• Title/Summary/Keyword: pattern recognition

Search Result 2,460, Processing Time 0.037 seconds

Association Analysis for Detecting Abnormal in Graph Database Environment (그래프 데이터베이스 환경에서 이상징후 탐지를 위한 연관 관계 분석 기법)

  • Jeong, Woo-Cheol;Jun, Moon-Seog;Choi, Do-Hyeon
    • Journal of Convergence for Information Technology
    • /
    • v.10 no.8
    • /
    • pp.15-22
    • /
    • 2020
  • The 4th industrial revolution and the rapid change in the data environment revealed technical limitations in the existing relational database(RDB). As a new analysis method for unstructured data in all fields such as IDC/finance/insurance, interest in graph database(GDB) technology is increasing. The graph database is an efficient technique for expressing interlocked data and analyzing associations in a wide range of networks. This study extended the existing RDB to the GDB model and applied machine learning algorithms (pattern recognition, clustering, path distance, core extraction) to detect new abnormal signs. As a result of the performance analysis, it was confirmed that the performance of abnormal behavior(about 180 times or more) was greatly improved, and that it was possible to extract an abnormal symptom pattern after 5 steps that could not be analyzed by RDB.

Automatically Converting HTML Documents with Similar Pattern into XML Documents (유사 패턴을 갖는 HTML 문서의 XML 자동 변환)

  • O, Geum-Yong;Hwang, In-Jun
    • The KIPS Transactions:PartD
    • /
    • v.9D no.3
    • /
    • pp.355-364
    • /
    • 2002
  • Recently, WWW(World Wide Web) has become a source of a large amount of information, and is now recognized not only as an information-sharing tool, but also as an information repository. Currently, the majority of documents on the web were created using HTML(Hypertext Markup Language). Although HTML is simple and easy to learn, its inherent lack of describing document structure makes it difficult to retrieve information effectively. One possible solution would be to convert such HTML documents into XML (extensible Markup Language) documents. This is a standard markup language for exchanging data on the web. It can describe a document structure freely by defining its own DTD (Document Type Definition). This makes it possible to integrate, store, and retrieve data on the web efficiently In this paper, we will propose a converter that automatically converts HTML documents with similar pattern into XML documents by analyzing the document structure and recognizing its path information.

Measurement of Travel Time Using Sequence Pattern of Vehicles (차종 시퀀스 패턴을 이용한 구간통행시간 계측)

  • Lim, Joong-Seon;Choi, Gyung-Hyun;Oh, Kyu-Sam;Park, Jong-Hun
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.7 no.5
    • /
    • pp.53-63
    • /
    • 2008
  • In this paper, we propose the regional travel time measurement algorithm using the sequence pattern matching to the type of vehicles between the origin of the region and the end of the region, that could be able to overcome the limit of conventional method such as Probe Car Method or AVI Method by License Plate Recognition. This algorithm recognizes the vehicles as a sequence group with a definite length, and measures the regional travel time by searching the sequence of the origin which is the most highly similar to the sequence of the end. According to the assumption of similarity cost function, there are proposed three types of algorithm, and it will be able to estimate the average travel time that is the most adequate to the information providing period by eliminating the abnormal value caused by inflow and outflow of vehicles. In the result of computer simulation by the length of region, the number of passing cars, the length of sequence, and the average maximum error rate are measured within 3.46%, which means that this algorithm is verified for its superior performance.

  • PDF

Analysis of the Effectiveness of Autonomous Unmanned Underwater Vehicle Mine Search Operation by Side Scan Sonar Characteristics (측면주사소나 특성에 따른 자율무인잠수정 기뢰탐색 효과도 분석)

  • Yoo, Tae-Suk;Park, Seok-Joon;Yoon, Seon-Il;Park, Ho-Gyu
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.24 no.8
    • /
    • pp.1077-1085
    • /
    • 2020
  • In order to Mine Countermeasure (MCM), the search is carried out for the expected mine zone. At this time, mine hunting uses Autonomous Unmanned Vehicle(AUV), taking into account the danger of mine and the stability of our forces. Sonar system for identifying buried mines are equipped with Side Scan Sonar(SSS) or Synthetic Aperture Sonar(SAS). This paper describes the analysis of mine hunting effects according to the commercial SSS characteristics. Based on the characteristics of each SSS, the insonified area and recognition probability were modeled, and the analysis was performed according to the search pattern of the AUV. AUV's search pattern defines three patterns depending on the presence or absence of SSS or shaded areas. The analysis results derived search time and detection probability for each search pattern, and finally, the improvement of search depending on the presence or absence of side injection or shaded area.

