• Animal Bioscience
• /
• 제37권4호
• /
• pp.622-630
• /
• 2024

Objective: Pig breeders cannot obtain phenotypic information at the time of selection for sow lifetime productivity (SLP). They would benefit from obtaining genetic information of candidate sows. Genomic data interpreted using deep learning (DL) techniques could contribute to the genetic improvement of SLP to maximize farm profitability because DL models capture nonlinear genetic effects such as dominance and epistasis more efficiently than conventional genomic prediction methods based on linear models. This study aimed to investigate the usefulness of DL for the genomic prediction of two SLP-related traits; lifetime number of litters (LNL) and lifetime pig production (LPP). Methods: Two bivariate DL models, convolutional neural network (CNN) and local convolutional neural network (LCNN), were compared with conventional bivariate linear models (i.e., genomic best linear unbiased prediction, Bayesian ridge regression, Bayes A, and Bayes B). Phenotype and pedigree data were collected from 40,011 sows that had husbandry records. Among these, 3,652 pigs were genotyped using the PorcineSNP60K BeadChip. Results: The best predictive correlation for LNL was obtained with CNN (0.28), followed by LCNN (0.26) and conventional linear models (approximately 0.21). For LPP, the best predictive correlation was also obtained with CNN (0.29), followed by LCNN (0.27) and conventional linear models (approximately 0.25). A similar trend was observed with the mean squared error of prediction for the SLP traits. Conclusion: This study provides an example of a CNN that can outperform against the linear model-based genomic prediction approaches when the nonlinear interaction components are important because LNL and LPP exhibited strong epistatic interaction components. Additionally, our results suggest that applying bivariate DL models could also contribute to the prediction accuracy by utilizing the genetic correlation between LNL and LPP.

• Structural Monitoring and Maintenance
• /
• 제2권1호
• /
• pp.77-93
• /
• 2015

The idea of using measured dynamic characteristics for damage detection is attractive because it allows for a global evaluation of the structural health and condition. However, vibration-based damage detection for complex structures such as long-span cable-supported bridges still remains a challenge. As a suspension or cable-stayed bridge involves in general thousands of structural components, the conventional damage detection methods based on model updating and/or parameter identification might result in ill-conditioning and non-uniqueness in the solution of inverse problems. Alternatively, methods that utilize, to the utmost extent, information from forward problems and avoid direct solution to inverse problems would be more suitable for vibration-based damage detection of long-span cable-supported bridges. The auto-associative neural network (ANN) technique and the probabilistic neural network (PNN) technique, that both eschew inverse problems, have been proposed for identifying and locating damage in suspension and cable-stayed bridges. Without the help of a structural model, ANNs with appropriate configuration can be trained using only the measured modal frequencies from healthy structure under varying environmental conditions, and a new set of modal frequency data acquired from an unknown state of the structure is then fed into the trained ANNs for damage presence identification. With the help of a structural model, PNNs can be configured using the relative changes of modal frequencies before and after damage by assuming damage at different locations, and then the measured modal frequencies from the structure can be presented to locate the damage. However, such formulated ANNs and PNNs may still be incompetent to identify damage occurring at the deck members of a cable-supported bridge because of very low modal sensitivity to the damage. The present study endeavors to enhance the damage identification capability of ANNs and PNNs when being applied for identification of damage incurred at deck members. Effort is first made to construct combined modal parameters which are synthesized from measured modal frequencies and modal shape components to train ANNs for damage alarming. With the purpose of improving identification accuracy, effort is then made to configure PNNs for damage localization by adapting the smoothing parameter in the Bayesian classifier to different values for different pattern classes. The performance of the ANNs with their input being modal frequencies and the combined modal parameters respectively and the PNNs with constant and adaptive smoothing parameters respectively is evaluated through simulation studies of identifying damage inflicted on different deck members of the double-deck suspension Tsing Ma Bridge.

