Efficient data preprocessing, episode classification, and source apportionment of particle number concentrations

Liang, Chun-Sheng; Wu, Hao; Li, Haiyan; Zhang, Qiang; Li, Zhanqing; He, Kebin

doi:10.1016/j.scitotenv.2020.140923

Cited by 23 publications

(14 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evolutionary learning is a metaheuristic that offers compelling advantages when applied to machine learning as an AI optimizer: it learns adaptively, surveys the search space randomly, is representation independent (e.g., accepts categorical variables) and is intuitive and transparent. Metaheuristic methodologies have been an active area of research for decades and are often inspired by natural, stochastic phenomena like genetic selection, particle swarms (which have been applied to model hyperparameter tuning) or insect colony behavior (Liang et al, 2020 ). They have made major impacts in providing practical solutions to combinatorial problems in diverse scientific fields (Osman and Laporte, 1996 ).…”

Section: Discussionmentioning

confidence: 99%

Integrated Evolutionary Learning: An Artificial Intelligence Approach to Joint Learning of Features and Hyperparameters for Optimized, Explainable Machine Learning

Lacy

Ramshaw

Kutz

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

Artificial intelligence and machine learning techniques have proved fertile methods for attacking difficult problems in medicine and public health. These techniques have garnered strong interest for the analysis of the large, multi-domain open science datasets that are increasingly available in health research. Discovery science in large datasets is challenging given the unconstrained nature of the learning environment where there may be a large number of potential predictors and appropriate ranges for model hyperparameters are unknown. As well, it is likely that explainability is at a premium in order to engage in future hypothesis generation or analysis. Here, we present a novel method that addresses these challenges by exploiting evolutionary algorithms to optimize machine learning discovery science while exploring a large solution space and minimizing bias. We demonstrate that our approach, called integrated evolutionary learning (IEL), provides an automated, adaptive method for jointly learning features and hyperparameters while furnishing explainable models where the original features used to make predictions may be obtained even with artificial neural networks. In IEL the machine learning algorithm of choice is nested inside an evolutionary algorithm which selects features and hyperparameters over generations on the basis of an information function to converge on an optimal solution. We apply IEL to three gold standard machine learning algorithms in challenging, heterogenous biobehavioral data: deep learning with artificial neural networks, decision tree-based techniques and baseline linear models. Using our novel IEL approach, artificial neural networks achieved ≥ 95% accuracy, sensitivity and specificity and 45–73% R2 in classification and substantial gains over default settings. IEL may be applied to a wide range of less- or unconstrained discovery science problems where the practitioner wishes to jointly learn features and hyperparameters in an adaptive, principled manner within the same algorithmic process. This approach offers significant flexibility, enlarges the solution space and mitigates bias that may arise from manual or semi-manual hyperparameter tuning and feature selection and presents the opportunity to select the inner machine learning algorithm based on the results of optimized learning for the problem at hand.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrated Evolutionary Learning: An Artificial Intelligence Approach to Joint Learning of Features and Hyperparameters for Optimized, Explainable Machine Learning

Lacy

Ramshaw

Kutz

2022

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…Although traditional receptor models such as PMF (Yue et al, 2008;Harrison et al, 2011;Dall'Osto et al, 2012;Tan et al, 2014;Liang et al, 2020;Liang et al, 2021) and k-means clustering (Charron et al, 2008;Beddows et al, 2009;Dall'Osto et al, 2012;Wegner et al, 2012;Salimi et al, 2014;Liang et al, 2020) have been applied for SA using particle number concentration, no attempts have been made previously to apply clustering algorithms on mass concentration data. In this study, we have implemented k-means clustering (kMC) as well as Spectral Clustering (SC) algorithms which are a part of Machine Learning (ML), on mass concentration data.…”

Section: A C C E P T E D Mmentioning

confidence: 99%

Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms

Kumar

Sahu

Biswas

2022

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

A source apportionment (SA) study was conducted on two PM2.5 data sets, two carbon fractions and eight temperature-resolved carbon fractions collected during Cincinnati Childhood Allergy and Air Pollution Study (CCAAPS). This study aimed to evaluate two clustering algorithms: k-means clustering (kMC) and spectral clustering (SC) as potential receptor models for source apportionment. The application of kMC produced unsatisfactory results, but the results obtained from SC demonstrated a significant correlation with the results obtained using positive matrix factorization (PMF). The clustering results obtained were associated with practical evidence available in the literature. SC identified six source factors on analyzing two carbon fractions data set and seven factors from eight temperature-resolved carbon fractions data set. The sources (source contribution in parentheses) identified are: combustion (45.9±3.66%) and secondary sulfate (11.4±1.09%), vegetative/wood burning (17.5±1.46%), diesel (10.6±0.92%) and gasoline (3.6±0.33%) vehicles, soil/crustal (2.07±0.2%), traffic (9.3±0.81%), and metal processing (8.8±0.72%). The source profiles obtained using SC also show similarity with the profiles derived using PMF. In summary, this study presented a basic framework for applying Machine Learning algorithms for SA analysis. Also, it presents SC as a potential receptor model technique for SA.

show abstract

“…36 The algorithms of receptor models for PNC source apportionment include principal component analysis (PCA), 39 Kmeans clustering, 40 positive matrix factorization (PMF) 36 and non-negative matrix factorization (NMF). 41 K-Means clustering is a semi-quantitative method based on occurrence frequency, which produces mixed sources. 23,41 PMF is the most popular method for source apportionment of atmospheric pollutants.…”

Section: Introductionmentioning

confidence: 99%

“…41 K-Means clustering is a semi-quantitative method based on occurrence frequency, which produces mixed sources. 23,41 PMF is the most popular method for source apportionment of atmospheric pollutants. However, intensive computation of matrix inversion, singular value decomposition and error weighting during the solving process of PMF limit its calculation capacities for long-term and ne-size-resolution PNSD datasets.…”

Section: Introductionmentioning

confidence: 99%

“…However, intensive computation of matrix inversion, singular value decomposition and error weighting during the solving process of PMF limit its calculation capacities for long-term and ne-size-resolution PNSD datasets. 41 These studies, which deployed PMF with reduced particle size bins, 32,36,42 sacriced the particle size resolution of PNSD. The latest research indicates that NMF is a promising source apportionment method for PNSD.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic, marine ships and nucleation as the main sources of ultrafine particles in suburban Shanghai, China

Wang,

Huo,

Chen

et al. 2023

Environ. Sci.: Atmos.

View full text Add to dashboard Cite

show abstract

Efficient data preprocessing, episode classification, and source apportionment of particle number concentrations

Cited by 23 publications

References 107 publications

Integrated Evolutionary Learning: An Artificial Intelligence Approach to Joint Learning of Features and Hyperparameters for Optimized, Explainable Machine Learning

Integrated Evolutionary Learning: An Artificial Intelligence Approach to Joint Learning of Features and Hyperparameters for Optimized, Explainable Machine Learning

Source Apportionment of Particulate Matter by Application of Machine Learning Clustering Algorithms

Traffic, marine ships and nucleation as the main sources of ultrafine particles in suburban Shanghai, China

Contact Info

Product

Resources

About