• 제목/요약/키워드: reclassification

검색결과 99건 처리시간 0.025초

문서 군집화의 정확률 향상을 위한 범용어 수집과 문서 재분류 알고리즘 (Gathering Common-word and Document Reclassification to improve Accuracy of Document Clustering)

  • 신준철;옥철영;이응봉
    • 정보처리학회논문지B
    • /
    • 제19B권1호
    • /
    • pp.53-62
    • /
    • 2012
  • 정보검색에서 많은 검색 결과 문서들을 효율적으로 다루기 위해 군집화 기술을 사용하고 있지만, 대체로 군집화의 정확률은 일부 영역에서만 요구 사항을 만족시키고 있다. 본 논문에서는 검색 결과 문서들의 군집화 정확률을 향상시키기 위한 두 가지 방법을 제안한다. 첫째는 군집화 과정에서 흔히 쓰이지만 낮은 가중치를 가진 범용어를 정의하고, 검색 결과들을 비교하여 범용어를 자동 수집하고 그의 가중치를 계산하는 방법을 제안한다. 실험 결과 불용어에 비해 범용어를 사용했을 때 군집화 오류의 34%가 개선되었다. 둘째는 집단평균연결 방식의 군집화 알고리즘으로 일차 군집들을 생성 후, 문서와 군집 간의 유사도를 측정하여 가장 유사도가 높은 군집으로 문서를 재분류하는 알고리즘을 제안한다. 네이버 지식인 카테고리를 이용한 군집 결과의 비교 실험을 통해 일차 군집보다 재분류된 군집의 정확률이 1.81% 향상되는 것을 확인하였다.

Oxygenation Index in the First 24 Hours after the Diagnosis of Acute Respiratory Distress Syndrome as a Surrogate Metric for Risk Stratification in Children

  • Kim, Soo Yeon;Kim, Byuhree;Choi, Sun Ha;Kim, Jong Deok;Sol, In Suk;Kim, Min Jung;Kim, Yoon Hee;Kim, Kyung Won;Sohn, Myung Hyun;Kim, Kyu-Earn
    • Acute and Critical Care
    • /
    • 제33권4호
    • /
    • pp.222-229
    • /
    • 2018
  • Background: The diagnosis of pediatric acute respiratory distress syndrome (PARDS) is a pragmatic decision based on the degree of hypoxia at the time of onset. We aimed to determine whether reclassification using oxygenation metrics 24 hours after diagnosis could provide prognostic ability for outcomes in PARDS. Methods: Two hundred and eighty-eight pediatric patients admitted between January 1, 2010 and January 30, 2017, who met the inclusion criteria for PARDS were retrospectively analyzed. Reclassification based on data measured 24 hours after diagnosis was compared with the initial classification, and changes in pressure parameters and oxygenation were investigated for their prognostic value with respect to mortality. Results: PARDS severity varied widely in the first 24 hours; 52.4% of patients showed an improvement, 35.4% showed no change, and 12.2% either showed progression of PARDS or died. Multivariate analysis revealed that mortality risk significantly increased for the severe group, based on classification using metrics collected 24 hours after diagnosis (adjusted odds ratio, 26.84; 95% confidence interval [CI], 3.43 to 209.89; P=0.002). Compared to changes in pressure variables (peak inspiratory pressure and driving pressure), changes in oxygenation (arterial partial pressure of oxygen to fraction of inspired oxygen) over the first 24 hours showed statistically better discriminative power for mortality (area under the receiver operating characteristic curve, 0.701; 95% CI, 0.636 to 0.766; P<0.001). Conclusions: Implementation of reclassification based on oxygenation metrics 24 hours after diagnosis effectively stratified outcomes in PARDS. Progress within the first 24 hours was significantly associated with outcomes in PARDS, and oxygenation response was the most discernable surrogate metric for mortality.

