• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제12권5호
• /
• pp.165-170
• /
• 2023

최근 블록체인 기술이 부상하면서 이를 이용한 암호화폐 플랫폼이 늘어나며 화폐 거래가 활발이 이뤄지고 있다. 그러나 암호화폐의 특성을 악용한 범죄 또한 늘어나 문제가 되고 있다. 특히 피싱 스캠은 이더리움 사이버 범죄의 과반수 이상을 차지하며 주요 보안 위협원으로 여겨지고 있다. 따라서 효과적인 피싱 스캠 탐지 방법이 시급하다. 그러나 전체 이더리움 참여 계정 주소에서 라벨링된 피싱 주소의 부족으로 인한 데이터 불균형 문제로 지도학습에 충분한 데이터 제공이 어려운 상황이다. 이를 해결하기 위하여 본 논문에서는 이더리움 트랜잭션 네트워크를 고려한 효과적인 그래프 임베딩 기법인 trans2vec과 준지도 학습 모델 tri-training을 함께 사용하여 라벨링된 데이터 뿐만 아니라 라벨링되지 않은 데이터도 최대한 활용하는 피싱 스캠 탐지 방법을 제안한다.

• 산업기술연구
• /
• 제33권A호
• /
• pp.31-39
• /
• 2013

There are two methods to make a distinction of deterioration of high-speed railway track. One is that an administrator checks for each attribute value of track induction data represented in graph and determines whether maintenance is needed or not. The other is that an administrator checks for monthly trend of attribute value of the corresponding section and determines whether maintenance is needed or not. But these methods have a weak point that it takes longer times to make decisions as the amount of track induction data increases. As a field of artificial intelligence, the method that a computer makes a distinction of deterioration of high-speed railway track automatically is based on machine learning. Types of machine learning algorism are classified into four type: supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning. This research uses supervised learning that analogizes a separating function form training data. The method suggested in this research uses SVM classifier which is a main type of supervised learning and shows higher efficiency binary classification problem. and it grasps the difference between two groups of data and makes a distinction of deterioration of high-speed railway track.

• Journal of Computing Science and Engineering
• /
• 제5권2호
• /
• pp.150-160
• /
• 2011

Automatic text classification has a long history and many studies have been conducted in this field. In particular, many machine learning algorithms and information retrieval techniques have been applied to text classification tasks. Even though much technical progress has been made in text classification, there is still room for improvement in text classification. In this paper, we will discuss remaining issues in improving text classification. In this paper, three improvement issues are presented including automatic training data generation, noisy data treatment and term weighting and indexing, and four actual studies and their empirical results for those issues are introduced. First, the semi-supervised learning technique is applied to text classification to efficiently create training data. For effective noisy data treatment, a noisy data reduction method and a robust text classifier from noisy data are developed as a solution. Finally, the term weighting and indexing technique is revised by reflecting the importance of sentences into term weight calculation using summarization techniques.

• 한국경영과학회지
• /
• 제31권2호
• /
• pp.69-85
• /
• 2006

Transductive Support Vector Machine(TSVM) is one of semi-supervised learning algorithms which exploit the domain structure of the whole data by considering labeled and unlabeled data together. Although it was proposed several years ago, there has been no efficient algorithm which can handle problems with more than hundreds of training examples. In this paper, we propose an efficient branch-and-bound algorithm which can solve large-scale TSVM problems with thousands of training examples. The proposed algorithm uses two bounding techniques: min-cut bound and reduced SVM bound. The min-cut bound is derived from a capacitated graph whose cuts represent a lower bound to the optimal objective function value of the dual problem. The reduced SVM bound is obtained by constructing the SVM problem with only labeled data. Experimental results show that the accuracy rate of TSVM can be significantly improved by learning from the optimal solution of TSVM, rather than an approximated solution.

