• 해양환경안전학회지
• /
• 제25권1호
• /
• pp.111-116
• /
• 2019

선박의 기관실에서 사용하고 있는 화재 검출기는 연기나 열이 검출기에 도달해야 하지만 기관실의 공기 흐름은 기기의 사용유무에 따라 매우 유동적이기 때문에 상부에 설치된 검출기에 도달하기에는 많은 시간이 필요하다. 이러한 단점을 보완하기 위해 근래에는 영상을 기반으로 화재를 검지하는 연구가 이루어지고 있다. 영상기반의 연기 검지는 공기의 흐름에 영향을 받지 않으며 전송속도가 빠르기 때문에 화재의 초기 검지에 효율적이다. 본 연구는 기관실에서 연기 발생기로 발생시킨 연기의 확산모습을 녹화한 영상으로 실험을 수행하였다. 연기의 질감특징을 추출하는 LBP와 GLCM연산자를 사용하여 생성된 학습 데이터를 기계학습 분류기인 SVM으로 학습한 후 분류하여 검출 성능을 평가함으로서 연기가 상부에 설치되어 있는 검출기까지 상승하지 않더라도 영상기반으로 먼저 검지 가능함을 확인하였다.

• 한국안전학회지
• /
• 제37권4호
• /
• pp.20-27
• /
• 2022

This article aims to develop an algorithm that detects fire pump defects by analyzing the current signals of an induction motor, which are triggered by changes in the flow rate and pressure of multistage volute pumps that are used for fire services. The operational status of the pumps was categorized into three: first, normal operation; second, a defect that is caused by a change in the current value; and third, a defect occasioned by a change in current, pressure, and flow rate. When a fire pump was in normal operation, the motor's operating current was measured between 5.06 A and 6.9 A, the flow rate was estimated at 0-0.27 m³/min, and the pressure ranged from 0 to 0.47 MPa. In the event that a defect was caused by an abnormal current value in the motor, it was attributed to the pump's adherence. Furthermore, if there was no source of water, the defect was considered to have been induced by phase-loss operation, no-load operation, or run-stop operation, with the current value of each scenario being measured at > 52.8 A, < 4.13 A, > 45.15 A, and < 3.8 A, respectively, placing its overall range between 0 and 50 A. The sources of defects were detected based on an analysis of the flow rate, pressure, and current, which represent the following causes: air inflow into the casing, inadequate suction of water, and reverse-phase operation, respectively. Each cause entailed the following values: when air seeped into the casing, the pressure was measured at 0.24 MPa irrespective of changes in the flow rate; when there was inadequate suction of water, the pressure was recorded between 0 and 0.05 MPa despite changes in the flow rate; and when the power line's reverse-phase loss was the cause of the defect, the pressure was measured at 0.33 MPa for a flow rate of 0 L/min, and a higher flow rate decreased the pressure to nearly 0 MPa. The results of this study will enable engineers to develop a pump defect detection algorithm that is based on an analysis of current, and this algorithm will facilitate the execution of a program that will control a fire pump defect detection system.

