• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.280-282
• /
• 2005

초파리 초기 발생과정은 gap 유전자, pair-rule 유전자, polarity 유전자의 세 가지 유전자 그룹에 의해서 조직화 된다. Gap 유전자들에 의해 pair-rules 유전자들의 발현이 조절되며, 이들에 의해 결국 polarity 유전자들의 발현을 조절함으로써, 정확한 위치에서 각 기관의 형성을 유도한다. 특히 분열 14단계에서는 pair-rule 유전자 중의 하나인 eve 유전자의 발현이 조절되는데, eve 유전자는 배아의 분할의 줄무늬를 형성시키는 유전자에 해당된다. 본 논문에서는 eve 유전자의 발현조절자인 hunchback, giant, kruppel, bicoid의 gap 유전자들로 구성된 조절 네트워크를 S-system을 이용하여 모델링하였다. 이를 통해 각 유전자들의 발현 데이터로부터 파라미터들을 진화 연산을 통해 예측하고, 각 유전자들의 발현에 대한 시뮬레이션 결과를 보여준다. 예측된 결과와 실제 데이터의 비교는 전체적으로 패턴이 서로 유사함을 보여주고 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.90-92
• /
• 2000

데이터마이닝 문제는 데이터를 그 속성들에 따라 분류하여 예측하는 것뿐만 아니라 분류된 속성들간의 연관성에 대해 잘 설명할 수 있어야 한다. 일반적으로 변수들간의 연관성을 잘 설명할 수 있으면서도 높은 예측력을 가지는 방법으로는 베이지안 네트웍 분류자(Bayesian network classifier)가 있다. 그러나 이것은 데이터 마이닝과 같은 대용량 데이터에서는 성능이 떨어지는 단점이 있다. 이에 이 논문에서는 최근 RBF 신경망이 입력변수 선정문제에 성공적으로 적용된 Reversible Jump Markov Chain Monte Carlo 방법을 이용하여 최적의 입력변수들만을 선택하여 베이지안 네트웍을 학습하는 Selective BN Augmented Naive-Bayes Classifier를 새로운 방안으로 제안하고 이를 실제 데이터마이닝 문제에 적용한 결과를 제시한다.

• Journal of Korean Society of Water and Wastewater
• /
• v.18 no.1
• /
• pp.66-72
• /
• 2004

In this study, quantity and quality of collected rainwater by sand, gravel, soil, lawn and concrete surface, as collection materials were investigated and Rainwater Collection Prediction Model was developed to predict the amount of collected rainwater. The quantity of collected rainwater in concrete surface, gravel, sand, soil and lawn collection system was 1,067L(93.2%), 1,006L(87.8%), 902L(78.8%), 800L(69.9%), 788.5L(68.8%) for 8 months period, respectively. The average turbidity of collected rainwater in concrete surface, gravel, sand, soil and lawn collection system was 3.2NTU, 2.2NTU, 1.9NTU, 1.7NTU, 1.5NTU for 8 months period, respectively. For sand collection material, predicted amount by the Model and actual collected amount were 931.5L and 902L, which were very closed. For gravel collection material, predicted amount by Model and actual collected amount were 1,028.21. and 1,006L, which were very closed. To simulate the optimal rainwater storage volume, the rainfall and evaporation data in Dae-jeon city were used. For sand collection system with 30m2 area, the maximum storage volume was $17m^3$ and 62% of the year was secured for use of 240L/day.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.1078-1090
• /
• 2022

The distribution patterns of battery usage time data per battery level are able to affect the performance of estimating battery remaining time in mobile devices. Outliers may mainly affect the estimation performance of statistical regression methods. In this paper, we propose a software framework that detects and processes outliers to improve the estimation performance of statistical regression methods. The proposed framework first detects outliers that degrade the estimation performance. The proposed framework replaces outliers with smoothed data. The difference between an outlier and its replaced data will be properly distributed into individual data. Finally, individual data are reinforced to improve the estimation performance. The numerical results obtained by experimenting the proposed framework confirmed that it yielded good performance of estimating battery remaining time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.2
• /
• pp.284-294
• /
• 2018

