• 제목/요약/키워드: Random measures

검색결과 291건 처리시간 0.027초

혼합자료에서 독립성검정에 의한 연관성 측정 (A unified measure of association for complex data obtained from independence tests)

  • 이승천;허문열
    • 응용통계연구
    • /
    • 제34권4호
    • /
    • pp.523-536
    • /
    • 2021
  • 두 확률변수의 연관성을 측정하는 측도는 많이 있으나, 이러한 측도는 같은 유형인 변수들 간의 관계를 측정하기 위한 것으로 여러 가지 유형의 변수들이 혼재되어 있는 혼합자료에서 사용하기는 곤란하다. 본 논문에서는 두 확률변수의 독립성 검정을 통해 구한 p-값으로 혼합자료에서 사용될 수 있는 새로운 연관성 측도를 구하였으며, 이렇게 구하여 진 연관성 측도가 혼합자료에서 변수들 간의 연관성을 비교하는데 유용하게 사용될 수 있음을 보였다.

A Study on the Performance of Similarity Indices and its Relationship with Link Prediction: a Two-State Random Network Case

  • Ahn, Min-Woo;Jung, Woo-Sung
    • Journal of the Korean Physical Society
    • /
    • 제73권10호
    • /
    • pp.1589-1595
    • /
    • 2018
  • Similarity index measures the topological proximity of node pairs in a complex network. Numerous similarity indices have been defined and investigated, but the dependency of structure on the performance of similarity indices has not been sufficiently investigated. In this study, we investigated the relationship between the performance of similarity indices and structural properties of a network by employing a two-state random network. A node in a two-state network has binary types that are initially given, and a connection probability is determined from the state of the node pair. The performances of similarity indices are affected by the number of links and the ratio of intra-connections to inter-connections. Similarity indices have different characteristics depending on their type. Local indices perform well in small-size networks and do not depend on whether the structure is intra-dominant or inter-dominant. In contrast, global indices perform better in large-size networks, and some such indices do not perform well in an inter-dominant structure. We also found that link prediction performance and the performance of similarity are correlated in both model networks and empirical networks. This relationship implies that link prediction performance can be used as an approximation for the performance of the similarity index when information about node type is unavailable. This relationship may help to find the appropriate index for given networks.

A Machine Learning-Driven Approach for Wildfire Detection Using Hybrid-Sentinel Data: A Case Study of the 2022 Uljin Wildfire, South Korea

  • Linh Nguyen Van;Min Ho Yeon;Jin Hyeong Lee;Gi Ha Lee
    • 한국수자원학회:학술대회논문집
    • /
    • 한국수자원학회 2023년도 학술발표회
    • /
    • pp.175-175
    • /
    • 2023
  • Detection and monitoring of wildfires are essential for limiting their harmful effects on ecosystems, human lives, and property. In this research, we propose a novel method running in the Google Earth Engine platform for identifying and characterizing burnt regions using a hybrid of Sentinel-1 (C-band synthetic aperture radar) and Sentinel-2 (multispectral photography) images. The 2022 Uljin wildfire, the severest event in South Korean history, is the primary area of our investigation. Given its documented success in remote sensing and land cover categorization applications, we select the Random Forest (RF) method as our primary classifier. Next, we evaluate the performance of our model using multiple accuracy measures, including overall accuracy (OA), Kappa coefficient, and area under the curve (AUC). The proposed method shows the accuracy and resilience of wildfire identification compared to traditional methods that depend on survey data. These results have significant implications for the development of efficient and dependable wildfire monitoring systems and add to our knowledge of how machine learning and remote sensing-based approaches may be combined to improve environmental monitoring and management applications.

  • PDF

Traffic-induced vibrations at the wet joint during the widening of concrete bridges and non-interruption traffic control strategies

