scholarly journals Spatial Dynamics of Invasive Para Grass on a Monsoonal Floodplain, Kakadu National Park, Northern Australia

2019 ◽  
Vol 11 (18) ◽  
pp. 2090
Author(s):  
Boyden ◽  
Wurm ◽  
Joyce ◽  
Boggs
Keyword(s):  
Satellite Imagery ◽  
Wild Rice ◽  
National Park ◽  
Fire History ◽  
Spatial Dynamics ◽  
Gradient Boosting ◽  
Native Vegetation ◽  
Northern Australia ◽  
Stochastic Gradient Boosting ◽  
The World

African para grass (Urochloa mutica) is an invasive weed that has become prevalent across many important freshwater wetlands of the world. In northern Australia, including the World Heritage landscape of Kakadu National Park (KNP), its dense cover can displace ecologically, genetically and culturally significant species, such as the Australian native rice (Oryza spp.). In regions under management for biodiversity conservation para grass is often beyond eradication. However, its targeted control is also necessary to manage and preserve site-specific wetland values. This requires an understanding of para grass spread-patterns and its potential impacts on valuable native vegetation. We apply a multi-scale approach to examine the spatial dynamics and impact of para grass cover across a 181 km2 floodplain of KNP. First, we measure the overall displacement of different native vegetation communities across the floodplain from 1986 to 2006. Using high spatial resolution satellite imagery in conjunction with historical aerial-photo mapping, we then measure finer-scale, inter-annual, changes between successive dry seasons from 1990 to 2010 (for a 48 km2 focus area); Para grass presence-absence maps from satellite imagery (2002 to 2010) were produced with an object-based machine-learning approach (stochastic gradient boosting). Changes, over time, in mapped para grass areas were then related to maps of depth-habitat and inter-annual fire histories. Para grass invasion and establishment patterns varied greatly in time and space. Wild rice communities were the most frequently invaded, but the establishment and persistence of para grass fluctuated greatly between years, even within previously invaded communities. However, these different patterns were also shown to vary with different depth-habitat and recent fire history. These dynamics have not been previously documented and this understanding presents opportunities for intensive para grass management in areas of high conservation value, such as those occupied by wild rice.

scholarly journals Computational Intelligence-Based Model for Mortality Rate Prediction in COVID-19 Patients

2021 ◽  
Vol 18 (12) ◽  
pp. 6429
Author(s):  
Irfan Ullah Khan ◽  
Nida Aslam ◽  
Malak Aljabri ◽  
Sumayh S. Aljameel ◽  
Mariam Moataz Aly Kamaleldin ◽  
...  
Keyword(s):  
Mortality Rate ◽  
Computational Intelligence ◽  
Nearest Neighbor ◽  
Gradient Boosting ◽  
K Nearest Neighbor ◽  
Detection And Identification ◽  
Proposed Model ◽  
Extreme Gradient Boosting ◽  
The World ◽  
Detection And Diagnosis

The COVID-19 outbreak is currently one of the biggest challenges facing countries around the world. Millions of people have lost their lives due to COVID-19. Therefore, the accurate early detection and identification of severe COVID-19 cases can reduce the mortality rate and the likelihood of further complications. Machine Learning (ML) and Deep Learning (DL) models have been shown to be effective in the detection and diagnosis of several diseases, including COVID-19. This study used ML algorithms, such as Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and K-Nearest Neighbor (KNN) and DL model (containing six layers with ReLU and output layer with sigmoid activation), to predict the mortality rate in COVID-19 cases. Models were trained using confirmed COVID-19 patients from 146 countries. Comparative analysis was performed among ML and DL models using a reduced feature set. The best results were achieved using the proposed DL model, with an accuracy of 0.97. Experimental results reveal the significance of the proposed model over the baseline study in the literature with the reduced feature set.

scholarly journals Structure, Diversity, and Environmental Determinants of High-Latitude Threatened Conifer Forests

Forests ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 775
Author(s):  
Carlos Esse ◽  
Francisco Correa-Araneda ◽  
Cristian Acuña ◽  
Rodrigo Santander-Massa ◽  
Patricio De Los Ríos-Escalante ◽  
...  
Keyword(s):  
Water Table ◽  
Environmental Variables ◽  
National Park ◽  
High Water ◽  
Forest Communities ◽  
Competitive Effect ◽  
Forest Patches ◽  
Last Glaciation ◽  
The World ◽  
Local Topography

