• Journal of the Korea Society of Computer and Information
• /
• v.15 no.2
• /
• pp.135-146
• /
• 2010

In this paper, we propose an Recommendation System for supporting self-directed learning on e-learning marketplace. The key idea of this system is recommendation system using revised collaborative filtering to support marketplace. Exisiting collaborative filtering method consists of 3 stages as preparing low data, building familiar customer group by selecting nearest neighbor, creating recommendation list. This study designs recommendation system to support self-directed learning by using collaborative filtering added nearest neighbor learning course that considered industry and learning level. This service helps to select right learning course to learner in industry. Recommendation System can be built by many method and to recommend the service content including explicit properties using revised collaborative filtering method can solve limitations in existing content recommendation.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.739-745
• /
• 2017

This paper presents and discusses an implementation of the GPU shifted sorting method to find approximate k nearest neighbors which executes within "warp", the minimum execution unit in GPU parallel architecture. Also, this paper presents the comparison results with other two common nearest neighbor searching methods, GPU-based kd-tree and ANN (Approximate Nearest Neighbor) library. The proposed implementation focuses on the cases when k is small, i.e. 2, 4, 8, and 16, which are handled efficiently within warp to consider it is very common for applications to handle small k's. Also, this paper discusses optimization ways to implementation by improving memory management in a loop for the CUB open library and adopting CUDA commands which are supported by GPU hardware. The proposed implementation shows more than 16-fold speed-up against GPU-based other methods in the tests, implying that the improvement would become higher for more larger input data.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.33-41
• /
• 2022

In this article, we proposed to predict natural gas (NG) leakage levels through feature selection based on a factor analysis (FA) of the integrating the Korean Meteorological Agency data and natural gas leakage data for considering complex factors. The paper has been divided into three modules. First, we filled missing data based on the linear interpolation method on the integrated data set, and selected essential features using FA with OrdinalEncoder (OE)-based normalization. The dataset is labeled by K-means clustering. The final module uses four algorithms, K-nearest neighbors (KNN), decision tree (DT), random forest (RF), Naive Bayes (NB), to predict gas leakage levels. The proposed method is evaluated by the accuracy, area under the ROC curve (AUC), and mean standard error (MSE). The test results indicate that the OrdinalEncoder-Factor analysis (OE-F)-based classification method has improved successfully. Moreover, OE-F-based KNN (OE-F-KNN) showed the best performance by giving 95.20% accuracy, an AUC of 96.13%, and an MSE of 0.031.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.603-608
• /
• 2024

Nonresponse and missing values are caused by sample dropouts and avoidance of answers to surveys. In this case, problems with the possibility of information loss and biased reasoning arise, and a replacement of missing values with appropriate values is required. In this paper, as an alternative to missing values imputation, we compare several replacement methods, which use mean, linear regression, random forest, K-nearest neighbor, autoencoder and denoising autoencoder based on deep learning. These methods of imputing missing values are explained, and each method is compared by using continuous simulation data and real data. The comparison results confirm that in most cases, the performance of the random forest imputation method and the denoising autoencoder imputation method are better than the others.

• Journal of the Korean Society for Library and Information Science
• /
• v.40 no.2
• /
• pp.333-355
• /
• 2006

Network generation methods to visualize bibliometric data for examining the intellectual structure of knowledge domains are investigated in some detail. Among the four methods investigated in this study, pathfinder network algorithm is the most effective method in representing local details as well as global intellectual structure. The nearest neighbor graph, although never used in bibliometic analysis, also has some advantages such as its simplicity and clustering ability. The effect of input data preparation process on resulting intellectual structures are examined, and concluded that unlike MDS map with clusters, the network structure could be changed significantly by the differences in data matrix preparation process. The network generation methods investigated in this paper could be alternatives to conventional multivariate analysis methods and could facilitate our research on examining intellectual structure of knowledge domains.

