• Title/Summary/Keyword: Media filtering

Search Result 288, Processing Time 0.028 seconds

A Study on Contents Preference Prediction Method using Tags based on Content-based Filtering (Tag를 이용한 CBF방식의 컨텐츠 선호도 예측 방법)

  • Um, Tae-Kwang;Choi, Sung-Hwan;Lee, Jae-Hwang
    • Proceedings of the IEEK Conference
    • /
    • 2008.06a
    • /
    • pp.613-614
    • /
    • 2008
  • A content recommendation according to users preferences comes up in the Internet application due to contents overwhelming. This paper newly proposes a method to predict contents preference using tags in conjunction with Content-Based Filtering. By implementing this method, this paper cleans up the contents sparsity problem in Content-Based Filtering, and shows the outstanding improvements.

  • PDF

Identification of operating parameters in auto-discharging filter system for treatment of urban storm water (자동방류가 가능한 여과형 비점오염처리장치의 운전인자 도출)

  • Kim, Sun-Hee;Gwon, Eun-Mi;Pak, Sung-Soon;Joh, Seong-Ju;Lim, Chea-Hoan;Kang, Seon-Hong
    • Journal of Korean Society of Water and Wastewater
    • /
    • v.24 no.4
    • /
    • pp.377-386
    • /
    • 2010
  • To identify operating parameters of the up-flow filtering system, which is available to discharge filtering residue after the rain, developed for treatment of urban storm runoff, lab scale test was carried out. Removal efficiency of SS was 68.7%, 62.2%, and 58.6% at the area roading rate of 2.46m/h, 4.68m/h, and 10m/h, respectively, filtering device is desirable to operate at the lower than 4.68m/h of area roading rate to get higher level of 60% SS removal efficiency. The removal efficiency of SS was 57.1% ~ 68.7% at the raw water SS of 100mg/L ~ 600mg/L, and the SS in treated water was maintained at the constant level through the elapsed time. It is indicate that filtering device can guarantee a certain level of effluent water quality at various raw water quality. The removal efficiency of SS to the depth of filter media was 68.3%, 78.6% at the filter depth of 10 cm, 20cm respectively. The final treated water quality was showed 30.2mg/L of CODMn, 1.60mg/L of TN and 0.25mg/L of TP. The average removal efficiencies by filtering device developed in this research were recorded slightly lower levels than other research. The main reason of these results were the first, the filter depth of the media used in this test was shallow, the second, the kind of filter media in discharge port of residue. More research to kind of filter media, filter packing rate, select of media for residue discharge port should be go on to produce optimum operating condition. The result of this study would be valuable for the application of filtration device to control of urban storm water.

Implementation and Evaluation of Harmful-Media Filtering Techniques using Multimodal-Information Extraction

  • Yeon-Ji, Lee;Ye-Sol, Oh;Na-Eun, Park;Il-Gu, Lee
    • Journal of information and communication convergence engineering
    • /
    • v.21 no.1
    • /
    • pp.75-81
    • /
    • 2023
  • Video platforms, including YouTube, have a structure in which the number of video views is directly related to the publisher's profits. Therefore, video publishers induce viewers by using provocative titles and thumbnails to garner more views. The conventional technique used to limit such harmful videos has low detection accuracy and relies on follow-up measures based on user reports. To address these problems, this study proposes a technique to improve the accuracy of filtering harmful media using thumbnails, titles, and audio data from videos. This study analyzed these three pieces of multimodal information; if the number of harmful determinations was greater than the set threshold, the video was deemed to be harmful, and its upload was restricted. The experimental results showed that the proposed multimodal information extraction technique used for harmfulvideo filtering achieved a 9% better performance than YouTube's Restricted Mode with regard to detection accuracy and a 41% better performance than the YouTube automation system.

A Study on Recommendation System Using Collaborative Filtering (Collaborative Filtering기반 추천 시스템에 관한 연구)

  • Lee, Jae-Hwang;Kim, Yong-Ku;Jang, Jeong-Rok;Um, Tae-Kwang
    • Proceedings of the KIEE Conference
    • /
    • 2008.10b
    • /
    • pp.231-232
    • /
    • 2008
  • 본 논문은 협업 필터링(Collaborative Filtering)기반의 추천시스템에 필요한 알고리즘을 제안한다. 제안한 알고리즘은 사용자의 선호도를 Implicit Feedback을 통해 예측하는 Implicit Rating과 사용자 선호도와 컨텐츠의 정보를 바탕으로 사용자의 프로파일을 형성하는 Tag 기반의 사용자 프로파일과 P2P망 내에서 자신과 유사한 사용자 그룹을 형성하는 알고리즘으로 구성되어 있다. 제안한 알고리즘을 적용하여 Web Text 기반의 CF기반의 개인화 추천시스템을 구현하였으며 구현된 프로그램을 실제 사용자에게 배포하여 Feasibility를 검증하였다.

  • PDF

Image Sequence Stabilization Scheme Using FIR Filtering

  • Kim, Pyung-Soo
    • International Journal of Control, Automation, and Systems
    • /
    • v.1 no.4
    • /
    • pp.515-519
    • /
    • 2003
  • This paper proposes a new image sequence stabilization (ISS) scheme based on filtering of absolute frame positions. The proposed ISS scheme removes undesired motion effects in real-time, while preserving desired gross camera displacements. The well-known finite impulse response (FIR) filter is adopted for filtering. The proposed ISS scheme provides a filtered position and velocity with fine inherent properties. It is demonstrated that the filtered position is not affected by the constant velocity. It is also shown that the filtered velocity is separated from the position. Via numerical simulations, the performance of the proposed scheme is shown to be superior to the existing Kalman filtering scheme.

