• ETRI Journal
• /
• 제39권5호
• /
• pp.621-631
• /
• 2017

Abnormal samples are usually difficult to obtain in production systems, resulting in imbalanced training sample sets. Namely, the number of positive samples is far less than the number of negative samples. Traditional Support Vector Machine (SVM)-based anomaly detection algorithms perform poorly for highly imbalanced datasets: the learned classification hyperplane skews toward the positive samples, resulting in a high false-negative rate. This article proposes a new imbalanced SVM (termed ImSVM)-based anomaly detection algorithm, which assigns a different weight for each positive support vector in the decision function. ImSVM adjusts the learned classification hyperplane to make the decision function achieve a maximum GMean measure value on the dataset. The above problem is converted into an unconstrained optimization problem to search the optimal weight vector. Experiments are carried out on both Cloud datasets and Knowledge Discovery and Data Mining datasets to evaluate ImSVM. Highly imbalanced training sample sets are constructed. The experimental results show that ImSVM outperforms over-sampling techniques and several existing imbalanced SVM-based techniques.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.559-562
• /
• 2003

In this paper, we introduce a new method detecting thyristor faults of the power converter module in Control Rod Control System. When we control the currents in each coil of Control Rod Drive Mechanism by using the current control method, the current value can follow the current reference despite the faults like the missing phase or the diode acting. Comparing the fault current values with the normal current values, the bad transient characteristics of the abnormal current can make the operations of control rods incorrect. In this case, the information from the current trends cannot be enough to detect the fault occurrence in thyristors. Instead of the coil currents, the state of thyristors can be watched by measuring the coil voltages. In the existing system of Westinghouse type, the ripple detector takes charge of this task. But this detector has some shortcomings in the point of time for fault detection, we come to devise a new fault detection method solving the problems which belong to the ripple detector.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.89-100
• /
• 2021

Smart Grid Network (SGN) is a next generation electrical power network which digitizes the power distribution grid and achieves smart, efficient, safe and secure operations of the electricity. The backbone of the SGN is information communication technology that enables the SGN to get full control of network station monitoring and analysis. In any network where communication is involved security is essential. It has been observed from several recent incidents that an adversary causes an interruption to the operation of the networks which lead to the electricity theft. In order to reduce the number of electricity theft cases, companies need to develop preventive and protective methods to minimize the losses from this issue. In this paper, we have introduced a machine learning based SVM method that detects malicious nodes in a smart grid network. The algorithm collects data (electricity consumption/electric bill) from the nodes and compares it with previously obtained data. Support Vector Machine (SVM) classifies nodes into Normal or malicious nodes giving the statues of 1 for normal nodes and status of -1 for malicious -abnormal-nodes. Once the malicious nodes have been detected, we have done a trust evaluation based on the nodes history and recorded data. In the simulation, we have observed that our detection rate is almost 98% where the false alarm rate is only 2%. Moreover, a Trust value of 50 was achieved. As a future work, countermeasures based on the trust value will be developed to solve the problem remotely.

• Journal of the Optical Society of Korea
• /
• 제9권4호
• /
• pp.157-161
• /
• 2005

Medical infrared imaging is obtained by measuring the self-emitted infrared radiance from the human body. Infrared emission is related to surface temperature and temperature is one of the most important physiological parameters related to health. Though recent applications such as security identification and oriental medicine have provided new fields of biomedical applications, infrared thermography has had ups and downs in its usages in cancer detection. Some of the main difficulties include finding proper applications and efficient diagnostic algorithms. In this study, infrared thermal imaging was used to detect regional metastasis of breast cancer. Our measurements were done for 110 women. From 63 individuals of a Healthy Group and a Benign Breast Disease Group, we developed algorithms for differentiating malignant regional metastasis based on temperature difference and asymmetry of temperature distribution. Testing with 47 cancer patients, we achieved a positive predictive value of $87.5\%$ and a negative predictive value of $95.6\%$. The results were better than for mammogram examination. A proper analysis of infrared imaging proved to be a highly informative and sensitive method for differentiating regional cancer metastasis from normal regions.

• 전자공학회논문지
• /
• 제51권9호
• /
• pp.200-207
• /
• 2014

부정맥 심전도 신호는 전도장애 및 발생부위에 따라 특정 부위에서 비정상 모양을 띄는 특이심박을 포함하고 있다. 특이심박은 부정맥 등 다양한 질환을 진단 및 분류하는데 있어 유용하기 때문에 부정맥 심전도 신호에서 특이심박의 검출은 매우 중요하다. R-peak점에서의 전위, 첨도 및 R-R 간격은 심전도 신호가 R파에서 가지는 특성이다. 본 논문에서는 이를 바탕으로 특이심박 검출 방법을 제안한다. 제안한 방법은 특이심박이 확실할수록 특성값이 평균에서 크게 벗어난다는 점을 기반으로 평균과 표준편차를 이용하여 순차적으로 특이심박을 검출한다. MIT-BIH 부정맥 데이터베이스 중 R파 왜곡을 가지는 15개의 심전도 신호에 대해 기존의 고정된 문턱값을 사용한 검출 방법과 제안한 방법을 적용하여 특이심박을 검출하여 비교하였다. 실험을 통해 민감도를 약 50~70%에서 제안한 방법을 통해 97%로 크게 상향할 수 있었다.

