• 제목/요약/키워드: Detection Techniques

검색결과 2,644건 처리시간 0.029초

능동 적외선 열화상 기법에 의한 SM45C 이면결함 검출 열영상에 관한 연구 (Thermal Imaging for Detection of SM45C Subsurface Defects Using Active Infrared Thermography Techniques)

  • 정윤재;;김원태
    • 비파괴검사학회지
    • /
    • 제35권3호
    • /
    • pp.193-199
    • /
    • 2015
  • 능동적 열화상 기법은 넓은 면적을 동시에 검사할 수 있으며, 결함부와 건전부 사이의 위상차로부터 결함의 유무를 판단할 수 있다. 지금까지 다양한 재료와 시험편을 가지고 결함 검출 기법에 대한 발전이 이루어졌다. 본 논문에서는 위상잠금 열화상 기법을 적용하여 각각 다른 결함의 크기와 깊이의 인공결함을 갖는 SM45C 시험편을 가지고 제안된 기법을 검증하였으며, 결론으로서 결함의 크기, 깊이에 따른 위상 이미지와 진폭 이미지 검사 결과를 비교하여 결함 검출능을 평가할 수 있었다.

Analyzing Effective of Activation Functions on Recurrent Neural Networks for Intrusion Detection

  • Le, Thi-Thu-Huong;Kim, Jihyun;Kim, Howon
    • Journal of Multimedia Information System
    • /
    • 제3권3호
    • /
    • pp.91-96
    • /
    • 2016
  • Network security is an interesting area in Information Technology. It has an important role for the manager monitor and control operating of the network. There are many techniques to help us prevent anomaly or malicious activities such as firewall configuration etc. Intrusion Detection System (IDS) is one of effective method help us reduce the cost to build. The more attacks occur, the more necessary intrusion detection needs. IDS is a software or hardware systems, even though is a combination of them. Its major role is detecting malicious activity. In recently, there are many researchers proposed techniques or algorithms to build a tool in this field. In this paper, we improve the performance of IDS. We explore and analyze the impact of activation functions applying to recurrent neural network model. We use to KDD cup dataset for our experiment. By our experimental results, we verify that our new tool of IDS is really significant in this field.

전류 센서를 이용한 디지탈 논리회로의 고장 검출 (On the detection of faults on digital logic circuits using current sensor)

  • 신재흥;임인칠
    • 전자공학회논문지A
    • /
    • 제33A권2호
    • /
    • pp.173-183
    • /
    • 1996
  • In this paper, a new structure that can do fault detection and location of digial logic circuits more efficiently using current testing techniques is proposed. In the conventional method, observation point for steady state power supply current was only one, but in the proposed method more fault classes are divided for fault detection and location through the ovservation of steady state power supply current at two points. Also, it is shown that this structure can be easily applied in detection of stuck-open fault which is not easy to do testing with conventional current testing techniques. In the presented mehtod, an extra trasnistor is used, and current path is made compulsorily in the CMOS circuits in which no current path can be established in steady state, then it can be known that stuck-open tault is in the MOS transistor on the considering current path, if this path disappears due to stuck-open fault. The validity and the effectiveness is shwon, thorugh the SPICE simulation of circuits with fault and the current path search experiment using current path search program based on transistor short model wirtten in C language on SUN sparc workstation.

  • PDF

손실함수의 특성에 따른 UNet++ 모델에 의한 변화탐지 결과 분석 (Analysis of Change Detection Results by UNet++ Models According to the Characteristics of Loss Function)

  • 정미라;최호성;최재완
    • 대한원격탐사학회지
    • /
    • 제36권5_2호
    • /
    • pp.929-937
    • /
    • 2020
  • 본 논문에서는 의미론적 분할을 위한 딥러닝 기술 중의 하나인 UNet++ 모델을 이용하여 다시기 위성영상의 변화지역을 탐지하고자 하였다. 다양한 손실함수에 대한 학습결과를 분석하기 위하여, 이진 교차 엔트로피, 자카드 변수에 의하여 학습된 UNet++ 모델에 의한 변화탐지 결과를 평가하였다. 또한, 딥러닝 모델의 결과는 WorldView-3 위성영상을 활용하여 기존의 화소기반 변화탐지 기법의 결과와 비교하여 평가하였다. 실험결과, 손실함수의 특성에 따라서 딥러닝 모델의 성능이 달라질 수 있음을 확인하였으나, 기존 기법들과 비교하여 우수한 결과를 나타내는 것도 확인하였다.

구조물 건전성 감시를 위한 스마트 PZT센서의 적용성 연구 (Application of smart piezoelectric transducers to structural health monitoring)

  • Park, Seung-Hee;Yi, Jin-Hak;Lee, Jong-Jae;Yun, Chung-Bang;Noh, Yong-Rae
    • 한국전산구조공학회:학술대회논문집
    • /
    • 한국전산구조공학회 2003년도 가을 학술발표회 논문집
    • /
    • pp.549-555
    • /
    • 2003
  • The objective of かis study is to investigate the feasibility of piezoelectric transducers as a damage detection system for civil infrastructures. There have been considerable amount of efforts by the modal analysis community to localize damage and evaluate its severity without looking at a reliable way to excite the structure. The detection of damages by modal analysis and similar vibration techniques depends upon the knowledge and estimation of various modal parameters. In addition to the associated difficulties, such low-frequency dynamic response based techniques fail to detect incipient damages. Smart piezoelectric ceramic (PZT) transducers which act as both actuators and sensors in a self-analyzing manner are emerging to be effective in non-parametric health monitoring of structural systems. In this paper, we present the results of an experimental study for the detection of damages using smart PZT transducers on the steel plate. The method of extracting the impedance characteristics of the PZT transducer, which is electro-mechanically coupled to the host structure, is adopted for damage detection. Two damages are simulated and assessed by the bonded PZT transducers for characterization. The experimental results verified the efficacy of the proposed approach and provided a demonstration of good robustness at the realistic steel structures, emphasizing the great potential for developing an automated in situ structural health monitoring system for application to large civil infrastructures without the need to blow the modal parameters.

