scholarly journals Increasing adoption rates at animal shelters: a two-phase approach to predict length of stay and optimal shelter allocation

2021 ◽  
Vol 17 (1) ◽  
Author(s):  
Janae Bradley ◽  
Suchithra Rajendran
Keyword(s):  
Length Of Stay ◽  
Performance Metrics ◽  
Gradient Boosting ◽  
Compromise Solution ◽  
Two Phase ◽  
Animal Shelters ◽  
Future Studies ◽  
Boosting Algorithm ◽  
Key Features ◽  
Animal Size

Abstract Background Among the 6–8 million animals that enter the rescue shelters every year, nearly 3–4 million (i.e., 50% of the incoming animals) are euthanized, and 10–25% of them are put to death specifically because of shelter overcrowding each year. The overall goal of this study is to increase the adoption rates at animal shelters. This involves predicting the length of stay of each animal at shelters considering key features such as animal type (dog, cat, etc.), age, gender, breed, animal size, and shelter location. Results Logistic regression, artificial neural network, gradient boosting, and the random forest algorithms were used to develop models to predict the length of stay. The performance of these models was determined using three performance metrics: precision, recall, and F1 score. The results demonstrated that the gradient boosting algorithm performed the best overall, with the highest precision, recall, and F1 score. Upon further observation of the results, it was found that age for dogs (puppy, super senior), multicolor, and large and small size were important predictor variables. Conclusion The findings from this study can be utilized to predict and minimize the animal length of stay in a shelter and euthanization. Future studies involve determining which shelter location will most likely lead to the adoption of that animal. The proposed two-phased tool can be used by rescue shelters to achieve the best compromise solution by making a tradeoff between the adoption speed and relocation cost.

scholarly journals Machine learning augmented predictive and generative model for rupture life in ferritic and austenitic steels

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Osman Mamun ◽  
Madison Wenzlick ◽  
Arun Sathanur ◽  
Jeffrey Hawk ◽  
Ram Devanathan
Keyword(s):  
Pearson Correlation ◽  
Rupture Life ◽  
Model Performance ◽  
Austenitic Stainless Steels ◽  
Generative Model ◽  
Austenitic Steels ◽  
Gradient Boosting ◽  
Variational Autoencoder ◽  
Feature Importance ◽  
Boosting Algorithm

AbstractThe Larson–Miller parameter (LMP) offers an efficient and fast scheme to estimate the creep rupture life of alloy materials for high-temperature applications; however, poor generalizability and dependence on the constant C often result in sub-optimal performance. In this work, we show that the direct rupture life parameterization without intermediate LMP parameterization, using a gradient boosting algorithm, can be used to train ML models for very accurate prediction of rupture life in a variety of alloys (Pearson correlation coefficient >0.9 for 9–12% Cr and >0.8 for austenitic stainless steels). In addition, the Shapley value was used to quantify feature importance, making the model interpretable by identifying the effect of various features on the model performance. Finally, a variational autoencoder-based generative model was built by conditioning on the experimental dataset to sample hypothetical synthetic candidate alloys from the learnt joint distribution not existing in both 9–12% Cr ferritic–martensitic alloys and austenitic stainless steel datasets.

An intelligent evolutionary extreme gradient boosting algorithm development for modeling scour depths under submerged weir

2021 ◽  
Author(s):  
Hai Tao ◽  
Maria Habib ◽  
Ibrahim Aljarah ◽  
Hossam Faris ◽  
Haitham Abdulmohsin Afan ◽  
...  
Keyword(s):  
Gradient Boosting ◽  
Algorithm Development ◽  
Extreme Gradient Boosting ◽  
Boosting Algorithm

scholarly journals Gradient boosting for linear mixed models

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Colin Griesbach ◽  
Benjamin Säfken ◽  
Elisabeth Waldmann
Keyword(s):  
Random Effects ◽  
Mixed Models ◽  
Selection Procedure ◽  
Classification Theory ◽  
Gradient Boosting ◽  
Random Structure ◽  
Boosting Algorithm ◽  
The One ◽  
Biased Estimates ◽  
Selection Of

