• Title/Summary/Keyword: active database

검색결과 387건 처리시간 0.027초

이종의 OCT 기기로부터 생성된 볼륨 데이터로부터 심층 컨볼루션 신경망을 이용한 AMD 진단 (AMD Identification from OCT Volume Data Acquired from Heterogeneous OCT Machines using Deep Convolutional Neural Network)

  • 권오흠;정유진;권기룡;송하주
    • 데이타베이스연구회지:데이타베이스연구
    • /
    • 제34권3호
    • /
    • pp.124-136
    • /
    • 2018
  • 신경망을 이용하여 OCT 영상을 분석하고 다양한 망막 질환을 자동 진단하는 것에 관한 연구들이 활발하게 이루어지고 있다. 이러한 연구가 현실에 적용되기 위한 하나의 중요한 요건은 학습된 신경망이 학습에 사용된 데이터와는 다른 기기에서 생성된 데이터에 대해서도 성능의 큰 하락 없이 일반화될 수 있어야 한다는 것이다. 본 논문에서는 심층 CNN을 이용하여 OCT 영상으로부터 노년기황반변성(AMD)을 자동 진단하는 것을 다룬다. 하나의 OCT 기기로부터 획득한 데이터 셋을 이용하여 신경망을 학습시킨 후 다른 OCT 기기로부터 생산된 이미지를 테스트한 결과 상당한 성능의 하락을 관찰할 수 있었다. 이러한 성능의 하락을 방지하기 위해서 OCT 이미지를 정규화 하는 기법을 제안하고 실험을 통해 그 효과를 분석하였다. 제안한 기법은 OCT 이미지를 분할하여 망막에 해당하는 영역을 찾아낸 후 이미지 내에서 망막 영역이 수평에 가까운 기울기를 가지도록 정렬(align)하여 형태적인 측면에서 OCT 이미지를 정규화 하는 것을 목적으로 한다. 실험을 통하여 제안한 기법이 이종의 기기에서 생성된 OCT 이미지로부터 AMD를 자동진단 하는데 있어서 상당한 성능의 향상을 달성함을 보였다.

가구당 기기별 에너지 사용량 예측을 위한 딥러닝 모델의 설계 및 구현 (Design and Implementation of Deep Learning Models for Predicting Energy Usage by Device per Household)

  • 이주희;이강윤
    • 한국빅데이터학회지
    • /
    • 제6권1호
    • /
    • pp.127-132
    • /
    • 2021
  • 우리나라는 자원 빈국인 동시에 에너지 다소비 국가이다. 또한 전기 에너지에 대한 사용량 및 의존도가 매우 높고, 총 에너지 사용의 20% 이상은 건물에서 소비된다. 딥러닝과 머신러닝에 대한 연구가 활발해지면서 다양한 알고리즘을 에너지 효율 분야에 적용하려는 연구가 진행되고 있으며, 에너지의 효율적인 관리를 위한 건물에너지관리시스템(BEMS)의 도입이 늘어가는 추세이다. 본 논문에서는 스마트플러그를 이용하여 직접 수집한 가구당 기기별 에너지 사용량을 바탕으로 데이터베이스를 구축하였다. 또한 RNN과 LSTM 모델을 이용하여 수집한 데이터를 효과적으로 분석 및 예측하는 알고리즘을 구현하였다. 추후 이 데이터는 에너지 사용량 예측을 넘어 전력 소비 패턴 분석 등에 적용할 수 있다. 이는 에너지 효율 개선에 도움이 될 수 있으며, 미래 데이터의 예측을 통해 효과적인 전력 사용량 관리에 도움을 줄 것으로 기대된다.

퍼지집합 모델을 이용한 암설지형 분포 가능지 추출 연구 (Extracting the Distribution Potential Area of Debris Landform Using a Fuzzy Set Model)

  • 위눈솔;장동호
    • 한국지형학회지
    • /
    • 제24권1호
    • /
    • pp.77-91
    • /
    • 2017
  • Many debris landforms in the mountains of Korea have formed in the periglacial environment during the last glacial stage when the generation of sediments was active. Because these landforms are generally located on steep slopes and mostly covered by vegetation, however, it is difficult to observe and access them through field investigation. A scientific method is required to reduce the survey range before performing field investigation and to save time and cost. For this purpose, the use of remote sensing and GIS technologies is essential. This study has extracted the potential area of debris landform formation using a fuzzy set model as a mathematical data integration method. The first step was to obtain information about the location of debris landforms and their related factors. This information was verified through field observation and then used to build a database. In the second step, we conducted the fuzzy set modeling to generate a map, which classified the study area based on the possibility of debris formation. We then applied a cross-validation technique in order to evaluate the map. For a quantitative analysis, the calculated potential rate of debris formation was evaluated by plotting SRC(Success Rate Curve) and calculating AUC(Area Under the Curve). The prediction accuracy of the model was found to be 83.1%. We posit that the model is accurate and reliable enough to contribute to efficient field investigation and debris landform management.