• 한국환경보건학회지
• /
• 제22권1호
• /
• pp.36-44
• /
• 1996

A comparison was made of two detection methods(UV absorbence detection and fluorescence detection with pre-column derivatization, with trifluoroacetic acid) coupled with HPLC for the simultaneous determination of aflatoxin $B_1, B_2, G_1$ and $G_2$. A good separation of the four aflatoxins was achieved on a reversed-phase $C_{18}$ column (30 cm x 3.9 mm) with methanol-acetonitrile-water(20+20+60) for absorbence detection or acetonitrile-water(25+75) for fluorescence detection at the flow rate of 1.0 ml/min. The calibration graphs were linear over the ranges 100 ppb-1 ppm for $B_1/G_1$ and 30~300 ppb for $B_2/G_1$ with absorbence detection, and 1~500 ppb for $B_1/G_1$ and 0.3~150 ppb for $B_2/G_2$ with fluorescence detection. The correlation coefficients were greater than 0.94 and 0.99 for absorbance detection and for fluorescence detection, respectively. The detection limit was 100 ng for $B_1/G_1$ and 30 ng for $B_2/G_2$ with absorbence detection, and 1 ng for $B_1/G_1$ and 0.3 ng for $B_2/G_2$ with fluorescence detection. Recovery rates of aflatoxin $B_1, B_2, G_1$ and $G_2$ added to yeast-extract sucrose broth medium were 66.6%, 59.4%, 67.5% and 59.2%, respectively, for absorbence detection and 82.9%, 71.5%, 80.0% and 69.3%, respectively, for fluorescence detection. The four aflatoxins in culture medium were quantitatively detected by the two methods. The aflatoxins in the rice sample were not detected the absorbence detection method, but were below 10 ppb using the fluorescence detection method. Analysis of aflatoxins by both the absorbence and fluorescence methods coupled with HPLC showed acceptable linearity and good recovery. The absorbence detection was less timeconsuming and safer for treatment. The fluorescence detection was more elective and sensitive though elevated $B_1$ and $G_1$ contents were determined from the TFA-induced conversion of $B_1$ to $B_{2a}$ and $G_1$ to $G_{2a}$.

• 한국ITS학회 논문지
• /
• 제11권2호
• /
• pp.29-38
• /
• 2012

검지기 자료의 품질은 동일한 교통 조건이라도 검지기의 종류, 보정 및 유지 보수의 노력, 도로의 기하구조 등에 의해 내재적으로 10% 이상 변수 값 차이를 보일 수 있다. 이러한 내재적인 변수 값 차이로 인해 성능이 검증된 돌발상황 자동감지알고리즘을 사용하더라도 검지율(DR)이 낮아지고 오보율(FAR)이 높아지는 문제가 야기될 수 있다. 본 연구는 교통특성 변수의 간단한 산술계산기법(SAO)를 활용하여 새로운 AIDA를 개발하는데 목적이 있다. SAO는 내재적으로 존재하는 변수 값 차이를 보정하여 AIDA의 성능 저하를 극복하기 위해 개발되었다. AIDA 모형의 개발 및 검증을 위해 내부순환도로와 경부고속도로에서 수집된 30초 단위의 점유율을 사용하였다. SAO 기반 알고리즘 분석 결과 100% 돌발상황을 검지하는 높은 검지율을 보였고, 검지시간(MTTD)은 1분 이내로 나타났다. 오보율의 경우 본 연구에서 개발된 SAO 기반 AIDA의 오보율이 기개발된 AIDA의 오보율보다 3.5%~31.0% 감소하는 것을 확인하였다. SAO 기반의 알고리즘은 돌발상황의 지속성 분석에서도 탁월한 능력을 보였다.

• 한국멀티미디어학회논문지
• /
• 제16권6호
• /
• pp.735-745
• /
• 2013

The emergence of Web 2.0 technologies, such as blogs and wiki, enable even naive users to easily create and share content on the Web using freely available content sharing tools. Wide availability of almost free data and promiscuous sharing of content through social networking platforms created a content borrowing phenomenon, where the same content appears (in many cases in the form of extensive quotations) in different outlets. An immediate side effect of this phenomenon is that identifying which content is re-used by whom is becoming a critical tool in social network analysis, including expert identification and analysis of information flow. Internet-scale reuse detection, however, poses extremely challenging scalability issues: considering the large size of user created data on the web, it is essential that the techniques developed for content-reuse detection should be fast and scalable. Thus, in this paper, we propose a $qSign_{lsh}$ algorithm, a mechanism for identifying multi-sentence content reuse among documents by efficiently combining sentence-level evidences. The experiment results show that $qSign_{lsh}$ significantly improves the reuse detection speed and provides high recall.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2003년도 춘계학술대회논문집
• /
• pp.749-754
• /
• 2003

