• 제목/요약/키워드: GoogleNet

검색결과 52건 처리시간 0.026초

베이지안 네트워크와 페트리넷을 이용한 모바일 상황정보로부터의 블로그 자동 생성 (Automatic Weblog Generation from Mobile Context using Bayesian Network and Petri Net)

  • 이영설;조성배
    • 한국정보과학회논문지:컴퓨팅의 실제 및 레터
    • /
    • 제16권4호
    • /
    • pp.467-471
    • /
    • 2010
  • 블로그는 가장 널리 퍼지고 있는 개인화 웹 서비스로서 전세계의 많은 사람들이 이용하고 있다. 이런 블로그의 내용은 대부분 일상 생활에서 겪은 경험이나 감정을 표현하고 있는 것들이다. 따라서 모바일 기기로 수집된 개인의 생활에 대한 정보를 모아 자동으로 블로그를 만든다면 그것을 바탕으로 보다 쉽게 자신만의 블로그를 만들수 있을 것이다. 이미 모바일 상황정보를 바탕으로 블로그를 자동으로 만들기 위한 몇몇 연구가 이루어지고 있다. 본 논문에서는 모바일 기기에서 수집된 정보를 바탕으로 사용자의 상태를 추론한다. 그리고 추론된 결과를 바탕으로 페트리 넷 스크립트를 이용하여 스토리 형태로 텍스트를 생성한 후, 최종적으로 사진과 지도상의 이동 패턴을 합쳐 사용자의 생활을 보여주는 블로그를 구성한다.

게임이론에 의한 양면시장에서의 망중립성 분석 (Analysis of Network Neutrality in Two-sided Markets Using Game Theory)

  • 오형술;이재하
    • 산업경영시스템학회지
    • /
    • 제41권3호
    • /
    • pp.162-169
    • /
    • 2018
  • Net neutrality, which has not been a problem, has recently become a problem for ISPs (Internet Service Providers), and their complaints have been paid by domestic platform companies, but overseas global IT companies such as Google and YouTube, generate huge revenues from domestic markets. In this situation, domestic IT companies claim that it is natural to impose more expensive charges or restrict speed on users who generate huge traffic. On the other side, however, the telecommunication network has become an essential public good that is essential to our everyday life, and because it has been given a monopoly position by a private company to efficiently respond to the explosive demand for telecommunication services, It is necessary to provide equal and universal service and fulfill public duty. In this paper, we deal with the network neutrality problem, focusing on the price elasticity between the CP (Contents Provider) and the ISP, rather than the user who is one side of the two-sided market for the already saturated satellites communication market. We present a game model that determines the optimal price for each platform by Nash equilibrium and analyze how the net neutrality affects CP according to the change of exogenous variables through the proposed game model.

Analysis of Weights and Feature Patterns in Popular 2D Deep Neural Networks Models for MRI Image Classification

  • Khagi, Bijen;Kwon, Goo-Rak
    • Journal of Multimedia Information System
    • /
    • 제9권3호
    • /
    • pp.177-182
    • /
    • 2022
  • A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

Landsat-8 OLI 영상정보의 대기 및 지표반사도 산출을 위한 OTB Extension 구현과 RadCalNet RVUS 자료를 이용한 성과검증 (An Implementation of OTB Extension to Produce TOA and TOC Reflectance of LANDSAT-8 OLI Images and Its Product Verification Using RadCalNet RVUS Data)

  • 김광섭;이기원
    • 대한원격탐사학회지
    • /
    • 제37권3호
    • /
    • pp.449-461
    • /
    • 2021
  • 광학 위성정보에 대한 분석대기자료(ARD)는 각 센서 별 분광특성과 촬영각 등을 적용하는 전처리 작업에 의한 성과물이다. 대기보정 처리과정은 통하여 얻을 수 있는 대기반사도와 지표반사도는 기본적이면서 복잡한 알고리즘을 요구한다. 대부분 위성 정보처리 소프트웨어에서는 Landsat 위성 대기보정 처리 알고리즘 및 기능을 제공하고 있다. 또한 사용자는 클라우드 환경에서 Google Earth Engine(GEE)을 통하여 USGS-ARD와 같은 Landsat 반사도 성과에 직접 접근할 수 있다. 이번 연구에서는 고해상도 위성정보 처리에 활용되고 있는 Orfeo ToolBox(OTB) 오픈 소스 소프트웨어의 대기보정 기능을 확장 구현하였다. 현재 OTB 도구는 어떠한 Landsat 센서도 지원하지 않기 때문에, 이 확장 도구는 최초로 개발된 사례이다. 이 도구를 이용하여 RadCalNet 사이트의 Railroad Valley, United States(RVUS) 반사율 자료 값을 이용한 결과 검증을 위하여 같은 지역의 Landsat-8 OLI 영상의 절대 대기보정에 의한 반사도 성과를 산출하였다. 산출된 결과는 RVUS 자료를 기준으로 반사도 값과의 차이가 5% 미만으로 나타났다. 한편 이 반사도 성과는 USGS-ARD 반사도 값뿐만 아니라 QGIS Semi-automatic Classification Plugin과 SAGA GIS와 같은 다른 오픈 소스 도구에서 산출된 성과를 이용한 비교 분석을 수행하였다. OTB 확장도구로부터 산출한 반사도 성과는 RadCalNet RVUS의 자료와 높은 일치도를 나타내는 USGS-ARD의 값과 가장 부합되는 것으로 나타났다. 이 연구에서 OTB 대기보정 처리의 다양한 위성센서 적용 가능성을 입증한 결과로 이 모듈을 다른 센서정보로 확장하여 구현하는 경우에도 정확도가 높은 반사도 산출이 가능한 것을 확인할 수 있었다. 이와 같은 연구 방법은 향후 차세대중형위성을 포함하는 다양한 광학위성에 대한 반사도 성과 산출 도구개발에도 활용할 수 있다.

