• Title/Summary/Keyword: Coverage index

Search Result 288, Processing Time 0.027 seconds

Interpretability Comparison of Popular Decision Tree Algorithms (대표적인 의사결정나무 알고리즘의 해석력 비교)

  • Hong, Jung-Sik;Hwang, Geun-Seong
    • Journal of Korean Society of Industrial and Systems Engineering
    • /
    • v.44 no.2
    • /
    • pp.15-23
    • /
    • 2021
  • Most of the open-source decision tree algorithms are based on three splitting criteria (Entropy, Gini Index, and Gain Ratio). Therefore, the advantages and disadvantages of these three popular algorithms need to be studied more thoroughly. Comparisons of the three algorithms were mainly performed with respect to the predictive performance. In this work, we conducted a comparative experiment on the splitting criteria of three decision trees, focusing on their interpretability. Depth, homogeneity, coverage, lift, and stability were used as indicators for measuring interpretability. To measure the stability of decision trees, we present a measure of the stability of the root node and the stability of the dominating rules based on a measure of the similarity of trees. Based on 10 data collected from UCI and Kaggle, we compare the interpretability of DT (Decision Tree) algorithms based on three splitting criteria. The results show that the GR (Gain Ratio) branch-based DT algorithm performs well in terms of lift and homogeneity, while the GINI (Gini Index) and ENT (Entropy) branch-based DT algorithms performs well in terms of coverage. With respect to stability, considering both the similarity of the dominating rule or the similarity of the root node, the DT algorithm according to the ENT splitting criterion shows the best results.

National perioperative outcomes of flap coverage for pressure ulcers from 2005 to 2015 using American College of Surgeons National Surgical Quality Improvement Program

  • Tran, Bao Ngoc N.;Chen, Austin D.;Kamali, Parisa;Singhal, Dhruv;Lee, Bernard T.;Fukudome, Eugene Y.
    • Archives of Plastic Surgery
    • /
    • v.45 no.5
    • /
    • pp.418-424
    • /
    • 2018
  • Background Complication rates after flap coverage for pressure ulcers have been high historically. These patients have multiple risk factors associated with poor wound healing and complications including marginal nutritional status, prolonged immobilization, and a high comorbidities index. This study utilizes the National Surgical Quality Improvement Program (NSQIP) to examine perioperative outcomes of flap coverage for pressure ulcers. Methods Data from the NSQIP database (2005-2015) for patient undergoing flap coverage for pressure ulcers was identified. Demographic, perioperative information, and complications were reviewed. One-way analysis of variance and Pearson chi-square were used to assess differences for continuous variables and nominal variables, respectively. Multivariate logistic regression was performed to identify independent risk factors for complications. Results There were 755 cases identified: 365 (48.3%) sacral ulcers, 321 (42.5%) ischial ulcers, and 69 (9.1%) trochanteric ulcers. Most patients were older male, with some degree of dependency, neurosensory impairment, high functional comorbidities score, and American Society of Anesthesiologists class 3 or above. The sacral ulcer group had the highest incidence of septic shock and bleeding, while the trochanteric ulcer group had the highest incidence of superficial surgical site infection. There was an overall complication rate of 25% at 30-day follow-up. There was no statistical difference in overall complication among groups. Total operating time, diabetes, and non-elective case were independent risk factors for overall complications. Conclusions Despite patients with poor baseline functional status, flap coverage for pressure ulcer patients is safe with acceptable postoperative complications. This type of treatment should be considered for properly selected patients.

The Impacts of the COVID-19 Pandemic on the Movement of Composite Stock Price Index in Indonesia

  • ZAINURI, Zainuri;VIPHINDRARTIN, Sebastiana;WILANTARI, Regina Niken
    • The Journal of Asian Finance, Economics and Business
    • /
    • v.8 no.3
    • /
    • pp.1113-1119
    • /
    • 2021
  • This study aims to determine the impact of the news coverage of the COVID-19 pandemic on the composite stocks' movement (IHSG) in Indonesia. This study used secondary data of daily time series with an observation range of March 2020-June 2020. This study used three main variables, namely, COVID-19 news, the daily price of a composite stock market index (IHSG), and interest rate. This study clarifies pandemic news into two forms to facilitate quantitative analysis, namely, good news and bad news. Both pandemic news conditions, which have been clarified, are then processed into the index and reprocessed along with two other variables using vector autoregressive (VAR). The results showed that the good news have a dominant effect on developing the composite stock price index (IHSG) in Indonesia during the COVID-19 pandemic. Although the good news dominates the composite stock price index (IHSG) movement in Indonesia, the bad news must also be anticipated. By implementing a series of macroeconomic policies that follow the conditions of the composite stock price index (IHSG) movements on the stock exchange floor, the bad news response can decrease the potential for a decline in investor confidence, so that the financial system's macroeconomic stability is maintained.

