• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.389-399
• /
• 2021

In recent years, word embedding has been a popular field of natural language processing research and a skip-gram has become one successful word embedding method. It assigns a word embedding vector to each word using contexts, which provides an effective way to analyze text data. However, due to the limitation of vector space model, primary word embedding methods assume that every word only have a single meaning. As one faces multi-sense words, that is, words with more than one meaning, in reality, Neelakantan (2014) proposed a multi-sense skip-gram (MSSG) to find embedding vectors corresponding to the each senses of a multi-sense word using a clustering method. In this paper, we propose a modified method of the MSSG to improve statistical accuracy. Moreover, we propose a data-adaptive choice of the number of clusters, that is, the number of meanings for a multi-sense word. Some numerical evidence is given by conducting real data-based simulations.

• Korean Journal of Ecology and Environment
• /
• v.38 no.4 s.114
• /
• pp.482-493
• /
• 2005

The objective of this research was to evaluate an sampling effect of fish species and individual number on sampling techniques of electrofishing and conventional capture methods of cast net and kick net in 38 stream sites sampled during June - September, 2005. For the study, sampling gears were categorized as three types of electrofishing method (EM), conventional sampling technique (CM), and the combined technique (CT) of the electrofishing and the conventional method to compare statistical differences. Major differences of species composition between the CM and EM method were found in some benthic species of Misgurnus mizolepis and Iksookimia koreensis along with lithophilic species of Pungtungia herzi. These species were predominated in the EM rather than the CM, indicating that conventional sampling can underestimate the abundance of benthic or lithophilic species. In contrast ,individual number of typical water column species such as Zacco platypus and Zacco temmincki were more sampled by the CM, so that these fish populations were community overestimated. Also, t-tests on the types of sampling gear from various watersheds of Chogang Stream, Yugu Stream, Daejeon Stream, and Gap Stream showed that total individual numbers and species number in each stream were significantly (t values = 2.806-6.896, p values<0.05, n = 5-14) greater in the CT than the CM. Similar statistical significance (p<1.001, n = (10-24) on sampling seasons were observed during the monsoon and postmonsoon. These results indicate that if the electrofishing is not added to the conventional gears, the abundance of fish population and community can be underestimated and some benthic or lithophilic species may be excluded from the analysis, resulting in overall errors including sampling, fish fauna, and final judgement of community abundance. Overall our results strongly suggest that new application of electrofishing method along with the conventional sampling gears reduce sampling bias on underestimation of the real fish populations and communities.

• Korean Journal of Ecology and Environment
• /
• v.50 no.1
• /
• pp.148-156
• /
• 2017

In this study, we analyzed the relationship between phytoplankton community and physicochemical factors in 12 lakes located in Jeollanam-do based on the data surveyed from March to November 2014. Totally, 297 species of phytoplankton were identified including 98 Bacillariophyceae, 148 Chlorophyceae, 23 Cyanophyceae and 28 other phytoplankton taxa. The standing crops ranged from 124 to $59,148cells\;mL^{-1}$ and showed the highest in August with the increase of Cyanophycean cells. The self-organizing map (SOM) was optimized into $9{\times}6$ grid and was classified into 5 clusters based on the similarity of environmental factors and phytoplankton indices. The SOM results showed that phytoplankton communities had positive relationship with water temperature, SS, DO, BOD, TP and Chl-a, whereas low relationship with pH, TN, $NH_3-N$, $NO_3-N$, $PO_4-P$ and Conductivity. In Pearson's correlation coefficient, relationship between environmental factors and phytoplankton communities showed similar results with SOM.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.3
• /
• pp.170-178
• /
• 2012

In the paper, phonetic decision tree of the triphone unit was built for the phoneme-based speech recognition of 640 stations which run by the Korail. The clustering rate was determined by Pearson and Regression analysis to decide threshold used in node splitting. Using the determined the clustering rate, thresholds are automatically decided by the threshold value according to the average clustering rate. In the recognition experiments for verifying the proposed method, the performance improved 1.4~2.3 % absolutely than that of the baseline system.

