• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2004년도 가을 학술발표회 논문집
• /
• pp.542-549
• /
• 2004

The compressive strength of concrete is commonly used criterion in producing concrete. However, the tests on the compressive strength are complicated and time-consuming. More importantly, it is too late to make improvement even if the test result does not satisfy the required strength, since the test is usually performed at the 28th day after the placement of concrete at the construction site. Therefore, accurate and realistic strength estimation before the placement of concrete is being highly required. In this study, the estimation of the compressive strength of concrete was performed by probabilistic neural network (PNN) on the basis of concrete mix proportions. The estimation performance of PNN was improved by considering the correlation between input data and targeted output value. Adaptive probabilistic neural network (APNN) was proposed to automatically calculate the smoothing parameter in the conventional PNN by using the scheme of dynamic decay adjustment algorithm. The conventional PNN and APNN were applied to predict the compressive strength of concrete using actual test data of a concrete company. APNN showed better results than the conventional PNN in predicting the compressive strength of concrete.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.61-63
• /
• 2005

Retreiving indoor scene reference image from database using visual information is important issue in Robot Navigation. Scene matching problem in navigation robot is not easy because input image that is taken in navigation process is affinly distorted. We represent probabilistic framework for the feature matching between features in input image and features in database reference images to guarantee robust scene matching efficiency. By reconstructing probabilistic scene matching framework we get a higher precision than the existing feaure-feature matching scheme. To construct probabilistic framework we represent each image as Gaussian Mixture Model using Expectation Maximization algorithm using SIFT(Scale Invariant Feature Transform).

• Structural Engineering and Mechanics
• /
• 제31권2호
• /
• pp.153-162
• /
• 2009

The reduction of the dynamic response of an offshore structure subjected to wind-generated random ocean waves is of extreme significance in the aspects of serviceability, fatigue life and safety of the structure. In this study, a new neuro-control scheme is applied to the vibration control of a fixed offshore platform under random wave loads to examine the applicability of the proposed method. It is called the Lattice Probabilistic Neural Network (LPNN), as it utilizes lattice pattern of state vectors as the training data of PNN. When control results of the LPNN are compared with those of the NN and PNN, LPNN showed better performance in effectively suppressing the structural responses in a shorter computational time.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2016년도 학술발표회
• /
• pp.197-197
• /
• 2016

Forecasting future drought events in a region plays a major role in water management and risk assessment of drought occurrences. The creeping characteristics of drought make it possible to mitigate drought's effects with accurate forecasting models. Drought forecasts are inevitably plagued by uncertainties, making it necessary to derive forecasts in a probabilistic framework. In this study, a new probabilistic scheme is proposed to forecast droughts, in which a discrete-time finite state-space hidden Markov model (HMM) is used aggregated with the Representative Concentration Pathway 8.5 (RCP) precipitation projection (HMM-RCP). The 3-month standardized precipitation index (SPI) is employed to assess the drought severity over the selected five stations in South Kore. A reversible jump Markov chain Monte Carlo algorithm is used for inference on the model parameters which includes several hidden states and the state specific parameters. We perform an RCP precipitation projection transformed SPI (RCP-SPI) weight-corrected post-processing for the HMM-based drought forecasting to derive a probabilistic forecast that considers uncertainties. Results showed that the HMM-RCP forecast mean values, as measured by forecasting skill scores, are much more accurate than those from conventional models and a climatology reference model at various lead times over the study sites. In addition, the probabilistic forecast verification technique, which includes the ranked probability skill score and the relative operating characteristic, is performed on the proposed model to check the performance. It is found that the HMM-RCP provides a probabilistic forecast with satisfactory evaluation for different drought severity categories, even with a long lead time. The overall results indicate that the proposed HMM-RCP shows a powerful skill for probabilistic drought forecasting.

• 콘크리트학회논문집
• /
• 제17권6호
• /
• pp.1075-1084
• /
• 2005

The compressive strength of concrete is commonly used criterion in producing concrete. However, the tests on the compressive strength are complicated and time-consuming. More importantly, it is too late to make improvement even if the test result does not satisfy the required strength, since the test is usually performed at the 28th day after the placement of concrete at the construction site. Therefore, accurate and realistic strength estimation before the placement of concrete is being highly required. In this study, the estimation of the compressive strength of concrete was performed by probabilistic neural network(PNN) on the basis of concrete mix proportions. The estimation performance of PNN was improved by considering the correlation between input data and targeted output value. Improved probabilistic neural network was proposed to automatically calculate the smoothing parameter in the conventional PNN by using the scheme of dynamic decay adjustment (DDA) algorithm. The conventional PNN and the PNN with DDA algorithm(IPNN) were applied to predict the compressive strength of concrete using actual test data of two concrete companies. IPNN showed better results than the conventional PNN in predicting the compressive strength of concrete.

• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1687-1696
• /
• 1995

An integrated fault diagnosis system for heterogeneous manufacturing environments is developed. This system has a contrast with existing diagnosis systems in the respect that they are mostly for diagnosing faults on individual machines. In addition to the usual (e.g., audio, electrical) diagnostic signals, the characteristics of products from the machines are considered as the unifying diagnostic parameters among heterogeneous machines in the diagnosis. The system is composed of a knowledge representation scheme and a diagnostic query processing mechanism. Its knowledge representation scheme allows the diagnostic knowledges from heterogeneous unit diagnostic systems to be uniformly expressed in terms of the causal relations among relevant data items. It is flexible in the sense that causes for one relation can be effects for another may be reflected on our knowledge representation scheme. The diagnosis mechanism is based on a probabilistic inferencing method. This probablistic diagnosis mechanism provides more general diagnosis than existing ones in that it accommodates multiple causes and takes complication among causes into account. These scheme and mechanism are applied to a typical example to demonstrate how our system works.

• 대한전자공학회논문지TC
• /
• 제45권11호
• /
• pp.15-22
• /
• 2008

1xEV-DO 시스템의 각 단말은 기지국이 전송하는 이진(binary) 제어정보와 고유한 확률모델을 기반으로 자신의 전송속도를 결정한다. 하지만, 이 전송속도 제어방법은 확률적 불확실성으로 인해 동작을 예측하기 어렵고, 역방향 링크의 과부하를 억제할 수 있는 확실한 수단이 없기 때문에, 간섭 제한(interference-limited) 용량을 갖는 CDMA 시스템의 성능을 저하시킬 수 있다. 본 논문에서는 기지국이 역방향 트래픽 부하를 예측하고, 순방향 제어채널을 통해 단말의 전송속도를 효과적으로 제어할 수 있는 방법을 제안한다. 본 논문은 제안한 방법을 다차원 마르코프 프로세스로 모델링하고 기존 방법들과 성능을 비교한다. 분석 결과에 의하면, 제안한 방법은 기존의 방법들과 비교하여 셀에서 지원할 수 있는 최대 전송효율(throughput)을 크게 향상시킴을 알 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제18권2호
• /
• pp.31-39
• /
• 2013

본 논문에서는 멀티코어 프로세서에서 단일 실시간 병렬 작업의 데드라인을 만족하면서 전력 소모량의 확률적 기대 값을 최소화하는 스케쥴링 기법을 제안하였다. 제안된 기법에서는 단일 작업을 여러 개의 코어들 상에서 동시에 수행하는 병렬 처리 기법을 적용하였고, 전체 코어들 중에서 일부의 코어들만을 사용하고 나머지 코어들의 전원을 소등하여 전력 소모량을 줄였다. 또한 한정된 개수의 이산적 클락 주파수 값들을 가지는 DVFS 기반 멀티코어 프로세서에 대해서, 확률적 계산량 모델을 가진 실시간 병렬 작업의 데드라인을 만족하면서 전력 소모량의 확률적 기대 값을 최소화함을 수학적으로 증명하였다. 성능평가 실험에서, 제안된 기법이 기존 방법의 전력소모량을 최대 81%까지 감소시킴을 확인하였다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2013년도 제48차 하계학술발표논문집 21권2호
• /
• pp.11-13
• /
• 2013

무선 센서 네트워크는 개방된 환경에서 무작위로 배치되어 악의적인 공격자들에게 쉽게 노출된다. 센서 노드는 한정된 에너지 자원과 손쉽게 훼손된다는 단점을 통해 허위 보고서와 투표 삽입 공격이 발생한다. Li와 Wu는 두 공격을 대응하기 위해 확률적 투표기반 여과기법을 제안하였다. 확률적 투표기반 여과기법은 고정적인 검증 경로를 결정하기 때문에 특정 노드의 에너지 자원고갈 위험이 있다. 본 논문에서는 센서 네트워크에서 보고서 여과 확률 향상을 위하여 퍼지 시스템을 기반으로 다음 노드 선택을 약 6% 효율적인 경로 선택 방법을 제안한다. 제안 기법은 전달 경로 상의 노드 중 상태정보가 높은 노드를 검증 노드로 선택하고, 선택된 검증 노드는 허용 범위 경계 값을 기준으로 공격 유형을 판별하고 여과한다. 실험결과를 통해 제안기법은 기존기법과 비교하였을 때 에너지 효율이 향상되었다.

• 한국지능시스템학회논문지
• /
• 제18권6호
• /
• pp.863-870
• /
• 2008

본 논문에서는 관측왜곡을 포함하고 있는 적응형 순항제어 시스템개발에 필수적인 필터링 방식에 대한 연구를 진행한다. 앞선 차량의 정확한 추적과 의도파악을 위하여 기본적으로 IMM (Interacting multiple model)을 사용하며 관측의 왜곡을 보상하기 위하여 확률적 퍼지 모델을 세안한다. 확률적 퍼지 모델은 기존의 결정형 퍼지모델과 달리 모델링 오차를 확률로 모델링한다. 끝으로 확률퍼지모델과 IMM을 결합한 FIMM (Fuzzy IMM)을 제안하여 관측왜곡이 발생하는 레이더를 이용한 전방차량의 추적 알고리즘을 제안한다.