Normalized Cross-Correlations of Solar Cycle and Physical Characteristics of Cloud

  • Chang, Heon-Young
    • Journal of Astronomy and Space Sciences
    • /
    • v.36 no.4
    • /
    • pp.225-234
    • /
    • 2019
  • We explore the associations between the total sunspot area, solar north-south asymmetry, and Southern Oscillation Index and the physical characteristics of clouds by calculating normalized cross-correlations, motivated by the idea that the galactic cosmic ray influx modulated by solar activity may cause changes in cloud coverage, and in turn the Earth's climate. Unlike previous studies based on the relative difference, we have employed cloud data as a whole time-series without detrending. We found that the coverage of high-level and low-level cloud is at a maximum when the solar north-south asymmetry is close to the minimum, and one or two years after the solar north-south asymmetry is at a maximum, respectively. The global surface air temperature is at a maximum five years after the solar north-south asymmetry is at a maximum, and the optical depth is at a minimum when the solar north-south asymmetry is at a maximum. We also found that during the descending period of solar activity, the coverage of low-level cloud is at a maximum, and global surface air temperature and cloud optical depth are at a minimum, and that the total column water vapor is at a maximum one or two years after the solar maximum.

Humidity Variation by Green Space Calculation Method (녹지의 산출방법이 습도변화에 미치는 영향)

  • Yoon, Yong-Han;Park, Heon
    • Asian Journal of Turfgrass Science
    • /
    • v.16 no.1
    • /
    • pp.41-47
    • /
    • 2002
  • For this study grasp quantitative humidity variation with planting stratification to various green space of calculation method, observed humidity distribution in the green space. with this data, coverage condition and humidity distribution, planting calculation method and humidity, planting stratification calculation method and humidity, analyzed by revolution analysis. In this result, as well as coverage condition, planting stratification effect humidity variation. increasing planting ratio (area) and planting volume (capacity) effect higher humidity. especially, if we compared between planting stratification calculation method and higher humidity, effect by a revolution coefficient and a correlation coefficient, effect relatively planting volume (capacity) higher than stratification ratio (area). today, in the index of higher humidity, planting calculation propose application of capacity method.

Correlation between the Trend toward Higher Temperature and Land Cover Structure in Haeundae District of Busan in Summer (부산시 해운대구의 하기 도시 고온화 현상과 토지피복 구성과의 상관관계)

  • Yoon, Seong-Hwan;Kim, Seong-Ha
    • Journal of the Korean Solar Energy Society
    • /
    • v.28 no.2
    • /
    • pp.19-27
    • /
    • 2008
  • This study aims at examining the correlation between air temperature and urban structure such as land cover. For this, it measured summer air temperature by using data log type thermometer installed the inside of instrument screen, in the 9 points of elementary school in Haeundae, Busan. The accomplished results of this study are followings. 1) As altitude goes up 100m, air temperature drops to $0.6{\sim}1.0^{\circ}C$. 2) As building coverage ratio increases 10%, air temperature increases $0.3{\sim}0.4^{\circ}C$. 3) As floor space index increases 100%, air temperature increases $0.4{\sim}0.5^{\circ}C$. 4) As artificial coverage ratio increases 10%, air temperature increases $0.1{\sim}0.2^{\circ}C$. 5) As natural coverage ratio increases 10%, air temperature decreases $0.1{\sim}0.2^{\circ}C$.

Status, Protection, and Management of Bird Community in Mt. Nam Area (남산 지역 조류 군집의 서식 현황과 보호 및 관리방안)

  • 이우신;조기현;임신재
    • The Korean Journal of Ecology
    • /
    • v.21 no.5_3
    • /
    • pp.665-673
    • /
    • 1998
  • This study was conducted to clarified the relationship between bird community and forest structure and present the counterplan for protection and management of bird community from February 1993 to July 1995 at deciduous and coniferous forest within Mt. Nam area, Seoul, Korea. DBH distribution has not significant differences in each study site. Deciduous forest had more foliage coverage in all layers than coniferous forest. Total 41 species of birds, which were 16 species of resident, 14 species of summer visitor, 4 species of winter visitor, and 7 species of passage migrant were recrded in two study sites. Leaf use rate of birds was increased the increase of coverage. The number of breeding species and pairs, breeding density, and diversity index were greater in deciduous forest than coniferous forest. The number of species and pairs on bush-nesting and foraging guild were greater than other guilds. And the nuber of species and pairs on hole nesting guild were the fewest in nesting guild. Use rate of artificial nests for improvement of habitat quality was greater in coniferous forest than deciduous forest. Maintenance of bush layer, increase of coverage and leaf layer diversity, supply of artificial nests, management of large trees, and control of natural enemy were necessary for protection and management of bird community in Mt. nam area.

