• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1348-1375
• /
• 2018

Support Vector Machine (SVM) is a well-known machine learning classification algorithm, which has been widely applied to many data mining problems, with good accuracy. However, SVM classification speed decreases with increase in dataset size. Some applications, like video surveillance and intrusion detection, requires a classifier to be trained very quickly, and on large datasets. Hence, this paper introduces two filter-based instance selection techniques for optimizing SVM training speed. Fast classification is often achieved at the expense of classification accuracy, and some applications, such as phishing and spam email classifiers, are very sensitive to slight drop in classification accuracy. Hence, this paper also introduces two wrapper-based instance selection techniques for improving SVM predictive accuracy and training speed. The wrapper and filter based techniques are inspired by Cuckoo Search Algorithm and Bat Algorithm. The proposed techniques are validated on three popular e-fraud types: credit card fraud, spam email and phishing email. In addition, the proposed techniques are validated on 20 other datasets provided by UCI data repository. Moreover, statistical analysis is performed and experimental results reveals that the filter-based and wrapper-based techniques significantly improved SVM classification speed. Also, results reveal that the wrapper-based techniques improved SVM predictive accuracy in most cases.

• 한국항공우주학회지
• /
• 제44권3호
• /
• pp.256-265
• /
• 2016

소프트웨어 기반의 고장허용이란 장비의 일부분에 소프트웨어 고장이 발생하더라도 허용할 수 있도록 장비를 설계하는 것을 의미힌다. 고장허용을 위한 설계 방법은 크게 하드웨어 기반 고장허용 설계 방법과 소프트웨어 기반 고장허용 설계 방법이 있으며, 시스템의 특징에 따라 적절한 방법의 고장허용 설계 방법 선택이 필요하다. 본 논문에서는 하드웨어적으로 이중화로 구성된 비행조종컴퓨터의 소프트웨어 기반 고장허용 설계 기법에 대하여 기술하였다. 소프트웨어 기반의 고장허용 설계를 위하여 소프트웨어 고장을 분류하고, 고장에 대한 검출 방법을 설계한 후, 고장발생시 복구 방법을 설계하였다. 설계된 방법의 유효성을 확인하기 위하여 전용 소프트웨어 시험 환경을 통해 설계된 소프트웨어 기반 고장허용 설계의 타당성을 검증하였다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제15권11호
• /
• pp.4377-4384
• /
• 2014

According to the World Health Organization (WHO), 1.37 million people died of lung cancer all around the world in 2008, occupying the first place in all cancer-related deaths. However, this number might be decreased if patients were detected earlier and treated appropriately. Unfortunately, traditional imaging techniques are not sufficiently satisfactory for early detection of lung cancer because of limitations. As one alternative, breath volatile organic compounds (VOCs) may reflect the biochemical status of the body and provide clues to some diseases including lung cancer at early stage. Early detection of lung cancer based on breath analysis is becoming more and more valued because it is non-invasive, sensitive, inexpensive and simple. In this review article, we analyze the limitations of traditional imaging techniques in the early detection of lung cancer, illustrate possible mechanisms of the production of VOCs in cancerous cells, present evidence that supports the detection of such disease using breath analysis, and summarize the advances in the study of E-noses based on gas sensitive sensors. In conclusion, the analysis of breath VOCs is a better choice for the early detection of lung cancer compared to imaging techniques. We recommend a more comprehensive technique that integrates the analysis of VOCs and non-VOCs in breath. In addition, VOCs in urine may also be a trend in research on the early detection of lung cancer.

• Imaging Science in Dentistry
• /
• 제30권1호
• /
• pp.23-32
• /
• 2000

Purpose : The purpose of this study is to compare radiographic techniques for the diagnostic accuracy in the detection of osteophytes of the mandibular condyle. Material and Methods : A series of bone chips were placed at four locations on the condylar head of a dried human skull. Eight radiographic techniques such as panoramic, transcranial, infracranial, transorbital, reverse-Towne's, submentovertex, multidirectional tomographic and computed tomographic techniques were compared. Three oral radiologists were asked to rate the lesions by four stage score. The statistical analysis was performed by ANOVA test. Results: For the detection of lateral osteophyte, transcranial, infracranial, transorbital and reverse-Towne' s views showed superiority. Also, transcranial and infracranial views showed superiority for medial osteophyte. While for the detection of superior and anterior osteophyte, panoramic, transcranial, infracranial, transorbital views showed superiority. Lateral tomograph showed superiority for the detection of superior and anterior osteophyte, but it showed inferiority for lateral and medial osteophyte. And antero-posterior tomograph showed superiority for the detection of all osteophytes. Axial computed tomograph showed superiority for the detection of all osteophytes, and coronal computed tomograph showed superiority for lateral, medial and superior osteophytes. While reconstructed sagittal computed tomograph showed relatively superiority for the detection of anterior and superior osteophytes. Conclusion : The conventional radiographs can be used for the detection of bony changes of the mandibular condyle, and tomograph or computed tomograph can be used additionally when it is difficult to detect bony changes on conventional radiographs.

