• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.316-320
• /
• 1998

한국어나 일본어처럼 문법형태소의 기능에 의해 단어의 통사적, 의미적 역할이 결정되는 교착어에서는 형태소 분석이 통사 분석과 의미 분석에 미치는 영향이 크기 때문에 한국어의 분석에 있어서 형태소 분석은 아주 중요하다. 관형적 표현이 많은 한글은 문법 규칙만으론 분석하기가 쉽지 않고, 분기가 많이 생성되므로 오류가 발생할 확률도 높다. 이러한 문제점을 해결하기 위해 본 논문에선 사전을 중심으로 해결하고자 한다. 그러기 위해선 방대한 용량의 사전이 필요로 하게 되고 이를 구축하기 위한 시간과 노력이 요구되므로 이미 구성된 코퍼스를 이용해 사전을 구성하여 많은 시간과 노력을 줄일 수 있도록 한다. 그리고 생성되는 많은 분기 가운데 올바른 경로를 찾아 가기 위해 코퍼스내의 각 태그 결합정보를 추출하고 추출한 결합정보의 통계정보-코퍼스내에서 사용된 빈도수-포함하여 우선순위를 정하도록 한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.309-314
• /
• 1998

언어학적 단위인 형태소의 특성을 유지하면서 음성인식 과정에 적합한 분리 기준의 새로운 디코딩 단위인 의사형태소를 정의하였다. 이러한 필요성을 확인하기 위해 새로이 정의된 37개의 품사 태그를 갖는 의사 형태소를 표제어 단위로 삼아 발음사전 생성과 형태소 해석에 초점을 두고 한국어 연속음성 인식 시스템을 구성하였다. 각 음성신호 구간에 해당되는 의사 형태소가 인식되면 언어모델을 사용하여 구성된 의사 형태소 단위의 상위 5개 문장을 기반으로 시작 시점과 끝 시점, 그리고 확률 값을 가진 의사 형태소 격자를 생성하고, 음성 사전으로부터 태그 정보를 격자에 추가하였다. Tree-trellis 탐색 알고리즘 기반에 의사 형태소 접속정보를 사용하여 음성언어 형태소 해석을 수행하였다. 본 논문에서 제안한 의사 형태소를 문장의디코딩 단위로 사용하였을 경우, 사전의 크기면에서 어절 기반의 사전 entry 수를 현저히 줄일 수 있었으며, 문장 인식률면에서 문자기반 형태소 단위보다 약 20% 이상의 인식률 향상을 얻을 수있었다. 뿐만 아니라 형태소 해석을 수행하기 위해 별도의 분석과정 없이 입력값으로 사용되며, 전반적으로 문자을 구성하는 디코딩 수를 안정화 시킬 수 있었다. 이 결과값은 상위레벨 언어처리를 위한 입력？으로 사용될 뿐만 아니라, 언어 정보를 이용한 후처리 과정을 거쳐 더 나은 인식률 향상을 꾀할 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.279-284
• /
• 2008

본 연구에서는 어절패턴을 이용하는 새로운 방식의 한국어 형태소 분석기 KGuru-MA에 대해서 설명한다. KGuru-MA는 품사 부착 말뭉치에서 개방어를 생략하여 어절 패턴을 반자동으로 학습하여 어절 패턴 사전과 형태소 확률 정보 사전을 구성한 후, 이 사전을 이용하여 형태소를 분석한다. 본 형태소 분석기는 어절패턴을 사용하여 형태소 분석하기 때문에 기존 형태소 분석기에 존재하는 접속검사 과정이 생략된다. 또한, 형태소 분석 과정이 기존의 형태소 분석기에 비해 단순하여 기초 자연언어 처리 시스템이 가지는 강건성을 보장한다. 본 연구는 "21세기 세종기획 3차년도 말뭉치"를 이용한 실험 결과, 기존 형태소 분석기 못지 않은 성능을 보였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.3
• /
• pp.465-470
• /
• 2013

Dempster-Shafer Evidence Theory is available for multi-sensor data fusion. Basic Probability Assignment is essential for multi-sensor data fusion using Dempster-Shafer Theory. In this paper, we proposed a novel method of BPA calculation with signal assessment. We took notice of the signal that reported from the sensor mote at the time slot. We assessed the variation rate of the reported signal from the terminal. The trend of variation implies significant component of the context. We calculated the variation rate of signal for reveal the relation of the variation and the context. We could reach context inference with BPA that calculated with the variation rate of signal.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.1
• /
• pp.1-12
• /
• 2014

