• 환경생물
• /
• 제34권1호
• /
• pp.41-47
• /
• 2016

우리나라에 발생하는 해안 식생의 식생 구조에 대하여 식물사회학적 연구를 수행하였다. 총 102개 조사구에 대한 식생자료의 분석은 ZM 학파의 방법을 활용하였다. 국내 해안에 발생하는 식물 군집 구분은 총 11개의 군락으로 순비기나무-돌가시나무 군락, 갯메꽃 군락, 통보리사초-갯그령 군락, 갯잔디 군락, 해홍나물 군락, 방석나물 군락, 나문재-가는갯는쟁이군락, 칠면초 군락, 천일사초 군락, 갈대 군락, 산조풀 군락이 구분되었다. 각 군락 들은 발생지역과 환경에서 다양성을 보였다. 식생 자료에 대한 주성분분석 (PCA) 결과 식물사회학적 군락 분류 결과를 지지하였다.

• 한국화재소방학회논문지
• /
• 제19권3호
• /
• pp.64-69
• /
• 2005

산불은 경제적 손실뿐만 아니라 인명을 위협할 수 있는 국가적 재해다. 이러한 산불을 미연에 방지하고 피해를 저감하기 위해서는 산불발생위험지역을 사전에 판단하여 효율적으로 관리하는 것이 필요하다. 본 연구에서는 입지환경에서 중요한 부분을 차지하는 산림토양특성 중 토양형, 지형, 토성, 경사, 배수 등과 산불발생지점을 가지고 각 지점별 산불발생위험을 예측할 수 있는 산불발생확률 모형을 개발하였다. 개발 시 조건부확률과 GIS를 이용하였다 개발된 산불발생확률 모형의 적합성 검정을 위하여 추정모형의 예측력 비율을 검토할 수 있는 예측비곡선에 적용한 결과 실효성이 있는 것으로 나타났다. 이러한 결과를 적용하여 산불관리자가 손쉽게 산불발생위험지역을 파악할 수 있도록 위험지역을 구분하였다.

• Earthquakes and Structures
• /
• 제9권5호
• /
• pp.983-997
• /
• 2015

This research evaluates the soil conditions for seismic stations situated in Romania using the horizontal-to-vertical spectral ratio (HVSR). The strong ground motion database assembled for this study consists of 179 analogue and digital strong ground motion recordings from four intermediate-depth Vrancea seismic events with $M_w{\geq}6.0$. In the first step of the analysis, the influence of the earthquake magnitude and source-to-site distance on the H/V curves is evaluated. Significant influences from both the earthquake magnitude and hypocentral distance are found especially for soil class A sites. Next, a site classification method proposed in the literature is applied for each seismic station and the soil classes are compared with those obtained from borehole data and from the topographic slope method. In addition, the success and error rates of this method are computed and compared with other studies from the literature. A more in-depth analysis of the H/V results is performed using data from seismic stations in Bucharest and a comparison of the free-field and borehole H/V curves is done for three seismic stations. The results show large differences between the free-field and the borehole curves. As a conclusion, the results from this study represent an intermediary step in the evaluation of the soil conditions for seismic stations in Romania and the need to perform more detailed soil classification analysis is highly emphasized.

• 한국지능시스템학회논문지
• /
• 제9권5호
• /
• pp.472-479
• /
• 1999

본 논문에서는 뉴로-퍼지 알고리즘을 이용한 원격탐사 화상의 지표면 패턴분류기를 제안한다. 제안된 패턴 분류기는 일반적인 퍼지 인식기를 가지고 있는 3층 전방향 신경회로망 구조로 되어 있고 가중치들은 퍼지집합으로 구성된다. 이러한 퍼지-뉴로 패턴분류 시스템을 Visual C++ 환경을 구현한다. 성능평가를 위해 기존의 역전파 학습기능을 가진 신경회로망과 Maximum-likelihood 알고리즘을 이용해처리한 결과와비교분석한다. 대표적인 지표면 특징을 나타내는 8개의 클래스에 대해 훈련집합을 선정하고 각각의 분류 알고리즘에 같은 훈련집합을 사용하여 학습시킨 후 실험화상을 적용하여 지표면 특징을 8개의 클래스로 분류하였다. 실험결과 제안된 뉴로-퍼지 분류기는 여러개의 클래스로 혼합된 패턴에 대해서 기존의 분류기들에 비해 보다 더 좋은 성능을 보인다.

