• Geomechanics and Engineering
• /
• 제25권1호
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• Journal of the Korean Statistical Society
• /
• 제35권2호
• /
• pp.157-166
• /
• 2006

This research proposes an efficient Monte Carlo algorithm for computing error probability in high performance digital communication st stems. It characterizes special features of the problem and suggests an importance sampling algorithm specially designed to handle the problem. It uses a shifted exponential density as the importance sampling density, and shows an adaptive way of choosing the rate and the origin of the shifted exponential density. Instead of equal allocation, an intelligent allocation of the samples is proposed so that more samples are allocated to more important part of the error probability. The algorithm uses the nested feature of the error space and avoids redundancy in estimating the probability. The algorithm is applied to an example data set and shows a great improvement in accuracy of the error probability estimation.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.283-285
• /
• 2005

To account for the importance of variable in multi-sensor data fusion, random forests are applied to supervised land-cover classification. The random forests approach is a non-parametric ensemble classifier based on CART-like trees. Its distinguished feature is that the importance of variable can be estimated by randomly permuting the variable of interest in all the out-of-bag samples for each classifier. Supervised classification with a multi-sensor remote sensing data set including optical and polarimetric SAR data was carried out to illustrate the applicability of random forests. From the experimental result, the random forests approach could extract important variables or bands for land-cover discrimination and showed good performance, as compared with other non-parametric data fusion algorithms.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제9권2호
• /
• pp.158-165
• /
• 2003

영상간의 유사도는 일반적으로 영상으로부터 추출한 특징벡터간의 벡터공간상의 거리를 계산해서 판단한다. 그러나 이러한 특징벡터가 유사도 계산을 위한 하나의 방법이지만 항상 인간의 유사도 개념을 충실히 반영하지는 않는다. 그러므로 현존하는 대부분의 영상검색시스템들은 각 특징간의 중요도를 선정하여 유사도에 반영하는 방법을 사용하고 있다. 본 논문에서는 영상검색을 위한 새로운 초기 가중치 설정과 갱신 알고리즘을 제안한다. 이를 위해서 먼저 데이터 베이스 영상을 인간의 인지도 판단에 의해 그룹화 한 후, 내부질의와 외부질의를 수행하고, 검색된 영상중 유사한 영상이 어느 그룹에 속하는지 알아내어 각 영상별로 유사도 계산에 필요한 최적 특징 가중치를 계산한다. 2000개의 영상 데이타에 대한 실험을 통해서 제안된 알고리즘의 우수성을 보인다.

• 한국재료학회지
• /
• 제33권4호
• /
• pp.164-174
• /
• 2023

The bandgap characteristics of semiconductor materials are an important factor when utilizing semiconductor materials for various applications. In this study, based on data provided by AFLOW (Automatic-FLOW for Materials Discovery), the bandgap of a semiconductor material was predicted using only the material's compositional features. The compositional features were generated using the python module of 'Pymatgen' and 'Matminer'. Pearson's correlation coefficients (PCC) between the compositional features were calculated and those with a correlation coefficient value larger than 0.95 were removed in order to avoid overfitting. The bandgap prediction performance was compared using the metrics of R² score and root-mean-squared error. By predicting the bandgap with randomforest and xgboost as representatives of the ensemble algorithm, it was found that xgboost gave better results after cross-validation and hyper-parameter tuning. To investigate the effect of compositional feature selection on the bandgap prediction of the machine learning model, the prediction performance was studied according to the number of features based on feature importance methods. It was found that there were no significant changes in prediction performance beyond the appropriate feature. Furthermore, artificial neural networks were employed to compare the prediction performance by adjusting the number of features guided by the PCC values, resulting in the best R² score of 0.811. By comparing and analyzing the bandgap distribution and prediction performance according to the material group containing specific elements (F, N, Yb, Eu, Zn, B, Si, Ge, Fe Al), various information for material design was obtained.