In this paper, we introduce the measurement of the underwater noise with 32channel hydrophone array of Samsung CAvitation Tunnel (SCAT) and the detection technique of noise sources by using the beam-forming method. Measurement and way signal Processing under fluid flow are essential works for the underwater acoustics, especially for the detection of noise sources. As the acoustic impedance of the water is relatively high and the tunnel is an enclosed system, we have to consider the interaction between tunnel and water together with the reflection of noise in the beam-forming technique. Also, for a hydrophone array system that is fixed on one side of tunnel wall as done in SCAT is liable to suffer from some limitations in the detection of the noise sources with the array, we discuss these limitations particularly on the frequency range and spacing of noise sources.

• ETRI Journal
• /
• 제41권5호
• /
• pp.560-573
• /
• 2019

Two supervised learning algorithms, a basic neural network and a long short-term memory recurrent neural network, are applied to traffic including DDoS attacks. The joint effects of preprocessing methods and hyperparameters for machine learning on performance are investigated. Values representing attack characteristics are extracted from datasets and preprocessed by two methods. Binary classification and two optimizers are used. Some hyperparameters are obtained exhaustively for fast and accurate detection, while others are fixed with constants to account for performance and data characteristics. An experiment is performed via TensorFlow on three traffic datasets. Three scenarios are considered to investigate the effects of learning former traffic on sequential traffic analysis and the effects of learning one dataset on application to another dataset, and determine whether the algorithms can be used for recent attack traffic. Experimental results show that the used preprocessing methods, neural network architectures and hyperparameters, and the optimizers are appropriate for DDoS attack detection. The obtained results provide a criterion for the detection accuracy of attacks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3946-3965
• /
• 2018

Network anomaly detection in Software Defined Networking, especially the detection of DDoS attack, has been given great attention in recent years. It is convenient to build the Traffic Matrix from a global view in SDN. However, the monitoring and management of high-volume feature-rich traffic in large networks brings significant challenges. In this paper, we propose a moving window Principal Components Analysis based anomaly detection and mitigation approach to map data onto a low-dimensional subspace and keep monitoring the network state in real-time. Once the anomaly is detected, the controller will install the defense flow table rules onto the corresponding data plane switches to mitigate the attack. Furthermore, we evaluate our approach with experiments. The Receiver Operating Characteristic curves show that our approach performs well in both detection probability and false alarm probability compared with the entropy-based approach. In addition, the mitigation effect is impressive that our approach can prevent most of the attacking traffic. At last, we evaluate the overhead of the system, including the detection delay and utilization of CPU, which is not excessive. Our anomaly detection approach is lightweight and effective.

• 대한세포병리학회지
• /
• 제8권1호
• /
• pp.20-26
• /
• 1997

The specificity of cytologic examination in effusions is high but the sensitivity is low. Therefore, various ancillary methods for the detection of malignant cells in effusions have been proposed. The presence of an aneuploid cell population is generally considered diagnostic of malignancy. The purpose of this study is to determine whether the routine use of flow cytometry adds to standard cytologic evaluation in effusions. We did flow cytometric DNA analysis in 76 effusions(28 malignant and 48 benign fluids). All the 48 benign effusions were diploid. There were 12(42.9%) aneuploid and 16(67.1%) diploid malignant effusions. Based on these results flow cytometric DNA analysis had a sensitivity of 42.9% and a specificity of 100%. These results suggest that flow cytometric DNA analysis may be a useful adjunct to conventional cytology, but its principal limitation is us relatively low sensitivity.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1239-1242
• /
• 1987

With the convention CW Doppler velocity meter, bi-directional velocities cannot be separated. The new CW Doppler system usee quadrature detection and phase rotation to Produce simultaneous independent audio and velocity signals for forward and reverse blood flow direction, is fabricated. Specially, this system shows that phase rotation method for flow direction separation provides easy and satisfactory feature. From in vivo blood flow measurement, can easily differentiate typical artery flow from vein flow. and measure both velocity characteristics qualitatively.