  • PDF

Imbalanced SVM-Based Anomaly Detection Algorithm for Imbalanced Training Datasets

  • Wang, GuiPing;Yang, JianXi;Li, Ren
    • 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.

Skin Region Detection Using a Mean Shift Algorithm Based on the Histogram Approximation

  • Byun, Ki-Won;Nam, Ki-Gon;Ye, Soo-Young
    • Transactions on Electrical and Electronic Materials
    • /
    • 제13권1호
    • /
    • pp.10-15
    • /
    • 2012
  • In conventional, skin detection methods using for skin color definitions is based on prior knowledge. By experimentation, the threshold value for dividing the background from the skin region is determined subjectively. A drawback of such techniques is that their performance is dependent on a threshold value which is estimated from repeated experiments. To overcome this, the present paper introduces a skin region detection method. This method uses a histogram approximation based on the mean shift algorithm. This proposed method applies the mean shift procedure to a histogram of a skin map of the input image. It is generated by comparing with the standard skin colors in the $C_bC_r$ color space. It divides the background from the skin region by selecting the maximum value according to the brightness level. As the histogram has the form of a discontinuous function. It is accumulated according to the brightness values of the pixels. It is then, approximated by a Gaussian mixture model (GMM) using the Bezier curve technique. Thus, the proposed method detects the skin region using the mean shift procedure to determine a maximum value. Rather than using a manually selected threshold value, as in existing techniques this becomes the dividing point. Experiments confirm that the new procedure effectively detects the skin region.

Gray 채널 분석을 사용한 딥페이크 탐지 성능 비교 연구 (A Comparative Study on Deepfake Detection using Gray Channel Analysis)

  • 손석빈;조희현;강희윤;이병걸;이윤규
    • 한국멀티미디어학회논문지
    • /
    • 제24권9호
    • /
    • pp.1224-1241
    • /
    • 2021
  • Recent development of deep learning techniques for image generation has led to straightforward generation of sophisticated deepfakes. However, as a result, privacy violations through deepfakes has also became increased. To solve this issue, a number of techniques for deepfake detection have been proposed, which are mainly focused on RGB channel-based analysis. Although existing studies have suggested the effectiveness of other color model-based analysis (i.e., Grayscale), their effectiveness has not been quantitatively validated yet. Thus, in this paper, we compare the effectiveness of Grayscale channel-based analysis with RGB channel-based analysis in deepfake detection. Based on the selected CNN-based models and deepfake datasets, we measured the performance of each color model-based analysis in terms of accuracy and time. The evaluation results confirmed that Grayscale channel-based analysis performs better than RGB-channel analysis in several cases.

An Interactive Multi-Factor User Authentication Framework in Cloud Computing

  • Elsayed Mostafa;M.M. Hassan;Wael Said
    • International Journal of Computer Science & Network Security
    • /
    • 제23권8호
    • /
    • pp.63-76
    • /
    • 2023
  • Identity and access management in cloud computing is one of the leading significant issues that require various security countermeasures to preserve user privacy. An authentication mechanism is a leading solution to authenticate and verify the identities of cloud users while accessing cloud applications. Building a secured and flexible authentication mechanism in a cloud computing platform is challenging. Authentication techniques can be combined with other security techniques such as intrusion detection systems to maintain a verifiable layer of security. In this paper, we provide an interactive, flexible, and reliable multi-factor authentication mechanisms that are primarily based on a proposed Authentication Method Selector (AMS) technique. The basic idea of AMS is to rely on the user's previous authentication information and user behavior which can be embedded with additional authentication methods according to the organization's requirements. In AMS, the administrator has the ability to add the appropriate authentication method based on the requirements of the organization. Based on these requirements, the administrator will activate and initialize the authentication method that has been added to the authentication pool. An intrusion detection component has been added to apply the users' location and users' default web browser feature. The AMS and intrusion detection components provide a security enhancement to increase the accuracy and efficiency of cloud user identity verification.

A Deep Learning Approach for Intrusion Detection

  • Roua Dhahbi;Farah Jemili
    • International Journal of Computer Science & Network Security
    • /
    • 제23권10호
    • /
    • pp.89-96
    • /
    • 2023
  • Intrusion detection has been widely studied in both industry and academia, but cybersecurity analysts always want more accuracy and global threat analysis to secure their systems in cyberspace. Big data represent the great challenge of intrusion detection systems, making it hard to monitor and analyze this large volume of data using traditional techniques. Recently, deep learning has been emerged as a new approach which enables the use of Big Data with a low training time and high accuracy rate. In this paper, we propose an approach of an IDS based on cloud computing and the integration of big data and deep learning techniques to detect different attacks as early as possible. To demonstrate the efficacy of this system, we implement the proposed system within Microsoft Azure Cloud, as it provides both processing power and storage capabilities, using a convolutional neural network (CNN-IDS) with the distributed computing environment Apache Spark, integrated with Keras Deep Learning Library. We study the performance of the model in two categories of classification (binary and multiclass) using CSE-CIC-IDS2018 dataset. Our system showed a great performance due to the integration of deep learning technique and Apache Spark engine.