Abstract Gradient boosting from the field of statistical learning is widely known as a powerful framework for estimation and selection of predictor effects in various regression models by adapting concepts from classification theory. Current boosting approaches also offer methods accounting for random effects and thus enable prediction of mixed models for longitudinal and clustered data. However, these approaches include several flaws resulting in unbalanced effect selection with falsely induced shrinkage and a low convergence rate on the one hand and biased estimates of the random effects on the other hand. We therefore propose a new boosting algorithm which explicitly accounts for the random structure by excluding it from the selection procedure, properly correcting the random effects estimates and in addition providing likelihood-based estimation of the random effects variance structure. The new algorithm offers an organic and unbiased fitting approach, which is shown via simulations and data examples.

scholarly journals A Robust UWSN Handover Prediction System Using Ensemble Learning

Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5777
Author(s):  
Esraa Eldesouky ◽  
Mahmoud Bekhit ◽  
Ahmed Fathalla ◽  
Ahmad Salah ◽  
Ahmed Ali
Keyword(s):  
Decision Tree ◽  
Ensemble Learning ◽  
Prediction Accuracy ◽  
Performance Metrics ◽  
Prediction Models ◽  
Sensor Nodes ◽  
Wireless Sensor ◽  
Water Current ◽  
Gradient Boosting ◽  
Marine Data

The use of underwater wireless sensor networks (UWSNs) for collaborative monitoring and marine data collection tasks is rapidly increasing. One of the major challenges associated with building these networks is handover prediction; this is because the mobility model of the sensor nodes is different from that of ground-based wireless sensor network (WSN) devices. Therefore, handover prediction is the focus of the present work. There have been limited efforts in addressing the handover prediction problem in UWSNs and in the use of ensemble learning in handover prediction for UWSNs. Hence, we propose the simulation of the sensor node mobility using real marine data collected by the Korea Hydrographic and Oceanographic Agency. These data include the water current speed and direction between data. The proposed simulation consists of a large number of sensor nodes and base stations in a UWSN. Next, we collected the handover events from the simulation, which were utilized as a dataset for the handover prediction task. Finally, we utilized four machine learning prediction algorithms (i.e., gradient boosting, decision tree (DT), Gaussian naive Bayes (GNB), and K-nearest neighbor (KNN)) to predict handover events based on historically collected handover events. The obtained prediction accuracy rates were above 95%. The best prediction accuracy rate achieved by the state-of-the-art method was 56% for any UWSN. Moreover, when the proposed models were evaluated on performance metrics, the measured evolution scores emphasized the high quality of the proposed prediction models. While the ensemble learning model outperformed the GNB and KNN models, the performance of ensemble learning and decision tree models was almost identical.

scholarly journals Prediction and Analysis of Length of Stay Based on Nonlinear Weighted XGBoost Algorithm in Hospital

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yong Chen
Keyword(s):  
Length Of Stay ◽  
Prediction Performance ◽  
Gradient Boosting ◽  
Distribution Law ◽  
Effective Technique ◽  
Weighting Method ◽  
Imbalance Data ◽  
Extreme Gradient Boosting ◽  
Hospital Beds ◽  
Log Likelihood

An improved nonlinear weighted extreme gradient boosting (XGBoost) technique is developed to forecast length of stay for patients with imbalance data. The algorithm first chooses an effective technique for fitting the duration of stay and determining the distribution law and then optimizes the negative log likelihood loss function using a heuristic nonlinear weighting method based on sample percentage. Theoretical and practical results reveal that, when compared to existing algorithms, the XGBoost method based on nonlinear weighting may achieve higher classification accuracy and better prediction performance, which is beneficial in treating more patients with fewer hospital beds.

Significant of Gradient Boosting Algorithm in Data Management System

2021 ◽  
Vol 9 (2) ◽  
pp. 85-100
Author(s):  
Md Saikat Hosen ◽  
Ruhul Amin
Keyword(s):  
Data Management ◽  
Text Classification ◽  
Learning Process ◽  
Learning Algorithm ◽  
Error Function ◽  
Data Management System ◽  
Gradient Boosting ◽  
Response Parameter ◽  
Boosting Algorithms ◽  
Boosting Algorithm

