• Journal of Multimedia Information System
• /
• 제8권2호
• /
• pp.93-100
• /
• 2021

Under the time-varying temperature, the high-temperature radiation of forgings and the change of reflection characteristics of oxide skin on the surface of forgings lead to the difficulty of obtaining images to truly reflect the geometric characteristics of forgings. It is urgent to study the clear and reliable acquisition method of hot forging feature image under time-varying temperature to meet the requirements of visual measurement of hot geometric parameters of forgings. Based on this, this chapter first puts forward the quality evaluation method of forging feature image, which provides guarantee for the accurate evaluation of feature image quality. Furthermore, the factors that affect the image quality, such as the radiation characteristics of forgings and the photographic characteristics of cameras, are analyzed, and the imaging spectrum which can effectively suppress the radiation intensity of forgings is determined. Finally, aiming at the problem that the quality of image acquisition is difficult to guarantee due to the drastic change of radiation intensity of forgings under time-varying temperature, an image acquisition method based on minimum signal-to-noise ratio (SNR) based laser light intensity adaptation is proposed, which significantly improves the definition of feature light strips in forging images at high temperature, and finally realizes the clear acquisition of feature images of large-scale hot forging under time-varying temperature.

• ETRI Journal
• /
• 제45권3호
• /
• pp.448-461
• /
• 2023

This article performs a detailed data scrutiny on a chronic kidney disease (CKD) dataset to select efficient instances and relevant features. Data relevancy is investigated using feature extraction, hybrid outlier detection, and handling of missing values. Data instances that do not influence the target are removed using data envelopment analysis to enable reduction of rows. Column reduction is achieved by ranking the attributes through feature selection methodologies, namely, extra-trees classifier, recursive feature elimination, chi-squared test, analysis of variance, and mutual information. These methodologies are ranked via Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using weight optimization to identify the optimal features for model building from the CKD dataset to facilitate better prediction while diagnosing the severity of the disease. An efficient hybrid ensemble and novel similarity-based classifiers are built using the pruned dataset, and the results are thereafter compared with random forest, AdaBoost, naive Bayes, k-nearest neighbors, and support vector machines. The hybrid ensemble classifier yields a better prediction accuracy of 98.31% for the features selected by extra tree classifier (ETC), which is ranked as the best by TOPSIS.

• 인지과학
• /
• 제10권3호
• /
• pp.1-15
• /
• 1999

시각적 선택에 대한 과거 정신물리학적, 신경 생리학적 연구결과를 토대로 Feature Gate 라는 신경 망 모형을 제안하였다. 이 모형에는 공간 배치도가 위계 적으로 구성되어 있으며, 정보의 흐름이 위계의 각 수준으로부터 그 다음 수준으로 넘어갈 때 주의 게이트에 의해 조절되도록 되어 있다. 주의 게이트들은 독특한 세부 특징을 가진 위치에 반응하는 상향식 시스템과 표적 세부 특징이 있는 위치에 반응하는 하향식 기제 모두에 의해 조절된다. 본 연구는 Feature Gate 모형의 하향식 기제에 초점을 맞추어 모형을 설명하고, 현재 다른 모형들이 설명하지 못하는 Moran & Desimone(1985)의 연구결과를 이 모형이 어떻게 설명하는지를 제시하고자 한다. Feature Gate 모형은 병렬 적인 세부특징 검색, 계열 적 접합표적 검색, 단서에 의한 주의의 점진적 감소 모형, 세부특징-주도적인 공간적 선택, 주의의 분할, 방해자극 위치의 억제, 주변 억제 등을 포함한 시각적 주의 연구의 여러 가지 많은 현상들을 설명하는데 하나의 일관적인 해석을 제공해 준다. 앞으로 이 모형을 더욱 확장, 발전 시켜 세부특징의 조합된 배열에 반응하는 상위 수준의 유닛을 사용한다면 시각적 선택과정이 포함된 형태 재인 모형으로 개발될 수 있다.

• 한국정보통신학회논문지
• /
• 제22권1호
• /
• pp.125-130
• /
• 2018

선형판별분석(LDA) 기법은 특징벡터의 차원을 줄이거나 클래스 식별에 이용되는 통계적 분석 방법이다. 그러나 선형 분리가 불가능한 데이터 집합의 경우에는 비선형 함수를 이용하여 특징벡터를 고차원의 공간으로 사상(mapping) 시켜줌으로써 선형 분리가 가능하도록 만들 수 있는데, 이러한 기법을 일반화된 판별분석(GDA) 또는 커널판별분석(KDA) 기법이라고 한다. 본 연구에서는 인터넷에 공개되어 있는 능동소나 표적신호에 LDA 및 GDA 기법을 이용하여 표적식별 실험을 수행하고, 그 결과를 비교/분석하였다. 실험 결과 104개의 테스트 데이터에 대해 LDA 기법으로는 73.08% 인식률을 얻었으나 GDA 기법으로는 95.19%로 기존의 MLP 또는 커널 기반 SVM에 비해 나은 성능을 보였다.

