Components of Artificial Intelligence and Data Analytics

Carvajal, Gustavo; Maučec, Marko; Cullick, Stan

doi:10.1016/b978-0-12-804642-5.00004-9

Cited by 6 publications

(8 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the boundaries, the RF model showed that δ 13 C was almost four‐fold more important for the classification than δ 15 N. In terms of the seemingly contradictory δ 15 N results, both approaches are based on different perspectives and thus provide information in two different ways. The Bayesian models described the differences among species based on their descriptions, while the RF model directly described the differences among them (Carvajal et al, 2018; Ng & Jordan, 2002). In other words, the differences among the δ 13 C values had a greater effect on the classification than those in δ 15 N values.…”

Section: Discussionmentioning

confidence: 99%

“…As such, a random forest (RF) classifier was implemented. This method classifies objects (i.e., individuals), creating T uncorrelated decision trees and assigning each object to its most frequently found class (Carvajal et al, 2018). Each tree is constructed by recursively partitioning the feature space into regions with similar response values (Strobl et al, 2009).…”

Section: Methodsmentioning

confidence: 99%

“…The RF approach is considered as one of the more efficient supervised machine learning approaches because it is insensitive to biased distributions, extreme data points, and missing data (Carvajal et al, 2018). Moreover, given its hierarchical nature, it automatically includes the interaction between features, among other characteristics (Carvajal et al, 2018). The model was implemented in Python 3 using the Scikit‐Learn library v. 0.23.1 (Pedregosa et al, 2011).…”

Section: Methodsmentioning

confidence: 99%

“…T uncorrelated decision trees and assigning each object to its most frequently found class (Carvajal et al, 2018).…”

Section: Comparison Of Isotopic Valuesmentioning

confidence: 99%

See 3 more Smart Citations

Foraging segregation between spotted (Stenella attenuata) and spinner (Stenella longirostris) dolphins in the Mexican South Pacific

Enríquez‐García

Villegas‐Zurita

Valdéz

et al. 2022

Marine Mammal Science

View full text Add to dashboard Cite

Coexistence among sympatric species requires a certain degree of resource partitioning. In the Mexican South Pacific, information regarding the coexistence of Stenella attenuata (SA) and Stenella longirostris (SL) is lacking. Stable isotope analyses (δ15N and δ13C) were conducted to assess the differences in feeding habits to infer trophic position and amplitude as well as habitat use, based on Bayesian inference and a random forest (RF) classifier. Potential trophic relationships with other species were assessed by Bayesian mixing models. Feeding segregation between species was mainly based on carbon sources (δ13C: p(SA > SL) = 100%, RF Gini Impurity = 80%). Moreover, SA (n = 22) presented a broader isotopic niche than that of SL (n = 25; SIBER Bayesian Standard Ellipse areas = 0.91‰2 vs. 0.77‰2) with a 33% overlap, suggesting that SA uses more coastal habitats than SL. The most relevant prey species were the mesopelagic fish Benthosema panamense and the epipelagic fish Hyporhamphus naos (~50%), although B. panamense was more related to SL than SA: p(%SL > %SA) = 76.6%. The trophic positions were 4.0 (SA) and 3.8 (SL). Our results provide evidence of resource partitioning within a potential foraging ground for both dolphin species.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…T uncorrelated decision trees and assigning each object to its most frequently found class (Carvajal et al, 2018).…”

Section: Comparison Of Isotopic Valuesmentioning

confidence: 99%

See 2 more Smart Citations

Foraging segregation between spotted (Stenella attenuata) and spinner (Stenella longirostris) dolphins in the Mexican South Pacific

Enríquez‐García

Villegas‐Zurita

Valdéz

et al. 2022

Marine Mammal Science

View full text Add to dashboard Cite

show abstract

“…Handling of missing values 66 Robustness to outliers in input space 66 Insensitive to the monotone transformation of inputs 67 …”

Section: Discussionmentioning

confidence: 99%

Application of machine learning methods in predicting schizophrenia and bipolar disorders: A systematic review

Montazeri

Bahaadinbeigy

et al. 2022

Health Science Reports

View full text Add to dashboard Cite

Background and Aim Schizophrenia and bipolar disorder (BD) are critical and high‐risk inherited mental disorders with debilitating symptoms. Worldwide, 3% of the population suffers from these disorders. The mortality rate of these patients is higher compared to other people. Current procedures cannot effectively diagnose these disorders because it takes an average of 10 years from the onset of the first symptoms to the definitive diagnosis of the disease. Machine learning (ML) techniques are used to meet this need. This study aimed to summarize information on the use of ML techniques for predicting schizophrenia and BD to help early and timely diagnosis of the disease. Methods A systematic literature search included articles published until January 19, 2020 in 3 databases. Two reviewers independently assessed original papers to determine eligibility for inclusion in this review. PRISMA guidelines were followed to conduct the study, and the Prediction Model Risk of Bias Assessment Tool (PROBAST) to assess included papers. Results In this review, 1243 papers were retrieved through database searches, of which 15 papers were included based on full‐text assessment. ML techniques were used to predict schizophrenia and BDs. The main algorithms applied were support vector machine (SVM) (10 studies), random forests (RF) (5 studies), and gradient boosting (GB) (3 studies). Input and output characteristics were very diverse and have been kept to enable future research. RFs algorithms demonstrated significantly higher accuracy and sensitivity than SVM and GB. GB demonstrated significantly higher specificity than SVM and RF. We found no significant difference between RF and SVM in terms of specificity. Conclusion ML can precisely predict results and assist in making clinical decisions‐concerning schizophrenia and BD. RF often performed better than other algorithms in supervised learning tasks. This study identified gaps in the literature and opportunities for future psychological ML research.

show abstract

Spatial distribution of pyrogenic carbon in Iberian topsoils estimated by chemometric analysis of infrared spectra

Jiménez-González

Rosa

Aksoy

et al. 2021

Science of The Total Environment

View full text Add to dashboard Cite

Components of Artificial Intelligence and Data Analytics

Cited by 6 publications

References 3 publications

Foraging segregation between spotted (Stenella attenuata) and spinner (Stenella longirostris) dolphins in the Mexican South Pacific

Foraging segregation between spotted (Stenella attenuata) and spinner (Stenella longirostris) dolphins in the Mexican South Pacific

Application of machine learning methods in predicting schizophrenia and bipolar disorders: A systematic review

Spatial distribution of pyrogenic carbon in Iberian topsoils estimated by chemometric analysis of infrared spectra

Contact Info

Product

Resources

About