• Title/Summary/Keyword: 목표분류

Search Result 888, Processing Time 0.032 seconds

A Study of Histogram of Oriented Gradients Feature Vector Based on Support Vector Machine for Medical Image Classification (의료 이미지 분류를 위한 서포트 벡터 머신 기반의 Histogram of Oriented Gradients 특징 벡터 연구)

  • Lee, SeungHwan;Yoo, JaeChern
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2020.01a
    • /
    • pp.5-6
    • /
    • 2020
  • 현대 의학에서 의료 영상은 수많은 영상처리 의료기기의 핵심이다. PACS(Picture Archiving Communication System)를 통해 관리되는 의료 영상 자료들은 요청에 따라 저장, 검색 및 전송을 수행하여 신속한 의료 서비스를 가능하게 한다. 그러나 만약에 관리자의 실수로 의료 영상 데이터가 바뀐다면 이는 사용자로 하여금 불편함과 낮은 신뢰성을 야기한다. 그리하여 본 논문에서는 서포트 벡터 머신 기반의 HOG(Histogram of Oriented Gradients) 특징 벡터를 이용하여 X-ray와 MRI(Magnetic Resonance Imaging) 사진을 분류하고 의료 영상 분류의 가능성을 제시하는 것을 목표로 한다.

  • PDF

Classification of Education Video by Subtitle Analysis (자막 분석을 통한 교육 영상의 카테고리 분류 방안)

  • Lee, Ji-Hoon;Lee, Hyeon Sup;Kim, Jin-Deog
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2021.05a
    • /
    • pp.88-90
    • /
    • 2021
  • This paper introduces a method for extracting subtitles from lecture videos through a Korean morpheme analyzer and classifying video categories according to the extracted morpheme information. In some cases incorrect information is entered due to human error and reflected in the characteristics of the items, affecting the accuracy of the recommendation system. To prevent this, we generate a keyword table for each category using morpheme information extracted from pre-classified videos, and compare the similarity of morpheme in each category keyword table to classify categories of Lecture videos using the most similar keyword table. These human intervention reduction systems directly classify videos and aim to increase the accuracy of the system.

  • PDF

Design for Reliability of Air-Launching Rocket, MirinaeII Using FMEA(Failure Modes and Effects Analysis) (FMEA를 통한 공중발사 로켓, 미리내II의 신뢰성 설계)

  • Kim, Jin-Ho;Bae, Bo-Young;Lee, Jae-Woo;Byun, Yung-Hwan;Kim, Kyung-Mee
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.36 no.12
    • /
    • pp.1193-1200
    • /
    • 2008
  • The procedure of design for reliability which consists of reliability analysis and Failure Modes and Effects Analysis(FMEA) is established and reliability assesment is performed for the nano-satellite air-launching rocket, Mirinae II. By means of using the reliability analysis result, the feasibility to insert the Mirinae II to the target orbit for given mission time under operating environment is assessed. During the reliability analysis process, the system is categorized by Work Breakdown Structure(WBS), and reliability structure is defined by both Reliability Block Diagram(RBD) and schematics of the system. FMEA is used to determine the risk priority number of components and parts. The target reliability is satisfied by changing the design of components and parts with high-risk, hence the design for reliability to put the satellite in to the target orbit safely has been performed.

Lessons Learned from Eco-town Cases for Sustainable Development (지속가능한 발전을 위한 국제 에코타운개발 사례분석)

  • Chang, Hoon
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.33 no.3
    • /
    • pp.1253-1260
    • /
    • 2013
  • Eco-town development projects have often prevailed throughout the World to initiate the new form of sustainable development plans. As a future development type, the eco-town project shares underlying notions with sustainable development, which has been recently revised into a wider definition; (i) energy efficiency, (ii) climate adaptation, and (iii) socio-economic development. There are four types of eco-town projects based on its characteristics and aims depending on project sites, regions, or countries. This paper tried to demonstrate the types of eco-town projects and summarizes its strategy plans from each type. Many eco-town cases can be placed in one of types, however there cannot be strictly discrete classification by its complicated and composite characteristics of them. In conclusion, the analyzed types can be a useful strategy plan for pursuing further eco-town projects in domestic as well as in international regions.

