• Journal of Environmental Science International
• /
• v.26 no.4
• /
• pp.521-527
• /
• 2017

Solar radiation forecasts are important for predicting the amount of ice on road and the potential solar energy. In an attempt to improve solar radiation predictability in Jeju, we conducted machine learning with various data mining techniques such as tree models, conditional inference tree, random forest, support vector machines and logistic regression. To validate machine learning models, the results from the simulation was compared with the solar radiation data observed over Jeju observation site. According to the model assesment, it can be seen that the solar radiation prediction using random forest is the most effective method. The error rate proposed by random forest data mining is 17%.

• Journal of the Korean Society of Safety
• /
• v.30 no.3
• /
• pp.93-99
• /
• 2015

Economic burden of work-related musculoskeletal disorder(WMDs) is increasing. Known causes of WMDs include improper posture, repetition, load, and temperature of workplace. Among them, improper postures play an important role. A smart sensor called SensorTag is employed to estimate the trunk postures including flexion-extension, lateral bend, and the trunk rotational speeds. Measuring gravitational acceleration vector in the smart sensor along the tri-orthogonal axes offers an orientation of the object with the smart sensor attached to. The smart sensor is light in weight and has small form factor, making it an ideal wearable sensor for body posture measurement. Measured data from the smart senor is wirelessly transferred for analysis to a smartphone which has enough computing power, data storage and internet-connectivity, removing need for additional hardware for data post-processing. Based on the estimated body postures, WMDs risks can be conviently gauged by using existing WMDs risk assesment methods such as OWAS, RULA, REBA, etc.

• Journal of the Korean Society of Safety
• /
• v.33 no.2
• /
• pp.39-44
• /
• 2018

Dust explosions are occurring in a variety of industries. A dust explosion caused by a specific energy generates huge amount of energy in the ignition and releases decomposition gas. Damages can be increased since this released decomposition gas can cause second and subsequent explosions. In this study, the goal was to obtain practical information on what could affect the explosion by comparing the characteristics of two kinds of dusts with completely different chemical properties. Three kinds of dusts were measured and evaluated for explosion pressure, dust explosion index, explosion limit and minimum ignition energy. It is possible to grasp the characteristics of each dust and use it as useful accident prevention data in the production of raw material powder.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.12
• /
• pp.3645-3652
• /
• 2009

Most important factor for successful operation of collaborative project, which is a project based curriculum, is systematic and rational assesment. In this paper, we design and implement multidimensional performance assessment support system which can overcome simplicity of result-oriented evaluation. In the proposed system, learner can diagnose problems and improve those by oneself. We design the system satisfying both professor and student about evaluation results through evaluating total course of collaborative project.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.6
• /
• pp.1034-1040
• /
• 2010

This paper presents a calculation method of the area of severity for the stochastic assessment of voltage sags. In general, the annual expected numbers of voltage sags at an individual load point can be estimated stochastically. However, in order to assess the system voltage sag performance considering many sensitive load points together, it is necessary to determine and analysis the area of severity for the load points. The area of severity to voltage sags is the network region where the fault occurrences will simultaneously lead to voltage sags at different load points. In this paper, the concept of the voltage sag assessment and the calculation method of the area of severity are addressed. The analysis of the area of severity is performed on the IEEE 30-bus test system by using the proposed method. The method is useful for the stochastic assesment of voltage sags and the establishment of systematic plans for voltage sag mitigation.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2001.11a
• /
• pp.122-126
• /
• 2001

본 연구는 자동차 시뮬레이터에서 정속(60∼80km/h)으로 2시간 도안 주행하는 동안 운전자의 주관적 피로감과 운전수행도에 대한 평가를 통하여 산소농도(18％, 21％, 30％)의 변화에 따른 운전 피로감을 평가하였다. 분석 결과 산소농도의 변화에 따른 주관적 피로감은 모든 산소 농도에서 시간이 경과함에 따라 유의하게 증가하였는데 특히 저농도의 산소일 때가 다른 산소 조건들에 비해 높았고 고농도의 산소일 때 낮았다. 또한, 브레이크 반응 시간은 고농도의 산소일 때가 저농도의 산소에 비하여 유의하게 감소하였다. 이와 같이 산소 조건에 따른 운전 피로감의 현저한 차이를 볼 수 있었다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.47-52
• /
• 2000

단기기억 작업시 집중도를 평가하기 위하여 평가용 task를 설계하고 5단계의 난이도에 대하여 실험을 실시하였다. 난이도에 따른 집중도의 변화를 측정하기 위하여 주관평가를 실시하고 행동지표와 생리신호를 측정하였다. 측정된 생리신호 중 전두엽(Ep1, Ep2)에서 측정한 뇌전도 신호의 $\alpha$-band와 $\beta$-band의 전력의 비와, 심박변화율의 전력 스펙트럼의 MF/(LF+MF+HF)비를 구하였다. 실험 결과 집중도 높게 보고된 단계에서 task를 수행함에 따라 뇌전도 신호의 $\alpha$/$\beta$ 비와 심박변화율의 MF/(LF+MF+HF) 비도 점차로 증가하였다.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.9
• /
• pp.61-69
• /
• 2006

The tensile strength of an overhead transmission line's conductor in response to an aging is being assessed in this paper. It is our view that, the decrement in the conductor's tensile strength is a key index that can be used to determine a conductor's end of life and a current limits. This paper describes a probabilistic method of assessing this index for main transmission lines which are responsible for the north bound power flow in the Seoul metropolitan area. Such an assessment can be a useful guide for economic system operation.

• Journal of the Korean Society of Safety
• /
• v.27 no.5
• /
• pp.164-170
• /
• 2012

In this study, a new technique for detecting near miss using 4M risk assessment method is suggested. Until now, the safety education with instances of near miss has just been progressed in most industrial settings, without any systematic guideline. By menas of appling 4M risk assessment method, the organized technique, which could effectively manage the fundamental prevention of industrial accident in advance, is developed. The organized technique of near miss-management suggested in this study will take an effective role in basically expanding the application of risk assessment method, as well as in contributing the activity of zero-accident as a safety guideline in hazardous workshops.

• Proceedings of the KOSOMBE Conference
• /
• v.1995 no.11
• /
• pp.117-120
• /
• 1995

The electronencephalogram (EEG) is a complex electrical signal which reflects generalized brain activity. The EEG is utilized in the clinical assesment of many neurological and psychiatric disorders and offers promise for monitoring of patients undergoing operation. This paper describes a technique for quantitative analysis of EEG signals which is based on an eigenspace. Examples of the application approach to simulated and clinical EEG data illustrate the capabilities.