• Journal of information and communication convergence engineering
• /
• 제21권2호
• /
• pp.159-166
• /
• 2023

The COI gene is a sequence of approximately 650 bp at the 5' terminal of the mitochondrial Cytochrome c Oxidase subunit I (COI) gene. As an effective DeoxyriboNucleic Acid (DNA) barcode, it is widely used for the taxonomic identification and evolutionary analysis of species. We created a CNN-LSTM hybrid model by combining the gene features partially extracted by the Long Short-Term Memory ( LSTM ) network with the feature maps obtained by the CNN. Compared to K-Means Clustering, Support Vector Machines (SVM), and a single CNN classification model, after training 278 samples in a training set that included 15 genera from two orders, the CNN-LSTM hybrid model achieved 94% accuracy in the test set, which contained 118 samples. We augmented the training set samples and four genera into four orders, and the classification accuracy of the test set reached 100%. This study also proposes calculating the cosine similarity between the training and test sets to initially assess the reliability of the predicted results and discover new species.

• 항공우주기술
• /
• 제13권2호
• /
• pp.54-59
• /
• 2014

논문은 신뢰성 높은 심우주통신을 위해 명령 및 데이터를 파일의 형태로 송/수신하는 프로토콜인 CFDP(CCSDS File Delivery Protocol)의 개발을 지원하기 위한 시험 및 분석 장비에 대한 소개이다. 본 논문에서는 기본적인 CFDP 설명과 CFDP-TASS(CFDP - Test Analysis & Support Set)의 개발 목적 및 기능을 소개하였다. CFDP-TASS는 OBC(On-Board Computer)와 연동하여 정상적인 상황에서의 시험뿐만 아니라 사용자가 의도적으로 오류를 생성하여 CFDP 시험 및 검증하는 기능을 보유하고 있으며, 결과 분석을 용이하게 하기 위해 시험 시 발생하는 모든 데이터를 보관/관리하고, 다양한 형태로 시험데이터를 표시하는 기능을 보유하고 있다.

• 한국레이저가공학회지
• /
• 제7권2호
• /
• pp.1-10
• /
• 2004

This work was attempted to join SCP sheet and STS304 sheet by using Nd:YAC laser beam. SCP sheet has good formability and low cost, while STS304 has excellent corrosion resistance and mechanical properties in high temp. In this experiment, butt joint type was used to develop the tailored blank welding for dissimilar steel. Sheets which have different thermal properties. Computer simulation was conducted to obtain the off-set position for efficient welding by considering laser power, scanning speed, focal length and basic properties. The result showed that the optimum thermal distribution was obtained when the laser beam was irradiated at $0.05{\sim}0.1$ mm off-set toward the SCP sheet side. The experiment was conducted based on the result of computer simulation to show the same optimum conditions. Optimum conditions were 3KW in laser beam power, 6m/min in scanning speed, -0.5mm in focal position, 0.1mm off-set toward SCP. Microhardness test, tensile test, bulge test, optical microscopy, EDS, and XRD were performed to observe the microstructure around fusion zone and to evaluate the mechanical properties of optimum conditions, The weld zone had high microhardness values by the formation of the martensitic structure. Tensile test measured the strength of welded region by vertical to strain direction and the elongation of welded region by parallel to strain direction. Bulge test showed $52\%$ formability of the original materials. Bead shape, grain size, and martensitic structure were observed by the optical microscopy in the weld zone. Detailed results of EDS, XRD confirmed that the welded region was connected of martensitic structure.

• Communications for Statistical Applications and Methods
• /
• 제8권2호
• /
• pp.395-406
• /
• 2001

In this paper, we propose the test statistic for the umbrella alternatives on c-samples ranked set samples(RSS), where the peak of the umbrella is known. We obtain the asymptotic property of the proposed test statistic and the asymptotic relative efficiencies of the proposed test statistic with respect to U-statistic based on simple random samples(SRS). From the simulation work, we compare the empirical powers of the proposed test statistic with U-statistic based on SRS.

