• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.207-216
• /
• 2024

As big data was built due to the 4th Industrial Revolution, personalized services increased rapidly. As a result, the amount of personal information collected from online services has increased, and concerns about users' personal information leakage and privacy infringement have increased. Online service providers provide privacy policies to address concerns about privacy infringement of users, but privacy policies are often misused due to the long and complex problem that it is difficult for users to directly identify risk items. Therefore, there is a need for a method that can automatically check whether the privacy policy is safe. However, the safety verification technique of the conventional blacklist and machine learning-based privacy policy has a problem that is difficult to expand or has low accessibility. In this paper, to solve the problem, we propose a safety verification technique for the privacy policy using the GPT-3.5 API, which is a generative artificial intelligence. Classification work can be performed evenin a new environment, and it shows the possibility that the general public without expertise can easily inspect the privacy policy. In the experiment, how accurately the blacklist-based privacy policy and the GPT-based privacy policy classify safe and unsafe sentences and the time spent on classification was measured. According to the experimental results, the proposed technique showed 10.34% higher accuracy on average than the conventional blacklist-based sentence safety verification technique.

• 대한공업교육학회지
• /
• v.42 no.1
• /
• pp.1-29
• /
• 2017

The purpose of this study was to investigate the vocational identity through the reflection of the major experience as the teacher through the life history of the technical high school. In order to achieve the purpose of this study, two technical high school mechanical and career teachers were selected as research participants and in-depth interviews were conducted with them. The data obtained through the in-depth interviews were analyzed through six steps. Six major experiences of the participants were identified as results of the research: (1) the experience of trying to train the specialist of precision machining in the beginning of teacher's life, (2) experience as a skill competition team teacher, (3) experience of innovating public education by introducing new industry field, (4) experience of constant learning new field and sharing with colleagues, (5) experience in the rapid change of the status of technical high school, (6) experience in the prevention of students' safety accidents and maintenance of the practice field. Through these educational experiences, each research participant was forming one's vocational identity as a mechanical teacher. The vocational identity of the research participants were identified as follows: (1) identity drifting phase, (2) identity stability stage, (3) transition stage of the teacher role, (4) suspended stage to preserve identity, (5) identification sublimation stage, (6) identification of the true meaning of the teacher, and integration of the identity. Through these six steps, their identities were formed, strengthened and changed at each stage.

• Journal of Practical Engineering Education
• /
• v.16 no.4
• /
• pp.529-540
• /
• 2024

In industrial sites, experiential virtual training contents are partially used to replace high-risk and high-cost training, and virtual training contents development is also becoming active along with the increasing demand for non-face-to-face industries. Existing studies mainly focused on quantitative research through surveys, and only measured the change in users' learning commitment. This study attempted to investigate the effect of the combination of theoretical education and virtual training on the improvement of actual job performance in a dual vocational training environment by conducting an experimental study. This study studied whether the combination of theoretical education and virtual training can improve the performance of vocational training in dual vocational training (comparative work and learning) in which companies and schools participate. The results of pre- and post-evaluation of vocational training using traditional vocational training and virtual training contents were compared with 24 vocational training trainees. As a result of the study, it was demonstrated that the outcome of virtual training education was higher than that of traditional vocational training, and the combination of virtual reality-based education was more effective in theoretical education. This study suggests that the virtual training content presents a new paradigm for industrial safety education, and through the interview results of trainees, it was confirmed that virtual training can lead to a change in attitude toward safety beyond just knowledge transfer. This contributes to the prevention of safety accidents in industrial sites and provides important implications for improving the quality of vocational training.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.33-42
• /
• 2016

Recently, the investment and study competition regarding machine running is accelerating mainly with Google, Amazon, Microsoft and other leading companies in the field of artificial intelligence. The security weakness of virtualization technology security structure have been a serious issue continuously. Also, in most cases, the internal data security depend on the virtualization security technology of platform provider. This is because the existing software, hardware security technology is hard to access to the field of virtualization and the efficiency of data analysis and processing in security function is relatively low. This thesis have applied user significant information to machine learning algorithm, created security authentication vector able to learn to provide with a method which the security authentication can be conducted in the field of virtualization. As the result of performance analysis, the interior transmission efficiency of authentication vector in virtualization environment, high efficiency of operation method, and safety regarding the major formation parameter were demonstrated.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.647-656
• /
• 2020

Recently, there has been an increasing number of cases in which important data (personal information, technology, etc.) of national and public institutions are leaked to the outside world. Surveys show that the largest cause of such leakage accidents is "insiders." Insiders of organization with the most authority can cause more damage than technology leaks caused by external attacks due to the organization. This is due to the characteristics of insiders who have relatively easy access to the organization's major assets. This study aims to present an optimized property selection model for detecting such abnormalities through supervised learning algorithms among machine learning techniques using actual data such as CrossNet data transfer system transmission log, e-mail transmission log, and personnel information, which safely transmits data between separate areas (security area and non-security area) of the business network and the Internet network.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.423-432
• /
• 2022

