• 한국멀티미디어학회논문지
• /
• 제18권3호
• /
• pp.287-297
• /
• 2015

A railway security detection system is very important. There are many safety factors that directly affect the safe operation of trains. Security detection technology can be divided into passive and active approaches. In this paper, we will first survey the railway security systems and compare them. We will also propose a subway security detection system with computer vision technology, which can detect three kinds of problems: the spark problem, the obstacle problem, and the lost screw problem. The spark and obstacle detection methods are unique in our system. In our experiment using about 900 input test images, we obtained about a 99.8% performance in F- measure for the spark detection problem, and about 94.7% for the obstacle detection problem.

• 한국음향학회지
• /
• 제18권6호
• /
• pp.57-64
• /
• 1999

본 논문에서는 잡음이 포함된 음성의 시작점과 끝점을 효율적으로 검출할 수 있는 알고리듬에 대하여 연구하였다. 이를 위해, 웨이브렛 영역에서의 에너지 분포를 고려함으로써 잡음환경하에서도 음성을 검출할 수 있는 새로운 검출 파라미터를 제안하였다. 제안된 끝점검출 파라미터는 웨이브렛 영역에서 세 번째 coarsed 스케일의 표준편차와 가중치를 곱한 첫 번째 detailed 스케일의 표준편차의 합으로 정의하였다. 제안된 끝점검출기의 성능평가를 위해서 다양한 SNR에서 기존방식과 비교하여 시작점과 끝점의 정확도 실험을 수행하였고 HMM 음성인식시스템을 이용하여 인식실험도 수행하였다.

• Journal of Electrical Engineering and Technology
• /
• 제9권4호
• /
• pp.1401-1410
• /
• 2014

This paper presents a modified adaptive fading EKF (AFEKF) for sensor fault detection and isolation in the satellite. Also, the fault detection and isolation (FDI) scheme is developed in three phases. In the first phase, the AFEKF is modified to increase sensor fault detection performance. The sensor fault detection and sensor selection method are proposed. In the second phase, the IMM filer with scalar penalty is designed to detect wherever actuator faults occur. In the third phase of the FDI scheme, the sub-IMM filter is designed to identify the fault type which is either the total or partial fault. An important feature of the proposed FDI scheme can decrease the number of filters for detecting sensor fault. Also, the proposed scheme can classify fault detection and isolation as well as fault type identification.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.358-361
• /
• 2021

In order to improve the accuracy of small target detection more effectively, this paper proposes an improved single shot detector (SSD) target detection and recognition method based on cspdarknet53, which introduces lightweight ECA attention mechanism and Feature Pyramid Network (FPN). First, the original SSD backbone network is replaced with cspdarknet53 to enhance the learning ability of the network. Then, a lightweight ECA attention mechanism is added to the basic convolution block to optimize the network. Finally, FPN is used to gradually fuse the multi-scale feature maps used for detection in the SSD from the deep to the shallow layers of the network to improve the positioning accuracy and classification accuracy of the network. Experiments show that the proposed target detection algorithm has better detection accuracy, and it improves the detection accuracy especially for small targets.

• Current Optics and Photonics
• /
• 제8권3호
• /
• pp.282-299
• /
• 2024

Target detection (TD) is a research hotspot in the field of hyperspectral imaging (HSI). Traditional TD methods often mine targets from HSIs under a single imaging condition, without considering the influence of imaging conditions. In fact, the spectra of ground objects in HSIs are uncertain and affected by the imaging conditions (weather, atmospheric, light, time, and other angle conditions including zenith angle). Hyperspectral data changes under different imaging conditions. Therefore, the detection result for a single imaging condition cannot accurately reflect the effectiveness of the detection method used. It is necessary to analyze the performance of various detection methods under different imaging conditions, to find a more applicable detection method. In this paper, we study the performance of TD methods under various land-based imaging conditions. We first summarize classical TD methods and evaluation methods. Then, the detection effects under various imaging conditions are analyzed. Finally, the concepts of the stability coefficient (SC) and effective area under the curve (EAUC) are proposed to comprehensively evaluate the applicability of detection methods under land-based imaging conditions, in terms of both detection accuracy and stability. This is conducive to our selection of detection methods with better applicability in land-based contexts, to improve detection accuracy and stability.

