• The Journal of Society for e-Business Studies
• /
• v.22 no.2
• /
• pp.1-18
• /
• 2017

Recently, identification of the extremely stressed condition of children is an essential skill for real-time recognition of a dangerous situation because incidents of children have been dramatically increased. In this paper, therefore, we present a model based on machine learning techniques for stress status identification of a child by using bio-signals such as voice and heart rate that are major factors for presenting a child's emotion. In addition, a smart band for collecting such bio-signals and a mobile application for monitoring child's stress status are also suggested. Specifically, the proposed method utilizes stress patterns of children that are obtained in advance for the purpose of training stress status identification model. Then, the model is used to predict the current stress status for a child and is designed based on conventional machine learning algorithms. The experiment results conducted by using a real-world dataset showed that the possibility of automated detection of a child's stress status with a satisfactory level of accuracy. Furthermore, the research results are expected to be used for preventing child's dangerous situations.

• Convergence Security Journal
• /
• v.3 no.3
• /
• pp.81-90
• /
• 2003

Risk analysis and internal control evaluation are key security management activities for securing organizational assets. Risk analysis is used to identify areas that need safeguarding while internal control evaluation is used to check whether the current control system is effective with a reasonable degree of assurance. Risk analysis usually focuses on unauthorised activities of unauthorised people and has not paid much attention to threats that could be committed by authorized users. As attention to fraud increases, these threats should be appropriately treated within organizations. This paper compares the difference between these two approaches.

• International Area Studies Review
• /
• v.16 no.1
• /
• pp.147-171
• /
• 2012

Even though many people loosely term a period of high inflation combined with stagnation "stagflation", it has been very difficult for us to find a more detailed and theoretical definition for such a period. In addition, most economic policy makers have faced some uncertainty and difficulty in identifying stagflation periods through analyzing a lot of economic data. This paper deeply researches the literature on specific definitions of stagflation and provides an empirical method by which we can systematically identify real-time stagflation pressure. Under this method, real-time stagflation pressure can be evaluated as a complex index by using both extensive monthly economic data indicating economic conditions or inflation pressure and a logit regression model. As a result of applying this method to the first half of 2008 in Korea when there was much debate as to whether the Korean economy was experiencing a corresponding stagflation or not, this period is not now evaluated as having been a stagflation period. This paper provides some implications. Namely, we need to put more emphasis on stabilizing inflation expectations.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.335-340
• /
• 2014

Crowd Sourcing-based Social App Manufacturing environment, a small app development project by a team of anonymous virtual performed without the constraints of time and space, and manage it for the app development process need to be automated method. Virtual teams with anonymity is a feature of the Social App Manufacturing, is an important factor that increases the uncertainty of whether the completion of the project or reduction in visibility of the progress of the project. In this study, as one of how to manage the project of Social App Manufacturing environment, the impact of risk that can be used to quantitatively measure the impact of the risk of delay in development has on the project also proposes a measurement model. Effects of risk and type of the impact of risks associated with delays in the work schedule also define the characteristic function, measurement model that has been proposed, suggest the degree of influence measurement equation of risk of the project in accordance with the progressive. The advantage of this model, the project manager is able to ensure the visibility of the progress of the project. In addition, identify the project risk of work delays, and to take precautions.

• Strategy21
• /
• s.32
• /
• pp.271-297
• /
• 2013

2010년 초반 이래 지역 해양안보는 보다 개선된 신뢰증진을 위한 안보구도와 메커니즘을 요구하고 있다. 특히 2011년 이래 전문가들은 지역 내 어려운 해양안보 문제들을 주요 현안으로 식별하고 있으며, 아울러 다양한 다루기 힘든 개념 위주의 지역 해양신뢰구축방안들을 제시하고 있었다. 최근 동북아는 다양한 해양분쟁과 갈등으로 점철되고 있으며, 대부분 국가들은 더욱 위험한 상황을 선택하기에 주저하지 않는 위험한 현상을 보이고 있다. 이러한 문제들은 첫째, 기본적으로 기존의 개념적 목적의 해양신뢰구축방안 이행에 대한 실패, 둘째, 개념적 해양신뢰구축방안을 넘어선 기능적이며 실질적 해양신뢰구축으로 변화에 어려움 그리고 셋째, 이를 동북아에서 어떻게 적용30)해야 하는가" 하는 문제로 귀결되고 있다. 대체적으로 전문가들은 개념적 방안 보다 효과적이며 기능적 해양신뢰구축방안을 적용하고 이해하는 것이 바른 "정답"이라고 보고 있다. 따라서 본 논문에서는 기존의 개념적 논쟁에 빠졌던 개념적 해양신뢰구축방안에 대한 과거 미련을 버리고 점차 진화된 복합적 문제로 대두되는 동북아 해양에서의 해양분쟁과 갈등을 기능적이며 실질적 해양 신뢰구축방안에 의해 해결하는 방법을 식별하여 제시하고자 한다. 이에 본 논문에서 제시하는 기술적이며 제도적 해양신뢰구축방안이 인정되면, 지금까지의 작용-반작용의 악순환적 주기를 넘어설 수 있는효과적 해양신뢰 각론, 레짐 또는 거버런스가 될 수 있을 것이다. 궁극적으로 본 논문의 목적은 고질적이고 새로운 해양갈등을 해소할 수 있는 신뢰 구축 전략을 제시하여 지역 해양안전과 평화를 유지하는 것이다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2012.10a
• /
• pp.138-140
• /
• 2012

