• Journal of Wetlands Research
• /
• v.19 no.1
• /
• pp.1-15
• /
• 2017

Wetland function assessment is not only a basic step to understand wetland ecosystems in detail but also an important process as a base of the term, ecosystem service to recognize wetland ecosystems as valuable and useful resources and goods for human being. WET (wetland evaluation technique), EMAP (environmental monitoring assessment program)-wetlands, and HGM (hydrogeomorphic method) were developed as pioneer wetland function assessments in U.S. at the end of $20^{th}$-century. RAMs (rapid assessment methods) became a major function assessment tool which is relatively simpler and easier assessment tool at the beginning of $21^{th}$-century. After that, the hierarchy of three levels of assessment (landscape assessment, rapid assessment, and intensive assesment) has been prepared and strategically utilized according to the objectives and purposes of function assessments. In South Korea, RAM and HGM were used to assess wetland functions with reforming a couple of items and contents at 2001. And, modified and reformed function assessments have been developed to complement and improve upon the existing RAMs and HGMs. Via the trend analysis on wetland function assessments, some needs which require supplements in terms of function assessment are pointed out: 1) wetland function assessments using useful indicators such as birds are needed with considering our environmental characteristics. 2) optimized wetland function assessments for coastal wetlands are also needed. 3) the network construction and further expansion to lead communications and co-operations between researchers and policy makers is needed in the field of wetland function assessment.

• Korean Journal of Ecology and Environment
• /
• v.51 no.1
• /
• pp.86-95
• /
• 2018

The objective of this study was to describe the development and testing of an initial ecological health assessment model, based on the index of biological integrity (IBI) using fish assemblages, before establishing the final and currently used model for ecological health assessment, conservation and management of freshwater fish in Korea. The initial fish IBI model was developed during 2004~2006 and included 10 metrics, and in 2007 the final IBI 8-metric model was established for application to streams and rivers in four major Korean watersheds. In this paper, we describe how we developed fish sampling methods, determined metric attributes and categorized tolerance guilds and trophic guilds during the development of the multi-metric model. Two of the initial metrics were removed and the initial evaluation categories were reduced from six to four (excellent, good, fair, poor) before establishing the final national fish model. In the development phase, IBI values were compared with chemical parameters (BOD and COD as indicators of organic matter pollution) and physical habitat parameters to identify differences in IBI model values between chemical and physical habitat conditions. These processes undertaken during the development of the IBI model may be helpful in understanding the modifications made and contribute to creating efficient conservation and management strategies for stream environments to be used by limnologists and fish ecologists as well as stream/watershed managers.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.5
• /
• pp.892-902
• /
• 2015

Agri-food ICT(Information and Communications Technologies) convergence has been raised as an important issue for agricultural industry competence. In this situation, this study is to enhance agricultural competitiveness and seek to development plan for agricultural corporation by diagnosing informatization level. For this purpose, this study conducted survey on informatization level of 3,019 agricultural corporations and calculated level score. And result is compared with SMEs(Small and Medium Enterprise) informatization survey, including manufacturing and service industries, conducted by Korea Technology & Information Promotion Agency for SMEs in recent agricultural corporations' growing with automation of agricultural production and improving service to customer satisfaction. Evaluation system is established to calculate informatization level score and AHP(Analytic Hierarchy Process) method was used by the experts to investigate weighting of assessment area, assessment indicators, assessment items. As a result, agricultural corporation informatization level score was 40.16 points which is lower than the benefitted organization of agri-food IT convergence modeling(43.44 points). By assessment area, the informatization level of promotional environment area was low and investment and training items were analyzed low especially so need to improve urgently. In the analysis result by organization type, agricultural company corporation's informatization level was higher than the agricultural association corporation and 'Processing and distribution' was higher than others by business type. Informatization level of agricultural corporation is 80 percent of 2013 SMEs' level(50.18 points) and 59.4 percent of a large corporation(67.64 points). In particular, big difference is occurred in investment feasibility analysis, informatization investment and education which will be need to improve.

• Journal of Environmental Impact Assessment
• /
• v.30 no.6
• /
• pp.413-424
• /
• 2021

Health impact assessment in the environmental impact assessment is conducted to determine whether to exceed the standard of each single substance and to establish appropriate reduction measures. In some development projects, although all substances in risk assessment meet the standard, exposure concentration is very close to it. However, considering the cumulative exposure of all substances, health effects are likely to occur considerably severer than those of individual substances, so it is necessary to prepare a concrete and improved methodology for integrating evaluation of emissions to identify the health effects actually exposed to receptors of living things. This study established the definition of cumulative risk assessment through overseas advanced cases and domestic and foreign literature reviews, and proposed a methodology for utilizing cumulative risk assessment considering health effects on multiple substances when developing industrial complexes. Applied by the proposed methodology, integrated indicators forfourtypes of hazardous heavy metals (Ni, Cr⁶⁺, Cd, As) emitted from industrial complexes were calculated, and applicability was tested with case of the industrial complex development projects conducted over the last decade (2011-2020).

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2D
• /
• pp.191-197
• /
• 2009

This study choose the Criteria by conducting survey questionnaire of expertise, ANP analysis, and reviewing literature to samples of School Zone in a synthetic and reasonable way. It draws the estimating factors including a variety of existing aspects (user, facility, operation and management, and education and institution) from the analyses and applies ANP to reflect the decision making process. The results show as follows: first, first level of weights presents proportion of 'facility' and 'user' takes 65% of total weights. It implies that the facility protects children from obstacles is the top priority of the settings. second, the second level of weights present similar importance with the first level. Facility management, road to school, surroundings, safety facility, decelerating facility hold approximately 72% of overall levels. This indicates that improving and repairing surroundings, and safety and decelerating facility are the first priority to consider. These estimating indicators will be properly utilized to rationally appoint prevention zone with reflecting various factors and social class.