Crown fire, the main propagation type of large forest fire, has caused extreme damage with the fast spread rate and the high flame intensity. In this paper, we developed the probability equation to predict the crown fires using the spatial features of topography, fuel and weather in damaged area by crown fire. Eighteen variables were collected and then classified by burn severity utilizing geographic information system and remote sensing. Crown fire ratio and logistic regression model were used to select related variables and to estimate the weights for the classes of each variables. As a results, elevation, forest type, elevation relief ratio, folded aspect, plan curvature and solar insolation were related to the crown fire propagation. The crown fire propagation probability equation may can be applied to the priority setting of fuel treatment and suppression resources allocation for forest fire.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.7
• /
• pp.537-546
• /
• 2020

The reliability used as a performance indicator during the development of space launch vehicle should be validated by the launch success probability, and the launch data need to be fed back for reliability management. In this paper, the launch data of space launch vehicles around the world were investigated and statistically analyzed for the success probabilities according to the launch vehicle models and maturity. The Bayesian estimation of launch success probability was reviewed and analyzed by comparing the estimated success probabilities using several prior distributions and the statistical success probability. We presented the method of generating prior distribution function and considerations for Bayesian estimation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.11A
• /
• pp.1063-1071
• /
• 2008

This paper proposes a prior maximum likelihood (ML) detection verifier which has an ability to verify if the zero forcing (ZF) detection results are identical to the ML detection results. Since more than 90% of ZF detection results are identical to ML detection results, the proposed verifier makes it possible to omit the computationally complex ML detection in 90% cases of MIMO signal detections. The proposed verifier is designed by using the diversity gain obtained from converting MIMO signal into single input multiple output (SIMO) signals. In the proposed method, single input multiple output (SIMO) signals for each transmit antenna are separated from MIMO signals after the MIMO signals are detected by ZF method. Computer simulations show that the true alarm probability of the proposed verifier is more than 80% and the false alarm probability is less than $10^{-4}$.

• The Journal of Engineering Geology
• /
• v.26 no.4
• /
• pp.485-495
• /
• 2016

To reinforce and improve the soft ground under a breakwater while using materials efficiently, the replacement ratio and leaving periods of surcharge load are optimized probabilistically. The results of Bayesian updating of the random variables using prior information decrease uncertainty by up to 39.8%, and using prior information with more samples results in a sharp decrease in uncertainty. Replacement ratios of 15%-40% are analyzed using First Order Reliability Method and Monte Carlo simulation to optimize the replacement ratio. The results show that replacement ratios of 20% and 25% are acceptable at the column jet grouting area and the granular compaction pile area, respectively. Life cycle costs are also compared to optimize the replacement ratios within allowable ranges. The results show that a range of 20%-30% is the most economical during the total life cycle. This means that initial construction cost, maintenance cost and failure loss cost are minimized during total life cycle. Probabilistic analysis for leaving periods of shows that three months acceptable. Design optimization with respect to life cycle cost is important to minimize maintenance costs and retain the performance of the structures for the required period. Therefore, more case studies that consider the maintenance costs of soil structures are necessary to establish relevant design codes.

• Korean Journal of Remote Sensing
• /
• v.27 no.4
• /
• pp.445-455
• /
• 2011

A probabilistic classification framework is presented that can combine temporal contextual information derived from an existing land-cover map in order to improve the classification accuracy of land-cover classes that can not be discriminated well when using spectral information only. The transition probability is computed by using the existing land-cover map and training data, and considered as a priori probability. By combining the a priori probability with conditional probability computed from spectral information via a Bayesian combination rule, the a posteriori probability is finally computed and then the final land-cover types are determined. The method presented in this paper can be adopted to any probabilistic classification algorithms in a simple way, compared with conventional classification methods that require heavy computational loads to incorporate the temporal contextual information. A case study for crop classification using time-series MODIS data sets is carried out to illustrate the applicability of the presented method. The classification accuracies of the land-cover classes, which showed lower classification accuracies when using only spectral information due to the low resolution MODIS data, were much improved by combining the temporal contextual information. It is expected that the presented probabilistic method would be useful both for updating the existing past land-cover maps, and for improving the classification accuracy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.3
• /
• pp.311-316
• /
• 2009

This paper presents the motion estimation algorithm on real-time for mobile surveillance robot using particle filter. the particle filter that based on the monte carlo's sampling method, use bayesian conditional probability model which having prior distribution probability and posterior distribution probability. However, the initial probability density was set to define randomly in the most of particle filter. In this paper, we find first the initial probability density using Sum of Absolute Difference(SAD). and we applied it in the partical filter. In result, more robust real-time estimation and tracking system on the randomly moving object was realized in the mobile surveillance robot environments.