This paper addresses the safety concern that the SOH of batteries in electric vehicles decreases sharply when drivers change or their driving patterns change. Such a change can overload the battery, reduce the battery life, and induce safety issues. This paper aims to present the SOH as the changes on a dashboard of an electric vehicle in real-time in response to user pattern changes. As part of the training process I used battery data among the datasets provided by NASA, and built models incorporating linear regression and ARIMA, and predicted new battery data that contained user changes based on previously trained models. Therefore, as a result of the prediction, the linear regression is better at predicting some changes in SOH based on the user's pattern change if we have more battery datasets with a wide range of independent values. The ARIMA model can be used if we only have battery datasets with SOH data.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.103-113
• /
• 2023

In recent years, Unmanned Aerial Vehicles (UAV) have been widely used in various industries. However, as the depend ence on UAV increases rapidly, concerns about the security and safety of UAV are growing. Currently, various vulnerabili ties such as stealing the control right of the UAV or the right to communicate with the UAV in the web application are being disclosed. However, there is a lack of research related to the security of UAV. Therefore, in this paper, a study was conducted to determine whether the packet data was normal or abnormal by collecting packet data of an unmanned aerial vehicle in a HITL(Hardware In The Loop) simulation environment similar to the real environment. In addition, this paper proposes a method for reducing computational cost in the modeling process and increasing the ease of data interpretation, a machine learning-based anomaly detection model that detects abnormal data by learning only normal data, and optimized hyperparameter values.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.101-102
• /
• 2019

산업용 IoT (IIoT)는 최근들어 제조 시스템의 중요한 구성 요소로 간주된다. IIoT를 통해 시설에서 감지된 데이터를 수집하여 작동 조건을 적절하게 분석하고 처리한다. 여기서 비정상적인 데이터는 전체 시스템의 안전성 및 생산성을 위해 신속하게 탐지되어야한다. 기존 임계 값 기반 방법은 임계 값 미만의 유휴 오류 또는 비정상적인 동작을 감지 할 수 없으므로 IIoT에 적합하지 않다. 본 논문에서는 예측 구간과 우선 순위기반 스케줄링을 이용한 분할 선형 회귀 분석을 기반으로 비정상적인 데이터를 검출하는 새로운 방법을 제안한다. 시뮬레이션 결과 제안한 기법은 비정상적인 데이터 검출 속도에서 임계치, 일반 선형 회귀 또는 FCFS 정책을 사용하는 기존의 기법보다 우수함을 알 수 있었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.317-320
• /
• 2021

본 연구는 주기적인 알츠하이머 병의 중증도 모니터링을 위해 스마트 인솔을 통한 보행 특징 추출과 머신러닝 기반 중증도 분류의 성능에 대해 살펴보았다. 최근 고령화가 가속화되는 추세에 있어 치매 환자가 급증하고 있으며, 중증도가 심해질수록 필요한 치료 비용 및 노력이 급증하기 때문에 조기 진단이 최선의 치료 전략으로 보여진다. 환자 친화적이고 저비용의 관성 측정 장치가 내장된 스마트 인솔만을 사용하여 다양한 보행 실험 패러다임에서 환자의 보행 특징을 추출하고, 이를 알츠하이머 병의 중증도 진단을 위한 머신러닝 기반 분류기를 훈련시켜 성능을 평가한 결과, 숫자세기와 같이 뇌에 부하를 주는 하위 작업이 포함된 복합 보행을 측정한 데이터셋을 사용하여 훈련된 분류 모델이 일반 걷기 데이터셋을 사용한 모델보다 성능이 높게 나타나는 것이 관찰되었다. 본 연구는 안전하고 환경적 제약이 적은 방법을 사용하여 시기 적절한 진단뿐만 아니라 주기적인 중증도 모니터링 시스템의 일환으로 활용될 수 있을 것이다.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.28 no.5
• /
• pp.257-266
• /
• 2024

Due to seismically deficient details, existing reinforced concrete structures have low lateral resistance capacities. Since these building structures suffer an increase in axial loads to the main structural element due to the green retrofit (e.g., energy equipment/device, roof garden) for CO₂ reduction and vertical extension, building capacities are reduced. This paper proposes a machine-learning-based methodology for allowable ranges of axial loading ratio to reinforced concrete columns using simple structural details. The methodology consists of a two-step procedure: (1) a machine-learning-based failure detection model and (2) column damage limits proposed by previous researchers. To demonstrate this proposed method, the existing building structure built in the 1990s was selected, and the allowable range for the target structure was computed for exterior and interior columns.