Algorithm quasi‐optimal (AQ) learning

Cervone, Guido; Franzese, Pasquale; Keesee, Allen P. K.

doi:10.1002/wics.78

Cited by 32 publications

(18 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A detailed description of the AQ algorithm and its implementation used for this study is provided by Cervone et al . (). The presented approach is not limited to AQ, and other classifiers could be used to discriminate between the chemical samples.…”

Section: Methodsmentioning

confidence: 97%

“…Each row of data is assigned a label indicating a level of As below or above the safety threshold. Unlike clustering, a form of unsupervised learning whose goal is dividing unlabeled data into distinct classes, classification is a form of supervised learning, where classified data are generalized to identify the characteristics of the entire class (Cervone et al, 2010).…”

Section: Methodsmentioning

confidence: 99%

“…The AQ is a general purpose symbolic machine learning classifier that learns induction rules from a set of examples and counterexamples. A detailed description of the AQ algorithm and its implementation used for this study is provided by Cervone et al (2010). The presented approach is not limited to AQ, and other classifiers could be used to discriminate between the chemical samples.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

The case of arsenic contamination in the Sardinian Geopark, Italy, analyzed using symbolic machine learning

Manca

Cervone

2013

Environmetrics

Self Cite

View full text Add to dashboard Cite

This paper analyzes the relationship among different chemical pollutants retrieved from in situ measurements of underground and surface water in a region of possible development. The area of study is the former mine of the Iglesiente district, which is now a United Nations Educational, Scientific, and Cultural Organization (UNESCO) protected region in the island of Sardinia (Italy). A full chemical analysis of water/soil samples were collected at the site in 2004. The data show the presence of several toxic contaminants above the national legal threshold. A symbolic machine learning classifier is employed to learn strong patterns associated with a high level of arsenic (As) in the soil samples. The patterns discovered show complex relationships that include both high and low concentrations of different chemicals. The strongest patterns are found between As and the chemicals which are usually found in the soil. This implies that when As is dissolved in the water table, it is expected these other chemicals are also present. It emerges that a specific relationship of As–phosphates is outlined and is clearly shown by applying the symbolic machine learning classifier. This leads to an understanding of the behavior of these elements in the soil, potential impacts on ecosystems, as well as the pollution of groundwater. Finally, an assertion of the advantages of the algorithm quasi‐optimal learning method is clarified in term of applicability in such circumstances. Copyright © 2013 John Wiley & Sons, Ltd.

show abstract

Section: Methodsmentioning

confidence: 97%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

The case of arsenic contamination in the Sardinian Geopark, Italy, analyzed using symbolic machine learning

Manca

Cervone

2013

Environmetrics

Self Cite

View full text Add to dashboard Cite

show abstract

“…AQ21 is the latest development from a series of AQ rule learners that dates back to the 1970s [ 23 ]. A number of well-known rule learners have been developed over the last decades [ 24 – 26 ], but many are not utilized in mainstream research at the present time. In the past few years the ML field has been dominated by statistical methods that focused primarily on providing highly accurate models.…”

Section: Methodsmentioning

confidence: 99%

Predicting activities of daily living for cancer patients using an ontology-guided machine learning methodology

et al. 2017

View full text Add to dashboard Cite

BackgroundBio-ontologies are becoming increasingly important in knowledge representation and in the machine learning (ML) fields. This paper presents a ML approach that incorporates bio-ontologies and its application to the SEER-MHOS dataset to discover patterns of patient characteristics that impact the ability to perform activities of daily living (ADLs). Bio-ontologies are used to provide computable knowledge for ML methods to “understand” biomedical data.ResultsThis retrospective study included 723 cancer patients from the SEER-MHOS dataset. Two ML methods were applied to create predictive models for ADL disabilities for the first year after a patient’s cancer diagnosis. The first method is a standard rule learning algorithm; the second is that same algorithm additionally equipped with methods for reasoning with ontologies. The models showed that a patient’s race, ethnicity, smoking preference, treatment plan and tumor characteristics including histology, staging, cancer site, and morphology were predictors for ADL performance levels one year after cancer diagnosis. The ontology-guided ML method was more accurate at predicting ADL performance levels (P < 0.1) than methods without ontologies.ConclusionsThis study demonstrated that bio-ontologies can be harnessed to provide medical knowledge for ML algorithms. The presented method demonstrates that encoding specific types of hierarchical relationships to guide rule learning is possible, and can be extended to other types of semantic relationships present in biomedical ontologies. The ontology-guided ML method achieved better performance than the method without ontologies. The presented method can also be used to promote the effectiveness and efficiency of ML in healthcare, in which use of background knowledge and consistency with existing clinical expertise is critical.

show abstract

“…This is usually turned into an optimization problem (Allen et al 2007;Cervone et al 2010) or using Bayesian inference methods (Keats et al 2007;Senocak et al 2008), along with a proper forward dispersion model. Both the direct ANN model for concentration distribution (Cao et al 2010), or the ANN models for dispersion coefficients of Gaussian models proposed herein, can be used as the forward dispersion model.…”

Section: Multi-variable Non-linear Regression Model Of Dispersion Coementioning

confidence: 99%

Dispersion Coefficients for Gaussian Puff Models

Cao

Roy

Hurley

et al. 2011

Boundary-Layer Meteorol

View full text Add to dashboard Cite

The Gaussian distribution is a good approximation for transient (instantaneously released) puff concentration distributions within a short period of time after release. Artificial neural network (ANN) models for puff dispersion coefficients were developed, based on observations from field experiments covering a wide range of meteorological conditions (in March, May, August and November). Their average predictions were in very good agreement with measurements, having high correlation coefficients (r > 0.99). A non-linear multi-variable regression model for dispersion coefficients was also developed, under the assumption that puff dispersion coefficients increase with time, and follow power laws. Both ANN-based and multi-regression non-linear models were able to use easily measured atmospheric parameters directly, without the necessity of predefining the Pasquill stability category. Predictions of ANN-based and multi-regression-based Gaussian puff models were compared with those of Gaussian puff models using Slade's dispersion coefficients and COMBIC, a sophisticated model based on Gaussian distributions. Predictions from our two new models showed better agreement with concentration measurements than the other Gaussian puff models, by having a much higher fraction within a factor of two of measured values, and lower normalized mean square errors.

show abstract

Algorithm quasi‐optimal (AQ) learning

Cited by 32 publications

References 30 publications

The case of arsenic contamination in the Sardinian Geopark, Italy, analyzed using symbolic machine learning

The case of arsenic contamination in the Sardinian Geopark, Italy, analyzed using symbolic machine learning

Predicting activities of daily living for cancer patients using an ontology-guided machine learning methodology

Dispersion Coefficients for Gaussian Puff Models

Contact Info

Product

Resources

About