• 대한안전경영과학회지
• /
• 제17권3호
• /
• pp.1-7
• /
• 2015

The study conducted questionnaire analysis to 413 industrial safety field employees in order to examine the necessity and validity of industrial safety field's 17th neo-job classification based on National Competency standards(NCS). As a result, 50.1% of industrial safety management field and 43.3% of industrial health management field answered that classification details of occupational safety and health management field are classified by job(duty) performance. Industrial safety management field recognizes that management and engineering section play a significant role in their work, while industrial health management field recognizes worker's health care and work environment management and overall control of work environment assessment to be significant in their work. Furthermore, industrial safety management field recognizes that separating qualification and foundation of 'construction safety manager', 'chemicals(safety and health) manager', '(toxic)risk assessment evaluator or risk factor manager' to be highly significant. The study is meaningful in that it suggests industrial safety field's qualification items practical in industrial sites.

• International Journal of Computer Science & Network Security
• /
• 제21권8호
• /
• pp.238-246
• /
• 2021

The rapid rise of the Internet and social media has resulted in a large number of text-based reviews being placed on sites such as social media. In the age of social media, utilizing machine learning technologies to analyze the emotional context of comments aids in the understanding of QoS for any product or service. The classification and analysis of user reviews aids in the improvement of QoS. (Quality of Services). Machine Learning algorithms have evolved into a powerful tool for analyzing user sentiment. Unlike traditional categorization models, which are based on a set of rules. In sentiment categorization, Bidirectional Long Short-Term Memory (BiLSTM) has shown significant results, and Convolution Neural Network (CNN) has shown promising results. Using convolutions and pooling layers, CNN can successfully extract local information. BiLSTM uses dual LSTM orientations to increase the amount of background knowledge available to deep learning models. The suggested hybrid model combines the benefits of these two deep learning-based algorithms. The data source for analysis and classification was user reviews of Indian Railway Services on Twitter. The suggested hybrid model uses the Keras Embedding technique as an input source. The suggested model takes in data and generates lower-dimensional characteristics that result in a categorization result. The suggested hybrid model's performance was compared using Keras and Word2Vec, and the proposed model showed a significant improvement in response with an accuracy of 95.19 percent.

• 한국건설관리학회논문집
• /
• 제22권1호
• /
• pp.106-115
• /
• 2021

이미지를 이용해 공종을 분류하는 작업은 건설 관리와 공정 관리와 같은 더욱 복잡한 어플리케이션에서 중요한 역할을 수행할 수 있다. 하지만, 공사 현장에서 수집한 이미지들은 항상 깨끗하지 않을 수 있고, 이와 같이 문제가 있는 이미지들은 이미지 분류기의 성능에 부정적인 타격을 입힐 수 있다. 이러한 가능성은 공종을 판별하는 시스템을 보조할 수 있는 데이터나 방법의 필요성을 부각한다. 본 연구에서 우리는 공종의 선·후행 관계를 이용해 이미지 분류기를 보조하여 공종을 판별하는 시스템의 성능을 높이는 방법을 제시한다. 그리고 제시하는 방법이 공종 판별의 성능을 향상시킬 수 있다는 것을 보인다. 특히, 이미지 판별기의 성능이 좋지 않을때 더욱 드라마틱한 성능의 향상을 경험할 수 있다는 것을 알 수 있었다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.744-751
• /
• 2022