• Journal of Korean Society of Transportation
• /
• v.32 no.5
• /
• pp.441-451
• /
• 2014

This study proposes a novel performance measure, which is referred to as Hazardous Spacing Index (HSI), to be used for evaluating safety of traffic stream on freeways. The basic principle of the proposed methodology is to investigate whether drivers would have sufficient stopping sight distance (SSD) under limited visibility conditions to eliminate rear-end crash potentials at every time step. Both Road Weather Information Systems (RWIS) and Vehicle Detection Systems (VDS) data were used to derive visibility distance (VD) and SSD, respectively. Moreover, the K-Nearest Neighbors (KNN) method was adopted to predict both VD and SSD in estimating predictive HSIs, which would be used to trigger advanced warning information to encourage safer driving. The outcome of this study is also expected to be used for monitoring freeway traffic stream in terms of safety.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.13-20
• /
• 2022

It's proposed and analyzed ML(Machine Learning) models to predict vehicle FC(Fuel Consumption) in real-time. The test driving was done for a car to measure vehicle speed, acceleration, road gradient and FC for training dataset. The various ML models were trained with feature data of speed, acceleration and road-gradient for target FC. There are two kind of ML models and one is regression type of linear regression and k-nearest neighbors regression and the other is classification type of k-nearest neighbors classifier, logistic regression, decision tree, random forest and gradient boosting in the study. The prediction accuracy is low in range of 0.5 ~ 0.6 for real-time FC and the classification type is more accurate than the regression ones. The prediction error for total FC has very low value of about 0.2 ~ 2.0% and regression models are more accurate than classification ones. It's for the coefficient of determination (R²) of accuracy score distributing predicted values along mean of targets as the coefficient decreases. Therefore regression models are good for total FC and classification ones are proper for real-time FC prediction.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.292-294
• /
• 2005

대사증후군은 당뇨병, 고혈압, 복부 비만, 고지혈증 등의 질병이 한 개인에게 동시에 발현하는 것을 말한다. 미국에서는 $25\%$ 이상의 성인이 대사성 증후군인 것으로 알려져 있으며, 경제 여건의 향상 및 식생활 습관의 변화와 함께 최근 우리나라에서도 심각한 문제가 되고 있다. 한편 불확실성의 처리를 위해 많이 사용되고 있는 베이지안 네트워크는 사람이 분석 가능한 확률 기반의 모델로 최근 의학 분야에서 지식 발견, 데이터 마이닝을 위한 도구로 유용하게 사용되고 있다. 본 논문에 서 는 대사증후군을 예측하는 문제를 다루며, 베이지안 네트워크와 의학 지식을 이용한 대사증후군의 예측 모델을 제안한다. 제안하는 모델을 통해 1993년의 데이터를 가지고 1995년의 상태를 예측하는 분류 실험을 수행하였으며, 실험 결과 다층 신경망, k-최근접 이웃 등의 분류기 보다 높은 $81.5\%$의 예측율을 보였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.1-3
• /
• 2006

대사증후군은 당뇨병, 고혈압, 복부 비만, 고지혈증 등의 질병이 한 개인에게 동시에 발현하는 것을 말하며, 최근 경제여건의 향상 및 식생활 습관의 변화와 함께 우리나라에서도 심각한 문제가 되고 있다. 한편 불확실성의 처리를 위해 많이 사용되는 베이지안 네트워크는 사람이 분석 가능한 확률 기반의 모델로 최근 의학분야에서 질병의 진단이나 예측모델을 구성하기 위한 방법으로 유용하게 사용되고 있다. 베이지안 네트워크의 구조를 학습하는 대표적인 알고리즘인 K2 알고리즘은 속성이 입력되는 순서의 영향을 받으며, 따라서 이 또한 하나의 주제로써 연구되어 왔다. 본 논문에서는 유전자 알고리즘을 이용하여 베이지안 네트워크에 입력되는 속성 순서를 최적화하며 이 과정에서 의학지식을 적용해 효율적인 최적화가 가능하도록 하였다. 제안하는 모델을 통해 1993년의 데이터를 가지고 1995년의 상태를 예측하는 분류 실험을 수행한 결과 속성 순서 최적화 후에 이전보다 향상된 예측율을 보였으며 또한 다층 신경망, k-최근접 이웃 등을 이용한 다른 모델보다 더 높은 예측율을 보였다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.27-32
• /
• 2005

Recently there has been much interest in applying data mining to computer network intrusion detection. A new approach, based on the k-Nearest Neighbour(kNN) classifier, is used to classify Program behaviour as normal or intrusive. Each system call is treated as a word and the collection of system calls over each program execution as a document. These documents are then classified using kNN classifier, a Popular method in text mining. A simple example illustrates the proposed procedure.