• Journal of the Korean Data and Information Science Society
• /
• 제9권2호
• /
• pp.345-355
• /
• 1998

다층전방향 신경망을 학습시키기 위해 역전파 알고리즘이 널리 사용되고 있으나 이 알고리즘은 긴 훈련시간, 극소점 문제, 이상치에 민감하다는 단점을 가지고 있다. 한편 실제문제에서는 많은 경우에 자료에 과대오차와 이상치가 포함되게 된다. 따라서 과대 오차에 민감하지 않고, 이상치의 영향을 최소화시키는 로버스트 역전파 알고리즘의 필요성이 대두되었다. 본 논문에서는 기존의 두종류의 로버스트 역전파 알고리즘을 이론적으로 비교하고 비선형 회귀 함수추정과 문자인식과 같은 패턴인식 문제에 적용하여 실험결과를 분석한다. 그리고 향후 연구과제로 신경망 학습을 위해 베이지안 기법의 사용을 제안한다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 한국컴퓨터종합학술대회논문집 Vol.34 No.1 (C)
• /
• pp.248-251
• /
• 2007

기존의 멀티 카메라 시스템은 넓은 영역을 커버하거나 이동 중인 물체를 트래킹 하기 위한 목적으로 주로 사용되어 왔다. 하지만 이러한 시스템은 하나의 카메라가 커버하는 영상이 가려지면 정보를 잃게 되는 단점이 있다. 멀티 카메라 시스템은 하나의 영역을 여러 카메라가 커버하도록 하여 이런 단점을 극복할 수 있다. 또한 다양한 시점의 카메라에서 수집되는 영상의 경우, 영상에 따라 담고 있는 정보가 다르므로 여러 카메라의 입력 정보를 함께 활용하여 보다 많은 정보를 얻을 수도 있다. 본 논문은 이런 장점을 활용하여 멀티 카메라 환경에서의 이벤트 인식 문제를 다룬다. 이를 위해 사무실 환경에 8대의 카메라를 설치하였으며, 시나리오에 따라 영상을 수집하였다. 수집된 영상은 전문가에 의해 어노테이션 된 후 인식 모델의 학습에 사용되며, 학습된 베이지안 네트워크 모델의 구조와 파라미터를 도메인 지식에 기반해서 수정하여 최종 이벤트 인식 모델을 설계하였다. 실험 결과 제안하는 이벤트 인식 모델의 인식률은 평균 87.0%로 Naive Bayes보다 우수한 성능을 보임을 확인하였다.

• Computers and Concrete
• /
• 제10권6호
• /
• pp.557-573
• /
• 2012

This paper discusses the combined application of two different techniques, Neural Networks (NN) and Principal Component Analysis (PCA), for improved prediction of concrete properties. The combination of these approaches allowed the development of six neural networks models for predicting slump and compressive strength of concrete with mineral additives such as blast furnace slag, fly ash and silica fume. The Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian regularization was used in all these models. They are produced to implement the complex nonlinear relationship between the inputs and the output of the network. They are also established through the incorporation of a huge experimental database on concrete organized in the form Mix-Property. Thus, the data comprising the concrete mixtures are much correlated to each others. The PCA is proposed for the compression and the elimination of the correlation between these data. After applying the PCA, the uncorrelated data were used to train the six models. The predictive results of these models were compared with the actual experimental trials. The results showed that the elimination of the correlation between the input parameters using PCA improved the predictive generalisation performance models with smaller architectures and dimensionality reduction. This study showed also that using the developed models for numerical investigations on the parameters affecting the properties of concrete is promising.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.477-480
• /
• 2007

얼굴 동작을 효과적으로 인식하는 방법을 제안하고자 한다. 얼굴 동작은 얼굴 표정, 얼굴 자세, 시선, 주름 같은 얼굴 특징이나 얼굴 행동 등으로 표출될 수 있다. 이러한 표출된 정보들은 얼굴 동작이 다양하고 명확하지 않아 연구 진행에 많은 어려움이 있다. 그러므로, 본 논문에서는 얼굴 동작을 묘사하는 FACS를 기반으로 하여 시각적 관찰에 의해 주요한 얼굴 동작을 표현하고, 베이지안 네트워크를 통하여 여러 정보를 분석 융합하여 얼굴 행동을 추론 할 수 있도록 하였다. 베이지안 네트워크의 하향식 추론으로 시각 정보를 선택 할 수 있고, 관측된 현상을 토대로 상향식 추론 하여 얼굴 동작의 신뢰 전파를 통하여 분류 인식한다.

