• 산업경영시스템학회지
• /
• 제14권24호
• /
• pp.123-132
• /
• 1991

This study deals with the experiment of perceiving visual information according to the positions of vehicle side mirrors. In the design of vehicle, the consideration of safety is very important. Therefore we consider the positions of side mirrors to use visual information effectively which is important factor to driver. This paper presents the position of side mirror to elevate the degree of visual perception for the circumstances of danger by experiments. To exhibit the circumstances of danger. 4 LED(Light Emitted Diode) art located at each side(right. left front. hack) of vehicle. A subject pushes the LED switch to see that if he perceives the circumstance of danger. To record the circumstance of randomly generated danger, computer interface card is used to control 4 LED and swithch on IBM PC/AT Experiments are divided into 2 parts. The 1st experiment present the independence of right & left side mirror. The 2nd experiment present optimal position of right & left side mirror. The vehicle used in experiment is model EL of H Co.. Statistical process of experimental data using SPSS(Statistical Package for Social Sciences)/PC package concludes that 1) the optimal position of right side mirror is 54cm forward of exist position. 2) for the left side mirror, the position of 120cm forward of exist position shows the worst degree of perception. and the optimal position does not exist in statistical meaning.

• 한국산림과학회지
• /
• 제99권2호
• /
• pp.163-171
• /
• 2010

Forest fires have potentials to change the structure and function of forest ecosystems and significantly influence on atmosphere and biogeochemical cycles. Forest fire also affects the quality of public benefits such as carbon sequestration, soil fertility, grazing value, biodiversity, or tourism. The prediction of fire occurrence and its spread is critical to the forest managers for allocating resources and developing the forest fire danger rating system. Most of fires were human-caused fires in Korea, but meteorological factors are also big contributors to fire behaviors and its spread. Thus, meteorological factors as well as social factors were considered in the fire danger rating systems. A total of 298 forest fires occurred during the fall season from 2002 to 2006 in South Korea were considered for developing a logistic model of forest fire occurrence. The results of statistical analysis show that only effective humidity and temperature significantly affected the logistic models (p<0.05). The results of ROC curve analysis showed that the probability of randomly selected fires ranges from 0.739 to 0.876, which represent a relatively high accuracy of the developed model. These findings would be necessary for the policy makers in South Korea for the prevention of forest fires.

• 한국컴퓨터정보학회논문지
• /
• 제29권1호
• /
• pp.151-161
• /
• 2024

이 논문에서는 제조공장 사업장 현장 내 각 공정을 촬영한 영상을 인공지능(AI)으로 분석하여 위험·유해 요인을 파악할 수 있도록 작업장 위험지도(Danger Map)를 개발하고 이 Danger Map 에서 도출된 빈도·강도에 기반한 위험도와 안전도를 실제 현장상황에 맞추어 자동으로 도출하여 유사 제조 업종에 적용할 수 있는 시스템을 제시히였다. 특히, 사업장의 안전도(위험도)를 엑셀 등 수동으로 평가하던 종래의 평가방식에서 영상으로부터 취득된 유해·위험 요인별 위험성 수준을 자동으로 산정 평가하여 시스템에 의한 안전 확보와 안전도(위험도)를 계산함으로써 이에 따라 기업에서 적절한 활동 및 조치를 마련할 수 있도록 하였다. 안전도(위험도) 산출 및 평가 자동화를 위해 '하인리히의 법칙(Heinrich's law)'을 모델로 하였으며, 위험한 행동 패턴에 대해 5X4점 평가척도를 계산하였다. 이 시스템을 실증적용하기 위해 금속주물주조공장에 적용하였으며 매월 안전도(위험도) 계산에 추가되는 시간적 비용 및 노동력을 2명 절감할 수 있었다.

• Journal of Multimedia Information System
• /
• 제7권3호
• /
• pp.205-214
• /
• 2020

Crime has become one of the major problems in modern society. Even though visual surveillances through closed-circuit television (CCTV) is extensively used for solving crime, the number of crimes has not decreased. This is because there is insufficient workforce for performing 24-hour surveillance. In addition, CCTV surveillance by humans is not efficient for detecting dangerous situations owing to accuracy issues. In this paper, we propose the autonomous detection of dangerous situations in CCTV scenes using a deep learning model with relational inference. The main feature of the proposed method is that it can simultaneously perform object detection and relational inference to determine the danger of the situations captured by CCTV. This enables us to efficiently classify dangerous situations by inferring the relationship between detected objects (i.e., distance and position). Experimental results demonstrate that the proposed method outperforms existing methods in terms of the accuracy of image classification and the false alarm rate even when object detection accuracy is low.