Pilgerodendron uviferum (D. Don) Florin is an endemic, threatened conifer that grows in South America. In the sub-Antarctic territory, one of the most isolated places in the world, some forest patches remain untouched since the last glaciation. In this study, we analyze the tree structure and tree diversity and characterize the environmental conditions where P. uviferum-dominated stands develop within the Magellanic islands in Kawésqar National Park, Chile. An environmental matrix using the databases WorldClim and SoilGrids and local topography variables was used to identify the main environmental variables that explain the P. uviferum-dominated stands. PCA was used to reduce the environmental variables, and PERMANOVA and nMDS were used to evaluate differences among forest communities. The results show that two forest communities are present within the Magellanic islands. Both forest communities share the fact that they can persist over time due to the high water table that limits the competitive effect from other tree species less tolerant to high soil water table and organic matter. Our results contribute to knowledge of the species’ environmental preference and design conservation programs.

scholarly journals Development and validation of an early warning tool for sepsis and decompensation in children during emergency department triage

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Louis Ehwerhemuepha ◽  
Theodore Heyming ◽  
Rachel Marano ◽  
Mary Jane Piroutek ◽  
Antonio C. Arrieta ◽  
...  
Keyword(s):  
Emergency Department ◽  
Severe Sepsis ◽  
Early Warning ◽  
Characteristic Curve ◽  
Vital Signs ◽  
Warning System ◽  
Receiver Operator Characteristic Curve ◽  
Warning Signs ◽  
Gradient Boosting ◽  
Stochastic Gradient Boosting

AbstractThis study was designed to develop and validate an early warning system for sepsis based on a predictive model of critical decompensation. Data from the electronic medical records for 537,837 visits to a pediatric Emergency Department (ED) from March 2013 to December 2019 were collected. A multiclass stochastic gradient boosting model was built to identify early warning signs associated with death, severe sepsis, non-severe sepsis, and bacteremia. Model features included triage vital signs, previous diagnoses, medications, and healthcare utilizations within 6 months of the index ED visit. There were 483 patients who had severe sepsis and/or died, 1102 had non-severe sepsis, 1103 had positive bacteremia tests, and the remaining had none of the events. The most important predictors were age, heart rate, length of stay of previous hospitalizations, temperature, systolic blood pressure, and prior sepsis. The one-versus-all area under the receiver operator characteristic curve (AUROC) were 0.979 (0.967, 0.991), 0.990 (0.985, 0.995), 0.976 (0.972, 0.981), and 0.968 (0.962, 0.974) for death, severe sepsis, non-severe sepsis, and bacteremia without sepsis respectively. The multi-class macro average AUROC and area under the precision recall curve were 0.977 and 0.316 respectively. The study findings were used to develop an automated early warning decision tool for sepsis. Implementation of this model in pediatric EDs will allow sepsis-related critical decompensation to be predicted accurately after a few seconds of triage.

scholarly journals Methodology and Models for Individuals’ Creditworthiness Management Using Digital Footprint Data and Machine Learning Methods

Mathematics ◽  
2021 ◽  
Vol 9 (15) ◽  
pp. 1820
Author(s):  
Ekaterina V. Orlova
Keyword(s):  
Interest Rates ◽  
Additional Data ◽  
Risk Level ◽  
Gradient Boosting ◽  
Cluster Number ◽  
New Approach ◽  
Credit Risks ◽  
Stochastic Gradient Boosting ◽  
The Stability ◽  
Digital Footprints

This research deals with the challenge of reducing banks’ credit risks associated with the insolvency of borrowing individuals. To solve this challenge, we propose a new approach, methodology and models for assessing individual creditworthiness, with additional data about borrowers’ digital footprints to implement comprehensive analysis and prediction of a borrower’s credit profile. We suggest a model for borrowers’ clustering based on the method of hierarchical clustering and the k-means method, which groups actual borrowers having similar creditworthiness and similar credit risks into homogeneous clusters. We also design the model for borrowers’ classification based on the stochastic gradient boosting (SGB) method, which reliably determines the cluster number and therefore the risk level for a new borrower. The developed models are the basis for decision making regarding the decision about lending value, interest rates and lending terms for each risk-homogeneous borrower’s group. The modified version of the methodology for assessing individual creditworthiness is presented, which is to reduce the credit risks and to increase the stability and profitability of financial organizations.

scholarly journals Development of a Radar Reflector Kit for Older Adults to Use to Signal Their Location and Needs in a Large-Scale Earthquake Disaster

2021 ◽  
Vol 13 (10) ◽  
pp. 1883
Author(s):  
Yuma Morisaki ◽  
Makoto Fujiu ◽  
Ryoichi Furuta ◽  
Junichi Takayama
Keyword(s):  
Older Adults ◽  
Synthetic Aperture Radar ◽  
Satellite Imagery ◽  
Disaster Response ◽  
Large Scale ◽  
Synthetic Aperture ◽  
Earthquake Disaster ◽  
Large Numbers ◽  
The World ◽  
Vulnerable People