Are Particulate Filtering Respirators Available in Korea Efficient for Nanoparticles? (<종설>국내 시판 방진마스크는 나노입자에 적합한가?)

  • Han, Don-Hee
    • Journal of Korean Society of Occupational and Environmental Hygiene
    • /
    • v.21 no.1
    • /
    • pp.62-71
    • /
    • 2011
  • There is widespread concern that particulate filtering respirators (PFRs) available in Korea will be efficient for nanoparticles. The purpose of this review study was to analyse research literature and recommend PFRs suitable for protection against nanoparticles. In all studies, respirators containing electret filter media (N95, P100 and FFP2, FFP3) consistently have their MPPS below 100 nm and particle penetration levels at the MPPS can vary widely, but they comply with NIOSH or EN certification criterion. Electret filtering facepieces respirators (FFRs) were found to shift in the Most-Penetrating Particle Size(MPPS) from 30-60 to 200-300 nm range after the electric charges were removed, and FFRs were above their minimum penetrations of criterion. Korean special class and first class FFRs (the same as FFP3 and FFP2, respectively) would be effcient for nanoparticles unless FFRs are removed electric charges. It is difficult to evaluate if mechanical PFRs is efficient for nanoparticles due to the lack of related materials.

Biofiltration of Ammonia Emission during Manure Composting (퇴비화 과정중 발생한 암모니아가스의 생물학적 탈취)

  • Park, Keum-Joo;Hong, Ji-Hyung;Cho, Ju-Sik;Choi, Won-Choon
    • Proceedings of the Korean Society of Agricultural Engineers Conference
    • /
    • 2001.10a
    • /
    • pp.431-434
    • /
    • 2001
  • This study was carried oui to investigate tile filtering performance of using fresh compost as a biofilter. Three biofilter vessels were made using fresh compost as a biofilter media. A mixtures of dairy manure, soy sludge, rice hulls and sawdust were composted in a pilot scale reactor of 605L to generate tile ammonia emission. The ammonia emission from the compost reactor was passed through three biofilters and collected in the boric acid trap to measure the ammonia emission. Filtering performance was influenced by the depth of biofilter media. Efficient filtering effect was acquired for the depth above 40 cm.

  • PDF

Personalized Bookmark Search Word Recommendation System based on Tag Keyword using Collaborative Filtering (협업 필터링을 활용한 태그 키워드 기반 개인화 북마크 검색 추천 시스템)

  • Byun, Yeongho;Hong, Kwangjin;Jung, Keechul
    • Journal of Korea Multimedia Society
    • /
    • v.19 no.11
    • /
    • pp.1878-1890
    • /
    • 2016
  • Web 2.0 has features produced the content through the user of the participation and share. The content production activities have became active since social network service appear. The social bookmark, one of social network service, is service that lets users to store useful content and share bookmarked contents between personal users. Unlike Internet search engines such as Google and Naver, the content stored on social bookmark is searched based on tag keyword information and unnecessary information can be excluded. Social bookmark can make users access to selected content. However, quick access to content that users want is difficult job because of the user of the participation and share. Our paper suggests a method recommending search word to be able to access quickly to content. A method is suggested by using Collaborative Filtering and Jaccard similarity coefficient. The performance of suggested system is verified with experiments that compare by 'Delicious' and "Feeltering' with our system.

Adaptive Filtering Processing for Target Signature Enhancement in Monostatic Borehole Radar Data

  • Hyun, Seung-Yeup;Kim, Se-Yun
    • Journal of electromagnetic engineering and science
    • /
    • v.14 no.2
    • /
    • pp.79-81
    • /
    • 2014
  • In B-scan data measured by a pulse-type monostatic borehole radar, target signatures are seriously obscured by two clutters that differ in orientation and intensity. The primary clutter appears as a nearly constant time delay, which is caused by internal ringing between antenna and transceiver in the radar system. The secondary clutter occurs as an oblique time delay due to the guided borehole wave along the logging cable of the radar antenna. This issue led us to perform adaptive filtering processing for orientation-based clutter removal. This letter describes adaptive filtering processing consisting of a combination of edge detection, data rotation, and eigenimage filtering. We show that the hyperbolic signatures of a dormant air-filled tunnel target can be more distinctly enhanced by applying the proposed approach to the B-scan data, which are measured in a well-suited test site for underground tunnel detection.

User-Information based Adaptive Service Management Algorithm (사용자 정보기반의 적응적인 서비스관리 알고리즘)

  • Park, Hea-Sook
    • Journal of the Korea Society of Computer and Information
    • /
    • v.14 no.8
    • /
    • pp.81-88
    • /
    • 2009
  • Many studies and policies are suggested for customer satisfaction to survive in multimedia content service markets. there are policies like a segregating the clients using the contents service and allocating the media server's resources distinctively by clusters using the cluster analysis method of CRM. The problem of this policy is fixed allocation of media server resources. It is inefficient for costly media server resource. To resolve the problem and enhance the utilization of media server resource, the ACRFA (Adaptive Client Request Filtering Algorithm) was suggested per cluster to allocate media server resources by flexible resource allocation method.