http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Classification Methods for Automated Prediction of Power Load Patterns
Piao Minghao,박진형(Jin-Hyung Park),이헌규(Heon-Gyu Lee),류근호(Keun-Ho Ryu) 한국정보과학회 2008 한국정보과학회 학술발표논문집 Vol.35 No.1
Currently an automated methodology based on data mining techniques is presented for the prediction of customer load patterns in long duration load profiles. The proposed our approach consists of three stages: (Ⅰ) data pre-processing: noise or outlier is removed and the continuous attribute-valued features are transformed to discrete values, (Ⅱ) cluster analysis: k-means clustering is used to create load pattern classes and the representative load profiles for each class and (Ⅲ) classification: we evaluated several supervised learning methods in order to select a suitable prediction method. According to the proposed methodology, power load measured from AMR (automatic meter reading) system, as well as customer indexes, were used as inputs for clustering. The output of clustering was the classification of representative load profiles (or classes). In order to evaluate the result of forecasting load patterns, the several classification methods were applied on a set of high voltage customers of the Korea power system and derived class labels from clustering and other features are used as input to produce classifiers. Lastly, the result of our experiments was presented.
( Minghao Piao ),박진형 ( Jin-hyung Park ),이헌규 ( Heon-gyu Lee ),신진호 ( Jin-ho Shin ),류근호 ( Keun-ho Ryu ) 한국정보처리학회 2008 한국정보처리학회 학술대회논문집 Vol.15 No.1
Currently an automated methodology based on data mining techniques is presented for the prediction of customer load patterns in load demand data. The main aim of our work is to forecast customers’ contract information from capacity of daily power consumption patterns. According to the result, we try to evaluate the contract information’s suitability. The proposed our approach consists of three stages: (i) data preprocessing: noise or outlier is detected and removed (ii) cluster analysis: SOMs clustering is used to create load patterns and the representative load profiles and (iii) classification: we applied the K-NNs classifier in order to predict the customers’ contract information base on power consumption patterns. According to the our proposed methodology, power load measured from AMR(automatic meter reading) system, as well as customer indexes, were used as inputs. The output was the classification of representative load profiles (or classes). Lastly, in order to evaluate KNN classification technique, the proposed methodology was applied on a set of high voltage customers of the Korea power system and the results of our experiments was presented.
Piao, Minghao,Jin, Cheng Hao,Lee, Jong Yun,Byun, Jeong-Yong IEEE 2018 IEEE transactions on semiconductor manufacturing Vol.31 No.2
<P>Wafer maps contain information about defects and clustered defects that form failure patterns. Failure patterns exhibit the information related to defect generation mechanisms. The accurate classification of failure patterns in wafer maps can provide crucial information for engineers to recognize the causes of the fabrication problems. In this paper, we proposed a decision tree ensemble learning-based wafer map failure pattern recognition method based on radon transform-based features. Radon transform is applied on raw wafer map data to generate the new features which are exhibiting the geometric information of failure patterns in wafer map. Decision tree algorithm is applied to build decision tree ensemble and the final decision is made by aggregating the prediction results of decision trees. The effectiveness of the proposed method has been verified by using the real world wafer map data set (WM-811K).</P>
Piao, Yongjun,Piao, Minghao,Park, Kiejung,Ryu, Keun Ho Oxford University Press 2012 Bioinformatics Vol.28 No.24
<P>Gene selection for cancer classification is one of the most important topics in the biomedical field. However, microarray data pose a severe challenge for computational techniques. We need dimension reduction techniques that identify a small set of genes to achieve better learning performance. From the perspective of machine learning, the selection of genes can be considered to be a feature selection problem that aims to find a small subset of features that has the most discriminative information for the target.</P>
( Minghao Piao ),변정용 ( Jeong-yong Byun ) 한국정보처리학회 2017 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.6 No.6
Nowadays, living standard is improved and people have high interest to the personal health care problem. Accordingly, people desire to know the personal physical condition and the related medical treatment. Thus, there is the necessary of the personalized medical treatment, and there are many studies about the automatic disease diagnosis and the related services. Those studies focus on the particular disease prediction which is based on the related particular data. However, there is no studies about the medical treatment prediction. In our study, national health data based medical treatment predictor is built by using SVM, and the performance is evaluated by comparing with other prediction methods. The experimental results show that the health data based medical treatment prediction resulted in the average accuracy of 80%, and the SVM performs better than other prediction algorithms.