Genome-Based Reclassification of Strain KIST612, Previously Classified as Eubacterium limosum, into a New Strain of Eubacterium callanderi

  • Ji-Yeon Kim;Byeongchan Kang;Soyoung Oh;Yeji Gil;In-Geol Choi;In Seop Chang
    • Journal of Microbiology and Biotechnology
    • /
    • 제33권8호
    • /
    • pp.1084-1090
    • /
    • 2023
  • The strain KIST612, initially identified as E. limosum, was a suspected member of E. callanderi due to differences in phenotype, genotype, and average nucleotide identity (ANI). Here, we found that E. limosum ATCC 8486T and KIST612 are genetically different in their central metabolic pathways, such as that of carbon metabolism. Although 16S rDNA sequencing of KIST612 revealed high identity with E. limosum ATCC 8486T (99.2%) and E. callanderi DSM 3662T (99.8%), phylogenetic analysis of housekeeping genes and genome metrics clearly indicated that KIST612 belongs to E. callanderi. The phylogenies showed that KIST612 is closer to E. callanderi DSM 3662T than to E. limosum ATCC 8486T. The ANI between KIST612 and E. callanderi DSM 3662T was 99.8%, which was above the species cut-off of 96%, Meanwhile, the ANI value with E. limosum ATCC 8486T was not significant, showing only 94.6%. The digital DNA-DNA hybridization (dDDH) results also supported the ANI values. The dDDH between KIST612 and E. callanderi DSM 3662T was 98.4%, whereas between KIST612 and E. limosum ATCC 8486T , it was 57.8%, which is lower than the species cut-off of 70%. Based on these findings, we propose the reclassification of E. limosum KIST612 as E. callanderi KIST612.

흉부 CT 영상을 이용한 폐 혈관 추출 및 폐 결절 재분류 기법 (Pulmonary Vessel Extraction and Nodule Reclassification Method Using Chest CT Images)

  • 김현수;팽소호;뮤잠멜;김덕환
    • 전자공학회논문지CI
    • /
    • 제46권6호
    • /
    • pp.35-43
    • /
    • 2009
  • 환자의 흉부 CT 영상을 입력으로 하여 폐 영역의 결절(nodule)을 효과적으로 분류하는 것이 목적인 컴퓨터 조력 진단(Computer Aided Diagnosis, CAD) 시스템에서는 대부분 폐 영역의 혈관 추출 단계가 우선적으로 진행된다. 혈관 조영제를 투여한 환자 영상에서 폐 혈관과 폐 결절은 흉부 CT 영상에서 비슷한 감쇄를 보이므로 혈관 추출 단계에서 혈관과 결절이 함께 추출될 수 있다. 때문에 폐 혈관이 제거된 나머지 영역에서 폐 결절을 탐지 및 분류하는 방식의 폐 결절 분류기는 혈관 추출 기법의 성능에 큰 영향을 받는다. 본 논문에서는 폐 결절이 혈관으로 오인식 되어 혈관과 함께 추출될 수 있는 문제를 극복하기 위해 혈관의 두께 패턴을 분석하여 폐 결절을 재분류하는 기법을 제안한다. 제안된 방법은 폐 영역 결정 단계, 폐 혈관 영역 추출 및 골격 형성 단계, 혈관 토폴로지 구성 및 보정 단계, 그리고 혈관 후보 내 결절 재분류 단계 등의 네 단계로 이루어져 있다. 제안한 방법의 정확도를 분석하기 위해 폐 결절이 혈관을 침투하여 분포하는 환자들의 입력 영상을 이용하여 판독 전문의의 도움을 받아 분류기의 정확도 평가를 진행하였다. 실험 결과에서는 제안한 혈관 추출 및 결절 재분류 기법을 사용한 CAD 시스템의 폐 결절 분류기 성능과 재분류 절차를 진행하지 않은 분류기 성능에 대해 비교하고 제안한 방법이 혈관 영역으로 잘못 포함된 결절을 자동으로 정확하게 재분류 할 수 있음을 보여준다.