• Journal of Industrial Convergence
• /
• v.21 no.12
• /
• pp.55-62
• /
• 2023

Recent ransomware attacks employ various techniques and pathways, posing significant challenges in early detection and defense. Consequently, the scale of damage is continually growing. This paper introduces a machine learning-based approach for effective ransomware detection by focusing on file encryption and encryption patterns, which are pivotal functionalities utilized by ransomware. Ransomware is identified by analyzing password behavior and encryption patterns, making it possible to detect specific ransomware variants and new types of ransomware, thereby mitigating ransomware attacks effectively. The proposed machine learning-based encryption behavior detection technique extracts encryption and encryption pattern characteristics and trains them using a machine learning classifier. The final outcome is an ensemble of results from two classifiers. The classifier plays a key role in determining the presence or absence of ransomware, leading to enhanced accuracy. The proposed technique is implemented using the numpy, pandas, and Python's Scikit-Learn library. Evaluation indicators reveal an average accuracy of 94%, precision of 95%, recall rate of 93%, and an F1 score of 95%. These performance results validate the feasibility of ransomware detection through encryption behavior analysis, and further research is encouraged to enhance the technique for proactive ransomware detection.

• Land and Housing Review
• /
• v.15 no.2
• /
• pp.57-71
• /
• 2024

This study aims to develop an evaluation method for solar power facilities considering disaster impacts and to analyse the vulnerabilities of existing facilities. Haenam-gun in Jeollanam-do, where the reassessment of existing facilities is urgent, was selected as the study area. To evaluate the vulnerability from a more objective perspective, principal component analysis and entropy methods were utilised. Seven vulnerability assessment indicators were selected: maximum hourly rainfall, maximum wind speed, number of typhoon occurrence days, number of rainfall days lasting more than five days, maximum daily rainfall, impermeable area ratio, and population density. Among these, maximum hourly rainfall, maximum wind speed, maximum daily rainfall, and number of rainfall days lasting more than five days were found to have the highest weights. The overlay of the derived weights showed that the southeastern regions of Haenam-eup and Bukil-myeon were classified as Grade 1 and 2, whereas the northern regions of Hwawon-myeon, Sani-myeon, and Munnae-myeon were classified as Grade 4 and 5, indicating differences in vulnerability. Of the 2,133 facilities evaluated, 91.1% were classified as Grade 3 or higher, indicating a generally favourable condition. However, there were more Grade 1 facilities than Grade 2, highlighting the need for countermeasures. This study is significant in that it evaluates solar power facilities considering urban disaster resilience and is expected to be used as a basic resource for the installation of new facilities or the management and operation of existing ones.

• Journal of KIISE
• /
• v.42 no.3
• /
• pp.367-378
• /
• 2015

This study was directed at the design of a hybrid algorithm for competition relation extraction. Previous works on relation extraction have relied on various lexical and deep parsing indicators and mostly utilize only the machine learning method. We present a new algorithm integrating machine learning with various filtering methods. Some simple but useful features for competition relation extraction are also introduced, and an optimum feature set is proposed. The goal of this paper was to increase the precision of competition relation extraction by combining supervised learning with various filtering methods. Filtering methods were employed for classifying compete relation occurrence, using distance restriction for the filtering of feature pairs, and classifying whether or not the candidate entity pair is spam. For evaluation, a test set consisting of 2,565 sentences was examined. The proposed method was compared with the rule-based method and general relation extraction method. As a result, the rule-based method achieved positive precision of 0.812 and accuracy of 0.568, while the general relation extraction method achieved 0.612 and 0.563, respectively. The proposed system obtained positive precision of 0.922 and accuracy of 0.713. These results demonstrate that the developed method is effective for competition relation extraction.

• Environmental Analysis Health and Toxicology
• /
• v.14 no.4
• /
• pp.189-201
• /
• 1999

Lead (Pb) is ubiquitous in the urban environment and is a well-known toxic element. It may cause adverse health effects on hematopoietic system, peripheral and central nervous systems, kidney functions, and others. In recent decades, lead concentration in blood has been widely used one of indicators for lead exposure and risk evaluation. In this study, we determined the blood-lead levels in general populations of Korea, and investigated the relationship among blood-lead levels, sociobehavioral factors, and lead concentrations in the contacted environments such as ambient air, drinking water, and foods. The study subjects consisted of volunteers who had lived in the residential or industrial area in Korea. Information about gender, age, living area, occupation, smoking, heat system, and dietary habits, etc was collected using a self-reported questionnaires. The lead concentrations of environments were collected by literature search to the study area. Participated subjects in industrial area were 726 and their blood-lead levels were 8.58 $\mu\textrm{g}$/dl for males and 6.26 $\mu\textrm{g}$/dl for female in average. The other subjects in residential area were 317 and their blood-lead levels were 4.58 $\mu\textrm{g}$/dl for males and 3.49 $\mu\textrm{g}$/dl for female in average. The distribution of blood-lead level in the industrial subjects was well fitted to the log -normal distribution and that in the residential subjects was well fitted to the normal distribution. Blood-lead levels in both area were affected by gender, smoking habit, age and residence duration except age in industrial area and residence duration in residential area. It was identified that 30% of blood-lead level was contributed from the inhalation of ambient air in the industrial area, and 8.4% of blood-lead level was from that in the residential area. from this study, it would be suggested for the health risk assessment and management of lead pollution concerns in urban, industrial and rural areas.