• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1872-1879
• /
• 2022

Recently, with the development of artificial intelligence technology, research to use artificial intelligence to detect hacking attacks is being actively conducted. However, the fact that security data is a representative imbalanced data is recognized as a major obstacle in composing the learning data, which is the key to the development of artificial intelligence models. Therefore, in this paper, we propose a W-VAE oversampling technique that applies VAE, a deep learning generation model, to data extraction for oversampling, and sets the number of oversampling for each class through weight calculation using K-NN for sampling. In this paper, a total of five oversampling techniques such as ROS, SMOTE, and ADASYN were applied through NSL-KDD, an open network security dataset. The oversampling method proposed in this paper proved to be the most effective sampling method compared to the existing oversampling method through the F1-Score evaluation index.

• Journal of Korean Society of Forest Science
• /
• v.112 no.4
• /
• pp.561-573
• /
• 2023

National forests have an advantage over private forests in terms of higher investment in capital, technology, and labor, allowing for more intensive management. As such, national forests are expected to serve not only as a strategic reserve of forest resources to address the long-term demand for timber but also to stably perform various essential forest functions demanded by society. However, most forest stands in the current national forests belong to the fourth age class or above, indicating an imminent timber harvesting period amid an imbalanced age class structure. Therefore, if timber harvesting is not conducted based on systematic management planning, it will become difficult to ensure the continuity of the national forests' diverse functions. This study was conducted to determine the optimal volume of timber production in the national forests to improve the age-class structure while sustainably maintaining their economic and public functions. To achieve this, the study first identified areas within the national forests suitable for timber production. Subsequently, a forest management planning model was developed using multi-objective linear programming, taking into account both the national forests' economic role and their public benefits. The findings suggest that approximately 488,000 hectares within the national forests are suitable for timber production. By focusing on management of these areas, it is possible to not only improve the age-class distribution but also to sustainably uphold the forests' public benefits. Furthermore, the potential volume of timber production from the national forests for the next 100 years would be around 2 million m³ per year, constituting about 44% of the annual domestic timber supply.

• Journal of Intelligence and Information Systems
• /
• v.16 no.1
• /
• pp.93-116
• /
• 2010

Ensemble approach is applied to the detection modeling of illegal cash accommodation (ICA) that is the well-known type of fraudulent usages of credit cards in far east nations and has not been addressed in the academic literatures. The performance of fraud detection model (FDM) suffers from the imbalanced data problem, which can be remedied to some extent using an ensemble of many classifiers. It is generally accepted that ensembles of classifiers produce better accuracy than a single classifier provided there is diversity in the ensemble. Furthermore, recent researches reveal that it may be better to ensemble some selected classifiers instead of all of the classifiers at hand. For the effective detection of ICA, we adopt ensemble size reduction technique that prunes the ensemble of all classifiers using accuracy and diversity measures. The diversity in ensemble manifests itself as disagreement or ambiguity among members. Data imbalance intrinsic to FDM affects our approach for ICA detection in two ways. First, we suggest the training procedure with over-sampling methods to obtain diverse training data sets. Second, we use some variants of accuracy and diversity measures that focus on fraud class. We also dynamically calculate the diversity measure-Forward Addition and Backward Elimination. In our experiments, Neural Networks, Decision Trees and Logit Regressions are the base models as the ensemble members and the performance of homogeneous ensembles are compared with that of heterogeneous ensembles. The experimental results show that the reduced size ensemble is as accurate on average over the data-sets tested as the non-pruned version, which provides benefits in terms of its application efficiency and reduced complexity of the ensemble.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.241-250
• /
• 2022

Due to the COVID-19 pandemic, with increased 'untact' services and with unstable household economy, the bike insurance fraud is expected to surge. Moreover, the fraud methodology gets complicated. However, the fraud detection model for bike insurance is absent. we deal with the issue of skewed class distribution and reflect the criterion of fraud detection expert. We utilize a balanced random-forest algorithm to develop an efficient bike insurance fraud detection model. As a result, while the predictive performance of balanced random-forest model is superior than it of non-balanced model. There is no significant difference between the variables used by the experts and the confirmatory models. The important variables to detect frauds are turned out to be age and gender of driver, correspondence between insured and driver, the amount of self-repairing claim, and the amount of bodily injury liability.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.482-488
• /
• 2014

This paper aims to analyze user's emotion automatically by analyzing Twitter, a representative social network service (SNS). In order to create sentiment analysis models by using machine learning techniques, sentiment labels that represent positive/negative emotions are required. However it is very expensive to obtain sentiment labels of tweets. So, in this paper, we propose a sentiment analysis model by using self-training technique in order to utilize "data without sentiment labels" as well as "data with sentiment labels". Self-training technique is that labels of "data without sentiment labels" is determined by utilizing "data with sentiment labels", and then updates models using together with "data with sentiment labels" and newly labeled data. This technique improves the sentiment analysis performance gradually. However, it has a problem that misclassifications of unlabeled data in an early stage affect the model updating through the whole learning process because labels of unlabeled data never changes once those are determined. Thus, labels of "data without sentiment labels" needs to be carefully determined. In this paper, in order to get high performance using self-training technique, we propose 3 policies for updating "data with sentiment labels" and conduct a comparative analysis. The first policy is to select data of which confidence is higher than a given threshold among newly labeled data. The second policy is to choose the same number of the positive and negative data in the newly labeled data in order to avoid the imbalanced class learning problem. The third policy is to choose newly labeled data less than a given maximum number in order to avoid the updates of large amount of data at a time for gradual model updates. Experiments are conducted using Stanford data set and the data set is classified into positive and negative. As a result, the learned model has a high performance than the learned models by using "data with sentiment labels" only and the self-training with a regular model update policy.