• 정보처리학회논문지C
• /
• 제10C권6호
• /
• pp.665-674
• /
• 2003

이 논문에서는 침입 탐지 시스템의 탐지 효율을 높이기 위해 데이터 마이닝의 클러스터링 기법을 이용하여 경보 데이터를 그룹화하고 그 결과를 이용하여 경보 데이터의 상관 관계를 분석하는 방법을 제안하였다. 즉 클러스터링 기법을 이용하여 경보데이터를 사용자가 원하는 개수의 그룹으로 분류하고, 생성된 경보 데이터 클러스터 모델을 이용하여 새로운 경보 데이터을 분류할 수 있도록 하였다. 또한, 결과 클러스터의 생성 원인이 되는 이전의 경보의 분포 데이터를 저장 관리하여 클러스터 간의 시퀀스를 생성하였고, 생성된 각각의 클러스터 시퀀스를 통합하여 클러스터들의 시퀀스를 추출하여 발생한 경보 이후의 향후 발생 가능한 경보 타입을 예측하기 위한방법을 제공하였다. 이는 과거에 탐지된 공격의 형태 뿐만 아니라 새로운 혹은 변형된 경보의 분류나 분석에도 이용 가능하다. 또한 생성된 클러스터간의 생성 원인의 분석에 의한 클러스터 간의 순차적인 관계의 추출을 통해 사용자가 공격의 순차적 구조나 탐지된 각 공격 이면에 감추어진 전략을 이해하는데 도움을 주며 현재의 경보 이후에 발생 가능한 경보들을 얘측할 수 있다.

• 전기전자학회논문지
• /
• 제25권2호
• /
• pp.330-336
• /
• 2021

하드웨어 이중화 구성 수를 줄이는 대표적인 방법은 마이크로컨트롤러로 고장을 검출, 식별 및 수용을 위한 해석적 기법으로 구현하는 것이다. 본 논문에서는 해석적 기법 중 하나인 고장 검출 필터를 항공기 터보팬 엔진 시스템에 적용하였다. 고장 검출 필터는 특수한 형태의 관측기로써 특정한 고장 발생시 잔차가 출력 공간에서 일정한 방향을 유지함으로써 고장의 위치 판별이 가능한 장점이 있다. 이에 본 논문에서는 터보팬 엔진 내 공기 터빈 시스템의 단일 입출력 동적 시스템 모델링, 고장 검출 필터 설계 및 이를 적용한 모의실험 결과를 나타내었다. 모의실험 결과를 통해 고장 검출 필터가 갖는 방향성에 대한 민감성 효과로 고장 검출이 유효하게 적용될 수 있음을 보였다.

• Journal of Information Technology Applications and Management
• /
• 제25권1호
• /
• pp.19-32
• /
• 2018

Fake news is defined as the news articles that are intentionally and verifiably false, and could mislead readers. Spread of fake news may provoke anxiety, chaos, fear, or irrational decisions of the public. Thus, detecting fake news and preventing its spread has become very important issue in our society. However, due to the huge amount of fake news produced every day, it is almost impossible to identify it by a human. Under this context, researchers have tried to develop automated fake news detection method using Artificial Intelligence techniques over the past years. But, unfortunately, there have been no prior studies proposed an automated fake news detection method for Korean news. In this study, we aim to detect Korean fake news using text mining and machine learning techniques. Our proposed method consists of two steps. In the first step, the news contents to be analyzed is convert to quantified values using various text mining techniques (Topic Modeling, TF-IDF, and so on). After that, in step 2, classifiers are trained using the values produced in step 1. As the classifiers, machine learning techniques such as multiple discriminant analysis, case based reasoning, artificial neural networks, and support vector machine can be applied. To validate the effectiveness of the proposed method, we collected 200 Korean news from Seoul National University's FactCheck (http://factcheck.snu.ac.kr). which provides with detailed analysis reports from about 20 media outlets and links to source documents for each case. Using this dataset, we will identify which text features are important as well as which classifiers are effective in detecting Korean fake news.