액상형 전자담배 용액에 의한 급성 니코틴 중독: 증례보고의 체계적 고찰 (Acute Nicotine Poisoning due to Electronic Cigarette Liquid: Systematic Review of Case Reports)

  • 양시용;좌민홍;유제성;정현수;정성필
    • 대한임상독성학회지
    • /
    • 제18권2호
    • /
    • pp.51-56
    • /
    • 2020
  • Purpose: Acute nicotine poisoning by liquid nicotine in electronic cigarettes is becoming an increasing problem worldwide. The current systematic review aimed to determine the harm of acute nicotine poisoning by reviewing published case reports. Methods: An online literature search with PubMed, Embase, Cochrane Library, and KoreaMed database was performed to identify relevant studies addressing acute nicotine poisoning with electronic cigarettes. Two investigators searched the case reports written in English or Korean. Results: Twenty-six cases were included in this study. The routes of intoxication included ingestion in 18 cases, intravenous injection in three cases, subcutaneous injection in two cases, and ocular exposure in two cases. Ten cases had a cardiac arrest, and seven of them died. Seven out of 12 cases with intentional poisoning had a cardiac arrest. Nine children under 18 years were reported, and three of them had a cardiac arrest. Sixteen cases without a cardiac arrest recovered well, except for one case with sudden sensorineural hearing loss. Conclusion: The authors reviewed the risks of electronic cigarette liquid in terms of acute poisoning through a systematic review. The nicotine solution of an e-cigarette can be life-threatening in cases of acute poisoning. Therefore, active emergency treatment with early recognition is necessary. In addition, various management methods and regulations for preventing acute nicotine poisoning, such as restriction of distribution and nicotine concentration, should be considered.

해면 추출물의 신경세포 보호 및 항염증 활성과 함유 성분의 HPLC 프로파일링 (Neuroprotective and anti-inflammatory activity of marine sponge extract and HPLC profiling of its components)

  • 김다은;김민선;안혜숙;이재욱;박진수
    • Journal of Applied Biological Chemistry
    • /
    • 제64권1호
    • /
    • pp.33-38
    • /
    • 2021
  • 해면동물은 강력한 세포독성을 나타내는 함유성분으로 의약후보물질 탐색의 중요한 소재로 이용되고 있으나 최근 해양생태계 보전에 관심이 높아짐에 따라 해면동물 확보는 더욱 어려움을 겪고 있다. 이러한 경향에 대응하고 해양 천연물연구의 활성화를 위한 해양생물자원 데이터베이스 구축을 위하여 181개 해면동물 추출물에 대한 HPLC 프로파일을 생성하고 항염증 및 신경세포보호 활성을 탐색하였다. 이를 통하여 해면동물 추출물 간의 HPLC를 통한 함유성분에 따른 클러스터링이 가능하였고 또한 각각 17개, 14개 시료에서 항염증 활성과 신경세포보호활성이 확인되었다. 이와 같은 연구는 해면동물을 포함한 해양생물자원에서의 효과적인 생리활성 탐색에 도움이 될 것이라고 판단한다.

