• Journal of the Korea Society for Simulation
• /
• v.21 no.3
• /
• pp.1-9
• /
• 2012

This paper proposes automatic precision approach radar (PAR) control system using digital signal to increase the safety of aircraft, and discrete event systems specification (DEVS) methodology is utilized to verify the proposed system. Traditionally, a landing aircraft is controlled by the human voice of a final approach controller. However, the voice information can be missed during transmission, and pilots may also act improperly because of incorrectness of auditory signals. The proposed system enables the stable operation of the aircraft, regardless of the pilot's capability. Communicating DEVS (C-DEVS) is used to analyze and verify the behavior of the proposed system. A composed C-DEVS atomic model has overall composed discrete state sets of models, and the state sequence acquired through full state search is utilized to verify the safeness and the liveness of a system behavior. The C-DEVS model of the proposed system shows the same behavior with the traditional PAR control system.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.2
• /
• pp.31-39
• /
• 2020

In this paper, we introduce a technique for generating synthetic benchmarks based on time series data. Many of the data measured on IoT devices have a time series characteristic that measures numerical changes over time. However, there is a problem that it is difficult to model the data measured over a long period as generalized time series data. To solve this problem, this paper introduces the BST-IGT model. The BST-IGT model separates the entire data into sections that can be easily time-series modeled, collects the generated data into templates, and produces new synthetic benchmarks that share or modify characteristics based on them. As a result of making a new benchmark using the proposed modeling method, we could create a benchmark with multiple aspects by mixing the composite benchmark with the statistical features of the existing data and other benchmarks.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.16 no.3
• /
• pp.250-257
• /
• 2011

This paper analyzes characteristic of the three-phase coupled inductor connected to ac source to effectively mitigate the high-frequency circulating current generated in parallel three-phase boost converters. The three-phase coupled inductor analysis presented in this paper uses the three-phase coupled inductor structure and voltage equations. Based on this analysis, the three-phase coupled inductor is added to the conventional low-frequency averaged model. As a result, the novel averaged model which can reduce the low and high-frequency circulating current simultaneously is developed. Using the zero-sequence component of the novel averaged model, each total inductance to the circulating current of the three-phase coupled inductor and line inductor can be obtained. Simulation and experiment results verify the usefulness of three-phase coupled inductor in parallel three-phase boost converters.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.13-22
• /
• 2021

Recently network based attack technologies are rapidly advanced and intelligent, the limitations of existing signature-based intrusion detection systems are becoming clear. The reason is that signature-based detection methods lack generalization capabilities for new attacks such as APT attacks. To solve these problems, research on machine learning-based intrusion detection systems is being actively conducted. However, in the actual network environment, attack samples are collected very little compared to normal samples, resulting in class imbalance problems. When a supervised learning-based anomaly detection model is trained with such data, the result is biased to the normal sample. In this paper, we propose to overcome this imbalance problem through One-Class Anomaly Detection using an auto encoder. The experiment was conducted through the NSL-KDD data set and compares the performance with the supervised learning models for the performance evaluation of the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.19-26
• /
• 2019

In this paper, the classification performance of learning algorithms is compared for TAB digit recognition. The TAB digits that are segmented from TAB musical notes contain TAB lines and musical symbols. The labeling method and non-linear filter are designed and applied to extract fret digits only. The shift operation of the 4 directions is applied to generate more data. The selected models are Bayesian classifier, support vector machine, prototype based learning, multi-layer perceptron, and convolutional neural network. The result shows that the mean accuracy of the Bayesian classifier is about 85.0% while that of the others reaches more than 99.0%. In addition, the convolutional neural network outperforms the others in terms of generalization and the step of the data preprocessing.

• Convergence Security Journal
• /
• v.18 no.2
• /
• pp.49-58
• /
• 2018

As the demand for Internet of Things(IoT) increases, the need for the security of IoT devices is increasing steadily. It is difficult to apply the conventional security theory to IoT devices because IoT devices are subject to be constrained by some factors such as hardware, processor, and energy. Nowadays we have several security guidelines and related documents on IoT device. Most of them, however, do not consider the characteristics of specific IoT devices. Since they describes the security issues comprehensively, it is not easy to explain the specific security level reflecting each characteristics of IoT devices. In addition, most existing guidelines and related documents are described in view of developers and service proposers, and thus ordinary users are not able to assess whether a specific IoT device can protect their information securely or not. We propose an security evaluation model, based on the existing guidelines and related documents, for more specific IoT devices and prove that this approach is more convenient to ordinary users by creating checklists for the smart watch.

• Korean Chemical Engineering Research
• /
• v.59 no.4
• /
• pp.532-541
• /
• 2021

Recently, research on the application of artificial intelligence in the chemical process has been increasing rapidly. However, overfitting is a significant problem that prevents the model from being generalized well to predict unseen data on test data, as well as observed training data. Cross validation is one of the ways to solve the overfitting problem. In this study, the time-series cross validation method was applied to optimize the number of batch and epoch in the hyperparameters of the prediction model for the 2,3-BDO distillation process, and it compared with K-fold cross validation generally used. As a result, the RMSE of the model with time-series cross validation was lower by 9.06%, and the MAPE was higher by 0.61% than the model with K-fold cross validation. Also, the calculation time was 198.29 sec less than the K-fold cross validation method.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.43-52
• /
• 2020

With the development of data technology, storing and sharing of data has increased, resulting in privacy invasion. Although de-identification technology has been introduced to solve this problem, it has been proved many times that identifying individuals using de-identified data is possible. Even if it cannot be completely safe, sufficient de-identification is necessary. But current laws and regulations do not quantitatively specify the degree of how much de-identification should be performed. In this paper, we propose an appropriate de-identification criterion considering the time required for re-identification. We focused on the case of using the k-anonymity model among various privacy models. We analyzed the time taken to re-identify data according to the change in the k value. We used a re-identification method based on linkability. As a result of the analysis, we determined which k value is appropriate. If the generalized model can be developed by results of this paper, the model can be used to define the appropriate level of de-identification in various laws and regulations.

• Journal of The Korean Association of Information Education
• /
• v.26 no.3
• /
• pp.153-165
• /
• 2022

This study is about the Novel Engineering(NE) education program : a class model that combines reading and engineering. By including the process of directly designing and programming a virtual reality using CospacesEdu (a VR authoring tool for the NE class), the effects of the educational program on learners' STEAM literacy and Learning immersion are demonstrated. Moreover, the subject of this education is Dokdo in South Korea. As a result, the average of STEAM literacy is increased, and a significant change is confirmed statistically in Convergence. Learning immersion shows significant improvement in Challenges-skills balance. On the other hand, some students experience difficulties due to the long research stages, from reading a book to researching for information to designing VR and rewriting a story with the collected information. In conclusion, this study will help generalise other education using NE, and this developed program will be a reference that would suggest a new way of teaching.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.147-157
• /
• 2022

Recently, many studies have been conducted to analyze traffic or object recognition that classifies vehicles through artificial intelligence-based prediction models using CCTV (Closed Circuit TeleVision)or drone images. In order to develop an object recognition deep learning model for accurate traffic estimation, systematic data construction is required, and related standardized guidelines are insufficient. In this study, previous studies were analyzed to derive guidelines for establishing artificial intelligence-based training data for traffic estimation using drone images, and business reports or training data for artificial intelligence and quality management guidelines were referenced. The guidelines for data construction are divided into data acquisition, preprocessing, and validation, and guidelines for notice and evaluation index for each item are presented. The guidelines for data construction aims to provide assistance in the development of a robust and generalized artificial intelligence model in analyzing the estimation of road traffic based on drone image artificial intelligence.