• 한국식품과학회지
• /
• 제32권3호
• /
• pp.525-530
• /
• 2000

국내에서 생산된 농산물의 방사선 조사유무를 확인하기 위하여 TL을 측정하였다. 모든 시료의 first glow curve는 조사선량이 증가할수록 TL intensity도 증가하는 경향을 보여 주었다. 당근, 생강, 감자, 고구마의 상관계수는 0.8522, 0.9968, 0.9612, 0.9071의 높은 값을 나타내었으며, first glow curve의 최대발광온도점은 $176.16{\sim}190.08^{\circ}C$사이에 있었고, second glow curve는 $143.84{\sim}146.56^{\circ}C$ 사이에서 나타났다. Glow curve ratio 1은 감자와 고구마를 제외하고 모두 0.1보다 작은 수치를 보여 비조사시료로 확인되었으며, 감자(0.1840)와 고구마(0.1655)는 0.1보다 큰 수치를 보였으나 독특한 first glow curve가 나타나지 않은 점으로 보아 비조사시료로 확인되었다. 그리고 모든 시료의 glow curve ratio 2는 0.7159보다 높은 수치를 나타내어 조사시료로 확인되었다. Glow curve의 모양을 분석한 결과 second glow curve의 모양이 first glow curve의 유사하였고, 더 낮은 온도에서 나타났다. 따라서 glow curve ratio와 glow curve의 모양에 의해 정확하게 조사유무를 확인할 수 있었고 TL을 이용하여 방사선 조사된 농산물의 검지가 가능함을 확인할 수 있었다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제14권6호
• /
• pp.765-770
• /
• 2001

Thirty second parity sows of the synthetic Nepalese Pakhribas genotype were used to investigate factors which might improve the occurrence and expression of estrus. The experiment had two sequential elements. In part 1, a change in suckling pattern was applied during lactation, and in part 2, different estrus detection methods were evaluated after weaning. All sows received the same pattern of weaning, which imitated the progressive weaning system used in Nepalese villages. Piglets from each litter were weaned at three ages (6, 7 and 8 weeks of age) in the proportion of 0.5 at 6 weeks followed by 0.25 at each of the subsequent weanings. In the first lactation treatment, the suckling pattern was left undisturbed, similar to the practice used in the villages in which the remaining piglets after first weaning are allowed continuous suckling. In the other treatment, the remaining piglets after first weaning were allowed to suckle their sows only during the night, whilst in the day time (09:00-16:00) they were excluded from the sow but left free to roam around. After weaning, estrus detection procedures were carried out in the absence or presence of two different boar stimuli: a synthetic boar pheromone spray or fresh boar urine. These were applied sequentially in a sequence of testing that alternated for each sow on a daily basis. The weaning to re-mating interval was significantly longer for the unrestricted suckling treatment. All sows were re-mated within 30 days after first weaning in the restricted suckling treatment groups, whereas only 71% of sows were re-mated within 30 days after weaning in the unrestricted suckling treatment groups ($x^2=3.877$, 1df, p<0.05). Both boar pheromone spray and boar urine increased the estrus detection probability, with no significant differences between the two stimuli treatments.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권12호
• /
• pp.4891-4894
• /
• 2015

