• 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.

• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.23-29
• /
• 2021

Recently, a situation in which a specific content service is impossible worldwide has occurred due to a failure of the platform service and a significant social and economic problem has been caused in the global service market. In order to secure the stability of platform services, intelligent platform operation management is required. In this study, big data flow management(BDFM) and implementation method were proposed to quickly detect to abnormal service status in the platform operation environment. As a result of analyzing, BDFM technique improved the characteristics of abnormal failure detection by more than 30% compared to the traditional NMS. The big data flow management method has the advantage of being able to quickly detect platform system failures and abnormal service conditions, and it is expected that when connected with AI-based technology, platform management is performed intelligently and the ability to prevent and preserve failures can be greatly improved.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.817-819
• /
• 2005

내장 시스템(Embedded System)기술은, 정부가 주도하는 기술과제로 여러 응용분야에서 각광을 받고 있다. 본 논문에서는 내장 시스템이 가지는 한계상황 하에서 프로세스가 좀더 빠르게 복구하는 기법을 제안하고자 한다. 빠른 복구를 위해서는 두 가지 조건이 만족되어야 한다. 첫째 조건은 실제 프로세스의 이상이 발생 했는지를 빠르게 감지해야 한다. 기존에는 주기적으로 프로세스를 감시하는 방법들이 많이 사용되었으나 이런 방법들은 내장 시스템에서 빠른 프로세스 복구를 하는데 한계점들이 나타냈다. 따라서 시스템 레벨에서 프로세스 종료를 시키는 시그널(signal)을 훔치는(hooking) 방법[1]과 프로세스 스케줄 순서를 조정하는 방법을 토대로 프로세스의 이상을 빠르게 감지할 수 있다. 두 번째는 한정된 자원 아래서 효율적으로 복구 데이터를 관리 및 복구해야 한다. 기존의 복구 기법에 경우 다양한 자원을 대한 복구를 위해서 자원을 많이 사용하였지만 우리가 사용하는 공유메모리 기법[1]은 자신의 필요한 정보만을 관리함으로써 한정된 자원 환경에서 복구가 가능하도록 하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.199-206
• /
• 2022

A malfunction or breakdown of a manufacturing facility leads to product defects and the suspension of production lines, resulting in huge financial losses for manufacturers. Due to the spread of smart factory services, a large amount of data is being collected in factories, and AI-based research is being conducted to predict and diagnose manufacturing facility breakdowns or manufacturing site efficiency. However, because of the characteristics of manufacturing data, such as a severe class imbalance about abnormalities and ambiguous label information that distinguishes abnormalities, developing classification or anomaly detection models is highly difficult. In this paper, we present an deep learning algorithm for anomaly detection of a manufacturing facility using reconstruction loss of CNN-based model and ananlyze its performance. The algorithm detects anomalies by relying solely on normal data from the facility's manufacturing data in the exclusion of abnormal data.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.23-35
• /
• 2021

In the era of the 4th industrial revolution, smart factories have received great attention, where production and manufacturing technology and ICT converge. With the development of IoT technology and big data, automation of production systems has become possible. In the advanced manufacturing industry, production systems are subject to unscheduled performance degradation and downtime, and there is a demand to reduce safety risks by detecting and reparing potential errors as soon as possible. This study designs a model based on supervised and unsupervised learning for detecting anomalies. The accuracy of XGBoost, LightGBM, and CNN models was compared as a supervised learning analysis method. Through the evaluation index based on the confusion matrix, it was confirmed that LightGBM is most predictive (97%). In addition, as an unsupervised learning analysis method, MD, AE, and LSTM-AE models were constructed. Comparing three unsupervised learning analysis methods, the LSTM-AE model detected 75% of anomalies and showed the best performance. This study aims to contribute to the advancement of the smart factory by combining supervised and unsupervised learning techniques to accurately diagnose equipment failures and predict when abnormal situations occur, thereby laying the foundation for preemptive responses to abnormal situations. do.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.9-14
• /
• 2016

This study evaluated a digital locking device design using detection distance of 13.4mm of a human body sensing type magnetic field coil. In contrast to digital locking devices that are used nowadays, the existing serial number entering buttons, lighting, number cover, corresponding pcb, exterior case, and data delivery cables have been deleted and are only composed of control ON/OFF power switches and emergency terminals. When the magnetic field coil substrates installed inside the inner case detects the electric resistance delivered from the opposite side of the 12mm interval exterior contacting the glass body part, the corresponding induced current flows. At this time, the magnetic field coil takes the role as a sensor when coil frequency of the circular coil is transformed. The magnetic coil as a sensor detects a change in the oscillation frequency output before and after the body is detected. This is then amplified to larger than 2,000%, transformed into digital signals, and delivered to exclusive software to compare and search for embedded data. The detection time followed by the touch area of the body standard to a $12.8{\emptyset}$ magnetic field coil was 30% contrast at 0.08sec and 80% contrast at 0.03sec, in which the detection distance was 13.4mm, showing the best level.

