCl_2$) concentration, that were made by using an industrial $CaCl_2$ reagent practical deicing material in Seoul. Physiological traits of the mature leaves were progressively reduced by $CaCl_2$ treatment, resulting in reductions of total chlorophyll contents, chlorophyll a:b, photosynthetic rate, quantum yield, stomatal conductance, $F_V/F_M$, and NPQ. On the contrary, light compensation point and dark respiration were increased at high $CaCl_2$ concentration. A decrease in intercellular $CO_2$ concentration by stomatal closure first resulted in a reduced photosynthetic rate and then was accompanied by low substance metabolic rates and photochemical damage. Based on the reduction of physiological activities at all treatments ($CaCl_2$ 0.5%, 1.0%, and 3.0%), C. kousa was determined as one of the sensitive species to $CaCl_2$.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.6
• /
• pp.121-132
• /
• 2018

Weather is an important factor affecting roadway transportation in many aspects such as traffic flow, driver 's driving patterns, and crashes. This study focuses on the relationship between weather and road surface condition and develops a model to estimate the road surface condition using machine learning. A road surface sensor was attached to the probe vehicle to collect road surface condition classified into three categories as 'dry', 'moist' and 'wet'. Road geometry information (curvature, gradient), traffic information (link speed), weather information (rainfall, humidity, temperature, wind speed) are utilized as variables to estimate the road surface condition. A variety of machine learning algorithms examined for predicting the road surface condition, and a two - stage classification model based on 'Random forest' which has the highest accuracy was constructed. 14 days of data were used to train the model and 2 days of data were used to test the accuracy of the model. As a result, a road surface state prediction model with 81.74% accuracy was constructed. The result of this study shows the possibility of estimating the road surface condition using the existing weather and traffic information without installing new equipment or sensors.

• Journal of Environmental Health Sciences
• /
• v.38 no.5
• /
• pp.407-414
• /
• 2012

Objectives: This study was performed to assess based on field investigation the distribution characteristics of airborne fungi in an area of Seongdong-gu, Seoul. Methods: Three sites, a living area, forest and traffic site, were selected for evaluation of monthly level of outdoor airborne fungi. An on-site survey was executed between January 2009 and December 2009. During the experimental period, air sampling was performed every month in the afternoon (2:00 pm-5:00 pm) using a cascade impactor. Results: Outdoor airborne fungi measured in Seoul, Korea over one year showed a concentration range from 850CFU $m^{-3}$ to 15,200CFU $m^{-3}$. The mean respirable fraction of outdoor airborne fungi was 67% compared to total concentration. Regardless of measurement site, there was no significant concentration difference in outdoor airborne fungi between periods of yellow dust and non-yellow dust (p>0.05). There was no significant correlation relationship between outdoor airborne fungi and atmospheric factors such as temperature and relative humidity. The predominant genera of airborne fungi identified were Aspergillus, Cladosporium, Paecilomyces and Penicillium. Conclusion: Monthly levels of outdoor airborne fungi were highest in April and November and lowest in August. In seasonal concentration distribution, the autumn showed the highest level of outdoor airborne fungi, followed by spring, summer and winter. In regional concentration distribution, the highest level of outdoor airborne fungi was generally found in the forest, followed by the living area and traffic site.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.483-490
• /
• 2019

In the Network Intrusion Detection System (NIDS), the function of classification is very important, and detection performance depends on various features. Recently, a lot of research has been carried out on deep learning, but network intrusion detection system experience slowing down problems due to the large volume of traffic and a high dimensional features. Therefore, we do not use deep learning as a classification, but as a preprocessing process for feature extraction and propose a research method from which classifications can be made based on extracted features. A stacked AutoEncoder, which is a representative unsupervised learning of deep learning, is used to extract features and classifications using the Random Forest classification algorithm. Using the data collected in the IOT environment, the performance was more than 99% when normal and attack traffic are classified into multiclass, and the performance and detection rate were superior even when compared with other models such as AE-RF and Single-RF.

• Journal of Korean Society of Forest Science
• /
• v.100 no.1
• /
• pp.88-94
• /
• 2011

This study was conducted to provide on a basic information for maintenance of roadside trees and identify the links between environmental pollution and tree damages (Ginkgo biloba, Platanus occidentalis) in Daejeon City by analyzing photosynthetic characteristics, water use efficiency, chlorophyll fluorescence and chlorophyll contents by the regions and plants. The investigations were conducted at Chungnam national university(CNU) considered as the least air-polluted area compared to other study sites, Daedeok science town(DS) which a new road with little traffic recently was built around, Daehwa industry complex(DIC) and Daejeon station(DS) which an old road with heavy is located around. The photosynthetic capacity of the two species were highest in CNU and lowest in the DS. However the water use efficiency was highest on the contrary to the photosynthetic capacity in DS. Chlorophyll fluorescence and chlorophyll contents were highest in CNU and lowest in DS as the photosynthetic capacity. On all of the test, Ginkgo biloba shows the more favorable physiological responses than Platanus occidentalis.