본 연구에서는 실제 AIS의 정적, 동적 데이터를 수집하여 항계내 통항 선박의 움직임을 파악하였다. 실제 완도항 부근의 직선항로을 통항하는 선박 항적의 분석하여 불규칙적인 선박의 특성을 알아보고자 하였다. 기존의 과거 누적 데이터의 퍼지이론을 활용한 이상 거동의 선박식별 시스템은 전문가 시스템에 의존하여 항적의 비정상성을 판단하므로 항로의 특성에 따른 실 항해상황을 간과할 수 있는 문제점이 있다. 본 연구는 실시간 AIS 정보를 활용하여 항로이탈의 변화율에 해당하는 곡률분석, 항로선으로부터 좌우의 변동을 보다 정확하게 모니터링 할 수 있는 이상 거동 선박을 식별하는 방법을 제안한다. 본 연구는 VTS 및 VMS의 응용서비스로서 해양사고의 사전예방을 위한 연안 및 항만수로의 효율적인 관리에 기여할 것이다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.211-218
• /
• 2021

Construction sites have various risk factors. There are various approaches to reduce safety accidents, but they have limitations to some extent. By utilizing the wireless communication technology of IT and the rapidly developing image processing technology, it will be possible to reduce accidents at the construction site if risk factors are identified and actively responded to. Therefore, in this study, a system that can detect risk factors of construction sites in advance is constructed, and a system is proposed to discover and respond to risk factors of construction sites using OpenCV for the purpose of real-time computer vision.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.4
• /
• pp.69-76
• /
• 2019

This paper presents a method that identifies the unsafe behaviors at the level of near-misses using image analysis. The method establishes potential collision hazardous area in earthmoving operation. It is implemented using a game engine to reproduce the dangerous events that have been accepted as major difficulty in utilizing computer vision technology to support construction safety management. The method keeps realistically track of the ever-changing hazardous area by reflecting the volatile field conditions. The method opens a way to distinguish unsafe conditions and unsafe behaviors that have been overlooked in previous studies, and reflects the causal relationship which causes an accident. The case study demonstrate how to identify the unsafe behavior of a worker exposed to an unsafe area created by dump trucks at the level of near-misses and to determine the hazardous areas.

• Journal of the Society of Disaster Information
• /
• v.19 no.1
• /
• pp.69-75
• /
• 2023

Purpose: The risk of disaster from extreme weather events is increasing due to the increase in occurrence and the strength of heavy rains and storms from continued climate change. To reduce these risks, emergency weather information customized for the characteristics of the information users and related circumstances should be provided. Method: A first-stage emergency weather information delivery system has been developed to provide weather information to the disaster-risk area residents and the disaster response personnel. Novel methods to apply artificial intelligence to identify emergencies have been studied. The relationship between special weather reports from meteorological administration and disaster-related news articles has been analyzed to identify the significance of a pilot study using text analytic artificial intelligence. Result: The basis to identify the significance of the relations between disaster-related articles and special weather reports has been established and the possibility of the development of a real-world applicable system based on a broader analysis of data has been suggested. Conclusion: Through direct alert delivery of weather emergency alerts, a weather emergency alert system is expected to reduce the risk of damage from extreme weather situations.

• Journal of Navigation and Port Research
• /
• v.40 no.6
• /
• pp.391-400
• /
• 2016

A number of maritime accidents, and accident response activities, including the command and control procedures that were implemented at accident scenes, are analyzed to derive useful information about responding to maritime accidents, and to understand how the chain of events developed after the initial accident. In this research, a new concept of a 'risk based accident response support system' is proposed. In order to identify the event chains and associated hazards related to the accident response activities, this study proposes a 'Brainstorming technique for scenario identification', based on the concept of the HAZID technique. A modified version of Event Tree Analysis was used for quantitative risk analysis of maritime accident response activities. PERT/CPM was used to analyze accident response activities and for calculating overall (expected) response activity completion time. Also, the risk based accident response support system proposed in this paper is explained using a simple case study of risk analysis for oil tanker grounding accident response.