• Journal of IKEEE
• /
• v.12 no.2
• /
• pp.87-94
• /
• 2008

Pelvic floor muscle is the main subsystem that maintains urinary continence. It is possible to diagnose the degree of the stress urinary incontinence(SUI) by evaluating the contraction pressure of the pelvic floor muscle. Bio-signal measurement system was developed to measure the contraction pressure. Diagnostic parameters were drawn out by analyzing the measured data. Statistical evaluations were done to classify the all subjects with five groups each has similar characteristics. SUI diagnostic algorithm was implemented to each group separately. The accuracy of the algorithm was about 78.9% and utility was confirmed by clinical trial.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.162-162
• /
• 2017

최근 우리나라는 전 지구적인 기후변화로 인하여 집중호우 및 돌발 홍수와 같은 극치 사상들이 증가하고 있는 추세이며, 이에 대한 분석을 위해 극치 분포를 이용한 수문통계적 특성에 대한 접근이 주로 이루어지고 있다. 이를 위해서는 충분한 수의 자료가 필요하나 우리나라 강우자료는 지점별로 자료 보유 년 수가 비교적 많지 않기 때문에, 이러한 문제를 극복하기 위하여 하나의 지역, 즉 주어진 지점을 포함하여 수문학적으로 동일한 조건을 만족하는 주변 지점의 자료를 모두 포함하여 빈도해석을 실시하는 지역빈도해석이 필요하다. 따라서 본 연구에서는 지역빈도해석과 두 개의 형상매개변수를 포함하여 다양한 극치 수문통계특성을 나타낼 수 있다고 알려진 Burr XII 분포를 이용하여 우리나라 강우자료에 대한 그 적용성을 살펴보았다. 이를 위해 군집분석을 통한 강우지점의 지역화 과정을 거치고 분류된 지역을 L-moment ratio diagram에 도시하여, Burr XII 분포 영역 내 포함여부를 통해 Burr XII 분포의 적합도를 도시적으로 살펴보고, Hosking and Wallis (1997)이 제안한 적합성 척도($^{IST}$)를 통한 적합성 여부를 판별하였다. 또한 우리나라 강우자료에 비교적 적합하다고 알려진 분포인 generalized extreme value, generalized logistic, Gumbel 분포와의 비교를 위해, 전체 지역에 대하여 재현기간에 따른 상대편의 (relative bias)와 상대평균제곱근오차 (relative root mean square error)를 산정하여 Burr XII 분포형의 적용 가능성을 살펴보았다.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.17 no.2
• /
• pp.93-101
• /
• 2015

This study was conducted to analyze the relationship between tree-ring growth of Quercus acutissima and climatic variables by dendroclimatological method. Annual tree-ring growth data of Quercus acutissima collected by the $5^{th}$ National Forest Inventory (NFI5) were organized to analyze the spatial distribution of the species growth pattern. To explain the relationship between tree-ring growth of Quercus acutissima and climatic variables, monthly temperature and precipitation data from 1950 to 2010 were compared with tree-ring growth data for each county. When tree-ring growth data were analyzed through cluster analysis based on similarity of climatic conditions, four clusters were identified. In addition, index chronology of Quercus acutissima for each cluster was produced through cross-dating and standardization procedures. The adequacy of index chronologies was tested using basic statistics such as mean sensitivity, auto correlation, signal to noise ratio, and expressed population signal of annual tree-ring growth. Response function analysis was conducted to reveal the relationship between tree-ring growth and climatic variables for each cluster. The results of this study are expected to provide valuable information necessary for estimating local growth characteristics of Quercus acutissima and for predicting changes in tree growth patterns caused by climate change.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.12
• /
• pp.1269-1273
• /
• 2010

Typically users prefer to manage and access personal photo collections taken from a cell phone based on events. In this paper we propose an event clustering algorithm that requires low computation cost with high accuracy supporting incremental operation. The proposed method is based on the statistical analysis of the elapsed interval of intra-event photos on the real sample data for the decision of an event boundary. We then incorporate both location and visual information for the ambiguous range to split with only temporal cue. According to test results, we show higher performance compared to existing general clustering approaches.