Statistical methods have been widely used to estimate the remaining battery runtime of mobile smart devices, such as smart phones, smart gears, tablets, and etc. However, existing work available in the literature only considers a particular statistical method. Thus, it is difficult to determine whether statistical methods are applicable to estimating thr remaining battery runtime of mobile devices or not. In this paper, we evaluated the performance of statistical methods applicable to estimating the remaining battery runtime of mobile smart devices. The statistical estimation methods evaluated in this paper are as follows: simple and moving average, linear regression, multivariate adaptive regression splines, auto regressive, polynomial curve fitting, and double and triple exponential smoothing methods. Research results presented in this paper give valuable data of insight to IT engineers who are willing to deploy statistical methods on estimating the remaining battery runtime of mobile smart devices.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.536-545
• /
• 2020

When general statistical regression methods are applied to predict the battery remaining time of a mobile smart device, they yielded the poor accuracy of estimating battery remaining time as the deviations of battery usage time per battery level became larger. In order to improve the estimation accuracy of general statistical regression methods, a preprocessing task is required to refine the measured raw data with large deviations of battery usage time per battery level. In this paper, we propose a data preprocessing framework that preprocesses raw measured battery consumption data and converts them into refined battery consumption data. The numerical results obtained by experimenting the proposed data preprocessing framework confirmed that it yielded good performance in terms of accuracy of estimating battery remaining time under general statistical regression methods for given refined battery consumption data.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1283-1293
• /
• 2022

The purpose of this study is to predict residual chlorine in order to maintain stable residual chlorine concentration in sedimentation basin by using artificial intelligence algorithms in water treatment process employing pre-chlorination. Available water quantity and quality data are collected and analyzed statistically to apply into mathematical multiple regression and artificial intelligence models including multi-layer perceptron neural network, random forest, long short term memory (LSTM) algorithms. Water temperature, turbidity, pH, conductivity, flow rate, alkalinity and pre-chlorination dosage data are used as the input parameters to develop prediction models. As results, it is presented that the random forest algorithm shows the most moderate prediction result among four cases, which are long short term memory, multi-layer perceptron, multiple regression including random forest. Especially, it is result that the multiple regression model can not represent the residual chlorine with the input parameters which varies independently with seasonal change, numerical scale and dimension difference between quantity and quality. For this reason, random forest model is more appropriate for predict water qualities than other algorithms, which is classified into decision tree type algorithm. Also, it is expected that real time prediction by artificial intelligence models can play role of the stable operation of residual chlorine in water treatment plant including pre-chlorination process.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10a
• /
• pp.53-58
• /
• 2006

MicroRNA (miRNA)는 약 22 nt의 작은 RNA 조각으로 이루어져 있으며 stem-loop 구조의 precursor 형태에서 최종적으로 만들어 진다. miRNA는 mRNA의 3‘UTR에 상보적으로 결합하여 유전자의 발현을 억제하거나 mRNA의 분해를 촉진한다. miRNA를 동정하기 위한 실험적인 방법은 조직 특이적인 발현, 적은 발현양 때문에 방법상 한계를 가지고 있다. 이러한 한계는 컴퓨터를 이용한 방법으로 어느 정도 해결될 수 있다. 하지만 miRNA의 서열상의 낮은 보존성은 homology를 기반으로 한 예측을 어렵게 한다. 또한 기계학습 방법인 support vector machine (SVM) 이나 naive bayes가 적용되었지만, 생물학적인 의미를 해석할 수 있는 generative model을 제시해 주지 못했다. 본 연구에서는 우수한 miRNA 예측을 보일 뿐만 아니라 학습된 모델로부터 생물학적인 지식을 얻을 수 있는 Bayesian network을 적용한다. 이를 위해서는 생물학적으로 의미 있는 특질들의 선택이 중요하다. 여기서는 position weighted matrix (PWM)과 Markov chain probability (MCP), Loop 크기, Bulge 수, spectrum, free energy profile 등을 특질로서 선택한 후 Information gain의 특질 선택법을 통해 예측에 기여도가 높은 특질 25개 와 27개를 최종적으로 선택하였다. 이로부터 Bayesian network을 학습한 후 miRNA의 예측 성능을 10 fold cross-validation으로 확인하였다. 그 결과 pre-/mature miRNA 각 각에 대한 예측 accuracy가 99.99% 100.00%를 보여, SVM이나 naive bayes 방법보다 높은 결과를 보였으며, 학습된 Bayesian network으로부터 이전 연구 결과와 일치하는 pre-miRNA 상의 의존관계를 분석할 수 있었다.