• Journal of the Korean Society of Safety
• /
• v.21 no.6 s.78
• /
• pp.55-63
• /
• 2006

Rapid economic growth in Korea, on the other side, has generated increase of multiple complex dangers. To take off dangers scattered in the Korean society and to conduct safe society for better life, it is needed to develop social safety index. Social safety index analyzed by time series could compare and estimate various social disasters, thus it act as the foundation to set up safety policy. The research has focused on 8 social safety indexes; natural disaster, fire, traffic accident, crime, industry accident, forest fire, collapse and explosion, and environmental pollution. To find out Korean society safety index analyzed by time series, the research analyzed changes of each safety indexes in 10 years since 1994. Looking at the changes of each indexes, traffic accident showed the most improvement overall the nation, with industrial accident and collapse and explosion rating second and third place. However, crime, fire and natural disaster get worse, and especially crime has turned worsened than any other divisions.

• Asian Journal of Atmospheric Environment
• /
• v.7 no.2
• /
• pp.65-71
• /
• 2013

Japanese cedar (Cryptomeria japonica) pollinosis is the most popular pollinosis in Japan. It has been reported that Cryptomeria japonica pollen allergenic species are suspended as fine particles in the urban atmosphere. These allergenic fine particles are responsible for inducing asthma by breaking into the lower respiratory tract. It has also been found that pollinosis symptoms on the sufferers appear mainly at night-time by the results from epidemiological studies. However, the exact reason for these phenomena is not yet clarified. In this study, the diurnal and nocturnal behaviours of Cryptomeria japonica pollen grains and their allergenic species in the urban area of Saitama city of Kanto Plain were investigated. Airborne pollen grains and allergenic Cry j 1 concentrations in total suspended particulate matter (TSP) were investigated at two sampling sites, a heavy traffic road (roadside site) and at the balcony of the $10^{th}$ floor of the Building of Research and Project of Saitama University (general urban site). The latter sampling site where located about 300 m away from the roadside site was used as a general urban site unaffected by automobile traffic. The airborne pollen counts were measured with a real-time pollen monitor. Cry j 1 particles were collected with two high volume air samplers, and these concentrations were measured by surface plasmon resonance method with a Biacore J system. The diurnal variation of the airborne pollen counts was similar to the trends of temperature and wind speed during the day-time; whereas its tendency with wind speed trend was not observed during the night-time. Airborne pollen counts were lower with northern wind than with southern wind because the pollen comes from the mountainous areas, and the mountains in the south are closer, about half the distance to the northern mountains. It is suggested that the peaks of airborne pollen counts during night-time in the sampling site occurred by transport of pollen grains released during day-time in the mountainous forest areas, located c.a. 100 km away from the sampling site. On the roadside site the allergenic Cry j 1 concentrations were higher than at the general urban site, nevertheless pollen grains counts were lower. These results suggested that worsening of pollinosis symptoms during night-time in urban area was caused by transport of pollen grains during day-time in the mountainous forest areas. Moreover, pollen allergenic species become different morphology from pollen grain at roadside site, and the subsequent pollen grains re-suspension by automobile traffic.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.2
• /
• pp.19-37
• /
• 2023

This study empirically analyzed the determinants of the assessment ratio (hereinafter 'AR') based on a total of 2,129 sales cases of forests in Gwangju, Gyeonggi-do. The main findings of this study through multiple regression analysis are summarized as follows. First, this study shows that regional characteristics have significantly different effects on the AR of forest land prices. Specifically, there was a significant difference in the AR depending on the location of the parcel by sub-region and the ratio of residential area, and the higher the number of development plans in progress, the more likely the officially assessed land price will be formed close to the sale price. Second, this study analyzed that location characteristics such as the proximity of the inner and outer center of the jurisdiction and traffic accessibility had a significant influence on the determination of the AR. Third, this study identified significant differences in AR depending on detailed factors such as planning management areas, production management areas, conservation areas for mountain, conservation areas for nature, and restricted development areas as land use and regulatory characteristics of forest lands. Fourth, this study found that land characteristics are a significant factor influencing the AR as an individual factor in forest land.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.169-178
• /
• 2021

Recently, a bike-sharing system (BSS) has become popular as a convenient "last mile" transportation. Rebalancing of bikes is a critical issue to manage BSS because the rents and returns of bikes are not balanced by stations and periods. For efficient and effective rebalancing, accurate traffic prediction is important. Recently, cluster-based traffic prediction has been utilized to enhance the accuracy of prediction at the station-level and the clustering step is very important in this approach. In this paper, we propose a k-means based clustering algorithm that overcomes the drawbacks of the existing clustering methods for BSS; indeterministic and hardly converged. By employing the centroid initialization and using the temporal proportion of the rents and returns of stations as an input for clustering, the proposed algorithm can be deterministic and fast.