Background: To evaluate the value of combined detection of serum carcinoembryonic antigen (CEA), cytokeratin 19 fragment (CYFRA21-1), and carbohydrateantigen 125 (CA125) for the clinical diagnosis of nonsmall cell lung cancer (NSCLC). Materials and Methods: Serum CEA, CYFRA21-1 and CA125 were assessed in 140 patients with NSCLC, 90 patients with benign lung disease and 90 normal control subjects, and differences of expression were compared in each group, and joint effects of these tumor markers in the diagnosis of NSCLC were analyzed. Results: Serum CEA, CYFRA21-1 and CA125 in patients with NSCLC were significantly higher than those with benign lung disease and normal controls (P<0.05). The sensitivity of CEA, CYFRA21-1 and CA125 were 49.45%, 59.67%, and 44.87% respectively. As expected, combinations of these tumor markers improved their sensitivity for NSCLC. The combined detection of CEA + CYFRA21-1 was the most cost-effective combination which had higher sensitivity and specificity in NSCLC. Elevation of serum CEA and CYFRA21-1 was significantly associated with pathological types (P<0.05) and elevation of serum CEA, CYFRA21-1 and CA125 was significantly associated with TNM staging (P<0.05). Conclusions: Single measurement of CEA, CYFRA21-1 and CA125 is of diagnostic value in the diagnosis of lung cancer, and a joint detection of these three tumor markers, could greatly improve the sensitivity of diagnosis on NSCLC. Combined detection of CEA + CYFRA21-1 proved to be the most economic and practical strategy in diagnosis of NSCLC, which can be used to screen the high-risk group.

• 드라이브 ㆍ 컨트롤
• /
• 제14권2호
• /
• pp.30-36
• /
• 2017

This paper presents a sliding mode observer-based fault detection algorithm for steering inputs of an all-terrain crane. All-terrain cranes with multi-axles have several steering modes for various working purposes. Since steering angles at the other axles except the first wheel are controlled by using the information of steering angle at the first wheel, a reliable signal of the first axle's steering angle should be secured for the driving safety of cranes. For the fault detection of steering input signal, a simplified crane model-based sliding mode observer has been used. Using a sliding mode observer with an equivalent output injection signal that represents an actual fault signal, a fault signal in steering input was reconstructed. The road steering mode of the crane's steering system was used to conduct performance evaluations of a proposed algorithm, and an arbitrary fault signal was applied to the steering angle at the first wheel. Since the road steering mode has different steering strategies according to different speed intervals, performance evaluations were conducted based on the curved path scenario with various speed conditions. The design of algorithms and performance evaluations were conducted on Matlab/Simulink environment, and evaluation results reveal that the proposed algorithm is capable of detecting and reconstructing a fault signal reasonably well.

• 한국항행학회논문지
• /
• 제23권1호
• /
• pp.1-7
• /
• 2019

본 연구에서는 항공기 지상 이동 fast-time 시뮬레이터를 개발하였다. 시뮬레이터는 FCFS (first-come first-served) 스케줄러로부터 생성된 스케줄을 사용하여 항공기를 지상 이동시키는데, 항공기의 움직임을 모사하기 위해 1차원 등속 이동 운동 모델을 적용하였다. 공항 내 항공기 충돌 위험이 발생하는 상황을 분석하여 총 6개의 상황으로 분류하였으며 충돌 감지 및 회피 알고리즘을 구현하여 분리 거리를 유지하고 교착 상태를 방지 하도록 하였다. 인천국제공항의 실제 운용상황을 모사한, 72대의 항공기가 포함된 시나리오에 대하여 테스트를 실시하였다. 충돌 감지 및 회피 기능을 사용하지 않은 경우, 다양한 위험 상황이 확인되었으며, 충돌감지 및 회피 알고리즘을 사용하면 위험 상황이 없어지는 대신 추가적인 지연이 발생함을 확인하였다. 또한 회피 알고리즘에서 3가지 통행 우선순위 부여 방식을 구현하여 각 방식에 따른 지연 대수와 평균 지연 시간을 비교하였다. 남은 거리 또는 남은 시간에 따라 우선 순위를 부여하는 방식이 각 상황별 최소 지연을 선택하는 방식에 비하여 전체 추가 지연이 작아짐을 확인하였다.