• Smart Structures and Systems
• /
• 제14권4호
• /
• pp.679-697
• /
• 2014

The strain data acquired from structural health monitoring (SHM) systems play an important role in the state monitoring and damage identification of bridges. Due to the environmental complexity of civil structures, a better understanding of the actual strain data will help filling the gap between theoretical/laboratorial results and practical application. In the study, the multi-scale features of strain response are first revealed after abundant investigations on the actual data from two typical long-span bridges. Results show that, strain types at the three typical temporal scales of $10^5$, $10^2$ and $10^0$ sec are caused by temperature change, trains and heavy trucks, and have their respective cut-off frequency in the order of $10^{-2}$, $10^{-1}$ and $10^0$ Hz. Multi-resolution analysis and wavelet shrinkage are applied for separating and extracting these strain types. During the above process, two methods for determining thresholds are introduced. The excellent ability of wavelet transform on simultaneously time-frequency analysis leads to an effective information extraction. After extraction, the strain data will be compressed at an attractive ratio. This research may contribute to a further understanding of actual strain data of long-span bridges; also, the proposed extracting methodology is applicable on actual SHM systems.

• Journal of Advanced Marine Engineering and Technology
• /
• 제38권5호
• /
• pp.557-565
• /
• 2014

This paper describes the extended pivot-based approach for bilingual lexicon extraction. The basic features of the approach can be described as follows: First, the approach builds context vectors between a source (or target) language and a pivot language like English, respectively. This is the same as the standard pivot-based approach which is useful for extracting bilingual lexicons between low-resource languages such as Korean-French. Second, unlike the standard pivot-based approach, the approach looks for similar context vectors in a source language. This is helpful to extract translation candidates for polysemous words as well as lets the translations be more confident. Third, the approach extracts translation candidates from target context vectors through the similarity between source and target context vectors. Based on these features, this paper describes the extended pivot-based approach and does various experiments in a language pair, Korean-French (KR-FR). We have observed that the approach is useful for extracting the most proper translation candidate as well as for a low-resource language pair.

• 한국컴퓨터정보학회논문지
• /
• 제11권3호
• /
• pp.133-139
• /
• 2006

컴퓨터 정보기술의 발달로 멀티미디어 데이터가 급증하고 있다. 특히, 영상검색 분야에서는 영상 데이터의 신속, 정확한 처리 및 분석이 요구된다. 그러나 일반적으로 신속성과 정확성을 모두 보장하는 데는 어려움이 있다. 본 논문은 이러한 문제를 해결하기 위하여 유전자 알고리즘을 이용해 영상의 대표 특징치를 추출하는 알고리즘을 제안한다. 이 알고리즘은 영상이 가지고 있는 대표적인 특징치 뽑아냄으로써 검색의 신속성과 정확성을 보장한다. 영상의 특징으로는 색상과 질감을 사용하였다. 실험결과, 기존의 연구에 비해 제안된 특징 추출법이 더 좋은 정확성을 보임으로서 제안된 방법의 타당성을 입증하였다.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1425-1430
• /
• 2018

In this paper, we propose a CNN based deep learning algorithm for semantic segmentation of images. In order to improve the accuracy of semantic segmentation, we combined pixel level object classification and image level object classification. The image level object classification is used to accurately detect the characteristics of an image, and the pixel level object classification is used to indicate which object area is included in each pixel. The proposed network structure consists of three parts in total. A part for extracting the features of the image, a part for outputting the final result in the resolution size of the original image, and a part for performing the image level object classification. Loss functions exist for image level and pixel level classification, respectively. Image-level object classification uses KL-Divergence and pixel level object classification uses cross-entropy. In addition, it combines the layer of the resolution of the network extracting the features and the network of the resolution to secure the position information of the lost feature and the information of the boundary of the object due to the pooling operation.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.17-22
• /
• 2021

The attack trend on end-users via mobile devices is increasing in both the danger level and the number of attacks. Especially, mobile devices using the Android operating system are being recognized as increasingly being exploited and attacked strongly. In addition, one of the recent attack methods on the Android operating system is to take advantage of Android Package Kit (APK) files. Therefore, the problem of early detecting and warning attacks on mobile devices using the Android operating system through the APK file is very necessary today. This paper proposes to use the method of analyzing abnormal behavior of APK files and use it as a basis to conclude about signs of malware attacking the Android operating system. In order to achieve this purpose, we propose 2 main tasks: i) analyzing and extracting abnormal behavior of APK files; ii) detecting malware in APK files based on behavior analysis techniques using machine learning or deep learning algorithms. The difference between our research and other related studies is that instead of focusing on analyzing and extracting typical features of APK files, we will try to analyze and enumerate all the features of the APK file as the basis for classifying malicious APK files and clean APK files.