  • Junyong Zhou;Zunian Zhou;Liwen Zhang;Junping Zhang;Xuefei Shi
    • Computers and Concrete
    • /
    • 제32권4호
    • /
    • pp.411-423
    • /
    • 2023
  • The rapid development of road transport has increased the number of bridges that require widening. A critical issue in the construction of bridge widening is the influence of vibrations of the old bridge on the casting of wet joint concrete between the old and new bridges owing to the running traffic. Typically, the bridge is closed to traffic during the pouring of wet joint concrete, which negatively affects the existing transportation network. In this study, a newly developed microscopic traffic load modeling approach and the vehicle-bridge interaction theory are incorporated to develop a refined numerical framework for the analysis of random traffic-bridge coupled dynamics. This framework was used to investigate traffic-induced vibrations at the wet joint of a widened bridge. Based on an experimental study on the vibration resistance of wet joint concrete, traffic control strategies were proposed to ensure the construction performance of cast-in-site wet joint concrete under random traffic without interruption. The results show that the vibration displacement and frequency of the old bridge, estimated by the proposed framework, were comparable with those obtained from field measurements. Based on the target peak particle velocity and vibration amplitude of the wet joint concrete, it was found that traffic control measures, such as limiting vehicle gross weight and limiting traffic volume by closing an additional traffic lane, could ensure the construction performance of the wet joint concrete.

지분구조의 반복측정 자료에 대한 혼합모형 (A Mixed Model for Nested Structural Repeated Data)

  • 최재성
    • 응용통계연구
    • /
    • 제22권1호
    • /
    • pp.181-188
    • /
    • 2009
  • 본 논문은 실험단위들의 구조적 특성으로 지분관계를 갖는 실험을 행해야 하는 경우를 가정한다. 지분계획하에서 처리를 구성하는 요인으로 반복측정 요인을 고려한다. 반복측정 요인의 수준들이 비확률화에 의해 지분구조의 실험단위들에 배정될 때, 비확률화에 따른 실험의 특성을 감안한 모형으로 복합대칭의 공분산 구조하에서 혼합효과 모형을 논의하고 있다. 처리의 일부 요인들이 시간 또는 공간상의 제약으로 인해 지분구조의 실험단위들에 임의적으로 배정될 수 없을 때, 지분구조의 실험단위들에 대한 반응 값들은 어떤 구조적 상관관계를 나타내는 값들로 관측될 수 있음을 예상할 수 있다. 자료의 구조적 상관성을 고려한 공분산 구조하의 선형모형으로 확률요인과 고정요인을 포함하는 혼합효과의 모형을 제시하고 모형내 미지모수들에 대한 추론방법을 다루고 있다.

사회네트워크분석에서 몬테칼로 방법의 활용 (Monte-Carlo Methods for Social Network Analysis)

  • 허명회;이용구
    • 응용통계연구
    • /
    • 제24권2호
    • /
    • pp.401-409
    • /
    • 2011
  • 사회네트워크분석(social network analysis)은 l개 연결선을 갖는 n개 노드의 자료를 대상으로 한다. 기본적인 자료기술로서 노드 간 최단거리(shortest distance), 근접 중심성(closeness centrality), 중개 중심성(betweenness centrality) 등을 산출한다. 기존의 사회학적 연구에서 다룬 네트워크는 대개 노드 수 n이 수십 또는 수백 정도였으나 최근에는 그 크기가 수십만 또는 수백만에 이르는 경우가 드물지 않다. 이에 따라 사회네트워크분석에서도 자료 규모성(data scalability)의 이슈가 생겼다. 본 연구에서는 몬테칼로(Monte Carlo) 방법을 활용하여 n = 100,000 규모의 임의 네트워크의 작은 세상(small world) 성질을 실증적으로 탐구하고 그 정도 규모에서의 중개 중심성과 근접 중심성의 산출 방법을 제안하고자 한다.

농촌청소년의 여가활동 활성화방안 (Rural Youth's Leisure Activity and Measures for Activation)

  • 최창욱;이채식
    • 농촌지도와개발
    • /
    • 제11권1호
    • /
    • pp.95-110
    • /
    • 2004
  • The purposes of this study were to analyze rural youth's leisure activity and to suggest measures for activation. This study was conducted by review of literature and questionnaire, The data was collected from 1,209 stratified cluster random sampled rural youth who are in middle school and high school. To analyze the data, SPSS/WIN program was employed. The major finding of the study were as follows: 1) About 30% of rural youths had less than 1-2 hours for leisure activity in daily life and more than 8 hours for leisure activity during the weekend, and over 40% of rural youths had no plan for leisure activity. 1) They recognized that leisure activity made them enjoy common life, decrease their stress, and get new experience far self-development, 3) participation in sports, organized-activity and self-directed activity of the middle schools youths were higher compare to youths in high schools, 4) to activate leisure life, rural youths expected to get a) direct support for participating leisure activity expenses(27%), b) develop and diffusion of diverse and interesting leisure programs(23%), and c) securing appropriate leisure facilities(22%).