의사결정 트리 앙상블을 구축하기 위한 상관성 기반 기법을 이용한 속성 중복성 제거
박영준 ( Yongjun Piao ),박명호 ( Minghao Piao ),손호선 ( Ho Sun Shon ),류근호 ( Keun Ho Ryu ) 한국정보처리학회 2011 한국정보처리학회 학술대회논문집 Vol.18 No.2
대량의 분류 규칙 탐사 과정은 앙상블기법을 사용하여 다양한 연구들이 이루어지고 있다. 본 논문에서는 의사결정 트리의 분열 문제와 singleton 포함 한계를 해결하기 위하여 Cascading-and-Sharing 앙상블 기법을 적용하여 점진적 다중 의사결정 트리를 구축하였다. 또한 분류의 정확도를 향상시키고, 트리의 복잡도와 모델 과잉접합을 피하기 위하여 다중 트리 구축과정에서 선형 상관분석기법을 기반으로 훈련 데이터 속성들의 중복성을 제거하였다. 실험 결과, 속성들의 중복성을 제거하여 구축한 트리들은 원래 기법보다 더 좋은 결과를 보여주었다.
Minghao Zhang,Dan Cai,Qiumei Song,Yu Wang,Haiyue Sun,Chunhong Piao,Hansong Yu,Junmei Liu,Jingsheng Liu,Yuhua Wang 한국축산식품학회 2019 한국축산식품학회지 Vol.39 No.3
Lactobacillus rhamnosus GG (LGG) has low resistance to low pH and bile salt in the gastrointestinal juice. In this study, the gel made from whey protein concentrate (WPC) and pullulan (PUL) was used as the wall material to prepare the microencapsulation for LGG protection. The gelation process was optimized and the properties of gel were also determined. The results showed the optimal gel was made from 10% WPC and 8.0% PUL at pH 7.5, which could get the best protective effect; the viable counts of LGG were 6.61 Log CFU/g after exposure to simulated gastric juice (SGJ) and 9.40 Log CFU/g to simulated intestinal juice (SIJ) for 4 h. Sodium dodecyl sulphite polyacrylamide gel electrophoresis (SDS-PAGE) confirmed that the WPC-PUL gel had low solubility in SGJ, but dissolved well in SIJ, which suggested that the gel can protect LGG under SGJ condition and release probiotics in the SIJ. Moreover, when the gel has highest hardness and water-holding capacity, the viable counts of LGG were not the best, suggesting the relationship between the protection and the properties of the gel was non-linear.
A New Direction of Cancer Classification: Positive Effect of Low-Ranking MicroRNAs
Feifei Li,Minghao Piao,Yongjun Piao,Meijing Li,류근호 질병관리본부 2014 Osong Public Health and Research Persptectives Vol.5 No.5
Objectives: Many studies based on microRNA (miRNA) expression profiles showed a new aspect of cancer classification. Because one characteristic of miRNA expression data is the high dimensionality, feature selection methods have been used to facilitate dimensionality reduction. The feature selection methods have one shortcoming thus far: they just consider the problem of where feature to class is 1:1 or n:1. However, because one miRNA may influence more than one type of cancer, human miRNA is considered to be ranked low in traditional feature selection methods and are removed most of the time. In view of the limitation of the miRNA number, low-ranking miRNAs are also important to cancer classification. Methods: We considered both high- and low-ranking features to cover all problems (1:1, n:1, 1:n, and m:n) in cancer classification. First, we used the correlation-based feature selection method to select the high-ranking miRNAs, and chose the support vector machine, Bayes network, decision tree, k-nearestneighbor, and logistic classifier to construct cancer classification. Then, we chose Chi-square test, information gain, gain ratio, and Pearson’s correlation feature selection methods to build the m:n feature subset, and used the selected miRNAs to determine cancer classification. Results: The low-ranking miRNA expression profiles achieved higher classification accuracy compared with just using high-ranking miRNAs in traditional feature selection methods. Conclusion: Our results demonstrate that the m:n feature subset made a positive impression of low-ranking miRNAs in cancer classification.