• 한국정보과학회논문지:정보통신
• /
• 제36권3호
• /
• pp.173-183
• /
• 2009

본 논문에서는 엔트로피에 기반한 이상징후 탐지 시스템을 제안한다. 엔트로피는 시스템의 무질서정도를 측정하는 지표로써, 이상징후 출현 시 네트워크의 엔트로피는 급증한다. 네트워크를 IP와 포트번호를 기준으로 분류하여, 패킷별로 역학을 관찰하고 엔트로피를 각각 측정한다. 분산서비스거부공격이나 웜, 스캐닝 등의 네트워크 공격 출현 시 패킷 교환과정이 정상적일 때와는 다르므로 엔트로피를 통하여 기존기법 보다 높은 탐지율로 이상징후를 탐지할 수 있다. 본 논문에서는 다수의 원과 서비스거부공격을 포함한 데이터 셋을 수집하여 제안기법을 검증하였다. 또한 지수평활법, Holt-winters 등의 시계열예측 기법과 주성분분석을 이용한 이상징후 탐지 기법과 정확도 측면에서 비교한다. 본 논문에서 제안한 기법으로 웜, 서비스거부공격 등의 이상징후 탐지에 있어 오탐지율을 낮출 수 있다.

• 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.

• 대한핵의학회지
• /
• 제9권1호
• /
• pp.51-58
• /
• 1975

It is a great value to find an early detection of involvement of ureteric obstruction in the carcinoma of cervix. Little or no knowledge of the condition of the kidneys or the lower urinary tract are able to elucidate by the biochemical studies such as blood nitrogen or urine creatinine in carcinoma of cervix. Findings of urography delineates the condition of urinary tract stasis in the renal pelvis and ureters, however, slight stasis maybe difficult to demonstrate. On the other hand isotope nephrography is accepted as a sensitive method to observe renal function especially in regarding to the excretory function of kidney. It was attempted to analysis the findings of urography conjunction with isotope nephrography in 50 cases of unselected patients with invasive carcinoma of cervix through pre and post irradiation follow up studies. Urography was done as a routine procedure and.analysed emphasising changes of collecting systems and ureter condition. Isotope nephrography was carried out by means of $15{\mu}ci\;I^{131}$-Hippuran injected intravenously and the curves were analysed as follows. Parameter were; time of maximum amplitude ($T_{max}$), half time of maximum amplitude ($T\frac{1}{2}$), Kac and Kex value calculated from these two parameters in Tobe's method. The excretion index by Aurell defines the ratio between the maximum activity and the activity measured on the slope of the third phase ten minites after it has reached its maximum. Results: 1. 28.8% had an abnormal IVP suggestive of ureteric involvement before irradiation therapy and the patient of stage III and IV were the great part. 2. 21.7% had abnormal findings of per-irradiation renogram whom showed normal IVP. The other group showed normal IVP which group also showed normal renogram prior irradiation. 3. The more severe the ureteric involvement, the change of excretion index was greater. 4. Even in stage I and II patient, abnormal renogram was revealed in 12 cases (39.4%) among 31 cases. 5. All cases of TAH showed abnormal findings of IVP and renogram. 6. No. definite change of renogram was obtained just after the irradiation therapy (point $A:8000{\sim}9000rads,\;B:5000{\sim}6000rads,\;Co:11000{\sim}13000rads$). Each 3 month follow up study was performed and comparing with preirradiation study which showed significant changes of excretion index of renogram were 42.8% in $6{\sim}9$ month follow-up and 75% in $9{\sim}12$ month, respectively. 7. It seems to be important to observe the parameter Kex and excretion index of renogram to determine early abnormality of kidney excretory function by means of post-irradiation follow up study.

• 정보과학회 논문지
• /
• 제45권3호
• /
• pp.294-302
• /
• 2018

정보통신 기술의 발전에 따른 새로운 서비스 산업의 출현으로 개인 정보 침해, 산업 기밀 유출 등 사이버 공간의 위험이 다양화 되어, 그에 따른 보안 문제가 중요한 이슈로 떠오르게 되었다. 본 연구에서는 기업 내 개인 정보 오남용 및 내부 정보 유출에 따른, 대용량 사용자 로그 데이터를 기반으로 기존의 시그니처(Signature) 보안 대응 방식에 비해, 실시간 및 대용량 데이터 분석기술에 적합한 행위 기반 이상 탐지방식을 제안하였다. 행위 기반 이상 탐지방식이 대용량 데이터를 처리하는 기술을 필요로 함에 따라, 역방향 인덱스(Inverted Index) 기반의 실시간 검색 엔진인 엘라스틱서치(Elasticsearch)를 사용하였다. 또한 데이터 분석을 위해 통계 기반의 빈도 분석과 전 처리 과정을 수행하였으며, 밀도 기반의 군집화 방법인 DBSCAN 알고리즘을 적용하여 이상 데이터를 분류하는 방법과 시각화를 통해 분석을 간편하게 하기위한 한 사례를 보였다. 이는 기존의 이상 탐지 시스템과 달리 임계값을 별도로 설정하지 않고 이상 탐지 분석을 시도하였다는 것과 통계적인 측면에서 이상 탐지 방식을 제안하였다는 것에 의의가 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1674-1688
• /
• 2023

The remarkable advancement of quantum steganography offers enhanced security for quantum communications. However, there is a significant concern regarding the potential misuse of this technology. Moreover, the current research on identifying malicious quantum steganography is insufficient. To address this gap in steganalysis research, this paper proposes a specialized quantum steganalysis algorithm. This algorithm utilizes quantum machine learning techniques to detect steganography in general quantum secure communication schemes that are based on pure states. The algorithm presented in this paper consists of two main steps: data preprocessing and automatic discrimination. The data preprocessing step involves extracting and amplifying abnormal signals, followed by the automatic detection of suspicious quantum carriers through training on steganographic and non-steganographic data. The numerical results demonstrate that a larger disparity between the probability distributions of steganographic and non-steganographic data leads to a higher steganographic detection indicator, making the presence of steganography easier to detect. By selecting an appropriate threshold value, the steganography detection rate can exceed 90%.