• 한국산학기술학회논문지
• /
• 제13권11호
• /
• pp.5471-5478
• /
• 2012

본 논문에서는 SURF 알고리즘을 이용하여 PCB에 발생하는 불량 중 한 형태인 쇼트-서킷 불량을 탐지하는 기술을 제안한다. 제안하는 방법의 기본적인 절차는 SURF를 이용하여 샘플 영상과 입력된 영상에서 특징점 추출, 특징점 매칭 및 매칭 결과를 이용한 원근변환 수행, 검사 위치 관심영역 추출, 이진화 및 쇼트-서킷 추출, 결과 검증 순이다. 본 논문에서 제안하는 방식은 수작업으로 진행되는 후 공정의 특징 상, 검사하고자 하는 PCB의 놓여진 위치와 각도가 균일하지 않고 제각각으로 놓여 있는 경우에도 강건하게 쇼트-서킷 불량을 탐지하는 것에 중점을 두고 있다. 이 방법은 PCB가 놓여진 위치와 각도가 다양한 경우에도 불량을 탐지할 수 있음을 보이며, 탐지율 및 탐지시간 관점에서 기존의 수작업으로 검사하는 경우보다 우수함을 실험을 통하여 보인다.

• 정보관리학회지
• /
• 제30권3호
• /
• pp.23-48
• /
• 2013

본 연구는 웹에서 접근 가능한 내용기반 음악검색(CBMR) 시스템들을 조사하여, 탐색질의의 종류, 접근점, 입출력, 탐색기능, 데이터베이스 성격과 크기 등의 관점에서 특성을 비교 분석하고자 하였다. 비교 분석에 사용된 특성을 추출하기 위해 내용기반 음악정보의 특성과 시스템 구축에 필요한 파일의 변환, 멜로디 추출 및 분할, 색인자질 추출과 색인, 매칭에 사용되는 기술들을 선행연구로 리뷰하였다. 15개의 시스템을 분석한 결과 다음과 같은 특성과 문제점이 분석되었다. 첫째, 도치색인, N-gram 색인, 불리언 탐색, 용어절단검색, 키워드 및 어구 탐색, 음길이 정규화, 필터링, 브라우징, 편집거리, 정렬과 같은 텍스트 정보 검색 기법이 CBMR에서도 검색성능을 향상시키는 도구로 사용되고 있었다. 둘째, 시스템들은 웹에서 크롤링하거나 탐색질의를 DB에 추가하는 등으로 DB의 성장과 실용성을 위한 노력을 하고 있었다. 셋째, 개선되어야 할 문제점으로 선율이나 주선율을 추출하는데 부정확성, 색인자질을 추출할 때 사용되는 불용음(stop notes)을 탐색질의에서도 자동 제거할 필요성, 옥타브를 무시한 solfege 검색의 문제점 등이 분석되었다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.548-551
• /
• 2007

Among components of digital topographic maps used officially in Korea, only contours have 3D values except buildings and trees that are demanded in landscape planning. This study presented a series of processes for 3Dreconstructing landscape features such as terrain, buildings and standing trees using LiDAR (Light Detection And Ranging) data and aerial digital photo graphs. The 3D reconstructing processes contain 1) building terrain model, 2) delineating outline of landscape features, 3) extracting height values, and 4) shaping and coloring landscape features using aerial photograph and 3-D virtual data base. LiDAR data and aerial photograph was taken in November 2006 for $50km^{2}$ area in Sorak National Park located in eastern part of Korea. The average scanning density of LiDAR pulse was 1.32 points per square meter, and the aerial photograph with RGB bands has $0.35m{\times}0.35m$ spatial resolution. Using reconstructed 3D landscape features, visibility with the growing trees with time and at different viewpoints was analyzed. Visible area from viewpoint could be effectively estimated considering 3D information of landscape features. This process could be applied for landscape planning like building scale with the consideration of surrounding landscape features.

• ETRI Journal
• /
• 제33권4호
• /
• pp.589-599
• /
• 2011

This paper presents an image description and matching scheme using synthetic features for a recommendation service. The recommendation service is an example of smart search because it offers something before a user's request. In the proposed extraction scheme, an image is described by synthesized spatial and statistical features. The spatial feature is designed to increase the discriminability by reflecting delicate variations. The statistical feature is designed to increase the robustness by absorbing small variations. For extracting spatial features, we partition the image into concentric circles and extract four characteristics using a spatial relation. To extract statistical features, we adapt three transforms into the image and compose a 3D histogram as the final statistical feature. The matching schemes are designed hierarchically using the proposed spatial and statistical features. The result shows that each feature is better than the compared algorithms that use spatial or statistical features. Additionally, if we adapt the proposed whole extraction and matching scheme, the overall performance will become 98.44% in terms of the correct search ratio.

• 한국정보통신학회논문지
• /
• 제6권2호
• /
• pp.339-345
• /
• 2002

자동차의 번호판을 인식하는 것은 차량을 식별하는데 있어서 매우 중요하다. 어두운 조명에서나 날씨가 나쁠 경우 차량의 형상이 왜곡 될 수 있고, 번호판을 식별하는데 어려움이 있다. 본 논문은 차량의 규격을 이용하여 효율적으로 번호판을 추출하는 방법을 제안한다. 이 방법에서 색상이나 형태처럼 차량의 규격을 따르는 자동차 번호판의 특징들은 번호판의 후보영역으로 결정되고, 신경망에 의해 숫자나 문자의 패턴 갖는 영역이 번호판 영역으로 인식된다. 또한 특징패턴인식의 결과로서 번호판을 확정하였다. 70개 차량영상을 실험해 본 결과 번호판 추출률에서는 84.29 ％, 인식률에서는 80.81 ％의 결과를 나타내었다.