• 인터넷정보학회논문지
• /
• 제6권3호
• /
• pp.159-170
• /
• 2005

OC-SVM(One Class Support Vector Machine)은 주어진 전체 데이터의 분포를 측정하는 대신에. 데이터 분포의 서포트(support)를 측정하는 기술로서 주어진 데이터를 가장 잘 설명할 수 있는 최적의 서포트 벡터(support vector)를 구하는 기술이다. OC-SVM은 데이터 분포의 표현에 아주 뛰어난 접근 방법이지만, 사람의 주관적인 중요도를 반영하는 것은 힘들다. 본 논문에서는 각 데이터에 퍼지 맴버쉽(fuzzy membership)을 적용하여 기존의 OC-SVM에 사용자의 주관적인 중요도를 표현할 수 있는 FOC-SVM(Fuzzy One class Support Vector Machine)을 유도 하였다. FOC-SVM은 데이터들을 동등하게 다루는 것이 아니라, 데이터 객체의 중요도에 따라 데이터를 다룬다. 즉, 덜 중요한 데이터의 특징 벡터는 OC-SVM의 처리과정에 덜 기여하도록 하기 위하여, 객체의 중요도에 따라 특징 벡터의 크기를 조정하였다. 이를 증명하기 위하여 가상의 데이터를 가지고 실험을 하였고, 실험 결과는 예측된 결과를 보여 주었다.

• International Journal of CAD/CAM
• /
• 제5권1호
• /
• pp.69-81
• /
• 2005

As collaborative design and configuration design gain increasing importance in product development, it becomes essential to exchange parametric CAD models among participants. Parametric CAD models can be represented and exchanged in the form of a macro file or a part file that contains the modeling history of a product. The modeling history of a parametric CAD model contains feature specifications and each feature has selection information that records the name of the referenced topological entities. Translating this selection information requires solving the problems of how to identify the referenced topological entities of a feature (persistent naming problem) and how to convert the selection information into the format of the receiving CAD system (naming mapping problem). The present paper introduces the problem of exchanging parametric CAD models and proposes a solution to naming mapping.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권9호
• /
• pp.3177-3195
• /
• 2014

In many moving object detection problems of an aerial video, accurate and robust stabilization is of critical importance. In this paper, a novel accurate image alignment algorithm for aerial electronic image stabilization (EIS) is described. The feature points are first selected using optimal derivative filters based Harris detector, which can improve differentiation accuracy and obtain the precise coordinates of feature points. Then we choose the Delaunay Triangulation edges to find the matching pairs between feature points in overlapping images. The most "useful" matching points that belong to the background are used to find the global transformation parameters using the projective invariant. Finally, intentional motion of the camera is accumulated for correction by Sage-Husa adaptive filtering. Experiment results illustrate that the proposed algorithm is applied to the aerial captured video sequences with various dynamic scenes for performance demonstrations.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권1호
• /
• pp.17-21
• /
• 2016

This paper investigates the importance of the computational overhead when machine learning methods, such as SVM, LASSO, AdaBoosting and AdaBagging, are used for automatic security classification.

• Journal of Information Processing Systems
• /
• 제18권3호
• /
• pp.302-310
• /
• 2022

Efficient use of limited blood products is becoming very important in terms of socioeconomic status and patient recovery. To predict the appropriateness of patient-specific transfusions for the intensive care unit (ICU) patients who require real-time monitoring, we evaluated a model to predict the possibility of transfusion dynamically by using the Medical Information Mart for Intensive Care III (MIMIC-III), an ICU admission record at Harvard Medical School. In this study, we developed an explainable machine learning to predict the possibility of red blood cell transfusion for major medical diseases in the ICU. Target disease groups that received packed red blood cell transfusions at high frequency were selected and 16,222 patients were finally extracted. The prediction model achieved an area under the ROC curve of 0.9070 and an F1-score of 0.8166 (LightGBM). To explain the performance of the machine learning model, feature importance analysis and a partial dependence plot were used. The results of our study can be used as basic data for recommendations related to the adequacy of blood transfusions and are expected to ultimately contribute to the recovery of patients and prevention of excessive consumption of blood products.