Clinical characteristics of adolescent nasal bone fractures

  • Kim, Se Hun;Han, Dong Gil;Shim, Jeong Su;Lee, Yong Jig;Kim, Sung-Eun
    • 대한두개안면성형외과학회지
    • /
    • 제23권1호
    • /
    • pp.29-33
    • /
    • 2022
  • Background: There have been many reports of nasal bone fractures in adults, but there are few clinical reports of them in adolescents, although adolescence is the main growth period of the nasal bone. In addition, previous studies have tended to classify and describe child and adolescent nasal fractures in the same category. The aim of this study was to identify the clinical aspects of nasal fractures in adolescents, and to evaluate the characteristics of nasal fractures in the growth period. Methods: Our institution's database was reviewed to extract data on adolescent patients between the age of 13 to 18 who had isolated nasal bone fractures from March 2012 to February 2020. The study excluded patients with other facial fractures, previous facial fractures, or congenital deformities. Results: This study included 243 boys and 26 girls. Interpersonal violence and sports-related accidents accounted for 85 and 79 cases, respectively. There were 128 frontal impact injuries and 132 lateral impact injuries, and 97 patients had accompanying septal fractures. An accompanying septal fracture was present in 36.06% of all patients, but in 51.20% of those who underwent surgery. Conclusion: The prevalence of adolescent nasal fractures was significantly higher in boys, to a greater extent than observed for pediatric or adult fractures. The main causes of fractures were interpersonal violence and sports-related accidents. An explanation for these results is that adolescent boys are more prone to have violent accidents or companionship with active sports than other age or sex groups, leading to substantially more fractures.

Integrated bioinformatics analysis of validated and circulating miRNAs in ovarian cancer

  • Dogan, Berkcan;Gumusoglu, Ece;Ulgen, Ege;Sezerman, Osman Ugur;Gunel, Tuba
    • Genomics & Informatics
    • /
    • 제20권2호
    • /
    • pp.20.1-20.13
    • /
    • 2022
  • Recent studies have focused on the early detection of ovarian cancer (OC) using tumor materials by liquid biopsy. The mechanisms of microRNAs (miRNAs) to impact OC and signaling pathways are still unknown. This study aims to reliably perform functional analysis of previously validated circulating miRNAs' target genes by using pathfindR. Also, overall survival and pathological stage analyses were evaluated with miRNAs' target genes which are common in the The Cancer Genome Atlas and GTEx datasets. Our previous studies have validated three downregulated miRNAs (hsa-miR-885-5p, hsa-miR-1909-5p, and hsa-let7d-3p) having a diagnostic value in OC patients' sera, with high-throughput techniques. The predicted target genes of these miRNAs were retrieved from the miRDB database (v6.0). Active-subnetwork-oriented Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis was conducted by pathfindR using the target genes. Enrichment of KEGG pathways assessed by the analysis of pathfindR indicated that 24 pathways were related to the target genes. Ubiquitin-mediated proteolysis, spliceosome and Notch signaling pathway were the top three pathways with the lowest p-values (p < 0.001). Ninety-three common genes were found to be differentially expressed (p < 0.05) in the datasets. No significant genes were found to be significant in the analysis of overall survival analyses, but 24 genes were found to be significant with pathological stages analysis (p < 0.05). The findings of our study provide in-silico evidence that validated circulating miRNAs' target genes and enriched pathways are related to OC and have potential roles in theranostics applications. Further experimental investigations are required to validate our results which will ultimately provide a new perspective for translational applications in OC management.

오령산 구성약재 성분의 Drug-likeness와 Oral bioavailability (Drug-likeness and Oral bioavailability for Chemical Compounds of Medicinal Materials Constituting Oryeong-san)

  • 김상균;이승호
    • 대한본초학회지
    • /
    • 제33권5호
    • /
    • pp.19-37
    • /
    • 2018
  • Objectives : Oryeong-san was composed of Alismatis Rhizoma, Atractylodis Rhizoma Alba, Poria Sclerotium, Polyporus, Cinnamomi Cortex, and known to have hundreds of chemical compounds. The aim of this study was to screen chemical compounds constituting Oryeong-san with the drug-likeness and oral bioavailability from the analysis of their physicochemical properties. Methods : A list of chemical compounds of Oryeong-san was obtained from TM-MC(database of medicinal materials and chemical compounds in Northeast Asian traditional medicine). To remove redundant compounds, the SMILES (Simplified Molecular Input Line Entry System) strings of each compound were identified. All of the physicochemical properties for the compounds were calculated using the DruLiTo(Drug Likeness Tool). Drug-likeness was estimated by QED(Quantitative Estimate of Druglikeness) and OB(Oral bioavailability) was checked based on the Veber's rules. Results : A total of 475 compounds were obtained by eliminating duplication among 544 compounds of 5 medicinal materials. Analysis of the physicochemical properties revealed that the most common values were MW(molecular weight) 200~300 g/mol, ALOGP(octanol-water partition coefficient) 1~2, HBA(number of hydrogen bond acceptors) 0~1, HBD(number of hydrogen bond donors) 0, PSA(polar surface area) 0~50 angstrom, ROTB(number of rotatable bonds) 1, AROM(number of aromatic rings) 0, and ALERT(number of structural alerts) 1. QED had 93% of the values between 0.2 and 0.7, and OB had 90% of the value of TRUE. Conclusions : We in this paper screened the candidate active compounds of Oryeong-san using the QED and Veber's rules. In the future, we will use the screening results to analyze the mechanism of Oryeong-san based on systems pharmacology.