• Journal of Korean Society of Disaster and Security
• /
• v.12 no.2
• /
• pp.25-34
• /
• 2019

The efficiency of sewage treatment was analyzed by statistical method based on the water quality and operation data of the sewage treatment plant applying the oxidation method. The obtained water quality data were pH, temperature, BOD, SS, T-N, ${NH_4}^+-N$, and T-P of influent and discharge water. Data analysis was performed by correlation analysis, ANOVA analysis, and cluster analysis. As a result of the statistical analysis, the influent flow rate in the sewage treatment plant was the highest in summer. The average inflow flow rate was $3.000m^3/s$. According to Box plot results, COD, and T-P concentrations of effluents were not significantly different from season to season. The Pearson correlation analysis showed strong positive correlation between BOD, COD, T-N, and T-P in influent flow. Seasonal BOD and T-N concentrations were highest in winter and COD and T-P in seasonal influences. BOD showed a strong negative correlation with the water temperature, but showed a positive correlation with other operating factors such as HRT, SRT and C/N. The higher the influent temperature, the lower the BOD concentration. Therefore, retention time was shortened and BOD treatment efficiency was lowered. It was found that T-N had a higher retention time and a higher concentration than DO concentration. On the other hand, T-P did not show a significant correlation with operating factors.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.247-249
• /
• 2004

마이크로어레이 기술은 근래에 개발된 신기술로써 동시에 수천-수만 개의 유전자 발현을 측정할 수 있어 다양한 생물학적 연구에 이용되고 있다. 여러 단계의 실험 과정과 이를 통해 얻은 다량의 데이터를 처리하기 위해서는 이를 효율적으로 관리. 저장, 분석할 수 있는 통할 정보 관리 시스템을 필요로 한다. 현재 외국에서는 몇몇 관리시스템이 개발되어 있고. 국내에서도 WEMA 등이 있지만 아직 데이터 관리부분에 기능이 치우쳐 있다. 따라서 우리는 복잡한 자료구조를 가지는 마이크로어레이의 실험 정보와 각 단계별 처리 정보 등을 사용자의 관점에서 효과적이고 체계적으로 관리할 수 있고, 데이터 정규화 및 다양한 통계적 분석 기능을 갖춰 불필요한 시간과 비용을 줄임으로써 마이크로어레이 연구에 도움을 주고자 통합 분석관리 시스템 cMAMS (cDNA Microarray Analysis and Management System)를 개발하였다. 웹 기반으로 구현된 cMAMS는 데이터를 저장, 관리하는 부분과 데이터를 분석하는 부분, 그리고 모든 관련 점보가 저장되는 데이터베이스 부분으로 구성되어 있다 데이터관리부분에서는 WEMA의 계층적 데이터구조론 도입해 관리의 효율성을 높이고 시스템의 이용자를 시스템운영자, 프로젝트관리자, 일반사용자로 구분하여 데이터 접근을 제한함으로써 보안성을 높였다. 통계처리 언어 R로 구현된 데이터분석 부분은 7 단계의 다양한 분석(전처리 정규화, 가시화, 군집분석. 판별분석, 특이적 발현 유전자 선뿐, 마이크로어레이 간의 상판분석)이 가능하도록 구현하였고, 분석결과는 데이터베이스에 저장되어 추후에 검토 및 연구자간의 공유가 가능하도록 하였다. 데이터베이스는 실험정보가 저장된 데이터베이스, 분석결과가 저장된 데이터베이스, 그리고 유전자 정보 탐색을 위한 데이터베이스로 분류해 데이터를 효율적으로 관리할 수 있게 하였다. 본 시스템은 LiNUX를 운영체계로 하고 데이터베이스는 MYSQL로 하여 JSP, Perl. 통계처리 언어인 R로 구현되었다.