• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.59-62
• /
• 2018

XML을 대상으로 하는 연구가 최근 5~6년 사이에 꾸준한 증가를 보이며 이루어지고 있지만 대다수의 연구들은 XML을 구성하고 있는 엘리먼트 자체에 대한 통계적인 모델을 기반으로 이루어졌다. 이는 XML의 고유 속성인 트리 구조에서의 텍스트, 문장, 문장 구성 성분이 가지고 있는 의미(semantics)가 명시적으로 분석, 표현되어 사용되기 보다는 통계적인 방법으로만 데이터의 발생을 계산하여 사용자가 요구한 질의에 대한 결과, 즉 해당하는 정보 및 지식을 제공하는 형식이다. 지능형 지식서비스 제공을 위한 환경에 부합하기 위한 정보 추출은, 텍스트 및 문장의 구성 요소를 분석하여 문서의 내용을 단순한 단어 집합보다는 풍부한 의미를 내포하는 형식으로 표현함으로써 보다 정교한 지식과 정보의 추출이 수행될 수 있도록 하여야 한다. 본 연구는 범람하는 XML 데이터로부터 사용자 요구의 의미까지 파악하여 정확하고 다양한 지식을 추출할 수 있는 방법을 연구하고자 한다. 레코드 구조가 아닌 트리 구조 데이터로부터 의미 추출이 가능한 효율적인 마이닝 기법을 진일보시킴으로써 다양한 사용자 중심의 서비스 제공을 최종 목적으로 한다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.2
• /
• pp.1-11
• /
• 2017

In this paper, we design and implement PADIL(Prediction And Detection of Information Leakage) system that predicts and detect information leakage behavior of insider by analyzing network traffic and applying a variety of machine learning methods. we defined the five-level information leakage model(Reconnaissance, Scanning, Access and Escalation, Exfiltration, Obfuscation) by referring to the cyber kill-chain model. In order to perform the machine learning for detecting information leakage, PADIL system extracts various features by analyzing the network traffic and extracts the behavioral features by comparing it with the personal profile information and extracts information leakage level features. We tested various machine learning methods and as a result, the DecisionTree algorithm showed excellent performance in information leakage detection and we showed that performance can be further improved by fine feature selection.

• Journal of Information Processing Systems
• /
• v.11 no.3
• /
• pp.389-405
• /
• 2015

Most traditional database systems exploit a record-oriented model where the attributes of a record are placed contiguously in a hard disk to achieve high performance writes. However, for read-mostly data warehouse systems, the column-oriented database has become a proper model because of its superior read performance. Today, flash memory is largely recognized as the preferred storage media for high-speed database systems. In this paper, we introduce a column-oriented database model based on flash memory and then propose a new column-aware flash indexing scheme for the high-speed column-oriented data warehouse systems. Our index management scheme, which uses an enhanced $B^+$-Tree, achieves superior search performance by indexing an embedded segment and packing an unused space in internal and leaf nodes. Based on the performance results of two test databases, we concluded that the column-aware flash index management outperforms the traditional scheme in the respect of the mixed operation throughput and its response time.

• Korean Journal of Remote Sensing
• /
• v.7 no.2
• /
• pp.149-163
• /
• 1991

This paper discusses the capabilities of airborne remotely sensed data to detect and classify forest damades. In this work the AMS (Aircraft Multiband Scanner) was used to obtain digital imagery at 300m altitude for forest damage inventory in the Black Forest of Germany. MSS(Multispectral Scanner) digital numbers were converted to spectral emittance and radiance values in 8 spectral bands from the visible to the thermal infrared and submitted to a maximum-likelihood classification for : (1) tree species ; and. (2) damage classes. As expected, the resulted, the results of MSS data with high spatial resolution 0.75m$\times$0.75m enabled the detection and identification of single trees with different damages and were nearly equivalent to the truth information of ground checked data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.23-26
• /
• 2019

사물인터넷(IoT)은 지금의 우리가 살고 일하는 모든 방식을 변화시키고 있다. IoT를 통해 데이터를 생성하고 저장하고 연결된 장치와 상호작용하여 비즈니스는 물론 우리의 일상 생활을 개선하고 있는 것이다. 무수히 많은 센서들이 연결된 세상은 센서들에 의해 그 어느 때보다 거대한 양의 데이터들을 생산하고 있다. JSON, XML 같은 트리 구조의 데이터 타입은 대량 데이터 저장 전송 교환 등에 주요하게 사용되는데 이는 트리 구조가 이형 데이터 간의 유연한 정보 전송과 교환을 가능하게 하기 때문이다. 반면에, 효용성 높은 정보나 감추어져 있는 정보들을 트리 구조의 대량 데이터들로부터 추출하는 것은 일반 데이터 구조에 비해 훨씬 어려우며 더 난해한 문제들을 발생시킨다. 본 논문에서는 트리 구조의 대량 스트리밍 데이터로부터 가중치가 부여된 주요한 부정 패턴들을 추출하기 위한 방법을 공식화한다.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.746-757
• /
• 2023

