Classification of spruce beetle hazard in Lutz spruce (Picea × lutzii) stands on the Kenai Peninsula, Alaska

1994 ◽  
Vol 24 (5) ◽  
pp. 1015-1021 ◽  
Author(s):  
K.M. Reynolds ◽  
E.H. Holsten
Keyword(s):  
Decision Tree ◽  
Basal Area ◽  
Model Verification ◽  
Final Decision ◽  
Validation Data ◽  
Worst Case ◽  
Kenai Peninsula ◽  
Area Loss ◽  
Spruce Beetle ◽  
High Hazard

Stand data from Lutz spruce (Picea × lutzii Little) forest types occurring on the Kenai Peninsula were analyzed by tree-based classification to develop a decision tree for classifying spruce beetle (Dendroctonusrufipennis Kby.) hazard. Model development and validation data sets contained 100 and 34 stand observations, respectively. The final decision-tree structure yielded seven possible hazard outcomes based on total stand basal area, percentage of total basal area composed of spruce, percentage of spruce basal area composed of trees with diameter >25 cm, stand elevation, and stand aspect. Three paths in the decision tree led to low-hazard outcomes (spruce basal area loss ≤10%); one path led to a high-hazard outcome (spruce basal area loss >40%). No paths through the decision tree led to a medium-hazard outcome (spruce basal area loss >10%, but ≤40%), but three less precise outcomes of low–medium and medium–high hazard were considered useful and retained in the final model. Results of model verification were considered very acceptable; in the worst case, predictions of high hazard were correct for 73% of the observations. Model validation results were also considered very acceptable considering the small number of observations available for this phase of analysis.

Vulnerability of white spruce with slowly expanding lower boles on dry, cold sites to early seasonal attack by spruce beetles in south central Alaska

1987 ◽  
Vol 17 (5) ◽  
pp. 428-435 ◽  
Author(s):  
John S. Hard
Keyword(s):  
Radial Growth ◽  
Basal Area ◽  
White Spruce ◽  
Kenai Peninsula ◽  
Tree Expansion ◽  
South Central ◽  
Spruce Beetle ◽  
Area Growth ◽  
Before And After ◽  
Tree Radial Growth

Two stands of white spruce (Piceaglauca (Moench) Voss), one on a south aspect and one on a north aspect on the Kenai Peninsula of Alaska, were sampled intensively to determine site and host variables associated with high attack densities by spruce beetle, Dendroctonusrufipennis (Kirby). Attacks peaked during the early phase of tree radial growth on both aspects as the rate of tree expansion slowed. Generally, the first trees attacked, also the most heavily attacked, expanded more slowly before and after beetle attack than did trees attacked later or not at all. High attack densities were concentrated in trees on dry, cold soils. Mean percent basal-area growth of plots was inversely related to stocking of live spruce and to percentage of sample trees attacked and killed.

scholarly journals 174 A comparison of machine learning algorithms in the classification of beef steers finished in feedlot

2020 ◽  
Vol 98 (Supplement_4) ◽  
pp. 126-127
Author(s):  
Lucas S Lopes ◽  
Christine F Baes ◽  
Dan Tulpan ◽  
Luis Artur Loyola Chardulo ◽  
Otavio Machado Neto ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Final Decision ◽  
Relevant Parameter ◽  
Good Prediction ◽  
Quality Traits ◽  
C4.5 Decision Tree