  • PDF

식후저혈압 위험 노인의 식전 물 섭취가 식후 혈압변화에 미치는 효과 (Effect of Water Drinking on the Postprandial Fall of Blood Pressure in the Elderly)

  • 손정태;이은주
    • 기본간호학회지
    • /
    • 제17권3호
    • /
    • pp.304-313
    • /
    • 2010
  • Purpose: The purpose of this study was to examine preventive effects of water drinking on postprandial fall of blood pressure in the elderly. Method: Participants were 25 elders who had experienced postprandial fall of systolic blood pressure of more than 15mmHg in a previous study. Within subject repeated measures design using random order allocation was used to control extraneous variables among participants. During the experiment, each participant had to drink 400mL water before lunch, whereas when in the control, they only had their lunch. Blood pressure and heart rate were measured for both times before lunch and at 15 minutes intervals up to 90 minutes after lunch. Data were analyzed using descriptive statistics, repeated measures of ANOVA, paired t-test and Bonferroni adjustment as Post-hoc analysis. Results: Water drinking before lunch elicited significant pressor effects by increasing systolic and diastolic pressure $13.9{\pm}4.7/5.2{\pm}2.2mmHg$ compared blood pressure during the control p<.005, p<.022. Heart rate, however, did not change significantly at either time. Conclusion: Drinking water before meal is recommended for elders who experience postprandial hypotension. However, the appropriate volume of water to prevent postprandial fall in blood pressure should be further studied.

Correlation of single leg vertical jump, single leg hop, and single leg squat distances in healthy persons

  • Shin, Seung-Ho;Woo, Hyunjae
    • Physical Therapy Rehabilitation Science
    • /
    • 제2권1호
    • /
    • pp.57-61
    • /
    • 2013
  • Objective: To determine the correlation among three functional tests: single leg vertical jump (SLVJ), single leg hop for distance (SLHD), and single leg squat (SLSQ). Design: Cross sectional study. Methods: Twenty healthy men (n=10) and women (n=10) with no history of lower extremity dysfucntion participated in this study and performed in university research laboratory. The procedures consisted of a general warm-up, a task-specific warm-up, actual testing, and a cool down. All participants performed the three tests in random order. Each test was performed three times for the dominant and non-dominant lower extremity (LE). SLVJ, SLHD, SLSQ were measured using a standard tape measure. Results: Statistically significant difference was presented between dominant LE and non-dominant LE in each function test (p<0.05). The strongest correlation was between SLVJ and SLSQ, 0.939 and 0.883 for dominant and non-dominant LE, respectively (p<0.05). The weakest correlation was between SLVJ and SLHD, 0.713 for dominant (p<0.05) and between SLSQ and SLHD, 0.739 for non-dominant (p<0.05). Conclusions: There is a strong correlation between SLVJ and SLSQ, suggesting that each test measures similar constructs of function and can be substitutive, while weak correlation between SLSQ and SLHD suggest these two tests do not measure the same functional components and could be paired as outcome measures for the clinical assessment of LE function. It will provide physical therapist with scientific evidence for effective test combination of LE function assessment in clinical practice.

  • PDF

An Investigation of Family Entrepreneurship in Ownership and Firm Performance: Empirical Evidence from Pakistan

  • KHAN, Muddasir Riaz;TARIQ, Yasir Bin
    • The Journal of Asian Finance, Economics and Business
    • /
    • 제9권5호
    • /
    • pp.63-73
    • /
    • 2022
  • In today's financial economics literature, the impact of innovative family ownership and management on firm performance is a prominent concern. In this study, the existence of family firms in the listed sector of Pakistan's economy is investigated. The objective of this study is to examine the performance-oriented relationship of family ownership and active involvement of family member at the CEO position. The theoretical perspectives that underpin this research are agency and stewardship. This analysis used a sample of 315 publicly traded companies from 2009 to 2019. The study's primary independent variables include family influence on ownership and family CEO. Financial performance is the dependent variable that is divided into accounting and market measures. The proxy for accounting measure is return on asset and proxy for market measure is Tobin's Q. This study employs univariate and balanced panel data analysis. For robustness of the analysis random-effects GLS regression is carried out. The empirical results show that that Family Firms outperform Non-Family Firms both in terms of accounting and market measures. In the later part family CEOs firms outperform the firms that have either insider or outsider non-family CEOs. This superior performance is subjected to the positive and statistically significant association between family ownership, management, and financial performance.