• 한국인터넷방송통신학회논문지
• /
• 제20권6호
• /
• pp.157-165
• /
• 2020

뉴-럴 네트워크와 자동운전 데이터 셋을 개발하는 목표중의 하나가 데이터 셋을 분할함에 따라서 움직이는 물체를 검출하는 성능을 개선하는 방법이 있다. 다크넷 (DarkNet) 프레임 워크에 있어서, YOLOv4 네트워크는 Udacity 데이터 셋에서 훈련하는 셋과 검증 셋으로 사용되었다. Udacity 데이터 셋의 7개 비율에 따라서 이 데이터 셋은 훈련 셋, 검증 셋, 테스트 셋을 포함한 3개의 부분 셋으로 나누어진다. K-means++ 알고리즘은 7개 그룹에서 개체 Box 차원 군집화를 수행하기 위해 사용되었다. 훈련을 위한 YOLOv4 네트워크의 슈퍼 파라메타를 조절하여 7개 그룹들에 대하여 최적 모델 파라메타가 각각 구해졌다. 이 모델 파라메타는 각각 7 개 테스트 셋 데이터에 비교하고 검출에 사용되었다. 실험결과에서 YOLOv4 네트워크는 Udacity 데이터 셋에서 트럭, 자동차, 행인으로 표현되는 움직이는 물체에 대하여 대/중/소 물체 검출을 할수 있음을 보여 주었다. 훈련 셋과 검증 셋, 테스트 셋의 비율이 7 ; 1.5 ; 1.5 일 때 최적의 모델 파라메타로서 가장 높은 검출 성능이었다. 그 결과값은, mAP50가 80.89%, mAP75가 47.08%에 달하고, 검출 속도는 10.56 FPS에 달한다.

• 한국경영과학회지
• /
• 제13권2호
• /
• pp.215-215
• /
• 1988

This paper presents a fuzzy set theory based formulation and heuristic which will allow plant layout problems to be solved for more than two input goals with different weights. The heuristic combines a construction and improvement procedure to generate a good layout from the formulation. To test the effectiveness of the heuristic, a set of examples previously used by various authors is solved and the results are compared to those from other known heuristics. The comparison indicates that the proposed method performs well for each of seventeen classical test problems.

• 경영과학
• /
• 제13권2호
• /
• pp.215-232
• /
• 1996

This paper presents a fuzzy set theory based formulation and heuristic which will allow plant layout problems to be solved for more than two input goals with different weights. The heuristic combines a construction and improvement procedure to generate a good layout from the formulation. To test the effectiveness of the heuristic, a set of examples previously used by various authors is solved and the results are compared to those from other known heuristics. The comparison indicates that the proposed method performs well for each of seventeen classical test problems.

• Communications for Statistical Applications and Methods
• /
• 제6권2호
• /
• pp.479-486
• /
• 1999

In this paper we propose the test statistic for ordered alternatives on multiple ranked set samples. Since the proposed test statistic is Page type its asymptotic properties are easily obtained. From the simulation works we calculate the power of test statistic($P_{RSS}$) under the underlying distributions such as uniform normal double exponential logistic and Cauchy distribution.

• 설비공학논문집
• /
• 제23권6호
• /
• pp.441-448
• /
• 2011

The energy consumption of a condensing gas boiler may be greatly reduced by the effective operation of the unit. In this study, the supply water algorithm for a condensing gas boiler control was developed by using the fuzzy logic. This includes the supply water set temperature algorithm, and the control algorithms of a gas valve, a blower and a pump. For the set temperature algorithm, the outside air temperature and the return water temperature were used as input variables. The supply water temperature difference and its slope were used as input variables of the gas valve and blower control algorithm. And the supply water temperature and the return water temperature were used as input variables of the pump control algorithm. In order to analyse performances of these algorithms, the dynamic model of a condensing gas boiler was used. The initial start-up test, the supply water set temperature change test, the outside air temperature change test, and the return water temperature change test were performed. Simulation results showed that algorithms developed in this study may be practically applied for the effective control of a condensing gas boiler.

• 디지털콘텐츠학회 논문지
• /
• 제18권3호
• /
• pp.525-534
• /
• 2017

열린 집합 인식 방법론은 테스트 데이터의 클래스를 학습 시에 모두 파악할 수 없는 경우에 대한 인식 방법론이다. 따라서 열린 집합 인식 방법론은 분류와 유효성 검증의 절차를 필요로 한다. 이러한 연구는 얼굴 인식 모듈의 상용화를 위해 필수적이지만 지금까지 국내에서 연구 결과들이 거의 발표되지 않았다. 우리는 두 개의 검증 단계를 가지는 열린 집합 얼굴 인식 방법론을 제안한다. 첫 번째 단계에서는 학습 클래스 외에 더미 클래스들을 설정하고 희소표현 기반 분류를 수행한다. 이 때 테스트 데이터가 더미 클래스로 분류되면 무효 데이터로 판별하고, 유효한 클래스로 분류되면 다음 유효성 검증 단계로 넘어간다. 두 번째 단계에서 제안하는 네 가지 특징을 추출하고, 확률분포에 기반을 둔 판별함수를 통해 유효성 검증을 수행한다. 우리는 실험을 통해 열린 집합 인식 방법론의 시뮬레이션 방법을 제안하였고 제안하는 방법론의 성능을 제시하고, 희소기반 분류 방식에서 널리 사용되는 SCI 지표를 이용한 유효성 테스트보다 높은 성능을 보임을 입증할 수 있었다.