  • PDF

Spatial Frequency Coverage and Image Reconstruction for Photonic Integrated Interferometric Imaging System

  • Zhang, Wang;Ma, Hongliu;Huang, Kang
    • Current Optics and Photonics
    • /
    • v.5 no.6
    • /
    • pp.606-616
    • /
    • 2021
  • A photonic integrated interferometric imaging system possesses the characteristics of small-scale, low weight, low power consumption, and better image quality. It has potential application for replacing conventional large space telescopes. In this paper, the principle of photonic integrated interferometric imaging is investigated. A novel lenslet array arrangement and lenslet pairing approach are proposed, which are helpful in improving spatial frequency coverage. For the novel lenslet array arrangement, two short interference arms were evenly distributed between two adjacent long interference arms. Each lenslet in the array would be paired twice through the novel lenslet pairing approach. Moreover, the image reconstruction model for optical interferometric imaging based on compressed sensing was established. Image simulation results show that the peak signal to noise ratio (PSNR) of the reconstructed image based on compressive sensing is about 10 dB higher than that of the direct restored image. Meanwhile, the normalized mean square error (NMSE) of the direct restored image is approximately 0.38 higher than that of the reconstructed image. Structural similarity index measure (SSIM) of the reconstructed image based on compressed sensing is about 0.33 higher than that of the direct restored image. The increased spatial frequency coverage and image reconstruction approach jointly contribute to better image quality of the photonic integrated interferometric imaging system.

Derivation of Green Coverage Ratio Based on Deep Learning Using MAV and UAV Aerial Images (유·무인 항공영상을 이용한 심층학습 기반 녹피율 산정)

  • Han, Seungyeon;Lee, Impyeong
    • Korean Journal of Remote Sensing
    • /
    • v.37 no.6_1
    • /
    • pp.1757-1766
    • /
    • 2021
  • The green coverage ratio is the ratio of the land area to green coverage area, and it is used as a practical urban greening index. The green coverage ratio is calculated based on the land cover map, but low spatial resolution and inconsistent production cycle of land cover map make it difficult to calculate the correct green coverage area and analyze the precise green coverage. Therefore, this study proposes a new method to calculate green coverage area using aerial images and deep neural networks. Green coverage ratio can be quickly calculated using manned aerial images acquired by local governments, but precise analysis is difficult because components of image such as acquisition date, resolution, and sensors cannot be selected and modified. This limitation can be supplemented by using an unmanned aerial vehicle that can mount various sensors and acquire high-resolution images due to low-altitude flight. In this study, we proposed a method to calculate green coverage ratio from manned or unmanned aerial images, and experimentally verified the proposed method. Aerial images enable precise analysis by high resolution and relatively constant cycles, and deep learning can automatically detect green coverage area in aerial images. Local governments acquire manned aerial images for various purposes every year and we can utilize them to calculate green coverage ratio quickly. However, acquired manned aerial images may be difficult to accurately analyze because details such as acquisition date, resolution, and sensors cannot be selected. These limitations can be supplemented by using unmanned aerial vehicles that can mount various sensors and acquire high-resolution images due to low-altitude flight. Accordingly, the green coverage ratio was calculated from the two aerial images, and as a result, it could be calculated with high accuracy from all green types. However, the green coverage ratio calculated from manned aerial images had limitations in complex environments. The unmanned aerial images used to compensate for this were able to calculate a high accuracy of green coverage ratio even in complex environments, and more precise green area detection was possible through additional band images. In the future, it is expected that the rust rate can be calculated effectively by using the newly acquired unmanned aerial imagery supplementary to the existing manned aerial imagery.

Complete Coverage Path Planning for Multi-Robots (멀티로봇에 대한 전체영역 경로계획)

  • Nam, Sang-Hyun;Shin, Ik-Sang;Kim, Jae-Jun;Lee, Soon-Geul
    • Journal of the Korean Society for Precision Engineering
    • /
    • v.26 no.7
    • /
    • pp.73-80
    • /
    • 2009
  • This paper describes a path planning algorithm, which is the minimal turning path based on the shape and size of the cell to clean up the whole area with two cleaning robots. Our method divides the whole cleaning area with each cell by cellular decomposition, and then provides some path plans among of the robots to reduce the rate of energy consumption and cleaning time of it. In addition we suggest how to plan between the robots especially when they are cleaning in the same cell. Finally simulation results demonstrate the effectiveness of the algorithm in an unknown area with multiple robots. And then we compare the performance index of two algorithms such as total of turn, total of time.