This study presents a novel safe landing algorithm for urban drone deliveries. The rapid advancement of drone technology has given rise to various delivery services for everyday necessities and emergency relief efforts. However, the reliability of drone delivery technology is still insufficient for application in urban environments. The proposed approach uses the "landing angle control" method to allow the drone to land vertically and a rapidly exploring random tree-based collision avoidance algorithm to generate safe and efficient vertical landing paths for drones while avoiding common urban obstacles like trees, street lights, utility poles, and wires; these methods allow for precise and reliable urban drone delivery. We verified the approach within a Gazebo simulation operated through ROS using a six-degree-of-freedom drone model and sensors with similar specifications to actual models. The performance of the algorithms was tested in various scenarios by comparing it with that of stateof-the-art 3D path planning algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1449-1461
• /
• 2024

As technology advances, processor speeds are increasing at a rapid pace and digital systems require a significant amount of data bandwidth. As a result, careful consideration of signal integrity is required to ensure reliable and high-speed data processing. Crosstalk has become a vital area of research in signal integrity for electronic packages, mainly because of the high level of integration. Analytic formulas were analyzed in this study to identify the features that can predict crosstalk in multi-conductor transmission lines. Through the analysis, five variables were found and obtained a dataset consisting of 302,500, data points. The study evaluated the performance of various regression models for optimization via automatic machine learning by comparing the machine learning predictions with the analytic solution. Extra tree regression consistently outperformed other algorithms, with coefficients of determination exceeding 0.9 and root mean square logarithmic errors below 0.35. The study also notes that different algorithms produced varied predictions for the two metrics.

• The Journal of Korean Medicine
• /
• v.27 no.2 s.66
• /
• pp.134-144
• /
• 2006

Tongue diagnosis is an important diagnostic method in traditional Oriental medicine. It has been especially accepted that quantitative analysis of tongue images allows the accurate diagnosis of the exterior-interior and cold-heat patterns of a patient. However, to ensure stable and reliable results, the color reproduction of such images must first be error-tree. Moreover, tongue diagnosis is much influenced by the surrounding illumination and subjective color recognition, so it has to be performed objectively and quantitatively using a digital diagnostic machine. In this study, 457 tongue images of outpatients were collected using the Digital Tongue Inspection System. Through statistical analysis, the result shows that the heat and cold patterns can be distinguished clearly based on the hue value of the tongue images. The average hue value (1.00) of the tongue's image in the cold pattern is higher than that in the heat pattern (0.99).

• Journal of Korea Game Society
• /
• v.8 no.1
• /
• pp.79-90
• /
• 2008

This paper describes a motivation-based hierarchical behavior planning framework to allow autonomous agents to select adaptive actions in simulation game environments. The combined behavior planning system is formed by four levels of specification, which are motivation extraction, goal list generation, action list determination and optimization. Our model increases the complexity of virtual human behavior planning by adding motivation with sudden and cumulative attributes. The motivation selection by probability distribution allows NPC to make multiple decisions in certain situations in order to embody realistic virtual humans. Hierarchical goal tree enhances the effective reactivity. Optimizing for potential actions provides NPC with safe and satisfying actions to adapt to the virtual environment. A restaurant simulation game was used to elucidate the mechanism of the framework.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.11 no.4
• /
• pp.69-79
• /
• 2015

This research proposes a modified data hiding method to hide data in a slack space of an NTFS index record. The existing data hiding method is for anti-forensics, which uses traces of file names of an index entry in an index record when files are deleted in a direcotry. The proposed method in this paper modifies the existing method to make non-admittable ASCII characters for a file name applicable. By improving the existing method, problems of a file creation error due to non-admittable characters are remedied; including the non-admittable 9 characters (i. e. slash /, colon :, greater than >, less than <, question mark ?, back slash ${\backslash}$, vertical bar |, semi-colon ;, esterisk * ), reserved file names(i. e. CON, PRN, AUX, NUL, COM1~COM9, LPT1~LPT9) and two non-admittable characters for an ending character of the file name(i. e. space and dot). Two results of the two message with non-admittable ASCII characters by keyboard inputs show the applicability of the proposed method.