Role of Multiparametric Prostate Magnetic Resonance Imaging before Confirmatory Biopsy in Assessing the Risk of Prostate Cancer Progression during Active Surveillance

  • Joseba Salguero;Enrique Gomez-Gomez;Jose Valero-Rosa;Julia Carrasco-Valiente;Juan Mesa;Cristina Martin;Juan Pablo Campos-Hernandez;Juan Manuel Rubio;Daniel Lopez;Maria Jose Requena
    • Korean Journal of Radiology
    • /
    • 제22권4호
    • /
    • pp.559-567
    • /
    • 2021
  • Objective: To evaluate the impact of multiparametric magnetic resonance imaging (mpMRI) before confirmatory prostate biopsy in patients under active surveillance (AS). Materials and Methods: This retrospective study included 170 patients with Gleason grade 6 prostate cancer initially enrolled in an AS program between 2011 and 2019. Prostate mpMRI was performed using a 1.5 tesla (T) magnetic resonance imaging system with a 16-channel phased-array body coil. The protocol included T1-weighted, T2-weighted, diffusion-weighted, and dynamic contrast-enhanced imaging sequences. Uroradiology reports generated by a specialist were based on prostate imaging-reporting and data system (PI-RADS) version 2. Univariate and multivariate analyses were performed based on regression models. Results: The reclassification rate at confirmatory biopsy was higher in patients with suspicious lesions on mpMRI (PI-RADS score ≥ 3) (n = 47) than in patients with non-suspicious mpMRIs (n = 61) and who did not undergo mpMRIs (n = 62) (66%, 26.2%, and 24.2%, respectively; p < 0.001). On multivariate analysis, presence of a suspicious mpMRI finding (PI-RADS score ≥ 3) was associated (adjusted odds ratio: 4.72) with the risk of reclassification at confirmatory biopsy after adjusting for the main variables (age, prostate-specific antigen density, number of positive cores, number of previous biopsies, and clinical stage). Presence of a suspicious mpMRI finding (adjusted hazard ratio: 2.62) was also associated with the risk of progression to active treatment during the follow-up. Conclusion: Inclusion of mpMRI before the confirmatory biopsy is useful to stratify the risk of reclassification during the biopsy as well as to evaluate the risk of progression to active treatment during follow-up.

현 입원의료이용량의 급성기진료 및 장기요양 서비스 재분류 (Reclassification of healthcare utilization of inpatients to estimate the demand for long-term care services)

  • 장혜정;김창엽;윤석준
    • 보건행정학회지
    • /
    • 제11권3호
    • /
    • pp.31-45
    • /
    • 2001
  • With an economic development and epidemiologic transition, the burden of disease due to chronic diseases and accidents is increasing. However, in most of developing countries, long-term care facilities are not available, therefore acute care facilities should provide both acute and long-term care services. It is also true in Korea. The demand for long-term care services needs to be estimated to establish the adequate supply system of health resources. This article introduces the reclassification methodology of inpatients' healthcare utilization to acute and long-term care services. All discharged patients from hospitals for one month were analyzed. The distribution of inpatients' hospital days were fitted to Chi-squared distribution by ICD disease categories, and they were grouped in five clusters. For each cluster, the lower and upper limit of classification criteria to acute and long-term care services were chosen. Summarizing all hospital days corresponding to acute and long-term care respectively, 24 to 28 percent of inpatient services fumed out to be long-term care services. The study results are consistent with those of the existing studies. They can be used practically in the allocation of long-term care resources.

  • PDF

프로바이오틱스로서의 Lactobacillus acidophilus (Lactobacillus acidophilus as a Probiotics)

  • 오세종
    • Journal of Dairy Science and Biotechnology
    • /
    • 제37권3호
    • /
    • pp.155-166
    • /
    • 2019
  • Bacteria from the genus Lactobacillus are important for the production of fermented food and dairy products, and as symbionts in human and animals. Lactobacillus acidophilus has widely been used in the production of yogurt, health foods, and even medicines. The efficacy of L. acidophilus has been proven with regards to the reduction of cholesterol, prevention and treatment of diarrhea, modulation of the immune system, suppression of cancer, etc. Using molecular biology tools, Lactobacillus acidophilus has now been reclassified into six species: L. acidophilus, L. amylovorus, L. crispatus, L gallinarium, L. gasseri, and L. johnsonii. Thus, since L. acidophilus has now been marked as a newly defined species, caution is advised when reading future publications regarding this bacterium. In this article, the results of the reclassification of L. acidophilus are mentioned after an analysis of its field inheritance was performed by my research team. Especially, L. amylovorus KU4 (formerly named as L. acidophilus KU4; KCCM 10975P) is a novel probiotic strain that is isolated from humans; it has the ability to reduce cholesterol. It has also been reported as a microorganism that effectively inhibits the growth of pathogenic E. coli. However, this Korean patent (No 10-1541280) refers to a strain obtained from calves; the origin of this strain was incorrectly labeled. Furthermore, after the discovery of L. acidophilus in 1900, its role in intestinal microbiological research was described and its utilization as a probiotic was presented.