Abstract The aim of this project is to compare some of the state-of-the-art machine learning algorithms on the classification of steers finished in feedlots based on performance, carcass and meat quality traits. The precise classification of animals allows for fast, real-time decision making in animal food industry, such as culling or retention of herd animals. Beef production presents high variability in its numerous carcass and beef quality traits. Machine learning algorithms and software provide an opportunity to evaluate the interactions between traits to better classify animals. Four different treatment levels of wet distiller’s grain were applied to 97 Angus-Nellore animals and used as features for the classification problem. The C4.5 decision tree, Naïve Bayes (NB), Random Forest (RF) and Multilayer Perceptron (MLP) Artificial Neural Network algorithms were used to predict and classify the animals based on recorded traits measurements, which include initial and final weights, sheer force and meat color. The top performing classifier was the C4.5 decision tree algorithm with a classification accuracy of 96.90%, while the RF, the MLP and NB classifiers had accuracies of 55.67%, 39.17% and 29.89% respectively. We observed that the final decision tree model constructed with C4.5 selected only the dry matter intake (DMI) feature as a differentiator. When DMI was removed, no other feature or combination of features was sufficiently strong to provide good prediction accuracies for any of the classifiers. We plan to investigate in a follow-up study on a significantly larger sample size, the reasons behind DMI being a more relevant parameter than the other measurements.

scholarly journals Brazilian Review of Finance 2015 Editorial Report

2016 ◽  
Vol 14 (1) ◽  
pp. 1
Author(s):  
Marcio Poletti Laurini
Keyword(s):  
Classification System ◽  
Acceptance Rate ◽  
Google Scholar ◽  
Final Decision ◽  
Editorial Process ◽  
Worst Case ◽  
Publication Schedule ◽  
Brazilian Publication

RBFin is the main Brazilian publication outlet of academic papers about finance. Using the Open Journals System to manage the editorial process, publication of RBFin adheres to a strict publication schedule. The journal is indexed by EconLit, RedALyC, Proquest, Google Scholar, Gale and Ebsco and is listed in the JEL, DOAJ, Latindex, OpenJGate, and Cabell’s directories. RBFin is rated B2 in the business and economics areas of the Brazilian classification system. The editorial board undergoes partial turnover every year and comprises 19 individuals from four countries, the Brazilian members being affiliated with universities in five different Brazilian states. The acceptance rate was 44\% for papers submitted in 2015. The average number of days between receipt and first decision for articles submitted in 2015 was 86. The average number of days between receipt and final decision for articles submitted in 2015 was 104. The worst case was 345 days. Thirty five individuals served as reviewers in 2015.

scholarly journals Satellite-Based Assessment of Grassland Conversion and Related Fire Disturbance in the Kenai Peninsula, Alaska

2019 ◽  
Vol 11 (3) ◽  
pp. 283 ◽  
Author(s):  
Katherine Hess ◽  
Cheila Cullen ◽  
Jeanette Cobian-Iñiguez ◽  
Jacob Ramthun ◽  
Victor Lenske ◽  
...  
Keyword(s):  
Land Cover ◽  
Land Cover Change ◽  
Landsat Imagery ◽  
Fire Danger ◽  
Fire Disturbance ◽  
Time Step ◽  
Kenai Peninsula ◽  
Spruce Beetle ◽  
Grassland Conversion ◽  
The Relationship

Spruce beetle-induced (Dendroctonus rufipennis (Kirby)) mortality on the Kenai Peninsula has been hypothesized by local ecologists to result in the conversion of forest to grassland and subsequent increased fire danger. This hypothesis stands in contrast to empirical studies in the continental US which suggested that beetle mortality has only a negligible effect on fire danger. In response, we conducted a study using Landsat data and modeling techniques to map land cover change in the Kenai Peninsula and to integrate change maps with other geospatial data to predictively map fire danger for the same region. We collected Landsat imagery to map land cover change at roughly five-year intervals following a severe, mid-1990s beetle infestation to the present. Land cover classification was performed at each time step and used to quantify grassland encroachment patterns over time. The maps of land cover change along with digital elevation models (DEMs), temperature, and historical fire data were used to map and assess wildfire danger across the study area. Results indicate the highest wildfire danger tended to occur in herbaceous and black spruce land cover types, suggesting that the relationship between spruce beetle damage and wildfire danger in costal Alaskan forested ecosystems differs from the relationship between the two in the forests of the coterminous United States. These change detection analyses and fire danger predictions provide the Kenai National Wildlife Refuge (KENWR) ecologists and other forest managers a better understanding of the extent and magnitude of grassland conversion and subsequent change in fire danger following the 1990s spruce beetle outbreak.