MZ세대의 라이프스타일 특성에 대한 탐색적 연구 - 2010년-2020년의 논문을 중심으로 - (An Exploratory Study on the Lifestyle Characteristics of the MZ Generation - A Focus on the 2010-2020 Studies -)

  • 강유림;김문영
    • 한국의류산업학회지
    • /
    • 제24권1호
    • /
    • pp.81-94
    • /
    • 2022
  • The purpose of this study is to analyze the trends of MZ generation's lifestyle-related research from 2010 to 2020. As a result of searching keywords such as MZ generation's and lifestyle using academic database search sites, a total of 218 cases were used as analysis data to conduct frequency and content analysis. First, research type was 74 dissertations(34.6%), 144 journals(65.4%). The study of MZ generation was relatively active in journals. Second, the current status of academic field was 85(39.7%) in the social field, followed by 66(30.8%) in the arts/physical education, 21(9.8%) in the complex studies, 16(7.5%) in education, 15(7.0%) in nature, 6(2.8%) in engineering, 4(1.9%) in humanities, 1(0.5%) in agriculture/marine. Third, the current status of MZ generation research topics is 54 social participations(25.3%), 35 fashion/beauty(16.3%), 31 social/organizational adaptations(14.5%), 25 cultural/leisure activities(11.7%), 24 design/development projects(11.2%), 21 economic/employment/job projects(9.8%), 11 educational/career/experiences(5.1%), 9 self-concepts(4.2%), 4 welfare services(1.9%). Fourth, the current status of MZ generation research methods was quantitative research(survey/experiment) 125(58.4%), qualitative research(depth interview/participant observation) 42(19.6%), theory/literature research 35(16.4%) and mixed research 12(5.6%). Fifth, the study on the lifestyle of the MZ generation was conducted in four cases, one in 2016, one in 2019, two in 2020. This study is meaningful in that it grasped the overall flow of data of information exchange that can share the research trends of the MZ generation and suggested the basic data on the direction of future research, the individual tendency, behavior, and lifestyle characteristics of the MZ generation.

Characteristics of injuries associated with electric personal mobility devices: a nationwide cross-sectional study in South Korea

  • Kim, Maro;Suh, Dongbum;Lee, Jin Hee;Kwon, Hyuksool;Choi, Yujin;Jeong, Joo;Kim, Sola;Hwang, Soyun;Park, Joong Wan;Jo, You Hwan
    • Journal of Trauma and Injury
    • /
    • 제35권1호
    • /
    • pp.3-11
    • /
    • 2022
  • Purpose: The increasing use of electric personal mobility devices (ePMDs) has been accompanied by an increasing incidence of associated accidents. This study aimed to investigate the characteristics of ePMD-related injuries and their associated factors. Methods: This cross-sectional study was conducted using data from the Emergency Department-based Injury In-depth Surveillance database from 2014 to 2018. All patients who were injured while operating an ePMD were eligible. The primary outcome was the rate of severe injury, defined as an excess mortality ratio-adjusted Injury Severity Score of ≥25. We calculated the adjusted odds ratios (AORs) of outcomes associated with ePMD-related injuries. Results: Of 1,391,980 injured patients, 684 (0.05%) were eligible for inclusion in this study. Their median age was 28 years old, and most injuries were sustained by men (68.0%). The rate of ePMD-related injuries increased from 3.1 injuries per 100,000 population in 2014 to 100.3 per 100,000 population in 2018. A majority of the injuries occurred on the street (32.7%). The most commonly injured area was the head and face (49.6%), and the most common diagnosis was superficial injuries or contusions (32.9%). Being aged 55 years or older (AOR, 3.88; 95% confidence interval, 1.33-11.36) and operating an ePMD while intoxicated (AOR, 2.78; 95% confidence interval, 1.52-5.08) were associated with severe injuries. Conclusions: The number of emergency room visits due to ePMD-related injuries is increasing. Old age and drunk driving are both associated with serious injuries. Active traffic enforcement and safety regulations regarding ePMDs should be implemented to prevent severe injuries caused by ePMD-related accidents.