• Convergence Security Journal
• /
• v.13 no.4
• /
• pp.27-32
• /
• 2013

In this paper, technologies applied to design urination detection device on diaper that issues an alarm signal to guardian within 10~20m are introduced. It features power saving that uses both low power bluetooth v4.0 chip and low-power program scheme that makes sensor and mirco-controller to be sleep mode while data is not receiving from sensor. Urination detection algorithm that utilizes the difference between previous sensing data and current values is used to improve the degree of the detection precision level. The device designed with the suggested technologies shows the performance that is 100ml of the minimum urine amount for detection, more than 90% of urination detection degree, and 100% of wireless communication success rate.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.73-79
• /
• 2020

As the number of earthquakes gradually increases on the Korean Peninsula, much research has been actively conducted to detect earthquakes quickly and accurately. Because traditional seismic stations are expensive to install and operate, recent research is currently being conducted to detect earthquakes using low-cost MEMS sensors. In this article, we evaluate how a low-cost MEMS acceleration sensor installed in a smartphone can be used to detect earthquakes. To this end, we installed about 280 smartphones at various locations in Korea to collect acceleration data and then assessed the installed sensors' noise floor through PSD calculation. The noise floor computed from PSD determines the magnitude of the earthquake that the installed MEMS acceleration sensors can detect. For the last few months of real operation, we collected acceleration data from 200 smartphones among 280 installed smartphones and then computed their PSDs. Based on our experiments, the MEMS acceleration sensor installed in the smartphone is capable of observing and detecting earthquakes with a magnitude 3.5 or more occurring within 10km from an epic center. During the last several months of operation, the smartphone acceleration sensor recorded an earthquake of magnitude 3.5 in Miryang on December 30, 2019, and it was confirmed as an earthquake using STA/LTA which is a simple earthquake detection algorithm. The earthquake detection system using MEMS acceleration sensors is expected to be able to detect increasing earthquakes more quickly and accurately.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.641-642
• /
• 2022

단일 데이터로부터의 이동 객체에 대한 행동 인식 연구는 데이터 수집 과정에서 발생하는 노이즈의 영향을 크게 받는다. 본 논문은 영상 데이터와 센서 데이터를 이용하여 다중 융합 네트워크 기반 이동 객체 행동 인식 방법을 제안한다. 영상으로부터 객체가 감지된 영역의 추출과 센서 데이터의 이상치 제거 및 결측치 보간을 통해 전처리된 데이터들을 융합하여 시퀀스를 생성한다. 생성된 시퀀스는 CNN(Convolutional Neural Networks)과 LSTM(Long Short Term Memory)기반 다중 융합 네트워크 모델을 통해 시계열에 따른 행동 특징들을 추출하고, 깊은 FC(Fully Connected) 계층을 통해 특징들을 융합하여 행동을 예측한다. 본 연구에서 제시된 방법은 사람을 포함한 동물, 로봇 등의 다양한 객체에 적용될 수 있다.

• Journal of the Korea Society for Simulation
• /
• v.20 no.4
• /
• pp.67-79
• /
• 2011

The statistical process control (SPC) assumes that observations follow the particular statistical distribution and they are independent to each other. However, the time-series data do not always follow the particular distribution, and most of cases are autocorrelated, therefore, it has limit to adopt the general SPC in tim series process. In this study, we propose a MPBC (Model Parameter Based Control-chart) method for fault detection in time-series processes. The MPBC builds up the process as a time-series model, and it can determine the faults by detecting changes parameters in the model. The process we analyze in the study assumes that the data follow the ARMA (p,q) model. The MPBC estimates model parameters using RLS (Recursive Least Square), and $K^2$-control chart is used for detecting out-of control process. The results of simulations support the idea that our proposed method performs better in time-series process.