A Study on the Impact of CIO Leadership Versatility on the IS Performance (CIO의 리더십 균형성이 IS 성과에 미치는 영향)

  • Park Jong-Soon;Park Jeong-Sook;Kim Jae-Hwan
    • Journal of Korea Society of Industrial Information Systems
    • /
    • v.10 no.2
    • /
    • pp.48-58
    • /
    • 2005
  • This paper studied the impact of CIO leadership on the IS performance. The survey was developed to measure the relationship between CIO leadership style and the IS performance. The study shows that the differences in CIO leadership style along the two dimensions of goals and modes do not cause a statistically meaningful difference in business efficiency, one of the IS performance. Contrary to the existing studies that suggest a balanced leadership is effective, this study illustrates that strategic leadership and enabling leadership are more effective in the aspects of targets and manners respectively. This study does contribute to the introduction and utilization of CIO: unlike existing studies on leadership, it proposes a new approach to classifying leadership style based on the styles exhibited by CIO's flexibly from one situation to another. It will provide companies considering appointing CIO's or already using CIO's with insights into effective CIO role. It is important to provide CIOs with position and authority to exhibit their leadership flexibly.

  • PDF

A Study on the Evaluation and Improvement of Water Quality Management in Miho Stream (미호천 수질관리 평가 및 개선방안 연구)

  • Song, Yang Ho;Park, Yoon Kyung;Jeong, Jae Hoon;Lee, Yun Hee
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2022.05a
    • /
    • pp.503-503
    • /
    • 2022
  • 미호천은 금강의 중권역에 위치하며 도심을 관통하는 전형적인 도심형 하천으로 금강대권역 물환경관리계획 내에서 다루는 지류하천 중 논산천과 함께 물환경 목표기준 미달성 하천으로 분류되어 중점관리 중권역으로 분류되어 있다. 금강 본류의 수질 악화에 큰 영향을 주는 하천으로 수질개선을 위해서는 목표기준 미달성 원인 파악 및 정책적 개선방안 모색을 통해 실질적인 정부와 지자체의 계획에 반영할 필요성이 있다. 그간 미호천 수질개선과 관련한 많은 연구가 진행되었으나, 연구의 대부분은 특정 오염원에 집중된 단기적인 조사에 편중되어 있다. 수질개선을 위한 정책분석 및 대응방안을 제시하기 위해서는 미호천 지류가 본류에 미치는 영향 등의 전반적인 하천 특성과 장기적인 이·화학적 수질 영향을 검토를 통한 정책적 지원 전략 수립이 필요한 상황이다. 본 연구에서는 미호천 수질개선을 목표로 수행되었던 환경기초조사업과 지자체별 정책사업들을 조사하고 수질개선 방안을 고찰함으로써 중권역의 수질개선을 위한 지역맞춤형 정책제언 및향후 지역 간 연계협력사업의 추진을 위한 참고자료를 제공하고자 하였다. 참고자료에는 수질현황조사 결과와 환경기초조사사업 및 미호천 관련 8개 지자체별 정책사업을 조사하였으며, 중권역 물환경관리계획에 수립된 예산 대비 현재까지 집행된 비율을 통해 이행도를 검토하였다. 마지막으로 미호천 수질관리 개선을 위한 축산오염원, 토지 비점오염원, 생활계 오염원, 산업계 오염원, 보 관리, 주민참여에 대한 부문별 개선방안을 제안하였다.