• Journal of Communications and Networks
• /
• 제10권3호
• /
• pp.268-286
• /
• 2008

In this work, we review the routing models that use game theoretical methodologies. A very common assumption in the analysis and development of networking algorithms is the full cooperation of the participating nodes. Most of the analytical tools are based on this assumption. However, the reality may differ considerably. The existence of multiple domains belonging to different authorities or even the selfishness of the nodes themselves could result in a performance that significantly deviates from the expected one. Even though it is known to be extensively used in the fields of economics and biology, game theory has attracted the interest of researchers in the field of communication networking as well. Nowadays, game theory is used for the analysis and modeling of protocols in several layers, routing included. This review aims at providing an elucidation of the terminology and principles behind game theory and the most popular and recent routing models. The examined networks are both the traditional networks where latency is of paramount importance and the emerging ad hoc and sensor networks, where energy is the main concern.

• 대한전자공학회논문지SP
• /
• 제42권3호
• /
• pp.1-6
• /
• 2005

변이 영상을 마코브 랜덤필드(MRF)로 모델링한 마코브 네트워크에서 신뢰확산 알고리듬은 각 화소에 대응되는 노드들 사이에 메시지를 전달하는 방식으로 이루어진다. 최초 메시지는 알고리듬의 반복을 통해 특정한 값으로 수렴하게 되며, 수렴된 값을 얻기 위해서는 많은 알고리듬의 반복이 필요하다. 본 논문에서는 알고리듬의 반복을 줄이기 위해 영상내 물체들을 선들의 조합 구성으로 보고 각각의 선들은 같은 메시지를 갖는 노드들의 집합으로 간주하여 기존의 신뢰확산 알고리듬을 단순화하였다.

• 한국인터넷방송통신학회논문지
• /
• 제10권2호
• /
• pp.13-18
• /
• 2010

오늘날의 스팸 메일이 메일 서버와 네트워크 저장장치의 대부분을 차지함으로 인해 네트워크 부하와 같은 부정적인 문제가 발생하고 있으며 사용자 입장에서는 스팸을 삭제하기 위한 시간과 자원 소모 같은 문제를 가지고 있다. 자동 스팸 메일 필터링은 문제 해결위한 필수적인 요소로 부각 되었다. 대표적인 방법은 나이브 베이지안 방법과 달리 PCA를 통하여 많은 차원을 가지는 스팸 테이터 집합을 몇 개의 주축으로 차원을 축소 시켜 연차 처리의 부담을 줄이고 특정 집으로 분류를 위한 로지스틱 회귀 분석 방법을 사용하여 스팸 필터링을 하였다. 이를 통하여 속도와 성능 두가지의 성과를 얻을 수 있었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.600-602
• /
• 1997

In this study, a hybrid neural net consisting of an Adaptive LVQ(ALVQ) algorithm and MLP is proposed to perform speaker identification task. ALVQ is a new learning procedure using adaptively feature vector sequence instead of only one feature vector in training codebooks initialized by LBG algorithm and the optimization criterion of this method is consistent with the speaker classification decision rule. ALVQ aims at providing a compressed, geometrically consistent data representation. It is fit to cover irregular data distributions and computes the distance of the input vector sequence from its nodes. On the other hand, MLP aim at a data representation to fit to discriminate patterns belonging to different classes. It has been shown that MLP nets can approximate Bayesian "optimal" classifiers with high precision, and their output values can be related a-posteriori class probabilities. The different characteristics of these neural models make it possible to devise hybrid neural net systems, consisting of classification modules based on these two different philosophies. The proposed method is compared with LBG algorithm, LVQ algorithm and MLP for performance.