A Study of Machine Learning based Face Recognition for User Authentication

  • Hong, Chung-Pyo
    • 반도체디스플레이기술학회지
    • /
    • 제19권2호
    • /
    • pp.96-99
    • /
    • 2020
  • According to brilliant development of smart devices, many related services are being devised. And, almost every service is designed to provide user-centric services based on personal information. In this situation, to prevent unintentional leakage of personal information is essential. Conventionally, ID and Password system is used for the user authentication. This is a convenient method, but it has a vulnerability that can cause problems due to information leakage. To overcome these problem, many methods related to face recognition is being researched. Through this paper, we investigated the trend of user authentication through biometrics and a representative model for face recognition techniques. One is DeepFace of FaceBook and another is FaceNet of Google. Each model is based on the concept of Deep Learning and Distance Metric Learning, respectively. And also, they are based on Convolutional Neural Network (CNN) model. In the future, further research is needed on the equipment configuration requirements for practical applications and ways to provide actual personalized services.

MobileMapGen : 모바일 맵 응용 생성기 (MobileMapGen: Mobile Map Application Generator)

  • 민경윤;박원진;음두헌
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2012년도 추계학술발표대회
    • /
    • pp.1464-1467
    • /
    • 2012
  • 스마트 폰 사용자 수가 2000만명 이상이 됨에 따라 모바일 맵 서비스에 대한 수요가 급증하고 있다. 한편, 모바일 기반의 맵 응용의 개발을 위해선 WINDEV Mobile 17과 같은 유료 개발 환경이 있지만 자동화 지원 경도가 미약하여 맵 응용의 생산성이 떨어지고 유지 보수 기간도 많이 소요된다. 우리가 설계하고 구현한 MobileMapGen은 GoogleMaps API를 사용하며 서버 측을 위해 CMS(Content Management System)인 Drupal 환경에 사용 가능 한 모듈들을 생성하고 클라이언트 측엔 iOS 앱을 생성해 맵 응용에 대한 생산성을 향상시켜 준다. 맵 컨텐츠와 그와 연관된 컨텐츠들을 함께 제공하는 모바일의 맵 응용 생성기인 MobileMapGen과 달리 WINDEV Mobile 17, MobilForms, 그리고 VisualStudio.NET는 맵 인터페이스를 지원하지 않거나 위치 정보 형태만을 표시한다. 그렇기 때문에 사용자가 원하는 지형/지물 컨텐츠 타입을 생성하거나 맵 상에 표시하고 관심의 대상인 지형/지물과 연관된 컨텐츠들을 검색할 수 없다.

Big Data Analysis on the Perception of Home Training According to the Implementation of COVID-19 Social Distancing

  • Hyun-Chang Keum;Kyung-Won Byun
    • International Journal of Internet, Broadcasting and Communication
    • /
    • 제15권3호
    • /
    • pp.211-218
    • /
    • 2023
  • Due to the implementation of COVID-19 distancing, interest and users in 'home training' are rapidly increasing. Therefore, the purpose of this study is to identify the perception of 'home training' through big data analysis on social media channels and provide basic data to related business sector. Social media channels collected big data from various news and social content provided on Naver and Google sites. Data for three years from March 22, 2020 were collected based on the time when COVID-19 distancing was implemented in Korea. The collected data included 4,000 Naver blogs, 2,673 news, 4,000 cafes, 3,989 knowledge IN, and 953 Google channel news. These data analyzed TF and TF-IDF through text mining, and through this, semantic network analysis was conducted on 70 keywords, big data analysis programs such as Textom and Ucinet were used for social big data analysis, and NetDraw was used for visualization. As a result of text mining analysis, 'home training' was found the most frequently in relation to TF with 4,045 times. The next order is 'exercise', 'Homt', 'house', 'apparatus', 'recommendation', and 'diet'. Regarding TF-IDF, the main keywords are 'exercise', 'apparatus', 'home', 'house', 'diet', 'recommendation', and 'mat'. Based on these results, 70 keywords with high frequency were extracted, and then semantic indicators and centrality analysis were conducted. Finally, through CONCOR analysis, it was clustered into 'purchase cluster', 'equipment cluster', 'diet cluster', and 'execute method cluster'. For the results of these four clusters, basic data on the 'home training' business sector were presented based on consumers' main perception of 'home training' and analysis of the meaning network.