• 정보보호학회논문지
• /
• 제32권2호
• /
• pp.181-192
• /
• 2022

신종 악성코드의 등장은 기존 시그니처 기반의 악성코드 탐지 기법들을 무력화시키며 여러 분석 방지 보호 기법들을 활용하여 분석가들의 분석을 어렵게 하고 있다. 시그니처 기반의 기존 연구는 악성코드 제작자가 쉽게 우회할 수 있는 한계점을 지닌다. 따라서 본 연구에서는 악성코드 자체의 특성이 아닌, 악성코드에 적용될 수 있는 패커의 특성을 활용하여, 단시간 내에 악성코드에 적용된 패커의 분석 방지 보호 기법을 탐지하고 분류해낼 수 있는 머신러닝 모델을 구축하고자 한다. 본 연구에서는 패커의 분석 방지 보호 기법을 적용한 악성코드 바이너리를 대상으로 n-gram opcode를 추출하여 TF-IDF를 활용함으로써 피처(feature)를 추출하고 이를 통해 각 분석 방지 보호 기법을 탐지하고 분류해내는 머신러닝 모델 구축 방법을 제안한다. 본 연구에서는 실제 악성코드를 대상으로 악성코드 패킹에 많이 사용되는 상용 패커인 Themida와 VMProtect로 각각 분석 방지 보호 기법을 적용시켜 데이터셋을 구축한 뒤, 6개의 머신러닝 모델로 실험을 진행하였고, Themida에 대해서는 81.25%의 정확도를, VMProtect에 대해서는 95.65%의 정확도를 보여주는 최적의 모델을 구축하였다.

• Journal of Biosystems Engineering
• /
• 제41권2호
• /
• pp.138-144
• /
• 2016

Purpose: Phosphorus is an essential element for water quality control. Excessive amounts of phosphorus causes algal bloom in water, which leads to eutrophication and a decline in water quality. It is necessary to maintain the optimum amount of phosphorus present. During the last decades, various studies have been conducted to determine phosphorus content in water. In this study, we present a comprehensive overview of colorimetric, electrochemical, fluorescence, microfluidic, and remote sensing technologies for the measurement of phosphorus in water, along with their working principles and limitations. Results: The colorimetric techniques determine the concentration of phosphorus through the use of color-generating reagents. This is specific to a single chemical species and inexpensive to use. The electrochemical techniques operate by using a reaction of the analyte of interest to generate an electrical signal that is proportional to the sample analyte concentration. They show a good linear output, good repeatability, and a high detection capacity. The fluorescence technique is a kind of spectroscopic analysis method. The particles in the sample are excited by irradiation at a specific wavelength, emitting radiation of a different wavelength. It is possible to use this for quantitative and qualitative analysis of the target analyte. The microfluidic techniques incorporate several features to control chemical reactions in a micro device of low sample volume and reagent consumption. They are cheap and rapid methods for the detection of phosphorus in water. The remote sensing technique analyzes the sample for the target analyte using an optical technique, but without direct contact. It can cover a wider area than the other techniques mentioned in this review. Conclusion: It is concluded that the sensing technologies reviewed in this study are promising for rapid detection of phosphorus in water. The measurement range and sensitivity of the sensors have been greatly improved recently.

• Journal of Power Electronics
• /
• 제8권2호
• /
• pp.181-191
• /
• 2008

The task performed by induction motors grows increasingly complex in modern industry and hence improvements are sought in the field of fault diagnosis. It is essential to diagnose faults at their very inception, as unscheduled machine down time can upset critical dead lines and cause heavy financial losses. Artificial intelligence (AI) techniques have proved their ability in detection of incipient faults in electrical machines. This paper presents an application of AI techniques for the detection of inter-turn insulation and bearing wear faults in single-phase induction motors. The single-phase induction motor is considered a proto type model to create inter-turn insulation and bearing wear faults. The experimental data for motor intake current, rotor speed, stator winding temperature, bearing temperature and noise of the motor under running condition was generated in the laboratory. The different types of fault detectors were developed based upon three different AI techniques. The input parameters for these detectors were varied from two to five sequentially. The comparisons were made and the best fault detector was determined.