• 대한의용생체공학회:의공학회지
• /
• 제27권6호
• /
• pp.370-375
• /
• 2006

The purpose of this work is to predict the systolic blood pressure (BP) during exercise from pulse transit time (PTT) for warning of possible danger. PTT was calculated as the time between R-peak of ECG and the peak of differential photoplethysmograph (PPG). For the PTT-BP model, we used regress equations from previous studies and 3 kinds of new models combining linear and nonlinear regress equation. The model parameters were estimated with the data measured under low to middle intensity exercise, and then was tested with the data measured under high intensity exercise. Predicted BP values after high intensity exercise were compared with those measured by cuff-type sphygmomanometer. The results showed that the error between measured and predicted values were acceptable for the monitoring BP. We tested PTT-BP models 1 month after the identification without further calibration. Models could predict the BP and the errors between measured and predicted BP were about 5mmHg. The suggested system is expected to be helpful in recognizing any danger during exercise.

• 한국산림과학회지
• /
• 제85권1호
• /
• pp.15-23
• /
• 1996

본격적인 산림자원조성시대를 대비하기 위해서는 가장 큰 피해를 주고 있는 산불에 대한 과학적이고 합리적인 산불발생에 관한 예측모형의 개발이 필수적이다. 따라서 본 연구는 이에 대한 현실적인 방안으로서 대구 경상북도지역을 대상으로 하여 기상요인을 이용한 산불발생확률모형을 개발하고자 수행하였다. 이를 위해 먼저 산불발생일의 모든 기상자료들을 검토하여 이들 기상요인과 산화발생빈도와의 함수관계를 파악하여 의미 있는 기상요인을 규명하고, 이와 병행하여 국지적(局地的) 차원(次元)의 기상자료 획득이 현실적으로 불가능하기 때문에, 각 시 군별 산불발생일의 유사정도를 적절한 통계적 기법에 이용하여 정량화(定量化)하고 이를 토대로 조사대상지역 범주화하였다. 그 결과 산불발생에 영향을 미치는 기상요인으로는 상대습도, 일조시간, 강우후 경과일로 밝혀졌으며, 조사대상지역은 대구를 중심으로 한 중남부지역, 안동을 중심으로 한 북부지역, 포항을 중심으로 한 동부해안지역으로 구분되었다. 따라서 구분된 각 지역의 시계열(時系列) 기상자료를 이용하여 logistic과 probit model을 기초로 한 산불발생확률모형이 개발되었다. 모의 실효성을 검정하기 위하여 과거 기상자료를 대입한 결과 상당한 정도의 예측능력이 확인되어, 이를 이용한 효율적인 감시활동과 진화장비의 배치 등 산불예방활동의 효율성을 제고할 수 있을 것으로 기대된다.

• 대한간호학회지
• /
• 제54권2호
• /
• pp.162-177
• /
• 2024

Purpose: This study aimed to investigate the influence of uncertainty-related factors on the health behavior of individuals with coronary artery disease (CAD) based on Mishel's uncertainty in illness theory (UIT). Methods: We conducted a cross-sectional study and path analysis to investigate uncertainty and factors related to health behavior. The study participants were 228 CAD patients who visited the outpatient cardiology department between September 2020 and June 2021. We used SPSS 25.0 and AMOS 25.0 software to analyze the data. Results: The final model demonstrated a good fit with the data. Eleven of the twelve paths were significant. Uncertainty positively affected danger and negatively affected self-efficacy and opportunity. Danger had a positive effect on perceived risk. Opportunity positively affected social support, self-efficacy, perceived benefit and intention, whereas it negatively affected perceived risk. Social support, self-efficacy, perceived benefit and intention had a positive effect on health behavior. We found that perceived benefit and intention had the most significant direct effects, whereas self-efficacy indirectly affected the relationship between uncertainty and health behavior. Conclusion: The path model is suitable for predicting the health behavior of CAD patients who experience uncertainty. When patients experience uncertainty, interventions to increase their self-efficacy are required first. Additionally, we need to develop programs that quickly shift to appraisal uncertainty as an opportunity, increase perceived benefits of health behavior, and improve intentions.

• 한국지능시스템학회논문지
• /
• 제13권2호
• /
• pp.148-153
• /
• 2003

서비스 거부 공격은 침입을 위한 침입시도 형태로 나타나며 대표적인 공격으로 Syn Flooding 공격이 있다. Syn Flooding 공격은 신뢰성 및 연결 지향적 전송서비스인 TCP의 종단간에 3-way handshake의 취약점을 이용한 공격이다. 본 논문에서는 네트워크 기반의 지능적 침입 방지 모델을 제안한다. 제안하는 모델은 Syn Flooding 공격을 탐지하기 위하여 패킷 정보를 수집하고 분석한다. 이 모델은 퍼지인식도(Fuzzy Cognitive Maps)를 적용한 결정모듈의 분석 결과를 활용하여 서비스 거부 공격의 위험도를 측정하고 공격에 대응하도록 대응모듈을 학습시킨다. 제안하는 모델은 Syn Flooding 공격의 위험을 격감 또는 방지하는 네트워크 기반의 지능적 침입 방지 모델이다.