A Study on the Meaning of The First Slam Dunk Based on Text Mining and Semantic Network Analysis

  • Kyung-Won Byun
    • International journal of advanced smart convergence
    • /
    • 제12권1호
    • /
    • pp.164-172
    • /
    • 2023
  • In this study, we identify the recognition of 'The First Slam Dunk', which is gaining popularity as a sports-based cartoon through big data analysis of social media channels, and provide basic data for the development and development of various contents in the sports industry. Social media channels collected detailed social big data from news provided on Naver and Google sites. Data were collected from January 1, 2023 to February 15, 2023, referring to the release date of 'The First Slam Dunk' in Korea. The collected data were 2,106 Naver news data, and 1,019 Google news data were collected. TF and TF-IDF were analyzed through text mining for these data. Through this, semantic network analysis was conducted for 60 keywords. Big data analysis programs such as Textom and UCINET were used for social big data analysis, and NetDraw was used for visualization. As a result of the study, the keyword with the high frequency in relation to the subject in consideration of TF and TF-IDF appeared 4,079 times as 'The First Slam Dunk' was the keyword with the high frequency among the frequent keywords. Next are 'Slam Dunk', 'Movie', 'Premiere', 'Animation', 'Audience', and 'Box-Office'. Based on these results, 60 high-frequency appearing keywords were extracted. After that, semantic metrics and centrality analysis were conducted. Finally, a total of 6 clusters(competing movie, cartoon, passion, premiere, attention, Box-Office) were formed through CONCOR analysis. Based on this analysis of the semantic network of 'The First Slam Dunk', basic data on the development plan of sports content were provided.

빅데이터를 활용한 "조리학원"의 의미연결망 분석에 관한 연구 (A Study on the Semantic Network Analysis of "Cooking Academy" through the Big Data)

  • 이승후;김학선
    • 한국조리학회지
    • /
    • 제24권3호
    • /
    • pp.167-176
    • /
    • 2018
  • In this study, Big Data was used to collect the information related to 'Cooking Academy' keywords. After collecting all the data, we calculated the frequency through the text mining and selected the main words for future data analysis. Data collection was conducted from Google Web and News during the period from January 1, 2013 to December 31, 2017. The selected 64 words were analyzed by using UCINET 6.0 program, and the analysis results were visualized with NetDraw in order to present the relationship of main words. As a result, it was found that the most important goal for the students from cooking school is to work as a cook, likewise to have practical classes. In addition, we obtained the result that SNS marketing system that the social sites, such as Facebook, Twitter, and Instagram are actively utilized as a marketing strategy of the institute. Therefore, the results can be helpful in searching for the method of utilizing big data and can bring brand-new ideas for the follow-up studies. In practical terms, it will be remarkable material about the future marketing directions and various programs that are improved by the detailed curriculums through semantic network of cooking school by using big data.

지식기반 의미 메타 검색엔진 (Knowledge-based Semantic Meta-Search Engine)

  • 이인근;손세호;권순학
    • 한국지능시스템학회논문지
    • /
    • 제14권6호
    • /
    • pp.737-744
    • /
    • 2004
  • 웹으로부터 사용자가 원하는 정보에 잘 부응하는 정보를 추출하는 것은 검색엔진이 갖추어야 할 기본적 요소라 할 수 있다. 그러나 질의어와의 패턴 매칭 방식에 의존하는 기존의 대부분의 검색엔진은 질의어가 갖는 애매성으로 인하여 사용자의 요구에 부합하는 검색결과를 제공하기가 쉽지 않다는 단점을 지니고 있다. 이를 극복하기 위하여 본 논문에서는 다음과 같은 5가지 과정, 즉, (i) 질의어 형성, (ii) 질의어 확장, (iii) 검색, (iv) 순위 재생성 및 (v) 지식베이스로 구성되는 지식기반 의미 메타 검색엔진의 기본 구조를 제안한다 영어로 구현된 웹 문서에 대한 모의실험을 통하여 본 논문에서 제안된 지식기반 의미 메타 검색엔진이 기존의 검색엔진(구글)을 사용하여 얻은 결과보다 좋은 결과를 보임을 확인할 수 있었다.