• Title/Summary/Keyword: learning distribution

Search Result 981, Processing Time 0.026 seconds

Convolutional neural network based amphibian sound classification using covariance and modulogram (공분산과 모듈로그램을 이용한 콘볼루션 신경망 기반 양서류 울음소리 구별)

  • Ko, Kyungdeuk;Park, Sangwook;Ko, Hanseok
    • The Journal of the Acoustical Society of Korea
    • /
    • v.37 no.1
    • /
    • pp.60-65
    • /
    • 2018
  • In this paper, a covariance matrix and modulogram are proposed for realizing amphibian sound classification using CNN (Convolutional Neural Network). First of all, a database is established by collecting amphibians sounds including endangered species in natural environment. In order to apply the database to CNN, it is necessary to standardize acoustic signals with different lengths. To standardize the acoustic signals, covariance matrix that gives distribution information and modulogram that contains the information about change over time are extracted and used as input to CNN. The experiment is conducted by varying the number of a convolutional layer and a fully-connected layer. For performance assessment, several conventional methods are considered representing various feature extraction and classification approaches. From the results, it is confirmed that convolutional layer has a greater impact on performance than the fully-connected layer. Also, the performance based on CNN shows attaining the highest recognition rate with 99.07 % among the considered methods.

The Power Line Deflection Monitoring System using Panoramic Video Stitching and Deep Learning (딥 러닝과 파노라마 영상 스티칭 기법을 이용한 송전선 늘어짐 모니터링 시스템)

  • Park, Eun-Soo;Kim, Seunghwan;Lee, Sangsoon;Ryu, Eun-Seok
    • Journal of Broadcast Engineering
    • /
    • v.25 no.1
    • /
    • pp.13-24
    • /
    • 2020
  • There are about nine million power line poles and 1.3 million kilometers of the power line for electric power distribution in Korea. Maintenance of such a large number of electric power facilities requires a lot of manpower and time. Recently, various fault diagnosis techniques using artificial intelligence have been studied. Therefore, in this paper, proposes a power line deflection detect system using artificial intelligence and computer vision technology in images taken by vision system. The proposed system proceeds as follows. (i) Detection of transmission tower using object detection system (ii) Histogram equalization technique to solve the degradation in image quality problem of video data (iii) In general, since the distance between two transmission towers is long, a panoramic video stitching process is performed to grasp the entire power line (iv) Detecting deflection using computer vision technology after applying power line detection algorithm This paper explain and experiment about each process.

A Study on Asset Valuation Method in Educational Facilities Delivered by BTL (BTL 사업 학교시설의 자산 가치평가 기법 연구)

  • Lee, Young-Joo;Soh, Ji-Yune;Lee, Jun-Bok;Han, Choong-Hee;Chae, Myung-Jin
    • Korean Journal of Construction Engineering and Management
    • /
    • v.12 no.4
    • /
    • pp.40-49
    • /
    • 2011
  • A number of BTL projects for educational facilities have been augmented because of the increase of newtown development and deflationary policy of class size for learning efficiency. As the operation and maintenance costs rapidly increase, the budget for operation and maintenance is expected to be short. Therefore the asset management maximizing asset value is required to clarify the budget plan and distribution and provide a qualitatively high service. The main objective of this research is to establish asset valuation process in educational facilities delivered by BTL project. In order to meet the research objective, the asset valuation process is established by literature reviews, expert advice, and lessons learned from the developed countries. The developed process includes depreciation by internal accounting law, the core element of valuation, and asset valuation process. The results of the research will be help to offer the qualitatively high service and explain the standard of budget plan. It will assist commencing the asset management system.

A Natural Scene Statistics Based Publication Classification Algorithm Using Support Vector Machine (서포트 벡터 머신을 이용한 자연 연상 통계 기반 저작물 식별 알고리즘)

  • Song, Hyewon;Kim, Doyoung;Lee, Sanghoon
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.42 no.5
    • /
    • pp.959-966
    • /
    • 2017
  • Currently, the market of digital contents such as e-books, cartoons and webtoons is growing up, but the copyrights infringement are serious issue due to their distribution through illegal ways. However, the technologies for copyright protection are not developed enough. Therefore, in this paper, we propose the NSS-based publication classification method for copyright protection. Using histogram calculated by NSS, we propose classification method for digital contents using SVM. The proposed algorithm will be useful for copyright protection because it lets us distinguish illegal distributed digital contents more easily.

The Comparative Study about General Education Curriculum of Engineering College in the United states (미국의 공과대학 교양교육과정에 대한 비교 연구)

  • Kim, Myoung-Lang;Park, Hye-Young;Chang, Sun-Young
    • Journal of Engineering Education Research
    • /
    • v.10 no.1
    • /
    • pp.5-19
    • /
    • 2007
  • A general education course is different from a major course in an engineering college. Therefore, they influence a learning outcomes according to their forms and contents. In particular, an engineering college in korea is open to argument against a general education course. Because a general education course has to observe the criterion of ABEEK. Consequently, the purpose of this study is to compare general education courses of engineering colleges in USA. For it, this study analyzes the completion method and academic area of a general education course. In result, this study suggests the property and implication of a general education course in an engineering college.