Crude Furnace Creep Assessment and High Temperature Degradation

2017 ◽  
Author(s):  
Gary Y. H. Lee ◽  
Ohgeon Kwon ◽  
Zuwairi Ramli ◽  
Zaki Mohamad Afifi
Keyword(s):  
High Temperature ◽  
Decision Tree ◽  
Degradation Mechanism ◽  
Surface Hardness ◽  
Furnace Operation ◽  
Outer Diameter ◽  
Final Decision ◽  
High Temperature Properties ◽  
Current Limit ◽  
Life Fraction

Creep calculations indicate a crude furnace radiant section carbon steel tubes exceeding their life fraction due to flame impingement reaching up to 700°C for a year. The ambiguity of the temperature and material data means the life fraction of creep calculations were based on limited inspection data and infra-red scanning giving a conservative indication of end of life. Due to unavailable tubes in stock, a planned pit stop cannot be arranged due to economic and safety reasons as the furnace may not be started back up safely. To safeguard the integrity of the furnace until the planned outage, the temperature on the furnace tube was stabilized to a current limit of 540°C through improvements in burner operations. The crude diet was also maintained within the crude acceptance envelope. Visual checks at every shift were done to ensure no observation from tube bulging or uneven flame pattern. A decision tree was created to facilitate quick decision making using a go/no go criteria of which tubes to replace during the August 2015 planned turnaround. The criteria set for the decision tree required tube wall thickness, surface hardness test, tube outer diameter ring gauge to be examined. Failing any of the criteria will require the tube to be replaced. The replaced tubes (one worst and one representative) will also be lab tested through destructive examination to identify the degradation mechanism and high temperature properties of the worst tubes to quantitatively define the high temperature properties and life fraction of the tubes that are left in the furnace. The lab test will provide results after a year of creep testing and can give assurance of continued furnace operation for 4 more years until the next outage. The final decision after the examination based on the decision tree was made required 17 tubes to be replaced in this turnaround. The worst degraded tubes were found to be at the vicinity of the initial observed location around the flame impingement zone.

scholarly journals Correlation based splitting criterionin multi branch decision tree

2011 ◽  
Vol 1 (2) ◽  
Author(s):  
Nima Salehi-Moghaddami ◽  
Hadi Yazdi ◽  
Hanieh Poostchi
Keyword(s):  
Decision Tree ◽  
Support Vector ◽  
Final Decision ◽  
Forward Selection ◽  
Splitting Criterion ◽  
Target Values ◽  
Future Data ◽  
Absolute Correlation ◽  
Concept Of Information

AbstractOne of the most commonly used predictive models in classification is the decision tree (DT). The task of a DT is to map observations to target values. In the DT, each branch represents a rule. A rule’s consequent is the leaf of the branch and its antecedent is the conjunction of the features. Most applied algorithms in this field use the concept of Information Entropy and Gini Index as the splitting criterion when building a tree. In this paper, a new splitting criterion to build DTs is proposed. A splitting criterion specifies the tree’s best splitting variable as well as the variable’s threshold for further splitting. Using the idea from classical Forward Selection method and its enhanced versions, the variable having the largest absolute correlation with the target value is chosen as the best splitting variable at each node. Then, the idea of maximizing the margin between classes in a support vector machine (SVM) is used to find the best classification threshold on the selected variable. This procedure will execute recursively at each node, until reaching the leaf nodes. The final decision tree has a shorter height than previous methods, which effectively reduces useless variables and the time needed for classification of future data. Unclassified regions are also generated under the proposed method, which can be interpreted as an advantage or disadvantage. The simulation results demonstrate an improvement in the generated decision tree compared to previous methods.

