• Journal of Internet Computing and Services
• /
• v.12 no.3
• /
• pp.1-16
• /
• 2011

In this paper, we proposed the Failure-Diagnostic Context-awareness Middleware (FDCM) for improving the reliability in the USN application service. The middleware diagnoses the failure occurred in sensors or facilities in the indoor USN application system. The new middleware suggested in this paper consists of DataManagement module, ContextProvider module, Contextlnterpreter module, ServiceProvider module and DataStorage module. By analysing the data obtained by the interaction between modules through the diagnostic algorithm, the FDCM determines the malfunction of sensors and equipment devices. Then we verified the performance of middleware by using simulation. As a result, the FDCM showed the high performance in the large systems that many of the sensors and devices are installed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.135-136
• /
• 2019

센서 데이터의 발전에 따라 자율주행 자동차 산업도 급격히 성장하고 있다. 미국 우버(UBER)는 2015년부터 자율주행 자동차 산업에 뛰어들었고, 국내에서도 '판교 자율주행 셔틀'이 시범운행 되었다. 따라서 자율주행 자동차는 앞으로 우리 삶에 보다 많은 영향을 끼칠 것이 분명하나, 아직 자율주행 자동차가 완벽하게 개발되지 않은 만큼 우리가 예상하지 못한 교통사고 등 새로운 문제가 나타날 위험이 있다. 따라서 본 논문은 자율주행 자동차에 대해 살펴보고 사고 사례를 분석하여 앞으로 나타날 수 있는 사고 유형을 예측하는 것에 목적이 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.141-151
• /
• 2011

This paper suggests the Facility Management System for plant factory promising to be a core technology of the agriculture in the future. This system makes diagnoses that status from sensors or facilities in the factory for exact operation and monitors the internal environment with the control status in real-time. It is expected that we could operate a plant factory safely and effectively by using the system. The system consists of the data management module, the context provider module, the context interpreter module, the service provider module, the data storage and user interface. The system provide with the failure diagnosis service, the facility control service, and the high-reliability monitoring service via the interactions between above modules. The failure diagnosis service determines whether the sensors or facility devices are in failure or not, and informs the administrator of their conditions. The facility control service is activated in case if the facilities need to be managed during the diagnosis for failure or malfunction processes. The high-reliability monitoring service provides the administrator with verified data through the failure diagnosis service. Then we confirmed that the suggested system operates correctly through the system simulation.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.644-649
• /
• 2022

대화 시스템은 훈련 중 보지 못한 데이터를 입력받았을 경우 오작동의 가능성이 높으며, 특히 상용화 시에는 작은 오작동이라도 치명적인 결과를 낳을 수 있다. 따라서 시스템의 안정성을 확보하기 위해 우리는 대화 시스템에 사용자 입력의 적절성을 분류하는 기능을 탑재하였다. 해당 기능을 훈련시키기 위해서 우리는 슬롯-밸류쌍에서 슬롯을 교체하는 방법과 밸류를 교체하는 방법을 나누어 제시하였다. 슬롯을 무작위로 교체할 경우 발생하는 노이즈를 완화시키기 위해 새로운 추출 방법을 제시하였으며, 밸류를 교체할 때도 이 때 훈련시킨 모델을 이용하여 위음성의 가능성을 최소화하였다. 또한 전후방 철자 교정 모듈을 도입하여 사용자의 실수로 인한 모델의 오작동도 방지하고자 하였다. 우리는 다른 방법론과의 비교 실험과 절제 실험을 통해 각각의 방법론의 효용성을 입증하였다.