  • PDF

Face Detection Based on Incremental Learning from Very Large Size Training Data (대용량 훈련 데이타의 점진적 학습에 기반한 얼굴 검출 방법)

  • 박지영;이준호
    • Journal of KIISE:Software and Applications
    • /
    • v.31 no.7
    • /
    • pp.949-958
    • /
    • 2004
  • race detection using a boosting based algorithm requires a very large size of face and nonface data. In addition, the fact that there always occurs a need for adding additional training data for better detection rates demands an efficient incremental teaming algorithm. In the design of incremental teaming based classifiers, the final classifier should represent the characteristics of the entire training dataset. Conventional methods have a critical problem in combining intermediate classifiers that weight updates depend solely on the performance of individual dataset. In this paper, for the purpose of application to face detection, we present a new method to combine an intermediate classifier with previously acquired ones in an optimal manner. Our algorithm creates a validation set by incrementally adding sampled instances from each dataset to represent the entire training data. The weight of each classifier is determined based on its performance on the validation set. This approach guarantees that the resulting final classifier is teamed by the entire training dataset. Experimental results show that the classifier trained by the proposed algorithm performs better than by AdaBoost which operates in batch mode, as well as by ${Learn}^{++}$.

Performance Evaluation of One Class Classification to detect anomalies of NIDS (NIDS의 비정상 행위 탐지를 위한 단일 클래스 분류성능 평가)

  • Seo, Jae-Hyun
    • Journal of the Korea Convergence Society
    • /
    • v.9 no.11
    • /
    • pp.15-21
    • /
    • 2018
  • In this study, we try to detect anomalies on the network intrusion detection system by learning only one class. We use KDD CUP 1999 dataset, an intrusion detection dataset, which is used to evaluate classification performance. One class classification is one of unsupervised learning methods that classifies attack class by learning only normal class. When using unsupervised learning, it difficult to achieve relatively high classification efficiency because it does not use negative instances for learning. However, unsupervised learning has the advantage for classifying unlabeled data. In this study, we use one class classifiers based on support vector machines and density estimation to detect new unknown attacks. The test using the classifier based on density estimation has shown relatively better performance and has a detection rate of about 96% while maintaining a low FPR for the new attacks.

Study on Curriculum Model Construction of Media Education (미디어 교육 교육과정 모델 구성에 관한 연구)

  • Kim, Yang-Eun
    • Korean journal of communication and information
    • /
    • v.37
    • /
    • pp.73-99
    • /
    • 2007
  • The study's purpose is to present model for constructing of media education's curriculum. The concept and goal of media education have changed by various media education's paradigm historically. Also this changed the content and the goal of the media education. Curriculum model of media education is various by the nation. AS so the study analyzed the media education's curriculum model to be applying in USA, United British, German, Australia, Canada. Through this, the model for constructing of media education' curriculum is presented. The curriculum model helps to be executed systematically media education in Korea. According to the result, The model is composed of the goal and content. The goal of media education is composed of media knowledge, media appreciation, media analyze, media production. The content of media education is composed of Media, Text, User.

  • PDF

Abatement Potentials of Power Generation Technologies for the Achievement of National INDC (자발적 온실가스 감축목표 달성을 위한 발전기술별 온실가스저감 잠재량 평가)

  • Baek, Minho;Roh, Minyoung;Yurnaidi, Zulfikar;Kim, Suduk
    • Environmental and Resource Economics Review
    • /
    • v.25 no.4
    • /
    • pp.565-590
    • /
    • 2016
  • In accordance with the global efforts to reduce greenhouse gas emissions, Korean government submitted its INDC (Intended Nationally Determined Contribution) of 25.7% for domestic reduction and the total of 37% reduction by 2030 including the purchase of emission reduction permit from abroad. In this study, 25.7% reduction target is being evaluated to see its impact on domestic energy system using the integrated assessment model, GCAM (Global Change Assessment Model). Results show that electricity generation from fossil fuel technologies using coal and gas decrease by 28.0%, 13.5% while that of biomass, wind power, solar energy increase by 47.6%, 22.0% and 45.4%, respectively. It is worth noting that so called new technology such as USC (ultra supercritical power generation) does not contribute to achieving the emission reduction target and careful and quantitative analysis is required for such categorization in the future.