• 대한산업공학회지
• /
• 제39권6호
• /
• pp.535-545
• /
• 2013

The goal of stock investment is earning high rate or return with stability. To accomplish this goal, using a portfolio that distributes stocks with high rate of return with less variability and a stock price prediction model with high accuracy is required. In this paper, three methods are suggested to require these conditions. First of all, in portfolio re-balance part, Max-Return and Min-Risk (MRMR) model is suggested to earn the largest rate of return with stability. Secondly, Entering/Leaving Rule (E/L) is suggested to upgrade portfolio when particular stock's rate of return is low. Finally, to use outstanding stock price prediction model, a model based on Semi-Supervised Learning (SSL) which was suggested in last research was applied. The suggested methods were validated and applied on stocks which are listed in KOSPI200 from January 2007 to August 2008.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.789-816
• /
• 2019

Text classification is a challenging task, especially when dealing with a huge amount of text data. The performance of a classification model can be varied depending on what type of words contained in the document corpus and what type of features generated for classification. Aside from proposing a new modified version of the existing algorithm or creating a new algorithm, we attempt to modify the use of data. The classifier performance is usually affected by the quality of learning data as the classifier is built based on these training data. We assume that the data from different domains might have different characteristics of noise, which can be utilized in the process of learning the classifier. Therefore, we attempt to enhance the robustness of the classifier by injecting the heterogeneous data artificially into the learning process in order to improve the classification accuracy. Semi-supervised approach was applied for utilizing the heterogeneous data in the process of learning the document classifier. However, the performance of document classifier might be degraded by the unlabeled data. Therefore, we further proposed an algorithm to extract only the documents that contribute to the accuracy improvement of the classifier.

• 대한산업공학회지
• /
• 제37권1호
• /
• pp.64-73
• /
• 2011

Oil price prediction is an important issue for the regulators of the government and the related industries. When employing the time series techniques for prediction, however, it becomes difficult and challenging since the behavior of the series of oil prices is dominated by quantitatively unexplained irregular external factors, e.g., supply- or demand-side shocks, political conflicts specific to events in the Middle East, and direct or indirect influences from other global economical indices, etc. Identifying and quantifying the relationship between oil price and those external factors may provide more relevant prediction than attempting to unclose the underlying structure of the series itself. Technically, this implies the prediction is to be based on the vectoral data on the degrees of the relationship rather than the series data. This paper proposes a novel method for time series prediction of using Semi-Supervised Learning that was originally designed only for the vector types of data. First, several time series of oil prices and other economical indices are transformed into the multiple dimensional vectors by the various types of technical indicators and the diverse combination of the indicator-specific hyper-parameters. Then, to avoid the curse of dimensionality and redundancy among the dimensions, the wellknown feature extraction techniques, PCA and NLPCA, are employed. With the extracted features, a timepointspecific similarity matrix of oil prices and other economical indices is built and finally, Semi-Supervised Learning generates one-timepoint-ahead prediction. The series of crude oil prices of West Texas Intermediate (WTI) was used to verify the proposed method, and the experiments showed promising results : 0.86 of the average AUC.

• 한국인터넷방송통신학회논문지
• /
• 제18권5호
• /
• pp.171-177
• /
• 2018

최근 많은 이미지 데이터 셋들은 일반적인 특성을 추출하기 위한 다양한 데이터 클래스와 특징을 가지고 있다. 하지만 이러한 다양한 데이터 클래스와 특징으로 인해 해당 데이터 셋으로 훈련된 물체 검출 딥러닝 모델은 데이터 특성이 다른 환경에서 좋은 성능을 내지 못하는 단점을 보인다. 이 논문에서는 하위 카테고리 기반 물체 검출 방법과 오픈셋 물체 검출 방법을 이용하여 이를 극복하고, 강인한 물체 검출 딥러닝 모델을 훈련하기 위해 능동 준지도 학습 (Active Semi-Supervised Learning)을 이용한 다중 분기 트리 구조를 제안한다. 우리는 이 구조를 이용함으로써 데이터 특성이 다른 환경에서 적응할 수 있는 모델을 가질 수 있고, 나아가 이 모델을 이용하여 이전의 모델보다 높은 성능을 확보 할 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제22권7호
• /
• pp.17-29
• /
• 2017

IRecently, researches on the recognition of indoor user situations through various sensors in a smart home environment are under way. In this paper, the case study was conducted to determine the operation of the robot vacuum cleaner by inferring the user 's indoor situation through the operation of home appliances, because the indoor situation greatly affects the operation of home appliances. In order to collect learning data for indoor situation awareness model learning, we received feedbacks from user when there was a mistake about the cleaning situation. In this paper, we propose a semi-supervised learning method using user feedback data. When we receive a user feedback, we search for the labels of unlabeled data that most fit the feedbacks collected through genetic algorithm, and use this data to learn the model. In order to verify the performance of the proposed algorithm, we performed a comparison experiments with other learning algorithms in the same environment and confirmed that the performance of the proposed algorithm is better than the other algorithms.