• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.89-92
• /
• 2021

In a manufacturing fields, an abnormality or breakdown of equipment is a factor that causes product defects. Recently, with the spread of smart factory services, a lot of research to predict and prevent machine's failures is actively ongoing. However, there is a big difficulty in developing a classification model because the number of abnormal or failure data of the machine is severely smaller than normal data. In this paper, we present an algorithm for detecting abnormalities in an MCT at manufacturing work site depending on the differences between inputs and outputs of Autoencoder model and analyze its performance. The algorithm detects abnormalities using only features of normal data from manufacturing data of the MCT in which abnormal data does not exist.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.465-472
• /
• 2021

In this paper, we present an approach for detection of adverse drug reactions from drug reviews to compensate limitations of the spontaneous adverse drug reactions reporting system. Considering negative reviews usually contain adverse drug reactions, sentiment analysis on drug reviews was performed and extracted negative reviews. After then, MedDRA dictionary and named entity recognition were applied to the negative reviews to detect adverse drug reactions. For the experiment, drug reviews of Celecoxib, Naproxen, and Ibuprofen from 5 drug review sites, and analyzed. Our results showed that detection of adverse drug reactions is able to compensate to limitation of under-reporting in the spontaneous adverse drugs reactions reporting system.

• Journal of Internet Computing and Services
• /
• v.6 no.5
• /
• pp.45-56
• /
• 2005

The weak foundation of the computing environment caused information leakage and hacking to be uncontrollable, Therefore, dynamic control of security threats and real-time reaction to identical or similar types of accidents after intrusion are considered to be important, h one of the solutions to solve the problem, studies on intrusion detection systems are actively being conducted. To improve the anomaly IDS using system calls, this study focuses on neural networks learning using the soundex algorithm which is designed to change feature selection and variable length data into a fixed length learning pattern, That Is, by changing variable length sequential system call data into a fixed iength behavior pattern using the soundex algorithm, this study conducted neural networks learning by using a backpropagation algorithm. The backpropagation neural networks technique is applied for anomaly detection of system calls using Sendmail Data of UNM to demonstrate its performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.5
• /
• pp.953-959
• /
• 2012

There are a number of idle nodes in sensor networks, these can act as detector nodes for anomaly detection in the network. For detecting node selection problem modeled as optimization equation, the conventional method using centralized genetic algorithm was evaluated. In this paper, a method to improve the convergence of the optimal value, while improving energy efficiency as a method of considering the characteristics of the network topology using parallel genetic algorithm is proposed. Through simulation, the proposed method compared with the conventional approaches to the convergence of the optimal value was improved and was found to be energy efficient.

• Proceedings of the KSEEG Conference
• /
• 1999.04a
• /
• pp.80-85
• /
• 1999

본 연구에서는 토목분야에서 중요한 문제가 되는 기초 파일의 깊이 탐지와 관련하여 시추공 자력탐사의 적용성을 확인하기 위하여 시추공 자력탐사 모형 반응 계산 및 역산 알고리즘을 개발하였다. 모형 반응 계산은 시추공 자력탐사에 적합하고 삼성분 이상을 계산할 수 있도록 기존의 방법을 수정하였으며, 역산 알고리즘은 일반적인 자력탐사 자료 역산의 불안정성을 고려하여 광역적 최적화 기법의 하나임 ASA(Adaptive Simulated Annealing : Ingber, 1993)를 이용하였다. 개발된 모형 반응 및 역산 알고리즘을 간단한 모형 및 합성자료에 대해 적용한 결과 그 타당성을 검증할 수 있었다. 또한 실제 현장에서 부딪힐 수 있는 무작위 잡음을 첨가한 자료, 주변 파일의 영향 및 지표 구조물에 의한 영향을 고려한 복잡한 모형에 대해 기초 파일의 깊이를 탐지해 낼 수 있었으며, 이를 토대로 실제 현장 적용시 고려해야할 현장지침에 대해서도 고찰할 수 있었다. 마지막으로 실제 현장자료에 적용한 결과 실제 파일의 깊이를 역산해 낼 수 있음을 확인함으로써, 기초 파일의 깊이 탐지를 위한 시추공 자력탐사의 적용성 및 본 알고리즘의 현장 적용성을 확인할 수 있었다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.5 no.3
• /
• pp.158-163
• /
• 2012