Construction is among the most dangerous industries with numerous accidents occurring at job sites. Following an accident, an investigation report is issued, containing all of the specifics. Analyzing the text information in construction accident reports can help enhance our understanding of historical data and be utilized for accident prevention. However, the conventional method requires a significant amount of time and effort to read and identify crucial information. The previous studies primarily focused on analyzing related objects and causes of accidents rather than the construction activities. This study aims to extract construction activities taken by workers associated with accidents by presenting an automated framework that adopts a deep learning-based approach and natural language processing (NLP) techniques to automatically classify sentences obtained from previous construction accident reports into predefined categories, namely TRADE (i.e., a construction activity before an accident), EVENT (i.e., an accident), and CONSEQUENCE (i.e., the outcome of an accident). The classification model was developed using Convolutional Neural Network (CNN) showed a robust accuracy of 88.7%, indicating that the proposed model is capable of investigating the occurrence of accidents with minimal manual involvement and sophisticated engineering. Also, this study is expected to support safety assessments and build risk management systems.

• 대한토목학회논문집
• /
• 제31권2B호
• /
• pp.155-163
• /
• 2011

본 연구에서는 의사결정나무(CART)기법, 인공신경망모형, 인공위성 원격탐사자료와 지형자료 및 지상 기상관측망자료를 이용하여 토양수분을 산정하는 모형을 개발하였다. 본 모형의 검증을 위하여 사용된 토양수분 관측자료는 용담댐 유역에서 관측된 5개 지점의 토양수분자료를 사용하였다. 가용자료에 대해 CART기법을 적용하여 자료를 분류한 다음 분류된 각 자료집단에 대하여 인공신경망(Artificial Neural Networks)모형을 적용하여 토양수분 분포를 예측하였다. 모형의 학습에 사용된 주천, 부귀, 상전, 안천 지점의 토양수분 산정치는 관측치와 약 0.92-0.96의 상관계수, 약 1.00-1.88%의 평균제곱근오차와 약 0.75-1.45%의 평균절대오차를 보여주었다. 토양수분 추정모형을 검증하기 위해 천천2의 지점에 적용한 결과 약 0.91의 상관계수, 약 3.19%의 평균제곱근오차, 약 2.72%의 평균절대오차를 보여 CART기법과 인공신경망모형을 연계한 토양수분 산정모형이 토양수분 분포제시 활용에 적절한 것으로 판단된다.

• 대기
• /
• 제27권2호
• /
• pp.225-233
• /
• 2017

Korea has recently suffered from severe hazes, largely being long-range transported from China but frequently mixed with domestic pollution. It is important to identify the origin of the frequently-occurring hazes, which is however hard to clearly determine in a quantitative term. In this regard, we suggest a possible classification procedure of various hazes into long-range transported haze (LH), Yellow Sand (YS), and urban haze (UH), based on mass loading of fine particles, time lag of PM mass concentrations between two sites aligned with dominant wind direction, backward trajectory of air mass, and the mass ratio of PM2.5 to PM10. The analysis sites are Seoul (SL) and Baengnyeongdo (BN), which are distant about 200 km from each other in the west to east direction. Aerosol concentrations at BN are overall lower than those of SL, indicative of BN being a background site for SL. We found distinct time lag of PM2.5 and PM10 concentrations between BN and SL in case of both LH and YS, but the intensity of YS being stronger than LH. Time scale (e-folding time scale) of LH appears to be longer and more variable than YS, which implies that LH covers much larger spatial scale. In addition, we found linear and significant correlations between ${\tau}_a$ obtained from sunphotometer and ${\tau}_{cal}$ calculated from surface aerosol scattering coefficient for LH episodes, relative to few correlation between those for YS, which might be associated with transported height of YS being much higher than LH. Therefore surface PM concentrations for the YS period are thought to be not representative for vertical integrated amount of aerosol loadings, probably by virtue of decoupled structure of aerosol vertical distribution. Improvement of various hazes classification based on the current result would provide the public as well as researchers with more accurate information of LH, UH, and YS, in terms of temporal scale, size, vertical distribution of aerosols, etc.