• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.364-373
• /
• 2022

Image morphing methods make seamless transition changes in the image and mask the meaningful information attached to it. This can be detected by traditional machine learning algorithms and new emerging deep learning algorithms. In this research work, scope of different Hybrid learning approaches having combination of Deep learning and Machine learning are being analyzed with the public dataset CASIA V1.0, CASIA V2.0 and DVMM to find the most efficient algorithm. The simulated results with CNN (Convolution Neural Network), Hybrid approach of CNN along with SVM (Support Vector Machine) and Hybrid approach of CNN along with Random Forest algorithm produced 96.92 %, 95.98 and 99.18 % accuracy respectively with the CASIA V2.0 dataset having 9555 images. The accuracy pattern of applied algorithms changes with CASIA V1.0 data and DVMM data having 1721 and 1845 set of images presenting minimal accuracy with Hybrid approach of CNN and Random Forest algorithm. It is confirmed that the choice of best algorithm to find image forgery depends on input data type. This paper presents the combination of best suited algorithm to detect image morphing with different input datasets.

• 한국정밀공학회지
• /
• 제25권8호
• /
• pp.29-36
• /
• 2008

An optical rotary encoder is easy to implement for automation system applications. In particular, the output of the encoder has a digital form pulse, which is also easy to be connected to a popular digital controller. By using an incremental encoder and a counting device, it is easy to measure angular displacement, as the number of the output pulses is proportional to the rotational displacement. This method can only detect the angular placement once a pulse signal comes out of the encoder. The angular displacement detection period is strongly subject to the change of the angular displacement in case of ultimate low velocity range. They have ultimate long detection period or cannot even detect angular displacement at near zero velocity. This paper proposes an algorithm for detecting angular displacement by using a dual encoder system with two encoders of normal resolution. The angular displacement detecting algorithm is able to keep detection period moderately at near zero velocity and even detect constant angular displacement within nominal period. It is useful for motion control applications in case of changing rotational direction at which there occurs zero velocity. In this paper, various experimental results are shown for the angular displacement detection algorithm.

• International journal of advanced smart convergence
• /
• 제9권3호
• /
• pp.232-238
• /
• 2020

In this paper, we study on aerial objects detection and position estimation algorithm for the safety of UAV that flight in BVLOS. We use the vision sensor and LiDAR to detect objects. We use YOLOv2 architecture based on CNN to detect objects on a 2D image. Additionally we use a clustering method to detect objects on point cloud data acquired from LiDAR. When a single sensor used, detection rate can be degraded in a specific situation depending on the characteristics of sensor. If the result of the detection algorithm using a single sensor is absent or false, we need to complement the detection accuracy. In order to complement the accuracy of detection algorithm based on a single sensor, we use the Kalman filter. And we fused the results of a single sensor to improve detection accuracy. We estimate the 3D position of the object using the pixel position of the object and distance measured to LiDAR. We verified the performance of proposed fusion algorithm by performing the simulation using the Gazebo simulator.

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.283-289
• /
• 2015

In this paper, a GNSS interference detection algorithm based on an adaptive fading Kalman filter is proposed to detect a spoofing signal which is one of the threatening GNSS intentional interferences. To detect and mitigate the spoofing signal, the fading factor of the filter is used as a detection parameter. For simulation, the effect of the spoofing signal is modeled by the ramp type bias error of the pseudorange to emulate a smart spoofer and the change of the fading factor value according to ramp type bias error is quantitatively analyzed. In addition, the detection threshold is established to detect the spoofing signal by analyzing the change of the error covariance and the effect of spoofing is mitigated by controlling the Kalman gain of the filter. To verify the performance analysis of the proposed algorithm, various simulations are implemented. Through the results of simulations, we confirmed that the proposed algorithm works well.

• 대한전자공학회논문지SD
• /
• 제37권4호
• /
• pp.71-79
• /
• 2000

기존의 March 알고리즘으로는 내장된 메모리의 CMOS ADOFs(Address Decoder Open Faults)를 점검할 수 없다. 번지 생성 순서 및 데이터 생성을 달리 할 수 있다는 자유도(DOF: Degree of Freedom)에 근거한 수정된 March 알고리즘이 제안되었다. 본 논문에서는 번지생성기로 완전 CA(Cellular Automata)를, 데이터 생성기로 Rl-LFSRs(Randomly Inversed LFSRs)을 사용하여 수정된 March 알고리즘을 개선하였다. 본 알고리즘은 기존의 March 알고리즘에서 점검할 수 있었던 SAF, ADF, CF, TF, 및 CMOS ADOF의 완점점검은 물론, NPSFs(Neighborhood Pattern Sensitive Faults)도 추가로 점검할 수 있으며, 알고리즘의 복잡도는 O(n)을 유지한다.