• Review of KIISC
• /
• v.30 no.5
• /
• pp.71-77
• /
• 2020

딥러닝 기술은 이미지 분류 문제에 뛰어난 성능을 보여주지만, 공격자가 입력 데이터를 조작하여 의도적으로 오작동을 일으키는 적대적 공격(adversarial attack)에 취약하다. 최근 이미지에 직접 스티커를 부착하는 형태로 딥러닝 모델의 오작동을 일으키는 적대적 패치(adversarial patch)에 관한 연구가 활발히 진행되고 있다. 하지만 기존의 적대적 패치는 대부분 눈에 잘 띄기 때문에 실제 공격을 받은 상황에서 쉽게 식별하여 대응할 수 있다는 단점이 있다. 본 연구에서는 GAN(Generative Adversarial Networks)을 이용하여 식별하기 어려운 적대적 패치를 생성하는 기법을 제안한다. 실험을 통해 제안하는 방법으로 생성한 적대적 패치를 이미지에 부착하여 기존 이미지와의 구조적 유사도를 확인하고 이미지 분류모델에 대한 공격 성능을 분석한다.

• Journal of Korea Game Society
• /
• v.21 no.1
• /
• pp.55-66
• /
• 2021

Multi-thread programming is essential in high performance game programming. But, the widely used C++11 shared_ptr and weak_ptr have malfunction and performance problems in multi-thread environments. In this paper, we propose Lock-Free shared_ptr and weak_ptr, which have higher performance than current error preventing methods. These use a non-blocking algorithm to prevent data race in multi-thread environments. As a result of experimenting in an 8 thread environment, performance has improved up to 7424% in a situation where competition between threads is low, and 3767% in high competition.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.113-120
• /
• 2018

In this study, we proposed a monitoring system for identifying and handling faulty sensing stream data on manufacturing equipments where low-cost sensors can be safely used. Low cost sensors will lessen the cost of implementing distributed monitoring system, but suffer from sensor noises and inaccurate sensed data. Therefore, a distributed monitoring system with low cost sensors should identify faulty signal data as either of sensor fault or machine fault, and filter out faulty signals from sensing fault. To this end, we adopted a fourier transform based diagnostic approach mixed with a weighed moving averaging method, in order to identify faulty signals. We measured how effective our approach is and found out our approach can filter out one-third faulty signals from our experimental environment. In addition, we attached wireless communication modules to reduce sensor and network installation cost. To handle massive sensor data efficiently, we employed unstructured data format with NoSQL based database.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 2000.11a
• /
• pp.68-75
• /
• 2000

지금까지는 전자파의 위험성으로 인체 유해성 문제와 기기의 오작동에 대해서는 널리 알려져 왔으나, 전자파의 유기에 의한 감전 및 점화 위험성에 대해서는 국내에서 그다지 인지하지 못하고 있는 실정에 있었다. 그러나 이러한 전자파중 고주파 방사에 의한 감전 및 점화 위험성은 수신안테나로 작용하는 금속성 구조물의 종류가 다양하기 때문에 이에 따른 전기적인 등가회로도 각각 달라 현장에서 일일이 측정한 데이터를 사용하는 시뮬레이션 및 실험이 필요하다. (중략)

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.2
• /
• pp.79-94
• /
• 2021

A GNSS receiver installed in autonomous vehicles is the most essential device for its navigation. However, if an intentional jamming signal is generated, there is a risk of exposure to an accident risk due to deterioration of the GNSS sensor's performance. Research is required to prevent this, and accordingly, a jamming generating device must be provided. However, according to the provisions of the law related to jamming, this is illegal. In this paper, we implement an in-vehicle jamming device that complies with the provisions of the law and does not affect the surrounding GNSS sensors. Driving simulation is used to evaluate the performance of the GNSS algorithm, and the malfunction of autonomous vehicles occurring in the interference environment and data errors output from the GNSS sensor are analyzed.

• Journal of Platform Technology
• /
• v.9 no.1
• /
• pp.23-31
• /
• 2021

In recent years, in the domestic industry, personal damage has occurred due to sensor malfunction and the emission of harmful gases. But there is a limit to the reliability verification of sensor data because the evaluation of environmental sensors is focused on durability and risk tests. This platform designed a sensor board that measures 10 major substances and a performance verification system for each sensor. In addition, the data collected by the sensor board was transferred to the server for data reliability evaluation and verification using LoRa communication, and a prototype of the sensor data platform was produced to monitor the transferred data. And the collected data is analyzed and predicted by using machine learning techniques.