• 한국멀티미디어학회논문지
• /
• 제25권10호
• /
• pp.1375-1385
• /
• 2022

In this paper, we propose a semi-supervised domain adaptation solution to deal with practical face recognition (FR) scenarios where a single face image for each target identity (to be recognized) is only available in the training phase. Main goal of the proposed method is to reduce the discrepancy between the target and the source domain face images, which ultimately improves FR performances. The proposed method is based on the Domain Adatation network (DAN) using an MMD loss function to reduce the discrepancy between domains. In order to train more effectively, we develop a novel loss function learning strategy in which MMD loss and cross-entropy loss functions are adopted by using different weights according to the progress of each epoch during the learning. The proposed weight adoptation focuses on the training of the source domain in the initial learning phase to learn facial feature information such as eyes, nose, and mouth. After the initial learning is completed, the resulting feature information is used to training a deep network using the target domain images. To evaluate the effectiveness of the proposed method, FR performances were evaluated with pretrained model trained only with CASIA-webface (source images) and fine-tuned model trained only with FERET's gallery (target images) under the same FR scenarios. The experimental results showed that the proposed semi-supervised domain adaptation can be improved by 24.78% compared to the pre-trained model and 28.42% compared to the fine-tuned model. In addition, the proposed method outperformed other state-of-the-arts domain adaptation approaches by 9.41%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• 한국인터넷방송통신학회논문지
• /
• 제18권3호
• /
• pp.61-69
• /
• 2018

본 논문에서는 밀리미터파대역의 공대지 레이다에서 이중 편파 채널을 활용한 지상 표적을 식별하기 위한 방법을 제안한다. 먼저 공대지 레이다의 조우 상황에서 Push-Broom 표적 탐지 방법을 설명하고 수신 신호를 모델링한다. 시간 영역 스펙트럼 추정 기법인 RELAX 알고리즘을 이용하여 산란점을 추출하고 표적의 특성 벡터를 생성하였다. 그리고 이를 기반으로 각각의 4표적에 대한 DB를 구성하였다. 제안하는 방법으로 표적 식별 시뮬레이션을 수행한 결과 이중 편파 채널의 데이터를 이용하면 단일 채널에 비해서 표적 식별률이 최대 15% 이상 높아지는 것을 확인할 수 있었다.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2001년도 춘계학술대회논문집D
• /
• pp.915-920
• /
• 2001

A spent fuel problem has prevented the nuclear power from claiming to be a completely clean energy source. The nuclear transmutation technology to incinerate the long lived radioactive nuclides and produce energy during the incineration process is believed to be one or the best solutions. HYPER(Hybrid Power Extraction Reactor) is the accelerator driven transmutation system which is being developed by KAERI(Korea Atomic Energy Research Institute). Some major feature of HYPER have been developed and employed. On-power fueling concepts are employed to keep system power constant with minimum variation of accelerator power. A hollow cylinder-type metal fuel is designed for the on-line refueling concept. Lead-bismuth(Pb-Bi) is adopted as a coolant and Spallation target material. HYPER is a subcritical reactor which needs an external neutron source. 1GeV proton beam is irradiated to Lead-bismuth(Pb-Bi) target inside HYPER, and spallation neutrons are produced. When proton beams are irradiated, much heat is also deposited in the Pb-Bi target and beam window which separates Pb-Bi and accelerator vacuum. Therfore, an effective cooling is needed for HYPER target. In this paper, we performed the thermal-hydraulic analysis of HYPER target using FLUENT code, and also calculated thermal and mechanical stress of the beam window using ANSYS code.

• Journal of Electrical Engineering and Technology
• /
• 제8권6호
• /
• pp.1520-1529
• /
• 2013

In this paper, we propose and assess the performance of "H infinity filter ($H_{\infty}$, HIF)" and "cost reference particle filter (CRPF)" in the problem of tracking a target based on the measurements of the range and the bearing of the target. HIF and CRPF have the common advantageous feature that we do not need to know the noise statistics of the problem in their applications. The performance of the extended Kalman filter (EKF) is also compared with that of the proposed filters, but the noise information is perfectly known for the applications of the EKF. Simulation results show that CRPF outperforms HIF, and is more robust because the tracking of HIF diverges sometimes, particularly when the target track is highly nonlinear. Interestingly, when the tracking of HIF diverges, the tracking of the EKF also tends to deviate significantly from the true track for the same target track. Therefore, CRPF is very effective and appropriate approach to the problems of highly nonlinear model, especially when the noise statistics are unknown. Nonetheless, HIF also can be applied to the problem of timevarying state estimation as the EKF, particularly for the case when the noise statistcs are unknown. This paper provides a good example of how to apply CRPF and HIF to the estimation of dynamically varying and nonlinearly modeled states with unknown noise statistics.

• 한국음향학회지
• /
• 제28권2호
• /
• pp.135-140
• /
• 2009

본 논문에서는 하이라이트 모델에 기반하여 능동소나의 표적신호를 합성하고, 합성된 신호를 이용하여 표적인식 실험을 수행하였다. 동일 표적이라도 표적의 자세각에 따라 다양한 형태의 파형을 갖는 신호가 합성되는데, 이에 대한 표적인식 결과를 알아보기 위해서 두 가지 방법으로 실험을 수행하였다. 하나는 고정된 여러 가지 자세각에 대한 표적신호에 대한 인식실험이고, 다른 하나는 임의의 자세각을 가지는 교신에 대만 인식 실험을 수행하였다. 인식실험을 위한 특징 인자로는 합성된 표적신호에 대해 시간영역에서 정합필터 및 포락선 검출을 통해 얻어지는 하이라이트 패턴을 사용하였으며, 패턴인식 기법으로는 다중클래스 SVM과 인공신경망을 사용하였다.