Data BILuring Method for Solving Sparseness Problem in Collaborative Filtering (협동적 여과에서의 희소성 문제 해결을 위한 데이타 블러링 기법)

  • Kim, Hyung-Il;Kim, Jun-Tae
    • Journal of KIISE:Software and Applications
    • /
    • v.32 no.6
    • /
    • pp.542-553
    • /
    • 2005
  • Recommendation systems analyze user preferences and recommend items to a user by predicting the user's preference for those items. Among various kinds of recommendation methods, collaborative filtering(CF) has been widely used and successfully applied to practical applications. However, collaborative filtering has two inherent problems: data sparseness and the cold-start problems. If there are few known preferences for a user, it is difficult to find many similar users, and therefore the performance of recommendation is degraded. This problem is more serious when a new user is first using the system. In this paper we propose a method of integrating additional feature information of users and items into CF to overcome the difficulties caused by sparseness and improve the accuracy of recommendation. In our method, we first fill in unknown preference values by using the probability distribution of feature values, then generate the top-N recommendations by applying collaborative filtering on the modified data. We call this method of filling unknown preference values as data blurring. Several experimental results that show the effectiveness of the proposed method are also presented.

A study on development methodology of web-based business simulation game (웹 기반의 경영시뮬레이션 게임 개발 방법론)

  • Kim, Hyung-Sub
    • Journal of Digital Convergence
    • /
    • v.15 no.1
    • /
    • pp.53-60
    • /
    • 2017
  • The time of digital era and the increasing complexity of the management environment have raised uncertainties about the future. Companies have made steady investments in education as a way to prepare for the future. In this study, design and development methodology based on web - based management simulation games (manufacturing, distribution, finance) which author participated in development was presented. The development methodology presented in this study can be roughly divided into business simulation game design methodology and business simulation game development methodology. Since there is no existing research methodology for development methodology, development model is presented based on empirical based on development case. In this paper, we propose an overall content development methodology and propose a detailed methodology of the content.

An Educational Simulator for Operational Strategies of the Block Train Services (블록 트레인 서비스 운영 전략 학습 시뮬레이터 개발)

  • Jung, Jae Un;Kim, Hyun Soo
    • Journal of Digital Convergence
    • /
    • v.10 no.11
    • /
    • pp.197-202
    • /
    • 2012
  • Block Train Services(BTS) are actively studied in many countries for higher productivity and eco-friendly systems of inland freight distribution. However it is difficult for an ordinary student or researcher to approach for understanding and studying BTS because rail transport is operated monopolistically by Korea government and most freight information in each company belongs to its business secret due to the industrial characteristics. For such reasons, the study aimed to develop a BTS simulation model that it supports understanding and strategic decision required for BT operation. To build the result, expert depth-interviews were conducted with analysis of relative references through the domestic representative BT operating company K. The simulator refers to the Busan NewPort-Uiwang section and functionally, it supports scenario generation and analysis on BT operation. It makes a contribution to study a new type's technological application for learning and strategic analysis of BTS.

Analysis on a Medical School Students' Academic Achievement by University Major Field (의학전문대학원생의 대학 전공 계열에 따른 학업성취도 분석)

  • Yoo, Hyo Hyun
    • The Journal of the Korea Contents Association
    • /
    • v.14 no.9
    • /
    • pp.634-638
    • /
    • 2014
  • The purpose of the study is to analyse students' academic achievement by their university major field and changes of grade. The subject was entering students of C medical graduate school in 2008. We divided entering students' major fields into two fields that are natural science and non-natural science filed. We analysed academic achievements of entering students by grades, curriculum from 2008 to 2011. And We analysed to find out whether there are differences in academic achievements by grades, curriculum of each major fields. There were no significant statistical differences in academic achievements by grade, curriculum of the two different university major fields. Futhermore, as a results of analysis on level(high, medium, low) distribution and differences of academic achievements by grade, curriculum of the two different university major fields, there were no statistically meaningful results. There is the need to keep entrance selection systems that open the possibility of selecting the students with other academic background. And there is the need to change general awareness assuming that there are differences in academic achievements by university major fields. We need to guide students with belief of their learning possibility.

Collaborative Dispositions of Participatory Arts in Contemporary Practices -Based on Nicolas Bourriaud's Notion of Postproduction- (동시대 예술 형식의 상호성과 공유 가능성 -니콜라 부리오의 포스트프로덕션 개념을 중심으로-)

  • Baik, Youngju
    • The Journal of the Korea Contents Association
    • /
    • v.18 no.6
    • /
    • pp.88-101
    • /
    • 2018
  • The collective narratives on global crisis such as the displaced, uneven distribution of resources, invasion of human rights is more than a recurring theme or polemics in the fields of contemporary arts. In the latest projects from Olafur Eliasson, Rirkrit Tiravanija and Ai WeiWei, art works are presented as performative 'platforms' for tackling these undiscriminating reality of human conditions. Here, 'the users' as driving forces of possible change, are postulated as prospective actors/players who lead and collaborate to defy the status-quo. Crossing over the on/off lines, the everyday-activities of exchanging, sharing and networking are strategically deployed and its meaning reconfigured within the context of post/production discourse. This historical, yet unsettling juncture between art and life, dystopian reality and utopian idealism has its formal-conceptual links to Russian Constructivism, Brechtian Learning-Play and Joseph Beuys' Social Sculpture. Based on Nicolas Bourriaud's notion of Postproduction, this paper aims to provide a diachronic analysis on collaborative dispositions of participatory arts practices.