White spruce regeneration following a major spruce beetle outbreak in forests on the Kenai Peninsula, Alaska

2008 ◽  
Vol 255 (10) ◽  
pp. 3571-3579 ◽  
Author(s):  
Keith Boggs ◽  
Michelle Sturdy ◽  
Daniel J. Rinella ◽  
Matthew J. Rinella
Keyword(s):  
White Spruce ◽  
Kenai Peninsula ◽  
Spruce Beetle

scholarly journals Equine Simplified Acute Physiology Score (EqSAPS): personalized medicine for the equine emergency patient

2020 ◽  
Author(s):  
Aline Barros ◽  
Ana Flavia Rocha da Silva ◽  
Miriam Zibordi ◽  
Julio David Spagnolo ◽  
Rodrigo Romero Corrêa ◽  
...  
Keyword(s):  
Decision Tree ◽  
Data Extraction ◽  
Characteristic Curve ◽  
Simplified Acute Physiology Score ◽  
Acute Physiology Score ◽  
Final Decision ◽  
Human Patient ◽  
Disease Evolution ◽  
Saps 3 ◽  
Probability Of Death

Scoring models are useful tools that guide the attending clinician in gauging the severity of disease evolution, and in evaluating the efficacy of treatment. There are few tools available with this purpose for the non-human patient, including horses. We aimed (i) to adapt the Simplified Acute Physiology Score 3 (SAPS-3) model for the equine species, reaching a margin of accuracy greater than 75% in the calculation of the probability of death, and (ii) to build a decision tree that helps the attending veterinarian in assessment of the clinical evolution of the equine patient. From an initial pool of 5 568 medical records from University-based Veterinary Hospitals, a final cohort of 1 000 was further mined manually for data extraction. A set of 19 variables were evaluated and tested by five data mining algorithms. The final scoring model, named EqSAPS for Equine Simplified Acute Physiology Score, reached 91.83% of correct estimates for probability of death within 24 hours upon hospitalization. The Area Under Receiver Operating Characteristic Curve (AUROC) for outcome “death” was 0.742, while for “survival” was 0.652. The final decision tree was able to refine prognosis of patients whose EqSAPS score suggested “death”. EqSAPS is an useful tool to gauge the severity of the clinical presentation of the equine patient.

scholarly journals Prediction of Disposition within 48-hours of Hospital Admission Using Patient Mobility Scores

2019 ◽  
Vol 15 (9) ◽  
pp. 540-543 ◽  
Author(s):  
Daniel L Young ◽  
Elizabeth Colantuoni ◽  
Lisa Aronson Friedman ◽  
Jason Seltzer ◽  
Kelly Daley ◽  
...  
Keyword(s):  
Decision Tree ◽  
Hospital Admission ◽  
Discharge Planning ◽  
Classification Tree ◽  
Care Facility ◽  
Predictive Ability ◽  
Early Discharge ◽  
Final Decision ◽  
Patient Mobility ◽  
Machine Learning Classification

Delayed hospital discharges for patients needing rehabilitation in a postacute setting can exacerbate hospital-acquired mobility loss, prolong functional recovery, and increase costs. Systematic measurement of patient mobility by nurses early during hospitalization has the potential to help identify which patients are likely to be discharged to a postacute care facility versus home. To test the predictive ability of this approach, a machine learning classification tree method was applied retrospectively to a diverse sample of hospitalized patients (N = 805) using training and validation sets. Compared with patients discharged to home, patients discharged to a postacute facility were older (median, 64 vs 56 years old) and had lower mobility scores at hospital admission (median, 32 vs 41). The final decision tree accurately classified the discharge location for 73% (95%CI:67%-78%) of patients. This study emphasizes the value of systematically measuring mobility in the hospital and provides a simple decision tree to facilitate early discharge planning.

Sign in / Sign up

Export Citation Format

Share Document