• Korean Journal of Ecology and Environment
• /
• v.48 no.3
• /
• pp.153-167
• /
• 2015

In order to understand the relationship between the distribution of epilithic diatoms and the habitual environments, land-use, water qualities, and epilithic diatoms were studied at 141 sampling sites in the midwestern stream of Korean peninsula (Geum river, Mangyeong river, Dongjin river, and Sapgyo river). The total 183 diatom taxa was appeared in the study, while the dominant species were found to be Nitzschia palea (10.9%) and Achnanthes convergens (8.4%). Based on the abundance of epilithic diatoms, a cluster analysis results indicate that the sampling sites divided the sampling sites into 4 groups (G) at the 25% level. In term of geographic and aquatic environments, G-I and -II accounted for the upper and mid streams of the Geum river, and had large forest areas and good in water quality. G-III accounted for farmland and urban, and high concentration nutrient levels (TN and TP) and electric conductivity. G-IV accounted for mostly farmland, and high levels in turbidity, BOD, nutrient and electric conductivity. CCA results showed that the saproxenous taxa Meridion circulare was the indicator species of G-I, which strongly influenced by altitude and forests. In G-II, the indifferent taxa Navicula cryptocephala was influenced by Chl-a, AFDM, and DO. In G-III and -IV, the indifferent taxa Fragilaria elliptica and saprophilous taxa Aulacoseira ambigua were influenced by electric conductivity, turbidity, and nutrient counts. Meanwhile, random forest results showed that the predicting factor of indicator species appearance in G-I, -II, and -III was found to be electric conductivity whereas in G-IV it was found to be turbidity. Collectively, the distribution of diatoms in the midwestern of Korean peninsula was found to depend more on the land-use and its subsequent water qualities than the inherent characteristics of the aquatic environment.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.18 no.3
• /
• pp.111-121
• /
• 2013

Accurate prediction of sea water temperature has been emphasized to make precise local weather forecast and to understand change of ecosystem. The Yellow Sea, which has turbid water and strong tidal current, is an unique shallow marginal sea. It is essential to include the effects of the turbidity and the strong tidal mixing for the realistic simulation of temperature distribution in the Yellow Sea. Evaluation of ocean circulation model response to vertical mixing scheme and turbidity is primary objective of this study. Three-dimensional ocean circulation model(Regional Ocean Modeling System) was used to perform numerical simulations. Mellor- Yamada level 2.5 closure (M-Y) and K-Profile Parameterization (KPP) scheme were selected for vertical mixing parameterization in this study. Effect of Jerlov water type 1, 3 and 5 was also evaluated. The simulated temperature distribution was compared with the observed data by National Fisheries Research and Development Institute to estimate model's response to turbidity and vertical mixing schemes in the Yellow Sea. Simulations with M-Y vertical mixing scheme produced relatively stronger vertical mixing and warmer bottom temperature than the observation. KPP scheme produced weaker vertical mixing and did not well reproduce tidal mixing front along the coast. However, KPP scheme keeps bottom temperature closer to the observation. Consequently, numerical ocean circulation simulations with M-Y vertical mixing scheme tends to produce well mixed vertical temperature structure and that with KPP vertical mixing scheme tends to make stratified vertical temperature structure. When Jerlov water type is higher, sea surface temperature is high and sea bottom temperature is low because downward shortwave radiation is almost absorbed near the sea surface.