In Japan, older adults account for the highest proportion of the population of any country in the world. When large-scale earthquake disasters strike, large numbers of casualties are known to particularly occur among seniors. Many are physically or mentally vulnerable and require assistance during the different phases of disaster response, including rescue, evacuation, and living in an evacuation center. However, the growing number of older adults has made it difficult, after a disaster, to quickly gather information on their locations and assess their needs. The authors are developing a proposal to enable vulnerable people to signal their location and needs in the aftermath of a disaster to response teams by deploying radar reflectors that can be detected in synthetic aperture radar (SAR) satellite imagery. The purpose of this study was to develop a radar reflector kit that seniors could easily assemble in order to make this proposal feasible in practice. Three versions of the reflector were tested for detectability, and a sample of older adults was asked to assemble the kits and provide feedback regarding problems they encountered and regarding their interest in using the reflectors in the event of a large-scale disaster.

Fire regimes and vegetation sensitivity analysis: an example from Bradshaw Station, monsoonal northern Australia

2003 ◽  
Vol 12 (4) ◽  
pp. 349 ◽  
Author(s):  
Cameron Yates ◽  
Jeremy Russell-Smith
Keyword(s):  
Fire History ◽  
Fire Regime ◽  
Landscape Scale ◽  
Fire Season ◽  
Individual Species ◽  
Northern Australia ◽  
Sensitive Species ◽  
Obligate Seeder ◽  
Return Interval ◽  
Noaa Avhrr

The fire-prone savannas of northern Australia comprise a matrix of mostly fire-resilient vegetation types, with embedded fire-sensitive species and communities particularly in rugged sandstone habitats. This paper addresses the assessment of fire-sensitivity at the landscape scale, drawing on detailed fire history and vegetation data assembled for one large property of 9100�km2, Bradshaw Station in the Top End of the Northern Territory, Australia. We describe (1) the contemporary fire regime for Bradshaw Station for a 10 year period; (2) the distribution and status of 'fire sensitive' vegetation; and (3) an assessment of fire-sensitivity at the landscape scale. Fire-sensitive species (FSS) were defined as obligate seeder species with minimum maturation periods of at least 3 years. The recent fire history for Bradshaw Station was derived from the interpretation of fine resolution Landsat MSS and Landsat TM imagery, supplemented with mapping from coarse resolution NOAA-AVHRR imagery where cloud had obstructed the use of Landsat images late in the fire season (typically October–November). Validation assessments of fire mapping accuracy were conducted in 1998 and 1999. On average 40% of Bradshaw burnt annually with about half of this, 22%, occurring after August (Late Dry Season LDS), and 65% of the property burnt 4 or more times, over the 10 year period; 89% of Bradshaw Station had a minimum fire return interval of less than 3 years in the study period. The derived fire seasonality, frequency and return interval data were assessed with respect to landscape units (landsystems). The largest landsystem, Pinkerton (51%, mostly sandstone) was burnt 41% on average, with about 70% burnt four times or more, over the 10 year period. Assessment of the fire-sensitivity of individual species was undertaken with reference to data assembled for 345 vegetation plots, herbarium records, and an aerial survey of the distribution of the long-lived obligate-seeder tree species Callitris intratropica. A unique list of 1310 plant species was attributed with regenerative characteristics (i.e. habit, perenniality, resprouting capability, time to seed maturation). The great majority of FSS species were restricted to rugged sandstone landforms. The approach has wider application for assessing landscape fire-sensitivity and associated landscape health in savanna landscapes in northern Australia, and elsewhere.

Enhanced prediction of vulnerable Web components using Stochastic Gradient Boosting Trees

2019 ◽  
Vol 15 (2) ◽  
pp. 201-214 ◽  
Author(s):  
Mahmoud Elish
Keyword(s):  
Web Applications ◽  
Prediction Models ◽  
Stochastic Gradient ◽  
Gradient Boosting ◽  
Data Sets ◽  
Content Type ◽  
Stochastic Gradient Boosting ◽  
Security Inspection ◽  
Novel Model ◽  
Efficient Software

Purpose Effective and efficient software security inspection is crucial as the existence of vulnerabilities represents severe risks to software users. The purpose of this paper is to empirically evaluate the potential application of Stochastic Gradient Boosting Trees (SGBT) as a novel model for enhanced prediction of vulnerable Web components compared to common, popular and recent machine learning models. Design/methodology/approach An empirical study was conducted where the SGBT and 16 other prediction models have been trained, optimized and cross validated using vulnerability data sets from multiple versions of two open-source Web applications written in PHP. The prediction performance of these models have been evaluated and compared based on accuracy, precision, recall and F-measure. Findings The results indicate that the SGBT models offer improved prediction over the other 16 models and thus are more effective and reliable in predicting vulnerable Web components. Originality/value This paper proposed a novel application of SGBT for enhanced prediction of vulnerable Web components and showed its effectiveness.

Sign in / Sign up

Export Citation Format

Share Document