Noise Removal Filter Algorithm using Spatial Weight in AWGN Environment (화소값 분포패턴과 가중치 마스크를 사용한 AWGN 제거 알고리즘)

  • Cheon, Bong-Won;Kim, Nam-Ho
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2022.05a
    • /
    • pp.428-430
    • /
    • 2022
  • Image processing is playing an important part in automation and artificial intelligence systems, such as object tracking, object recognition and classification, and the importance of IoT technology and automation is emphasizing as interest in automation increases. However, in a system that requires detailed data such as an image boundary, a precise noise removal algorithm is required. Therefore, in this paper, we propose a filtering algorithm based on the pixel value distribution pattern to minimize the information loss in the filtering process. The proposed algorithm finds the distribution pattern of neighboring pixel values with respect to the pixel values of the input image. Then, a weight mask is calculated based on the distribution pattern, and the final output is calculated by applying it to the filtering mask. The proposed algorithm has superior noise removal characteristics compared to the existing method and restored the image while minimizing blurring.

  • PDF

A Study On Context Sensitive Highway Design Based On Improved Operating Speed Prediction Methods in National Roads (환경 친화적 도로 설계를 위한 기초 연구 (노선대 지형 및 지역 요소를 고려한 일반국도 주행속도 예측 모형))

  • Kim, Sang-Youp;Choi, Jai-Sung
    • Journal of Korean Society of Transportation
    • /
    • v.23 no.7 s.85
    • /
    • pp.17-33
    • /
    • 2005
  • Highway design speed is a very important design element which determines highway design level. When determining highway design speed, one would estimate it utilizing the most likelihood of design speed and vehicle operating speed relationship. Existing operating speed prediction models only include highway geometric characteristics and their impacts on speed, which usually can not consider the impact of highway design speed on surrounding roadway environment and land use pattern. If this happens, excessive highway construction cost and huge environmental impact can occur. In this research project, a new vehicle operating speed prediction model was developed which can reflect the effect of surrounding roadway environment into vehicle speed prediction. The followings are the research findings : Firstly, highway terrain types and land use pattern on national roads were classified and integrated into drivers' visual recognition pattern. This was performed using a data management software. Secondly, the developed highway terrain types and land use pattern were related to vehicle speeds and it was found that there were significant statistical differences among vehicle speed for each different terrain and land use pattern. Thirdly. the General Linear Model analysis was employed to analyze the effects of highway geometric features, terrain types, and land use patterns. For two-lane highway and four-lane highway tested in this research project, it was found that R squares were 0.67 and 0.85, respectively. Additionally an optimal highway design speed range table, based on this research project. was proposed for practical use. This table can be reliably used on South Korean national road design, but discretion is required for applying this table to other types of highways including provincial roads and municipal roads.

The Comparative Study of Oriental Medicine in Korea, Japan and China (한국(韓國)과 일본(日本) 및 중국(中國)의 동양의학(東洋醫學)에 대한 비교연구(比較硏究))

  • Cho, Ki-Ho
    • The Journal of Korean Medicine
    • /
    • v.19 no.1
    • /
    • pp.271-298
    • /
    • 1998
  • During these days of new understanding, western medicine has developed remarkably and a revaluation of traditional medicine has been achieved. This appears to have resulted from the sound criticisms of what western medicine has achieved up to now; excessive subdivisions of clinical medicine, severe toxicity of chemical drugs, lack of understanding about patients complaints which cannot be understood objectively, and etc. It is thought that the role of traditional medicine will be more important in the future than it is now. Someone said that the research methods of traditional medicine depends on the way of experimental science too much. That there was no consideration of a system for traditional medicine and the critic also went so far as to assert that in some cases the characteristics of eastern ideas is to permit irrationalism itself. In view of this thinking, the term traditional medicine seems to have been used somewhat too vaguely. However, traditional medicine is a medical treatment which has existed since before the appearance of modern medicine and it was formed from a traditional culture with a long history. One form of traditional medicine, oriental medicine based upon ancient Chinese medicine, was received in such countries as Korea, Japan, Thailand, Vietnam, Tibet, and Mongolia. Oriental medicine then developed in accordance with its own environment, race, national characteristics, and history. Although there are some simultaneous differences between them, three nations in Eastern Asia; Korea, Japan, and China, have especially similar features in their clinical prescriptions and medical literature. These three nations are trying to understand each others unique traditional medicines through numerous exchanges. Even though many differences in their ways of studying have developed over history exist, recent academic discussions have been made to explore new ways into oriental medicine. Therefore a comparative study of oriental medicine has gradually been thought to be more important. In Korea the formation of a new future-oriented paradigm for oriental medicine is being demanded. The purpose of the new paradigm is to create a new recognition of traditional culture which creates an understanding of oriental medicine to replace the diminished understanding of oriental medicine that was brought about by the self-denial of traditional culture in modem history and cultural collisions between oriental and occidental points of view. Therefore, to make a new paradigm for oriental medicine which is suitable for these days, and fortifies the merit of oriental medicine while compensating its defects, the author has compared the characteristics of oriental medicines in Korea, Japan, and China. The conclusions of this research are as follows: 1. The fundamental differences of the traditional medicines of these three nations are caused by the differences in the systems of Naekyung and Sanghannon. 2. The pattern-identification of illnesses is generally divided into two categories; the pattern identification of Zang-Fu and the pattern identification of prescription. 3. There are many differences in the definition of terms, such as Yin and Yang, Deficiency and Excess, and etc. 4. Chinese traditional medicine has some new concepts about pattern identification and epidemic febrile disease. 5. Japanese traditional medicine has some characteristics about pattern identification of the whole bodys condition and signs of abdominal palpation. 6. In terms of the effects of herbal drugs, Chinese traditional medicine attaches great importance to the experiential efficacy of the herb, and Japanese traditional medicine is taking a serious view of the effects of experimental medical actions.

