• Journal of KIISE:Software and Applications
• /
• v.35 no.2
• /
• pp.59-69
• /
• 2008

Automatic obfuscation is known to be the most viable method for preventing reverse engineering intentional1y making code more difficult to understand for security purposes. In this paper, we study and implement an obfuscation method for protecting MS Visual C++ programs against attack on the intellectual property in software like reverse engineering attack. That is, the paper describes the implementation of a code obfuscator, a tool which converts a Visual C++ source program into an equivalent one that is much harder to understand. We have used ANTLR parser generator for handling Visual C++ sources, and implemented some obfuscating transformations such as 'Remove comments', 'Scramble identifiers', 'Split variables', 'Fold array', 'Insert class', 'Extend loop condition', 'Add redundant operands', and 'Insert dead code'. We have also evaluated the performance and effectiveness of the obfuscator in terms of potency, resilience, and cost. When the obfuscated source code has been compared with the original source code, it has enough effectiveness for software protection though it incurs some run-time overheads.

• The Journal of the Korea Contents Association
• /
• v.4 no.2
• /
• pp.68-75
• /
• 2004

In this paper, n study a distributed establishment scheme to setup lightpath in WDM/TDM Network considering user traffic characteristics. We propose a GBTA(guaranteed-bandwidth time-slot allocation) algorithm which assigns time-slots according to the requred traffic so that it can utilize given network resources efficiently in RWTA(routing and wavelength time-slot assignment) schemes. We consider traffic specification on the basis of ATM traffic classes. Also, in order to increase link utilization and minimize blocking probability, we extend distributed lightpath establishment protocol based on GBTA algorithm. In order to establish lightpath in distributed WDM/IDM network, we use backward resonation protocol that resewes resource with recent information. We use DOWTns(Distributed Optical WDM/TDM ns) that is extended from NS(Network Simulator), in order to verify proposed GBTA-based optical wavelength routed network.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.316-316
• /
• 2016

HyGIS는 DEM 기반의 수문지형처리를 중심으로 다양한 모형을 연계할 수 있도록 구성된 S/W 모음이다. 이는 한국건설기술연구원을 비롯한 다수의 기관 및 연구원들이 노력한 성과물이다. 본 연구는 기존 HyGIS 연구과정에서 도출된 성과물의 실용화 사업화를 위한 방안을 연구하였다. 이를 위하여 S/W 테스팅, 오픈소스 도입, 클라우드 컴퓨팅으로 나누어 접근하였다. 먼저 S/W의 테스팅에 있어서 기존 개발 소스코드는 블랙박스 테스트 방식의 동등 클래스 분할, 경계 값 분석 등 일부 모듈에 대한 단위 테스트와 제한적인 통합테스트가 수행된 바 있다. 보다 체계적인 테스트 단계로서 화이트박스 테스트 개념 중 문장/분기/조건 커버리지에 대하여 검토하였으며, 실제 소스코드 중 핵심 구간에 대한 적용 및 정량화를 통하여 현 수준을 객관적으로 진단하였고 보완 방안을 도출하였다. 오픈소스 적용을 위하여 QGIS, MapWindow 등 공간정보 분야의 최신 오픈소스 모듈을 비교 검토하였다. 적용 단계는 이를 기존 HyGIS S/W에 반영시키는 과정이며, S/W 관점에서는 컴포넌트 모듈의 대체라고 표현될 수 있다. 대규모의 전환 비용이 발생되므로 적용 후보에 대하여는 기능적 측면 뿐만 아니라 마이그레이션 비용과 중장기적인 유지보수 비용을 고려한 검토가 이루어 졌다. 한편 오픈소스 기술의 적용은 단순히 구성 요소 원가절감 측면만이 아닌, 중장기적 유지보수 체계 도모 및 지속가능한 생태계로의 전환에 더 큰 의의가 있다. 마지막으로 클라우드 컴퓨팅 기술의 적용 분야이다. HyGIS 입력 Data의 공급을 위한 인프라로서 자체 구축 인프라가 아닌 IaaS 클라우드인 Blob Storage 및 CDN을 시험 적용하였다. 클라우드를 활용함으로써 초기 비용을 최소화하고 합리적 비용으로 유연한 확장이 가능한(Scale Out, Scale Up) 구조를 취하게 되었다. 또한 입력 Data 공급 서버를 위한 Storage 측면만이 아니라 S/W의 배포에 있어서도 클라우드 컴퓨팅 기술을 활용하고자 시도하였다. 클라우드 기술을 활용하여 HyGIS S/W가 설치된 VM(Virtual Machine)자체를 임대하는 방식으로 시험 구성 되었다. VM에 대한 RDP 프로토콜 Access에 있어서 IP기반 접근 제어를 통하여 보안을 강화하는 방안을 실험하였으며, ISO 27001, ISO 27018 등 관련 보안 규정에 부합하는 서비스 제공이 가능하도록 검토하였다. 이러한 클라우드 VM방식 서비스를 통하여 Package형 S/W 뿐만 아니라 Subscription 방식의 서비스 제공 방식을 병행할 수 있다. 사용자에게는 S/W 설치 및 H/W Lock 구비 과정이 생략되는 이점이 있다.

• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1290-1304
• /
• 2020

Medical image analyses have been widely used to differentiate normal and abnormal cases, detect lesions, segment organs, etc. Recently, owing to many breakthroughs in artificial intelligence techniques, medical image analyses based on deep learning have been actively studied. However, sufficient medical data are difficult to obtain, and data imbalance between classes hinder the improvement of deep learning performance. To resolve these issues, various studies have been performed, and data augmentation has been found to be a solution. In this review, we introduce data augmentation techniques, including image processing, such as rotation, shift, and intensity variation methods, generative adversarial network-based method, and image property mixing methods. Subsequently, we examine various deep learning studies based on data augmentation techniques. Finally, we discuss the necessity and future directions of data augmentation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.5
• /
• pp.363-371
• /
• 2015

Feature extraction is one of the main goals in many remote sensing analyses. After high-resolution imagery became more available, it became possible to extract more detailed and specific features. Thus, considerable image segmentation algorithms have been developed, because traditional pixel-based analysis proved insufficient for high-resolution imagery due to its inability to handle the internal variability of complex scenes. However, the individual segmentation method, which simply uses color layers, is limited in its ability to extract various target features with different spectral and shape characteristics. Spectral indices can be used to support effective feature extraction by helping to identify abundant surface materials. This study aims to evaluate a feature extraction method based on a segmentation technique with spectral indices. We tested the extraction of diverse target features-such as buildings, vegetation, water, and shadows from eight band WorldView-2 satellite image using decision tree classification and used the result to draw the appropriate spectral indices for each specific feature extraction. From the results, We identified that spectral band ratios can be applied to distinguish feature classes simply and effectively.

• Database Research
• /
• v.34 no.3
• /
• pp.159-169
• /
• 2018

Discretization of continuous variables intended to improve the performance of various algorithms such as data mining by transforming quantitative variables into qualitative variables. If we use appropriate discretization techniques for data, we can expect not only better performance of classification algorithms, but also accurate and concise interpretation of results and speed improvements. Various discretization techniques have been studied up to now, and however there is still demand of research on discretization studies. In this paper, we propose a new discretization technique to set the cut-point using Wasserstein distance with considering the distribution of continuous variable values with classes of data. We show the superiority of the proposed method through the performance comparison between the proposed method and the existing proven methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.8-10
• /
• 2023

삼킴장애는 음식물이 입에서 식도로 가지않고 걸리거나 기도(Trachea)로 흡입되는 문제를 갖는 상태이다. 특히 노인이나 신경계 질환을 앓는 환자의 경우 기도로 흡입된 음식덩이가 폐렴을 일으키고 결국에는 사망으로 이어지기에 적절한 치료와 관리가 요구된다. 보통 영상으로 판단할 수 있는 삼킴단계는 구강준비단계(Oral Preparatory Phase), 구강단계(Oral Phase), 인두단계(Pharyngeal Phase), 식도단계(Esophageal Phase) 4가지로 분류하고 삼킴장애는 침습(Penetration)과 흡인(Aspiration)으로 크게 2가지로 분류한다. 본 논문에서는 이러한 6가지 클래스를 가지는 삼킴장애 환자 비디오 파일을 라벨링하기 위한 웹 애플리케이션을 제안한다. 이를 구현하기 위해서 대용량 멀티프레임 이미지를 수신해서 분리하여 저장하도록 개발하였다. 또한 음식덩이를 정교하게 분할할 수 있도록 GrabCut 알고리즘을 적용하여 라벨링할 수 있도록 하였다. 차후 라벨러와 전문의 간의 협업이 가능하도록 라벨링 데이터의 상태를 관리할 수 있도록 개발하고자 한다.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.127-132
• /
• 2006

K-NN (k-Nearest Neighbors), which is a well-known instance-based learning algorithm, simply stores entire training patterns in memory, and uses a distance function to classify a test pattern. K-NN is proven to show satisfactory performance, but it is notorious formemory usage and lengthy computation. Various studies have been found in the literature in order to minimize memory usage and computation time, and NGE (Nested Generalized Exemplar) theory is one of them. In this paper, we propose RPA (Recursive Partition Averaging) and IRPA (Incremental RPA) which is an incremental version of RPA. RPA partitions the entire pattern space recursively, and generates representatives from each partition. Also, due to the fact that RPA is prone to produce excessive number of partitions as the number of features in a pattern increases, we present IRPA which reduces the number of representative patterns by processing the training set in an incremental manner. Our proposed methods have been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.5
• /
• pp.2393-2399
• /
• 2013

In this paper, we proposed a method to screening of Alzheimer's disease (AD) from Raman spectra of platelet with synthesis of basis spectra using singular value decomposition (SVD). Raman spectra of platelet from AD transgenic mice are preprocessed with denoising, removal background and normalization method. The column vectors of each data matrix consist of Raman spectrum of AD and normal (NR). The matrix is factorized using SVD algorithm and then the basis spectra of AD and NR are determined by 12 column vectors of each matrix. The classification process is completed by select the class that minimized the root-mean-square error between the validation spectrum and the linear synthesized spectrum of the basis spectra. According to the experiments involving 278 Raman spectra, the proposed method gave about 97.6% classification rate, which is better performance about 6.1% than multi-layer perceptron (MLP) with extracted features using principle components analysis (PCA). The results show that the basis spectra using SVD is well suited for the diagnosis of AD by Raman spectra from platelet.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.1
• /
• pp.39-47
• /
• 2017

Nowadays, there have been an increasing number of illegal use cases where people try to fabricate the working hours by using fake fingerprints. So, the fingerprint liveness detection techniques have been actively studied and widely demanded in various applications. This paper proposes a new method to detect fake fingerprints using CNN (Convolutional Neural Ntworks) based on the patches of fingerprint images. Fingerprint image is divided into small square sized patches and each patch is classified as live, fake, or background by the CNN. Finally, the fingerprint image is classified into either live or fake based on the voting result between the numbers of fake and live patches. The proposed method does not need preprocessing steps such as segmentation because it includes the background class in the patch classification. This method shows promising results of 3.06% average classification errors on LivDet2011, LivDet2013 and LivDet2015 dataset.