• 전자공학회논문지S
• /
• 제35S권10호
• /
• pp.156-165
• /
• 1998

본 논문에서는 MPEG 기반 압축 영상데이터의 장면 변화를 검출하기 위한 하이브리드 알고리즘을 제안한다. MPEG이나 Motion JPEG으로 압축된 영상의 장면 변화를 검출하기 위해 사용된 알고리즘은 크게 두 가지로 나눌 수 있다. 한가지 방법은 압축된 상태의 영상에 직접 처리를 하는 방법으로서 수행시간을 줄일 수 있는 장점이 있지만 정확성이 떨어지는 문제점이 있고, 다른 방법은 복원된 영상에 처리를 하는 방법으로 보다 정확한 검출이 가능하나 속도가 느린 단점이 있다. 따라서 본 논문에서는 이러한 두 가지 알고리즘을 혼합하여, 우선 빠른 검출을 위하여 압축된 시퀀스로부터 DC값에 의한 영상에 의해 컷을 검출하고, 이 결과에서 적절한 영역을 선택한 뒤, 그 영역에 대해서만 영상을 복원하여 윤곽선 정보에 의해 점진적인 장면 변화를 검출한다. 실험결과 수행시간의 단축과 정확한 검출에 있어서 매우 효율적임을 확인하였다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권9호
• /
• pp.521-530
• /
• 2005

In this paper, a new high resolution reflectometry scheme, time-frequency domain reflectometry(TFDR), isproposed to detect and estimate a fault in a transmission line. Traditional reflectometry methodologies have been achieved either in the time domain or in the frequency domain only. However, the TFDR can jump over the performance limits of the traditional reflectometry methodologies because the acquired signal is analyzed in time and frequency domain simultaneously. In the TFDR, the new reference signal and the novel TFDR algorithm are proposed for analyzing the acquired signal in the time-frequency domain. Because the reference signal of Gaussian envelop chirp signal is localized in the time and frequency domain simultaneously, it is suitable to the analysis in the time-frequency domain. In the proposed TFDR algorithm, the time-frequency distribution function and the normalized time-frequency cross correlation function are used to detect and estimate a fault in a transmission line. That algorithm is verified for real-world coaxial cables which are typical transmission line with different types of faults by the TFDR system composed of real instruments. The performance of the TFDR methodology is compared with that o( the commercial time domain reflectomeoy(TDR) experiments, so that concludes the TFDR methodology can detect and estimate the fault with smaller error than TDR methodology.

• 조명전기설비학회논문지
• /
• 제29권5호
• /
• pp.71-79
• /
• 2015

Recently, new Low Voltage DC (LVDC) power distribution systems have been constantly researched as uses of DC in end-user equipment are increased. As in conventional AC distribution system, High Impedance Fault (HIF) which may cause a failure of protective relay can occur in LVDC distribution system as well. It, however, is hard to be detected since change in magnitude of current due to the fault is too small to detect the fault by the protective relay using overcurrent element. In order to solve the problem, this paper presents an algorithm for detecting HIF using accumulated energy in LVDC distribution system. Wavelet Singular Value Decomposition (WSVD) is used to extract abnormal high frequency components from fault current and accumulated energy of high frequency components is considered as the element to detect the fault. LVDC distribution system including AC/DC and DC/DC converter is modeled to verify the proposed algorithm using ElectroMagnetic Transient Program (EMTP) software. Simulation results considering various conditions show that the proposed algorithm can be utilized to effectively detect HIF.

• 한국정보통신학회논문지
• /
• 제12권12호
• /
• pp.2159-2164
• /
• 2008

유비쿼터스 헬스케어 시스템은 사용자의 건강 정보를 감독하고 관리하는 시스템이며, 이 헬스케어 시스템에서 가장 중요한 점은 측정된 건강 데이터의 정확성이다. 그러나 실생활에서는 사용자의 움직임 에 따라 그 정확성이 현저하게 달라진다. 따라서 건강 정보 정확성을 향상시키기 위해 본 연구에서는 심박수 추출에 있어 새로운 맥파 최대점 검출 알고리즘을 제안하였고, 제안된 알고리즘은 다중 하위 대역 필터와 퍼지 추론기를 이용하여 동잡음이 포함된 PPG 신호에서 맥파의 최대점을 검출하기 위한 것이다. 제안된 알고리즘에 대한 성능평가 실험에서 복잡한 동잡음에서도 맥파 최대점 추출이 가능함을 보였다.

• 한국정보통신학회논문지
• /
• 제23권1호
• /
• pp.70-76
• /
• 2019

UWB(Ultra-wideband)는 송신 안테나에서 UWB 대역을 송신한 신호를 수신 안테나를 통해 받은 신호를 가지고 목표물을 판단하는 고해상도 근거리 초광대역 레이더로 비접촉으로 사람의 호흡 및 심박을 감지할 수 있고, 환경에 영향을 받지 않아 최근 활용도가 높아지고 있다. 본 논문에서는 UWB 레이더 신호를 이용하여 사람의 호흡과 심박수를 감지하는 알고리즘을 구현한다. 인체에서부터 반사되어 들어온 레이더 신호를 메디안 필터, 칼만 필터, 밴드 패스필터 등을 이용하여 처리한다. 또한 호흡수와 심박수를 추출하기 위하여 CZT를 이용한다. 비교하는 심박 데이터로는 ECG(Electrocardiogram)를 사용하였으며, 약 98% 이상 일치함을 확인하였다.