  • PDF

Wafer bin map failure pattern recognition using hierarchical clustering (계층적 군집분석을 이용한 반도체 웨이퍼의 불량 및 불량 패턴 탐지)

  • Jeong, Joowon;Jung, Yoonsuh
    • The Korean Journal of Applied Statistics
    • /
    • v.35 no.3
    • /
    • pp.407-419
    • /
    • 2022
  • The semiconductor fabrication process is complex and time-consuming. There are sometimes errors in the process, which results in defective die on the wafer bin map (WBM). We can detect the faulty WBM by finding some patterns caused by dies. When one manually seeks the failure on WBM, it takes a long time due to the enormous number of WBMs. We suggest a two-step approach to discover the probable pattern on the WBMs in this paper. The first step is to separate the normal WBMs from the defective WBMs. We adapt a hierarchical clustering for de-noising, which nicely performs this work by wisely tuning the number of minimum points and the cutting height. Once declared as a faulty WBM, then it moves to the next step. In the second step, we classify the patterns among the defective WBMs. For this purpose, we extract features from the WBM. Then machine learning algorithm classifies the pattern. We use a real WBM data set (WM-811K) released by Taiwan semiconductor manufacturing company.

Dynamic Extension of Genetic Tree Maps (유전 목 지도의 동적 확장)

  • Ha, seong-Wook;Kwon, Kee-Hang;Kang, Dae-Seong
    • Journal of KIISE:Software and Applications
    • /
    • v.29 no.6
    • /
    • pp.386-395
    • /
    • 2002
  • In this paper, we suggest dynamic genetic tree-maps(DGTM) using optimal features on recognizing data. The DGTM uses the genetic algorithm about the importance of features rarely considerable on conventional neural networks and introduces GTM(genetic tree-maps) using tree structure according of the priority of features. Hence, we propose the extended formula, DGTM(dynamic GTM) has dynamic functions to separate and merge the neuron of neural network along the similarity of features.

Design and Implementation of Speech Music Discrimination System per Block Unit on FM Radio Broadcast (FM 방송 중 블록 단위 음성 음악 판별 시스템의 설계 및 구현)

  • Jang, Hyeon-Jong;Eom, Jeong-Gwon;Im, Jun-Sik
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 2007.11a
    • /
    • pp.25-28
    • /
    • 2007
  • 본 논문은 FM 라디오 방송의 오디오 신호를 블록 단위로 음성 음악을 판별하는 시스템을 제안하는 논문이다. 본 논문에서는 음성 음악 판별 시스템을 구축하기 위해 다양한 특정 파라미터와 분류 알고리즘을 제안 한다. 특정 파라미터는 신호처리 분야(Centroid, Rolloff, Flux, ZCR, Low Energy), 음성 인식 분야(LPC, MFCC), 음악 분석 분야(MPitch, Beat)에서 각각 사용되는 파라미터를 사용하였으며 분류 알고리즘으로는 패턴인식 분야(GMM, KNN, BP)와 퍼지 신경망(ANFIS)을 사용하였고, 거리 구현은 Mahalanobis 거리를 사용하였다.

  • PDF