This paper proposes an FHIDS(Fuzzy logic based Hybrid Intrusion Detection System) design that detects anomaly and misuse attacks by using a Naive Bayesian algorithm, Data Mining, and Fuzzy Logic. The NB-AAD(Naive Bayesian based Anomaly Attack Detection) technique using a Naive Bayesian algorithm within the FHIDS detects anomaly attacks. The DM-MAD(Data Mining based Misuse Attack Detection) technique using Data Mining within it analyzes the correlation rules among packets and detects new attacks or transformed attacks by generating the new rule-based patterns or by extracting the transformed rule-based patterns. The FLD(Fuzzy Logic based Decision) technique within it judges the attacks by using the result of the NB-AAD and DM-MAD. Therefore, the FHIDS is the hybrid attack detection system that improves a transformed attack detection ratio, and reduces False Positive ratio by making it possible to detect anomaly and misuse attacks.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.3
• /
• pp.449-458
• /
• 2011

Illegal waste dumping is one of the major problems that the government agency monitoring water quality has to face. Recently government agency installed COD (chemical oxygen demand) auto-monitering machines in river. In this article we provide an outlier detection algorithm using R based on the time series intervention model that detects some outlier values among those COD time series values generated from an auto-monitering machine. Through this algorithm using R, we can achieve an automatic algorithm that does not need manual intervention in each step, and that can further be used in simulation study.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.11a
• /
• pp.185-187
• /
• 2023

고장 진단은 IoT 장비의 안전성과 효율성을 유지하는데 필요한 기술 중 하나이다. 따라서, 본 연구는 IoT 센서 데이터를 기반한 고장 진단 알고리즘을 개발하는데 목적이 있다. 본 연구는 알고리즘의 효율성을 개선하기 위해 기술통계량을 기반하여 데이터 차원을 축소하였으며, 이를 바탕으로 고장 진단 알고리즘의 정확도 및 연산시간을 개선하였다. 본 연구는 다양한 후보 알고리즘을 활용하여 고장진단을 수행하였으며, 정확도를 기반으로 가장 우수한 알고리즘을 선정하였다. 연구 결과, Isolation Forest 알고리즘이 가장 뛰어난 분류 결과를 나타내었다. 본 연구결과를 통해 IoT 센서의 안전성과 신뢰성을 향상시키는 데 도움을 줄 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.970-972
• /
• 2004

최근 들어 웜 바이러스의 출현과 더불어, 인터넷 대란과 같은 서비스 거부 공격의 피해 사례가 급증하고 있다. 이에 따라 네트워크 보안이 많은 관심을 받고 있는데, 보안의 여러 분야 가운데에서도 특히 침입탐지와 대응에 관한 연구가 활발히 이루어지고 있다. 또한 이러한 작업들을 자동화하기 위한 도구들이 개발되고 있지만 그 정확성이 아직 신뢰할 만한 수준에 이르지 못하고 있는 것이 지금의 현실이다. 본 논문에서는 이벤트 로그를 분석하여 침입 패턴을 예측하고, 이를 기반으로 자동화된 침입 탐지 및 대응을 구현할 수 있는 String Matching 알고리즘을 제안하고자 한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.3
• /
• pp.233-238
• /
• 2016

In this paper, we propose the algorithms of processing the uncertainty data using data fusion for the next generation intrusion detection. In the next generation intrusion detection, a lot of data are collected by many of network sensors to discover knowledge from generating information in cyber space. It is necessary the data fusion process to extract knowledge from collected sensors data. In this paper, we have proposed method to represent the uncertainty data, by classifying where is a confidence interval in interval of uncertainty data through feature analysis of different data using inference method with Dempster-Shafer Evidence Theory. In this paper, we have implemented a detection experiment that is classified by the confidence interval using IRIS plant Data Set for anomaly detection of uncertainty data. As a result, we found that it is possible to classify data by confidence interval.