• 산업경영시스템학회지
• /
• 제38권3호
• /
• pp.64-77
• /
• 2015

An effective method for produce munitions effectiveness data is to calculate weapon effectiveness indices in the US military's Joint Munitions Effectiveness Manuals (JMEM) and take advantage of the damage evaluation model (GFSM) and weapon Effectiveness Evaluation Model (Matrix Evaluator). However, a study about the Range Safety that can be applied in the live firing exercises is very insufficient in the case of ROK military. The Range Safety program is an element of the US Army Safety Program, and is the program responsible for developing policies and guidance to ensure the safe operation of live-fire ranges. The methodology of Weapon Danger Zone (WDZ) program is based on a combination of weapon modeling/simulation data and actual impact data. Also, each WDZ incorporates a probability distribution function which provides the information necessary to perform a quantitative risk assessment to evaluate the relative risk of an identified profile. A study of method to establish for K-Range Safety data is to develop manuals (pamphlet) will be a standard to ensure the effective and safe fire training at the ROK military education and training and environmental conditions. For example, WDZs are generated with the WDZ tool as part of the RMTK (Range Managers Tool Kit) package. The WDZ tool is a Geographic Information System-based application that is available to operational planners and range safety manager of Army and Marine Corps in both desktop and web-based versions. K-Range Safety Program based on US data is reflected in the Korean terrain by operating environments and training doctrine etc, and the range safety data are made. Thus, verification process on modified variables data is required. K-Range Safety rather than being produced by a single program, is an package safety activities and measures through weapon danger zone tool, SRP (The Sustainable Range Program), manuals, doctrine, terrain, climate, military defence M&S, weapon system development/operational test evaluation and analysis to continuously improving range safety zone. Distribution of this K-range safety pamphlet is available to Army users in electronic media only and is intended for the standing army and army reserve. Also publication and distribution to authorized users for marine corps commands are indicated in the table of allowances for publications. Therefore, this study proposes an efficient K-Range Safety Manual producing to calculate the danger zones that can be applied to the ROK military's live fire training by introducing of US Army weapons danger zone program and Range Safety Manual

• 한국농림기상학회지
• /
• 제14권1호
• /
• pp.1-10
• /
• 2012

본 연구는 디지털예보(현 동네예보) 자료를 활용하여 우리나라의 산불위험예보의 정확도 향상은 물론 기상에 의한 산불위험지수를 산출하여 한반도의 산불위험예보 체계를 구축하는데 있다. 한반도 지역의 산불발생위험을 나타내는 기상지수(daily weather index, DWI)를 산출하기 위해 기상청의 5km 격자간격의 디지털예보자료를 이용하였다. DWI 분석을 위해 온도, 습도, 풍속 UV, 1시간 강우량, 12시간 강우량을 대상으로 한반도 전역에 대한 기상요소별 기후분포도를 제작하였다. 한반도의 기상에 의한 일일 DWI 산출을 위해 대형산불이 자주 발생하는 강원도 지역의 산불발생확률식 $[1+{\exp}\{-(2.494+(0.004{\times}T_{max})-(0.008{\times}EF))\}]^{-1}$을 적용하였다. 기상예보자료의 예측정확도 검증을 위해 RDAPS, 디지털예보, 실황자료 모두 2005년 12월 12일 15시 자료를 대상으로 비교 분석한 결과 76개 기상관측소에서 관측한 실황자료에 대응하는 기상요소별 디지털예보의 예측값이 RDAPS 추출 자료보다 향상된 예측결과를 보였다. 산불위험예보 정확도 검증을 위해 사용한 실황자료와 디지털예보자료의 평균오차는 평균 기온 $0.2^{\circ}C$, 실효습도 2.4%, 평균풍속 2.2m/s로 나타나 큰 변이는 없었지만, 평균풍속에서 실측값과 예측값간의 차이가 있는 것으로 나타났다. 디지털예보자료를 활용할 경우 RDAPS 자료보다 산불위험예보의 정확도가 크게 향상되는 결과를 얻을 수 있었으며, 산불위험예보의 정확도 검증을 위해 실황자료와 디지털예보자료를 적용하여 예측된 전국 233개 시 군 구의 평균 산불위험지수를 각각 추출하여 비교한 결과 $R^2$=0.854의 높은 정확도를 보였다. 산불위험도가 가장 높은 15시의 실제 76개소에서 관측한 기상자료를 적용하여 전국의 산불위험지수를 예측한 값은 70.5로 디지털예보자료를 적용하여 예측한 위험지수(70.0)와 0.5의 오차를 보여 예측력이 개선되었음을 확인할 수 있었다. 따라서 디지털예보를 적용할 경우 실황자료와의 예측력이 검증된 만큼 향후 기상에 의한 한반도의 산불발생위험지수를 보다 정확하게 계산하는데 유용하게 이용할 수 있을 것으로 기대된다.