옥상조경 구성 요소들의 특성을 분석한 정량적 유형구분 기준에 관한 연구 - 서울시 사례를 중심으로 - (A Study on Quantitative Classification of Styles through Analysing Characteristics of Components in Green Roofs - Focused on the examples in Seoul -)

  • 길승호;송병화;양병이
    • KIEAE Journal
    • /
    • 제11권1호
    • /
    • pp.21-28
    • /
    • 2011
  • The objective of this study is to analysis the properties for reclassifying green roofs into three types by cluster analysis after investigating the present condition in thirty green roofs which were created from 2002 to 2004 by Seoul Metropolitan Government. The previous classification was resulted in structure safety diagnosis in the type of green roofs and visible judgment by experts in sites. However, it should have been corrected. Therefore, it needed a reestablished concept and a reclassification in green roofs. The results of this study are as follows : the concept of a rooftop garden and a green roof is different from previous studies. The rooftop gardens named by intensive green roofs are closed to integrated management, whereas the green roofs are closed to low management. The reclassification of green type was also conducted to use the statistic analysis of categorical regression by previous studies, and the factors extracted by the categorical regression were influenced by greening type. The figure of R-square representing explanation in regression analysis is 95.2%. As this result was analyzed, it was proved into rooftop gardens demanded for high activity by people.

아시아-오세아니아 지역의 MODIS 지면피복분류 개선 (Improvement of MODIS land cover classification over the Asia-Oceania region)

  • 박지열;서명석
    • 대한원격탐사학회지
    • /
    • 제31권2호
    • /
    • pp.51-64
    • /
    • 2015
  • 본 연구에서는 MODerate resolution Imaging Spectroradiometer (MODIS) 지면피복 분류자료(MCD12Q1)에서 분류오류로 판단되는 화소들을 재분류함으로써 분류 정확도를 개선하였다. 최근 12년(2001-2012)간의 MODIS 지면피복 분류자료에서 지면피복 유형이 3개 이상으로 분류된 화소는 분류상에 오류가 있다고 판단하여 지면피복 재분류 화소로 선정하였다. 지면피복 재분류를 위해 공간해상도는 1 km이고 시간주기는 8일인 MODIS Normalized Difference Vegetation Index (NDVI) 자료를 이용하였다. NDVI 자료 중 구름 등으로 오염된 화소를 보정하기 위해 시 공간 연속성을 이용한 보정기법인 Correction based on Spatial and Temporal Continuity (CSaTC) 기법을 이용하였다. 보정된 NDVI 자료를 1개월 주기로 합성한 후 분류 오류로 판단된 화소들에 대해 Iterative Self-Organizing Data Analysis (ISODATA) 기법으로 군집화를 수행하였다. 각 군집별 식생 계절변동 특성을 고려하여 지면피복을 분류한 후 정상으로 판정된 MODIS 지면피복과 합성하여 최종 지면피복 재분류 자료를 산출하였다. 분류 정확도는 GPS를 이용한 현장관측 자료와 유럽우주국의 지상검증참조자료 등 총 138개 지상 관측자료를 이용하여 검증을 수행하였다. 2012년 MODIS 지면피복 분류자료의 정확도는 약 68%이었으나 본 연구에서 재분류한 지면피복자료의 정확도는 약 74%로 나타나 일부 화소들에서 분류 정확도가 개선되었다.