Gradient boosting machines, the learning process successively fits fresh prototypes to offer a more precise approximation of the response parameter. The principle notion associated with this algorithm is that a fresh base-learner construct to be extremely correlated with the “negative gradient of the loss function” related to the entire ensemble. The loss function's usefulness can be random, nonetheless, for a clearer understanding of this subject, if the “error function is the model squared-error loss”, then the learning process would end up in sequential error-fitting. This study is aimed at delineating the significance of the gradient boosting algorithm in data management systems. The article will dwell much the significance of gradient boosting algorithm in text classification as well as the limitations of this model. The basic methodology as well as the basic-learning algorithm of the gradient boosting algorithms originally formulated by Friedman, is presented in this study. This may serve as an introduction to gradient boosting algorithms. This article has displayed the approach of gradient boosting algorithms. Both the hypothetical system and the plan choices were depicted and outlined. We have examined all the basic stages of planning a specific demonstration for one’s experimental needs. Elucidation issues have been tended to and displayed as a basic portion of the investigation. The capabilities of the gradient boosting algorithms were examined on a set of real-world down-to-earth applications such as text classification.

scholarly journals Investigating the Impact of Indemnity Waivers on the Length of Stay of Cats at an Australian Shelter

Animals ◽  
2019 ◽  
Vol 9 (2) ◽  
pp. 50 ◽  
Author(s):  
Jessica Pockett ◽  
Bronwyn Orr ◽  
Evelyn Hall ◽  
Wye Li Chong ◽  
Mark Westman
Keyword(s):  
Length Of Stay ◽  
Coat Colour ◽  
Multivariate Model ◽  
Australian Capital Territory ◽  
Animal Shelters ◽  
Resource Limitations ◽  
Final Multivariate Model ◽  
Likelihood Model ◽  
Cruelty To Animals ◽  
The Impact

Due to resource limitations, animal shelters in Australia historically have focused on rehoming animals considered ‘highly adoptable’. Increasingly, animal shelters in Australia are rehoming animals with pre-existing medical and/or behavioural issues. These animals are often rehomed with an ‘indemnity waiver’ to transfer the responsibility of ongoing financial costs associated with these conditions from the shelter to the new owner. However, it is unknown what effect these indemnity waivers have on the length of stay (LOS) of animals prior to adoption. The current study used data collected from the Royal Society for the Prevention of Cruelty to Animals (RSPCA) Weston shelter located in the Australian Capital Territory (ACT), Australia in 2017 to investigate the effect of indemnity waivers on the LOS of cats. A restricted maximum likelihood model (REML) was used to determine the effect of breed, age, coat colour, presence of a waiver, waiver type (categorised into seven groups) and waiver number (no waiver, single waiver or multiple waivers) on LOS. In the final multivariate model, age, breed and waiver number were found to influence LOS. Young cats, purebred cats and cats adopted without a waiver were adopted fastest. This study is the first to report the effect of indemnity waivers on the adoptability of cats from shelters.

scholarly journals Fido-SNP: the first webserver for scoring the impact of single nucleotide variants in the dog genome

2019 ◽  
Vol 47 (W1) ◽  
pp. W136-W141 ◽  
Author(s):  
Emidio Capriotti ◽  
Ludovica Montanucci ◽  
Giuseppe Profiti ◽  
Ivan Rossi ◽  
Diana Giannuzzi ◽  
...  
Keyword(s):  
Matthews Correlation Coefficient ◽  
Genomic Variation ◽  
Gradient Boosting ◽  
Binary Classifier ◽  
Single Nucleotide Variants ◽  
Single Nucleotide ◽  
Coding Regions ◽  
Variation Data ◽  
Boosting Algorithm ◽  
The Impact

Abstract As the amount of genomic variation data increases, tools that are able to score the functional impact of single nucleotide variants become more and more necessary. While there are several prediction servers available for interpreting the effects of variants in the human genome, only few have been developed for other species, and none were specifically designed for species of veterinary interest such as the dog. Here, we present Fido-SNP the first predictor able to discriminate between Pathogenic and Benign single-nucleotide variants in the dog genome. Fido-SNP is a binary classifier based on the Gradient Boosting algorithm. It is able to classify and score the impact of variants in both coding and non-coding regions based on sequence features within seconds. When validated on a previously unseen set of annotated variants from the OMIA database, Fido-SNP reaches 88% overall accuracy, 0.77 Matthews correlation coefficient and 0.91 Area Under the ROC Curve.

Sign in / Sign up

Export Citation Format

Share Document