4.7 Article

Multiple machine learning algorithms assisted QSPR models for aqueous solubility: Comprehensive assessment with CRITIC-TOPSIS

Related references

Note: Only part of the references are listed.
Article Engineering, Environmental

Prediction models with multiple machine learning algorithms for POPs: The calculation of PDMS-air partition coefficient from molecular descriptor

Tengyi Zhu et al.

Summary: Thirteen QSPR models were developed in this study, with the GBDT model showing remarkable superiority in fitting, robustness and predictability. The main internal factors affecting the partition process were revealed to be molecular size, branches and types of bonds. Unlike existing models based on single category compounds, the models developed in this study considered multiple classes compounds, making their application domain more comprehensive.

JOURNAL OF HAZARDOUS MATERIALS (2022)

Article Economics

Oil price volatility predictability: New evidence from a scaled PCA approach

Yangli Guo et al.

Summary: In this study, the scaled principal component analysis (sPCA) method is introduced to forecast oil volatility and compared with principal component analysis (PCA) and partial least squares (PLS). The findings reveal that the model using the sPCA diffusion index performs better in out-of-sample tests and consistently demonstrates superior forecasting power under different macroeconomic conditions. The robustness of the findings is confirmed through various tests.

ENERGY ECONOMICS (2022)

Article Engineering, Environmental

Development of remote sensing algorithm for total phosphorus concentration in eutrophic lakes: Conventional or machine learning?

Junfeng Xiong et al.

Summary: This study proposes a framework for estimating total phosphorus (TP) using remote sensing technology in eutrophic lakes. A machine learning algorithm was developed and tested in Lake Taihu and other lakes. The algorithm exhibited robust performance and showed potential for long-term TP estimation in large-scale eutrophic lakes.

WATER RESEARCH (2022)

Article Chemistry, Multidisciplinary

A Double-Level Calculation Model for the Construction Schedule Planning of Urban Rail Transit Network

Songsong Li et al.

Summary: The construction of urban rail transit plays a crucial role in urban development, and the planning of construction schedule is a complex task. This study proposes a double-level construction schedule model based on an analysis of factors influencing the construction sequence and timing. The model provides quantitative theoretical support for the construction schedule planning of URT network.

APPLIED SCIENCES-BASEL (2022)

Article Green & Sustainable Science & Technology

A Hybrid TOPSIS-PR-GWO Approach for Multi-objective Process Parameter Optimization

Kanak Kalita et al.

Summary: This paper introduces a novel hybridized multi-objective optimization approach called TOPSIS-PR-GWO by combining TOPSIS and GWO for parametric optimization. The results of the experiments show that this method provides significantly better solutions and requires less computational time compared to the conventional approach.

PROCESS INTEGRATION AND OPTIMIZATION FOR SUSTAINABILITY (2022)

Article Engineering, Multidisciplinary

A comparison between fuzzy AHP and fuzzy TOPSIS methods to software requirements selection

Mohd. Nazim et al.

Summary: This paper presents a comparative analysis of fuzzy AHP and fuzzy TOPSIS methods in the context of software requirements selection problem. The study found that both methods produce the same set of functional requirements based on agreement measure metric. Fuzzy AHP has better time efficiency, while fuzzy TOPSIS performs better in terms of ranking consistency and number of judgments by decision makers.

ALEXANDRIA ENGINEERING JOURNAL (2022)

Article Green & Sustainable Science & Technology

Prioritizing strategies to eliminate barriers to renewable energy adoption and development in Ghana: A CRITIC-fuzzy TOPSIS approach

Dennis Asante et al.

Summary: This study utilized the CRITIC and F-TOPSIS methods to assess the barriers of renewable energy (RE) adoption and development in Ghana and proposed prioritized strategies. The results indicated that direct enabling and integrating policies, RE targets, education, and training are the most suitable strategies. The findings emphasized the importance of creating enabling conditions and policy initiatives for renewable energy development.

RENEWABLE ENERGY (2022)

Article Environmental Sciences

Predicting reaction rate constants of ozone with ionic/non-ionic compounds in water

Xiao Zhang et al.

Summary: In this study, two quantitative structure-activity relationship models were developed for non-ionic and ionic species to predict their reaction rate constants with ozone. These models showed good predictive performance and applicability and can be used to estimate the conversion rate of pollutants by ozone in urban sewage and drinking water treatment.

SCIENCE OF THE TOTAL ENVIRONMENT (2022)

Article Automation & Control Systems

Decision making framework based Fermatean fuzzy integrated weighted distance and TOPSIS for green low-carbon port evaluation

Sha Yang et al.

Summary: This study proposes a decision-making framework for GLCP evaluation based on Fermatean fuzzy integrated weighted distance measure and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The framework is applied to evaluate the development status of five major ports in China, and Guangzhou Port is found to have the best performance while Shenzhen Port performs the worst.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2022)

Article Environmental Sciences

A QSAR-ICE-SSD model prediction of the PNECs for alkylphenol substances and application in ecological risk assessment for rivers of a megacity

Yajun Hong et al.

Summary: This study focuses on developing computational models to predict the aquatic toxicity of alkylphenols (APs) with incomplete/unknown toxicity data in aquatic environments. A QSAR-ICE-SSD model was constructed for aquatic organisms, combining quantitative structure-activity relationship (QSAR), interspecies correlation estimation (ICE), and species sensitivity distribution (SSD) models to obtain the hazardous concentrations (HCs) of selected APs.

ENVIRONMENT INTERNATIONAL (2022)

Article Environmental Sciences

Tracing water-soluble, persistent substances in the Black Sea

S. Miladinova et al.

Summary: This study uses a model to simulate the transport and fate of water-soluble persistent substances in the Black Sea and estimates the concentration in specific sub-regions based on the correlation between average concentration and half-life. The results show a seasonal variation in the average concentration in the shelf area, while the deep region does not show significant variations.

ENVIRONMENTAL POLLUTION (2022)

Article Environmental Sciences

Versatile in silico modeling of XAD-air partition coefficients for POPs based on abraham descriptor and temperature

Cuicui Tao et al.

Summary: The study developed models for predicting the partition coefficients of persistent organic pollutants (POPs) between XAD resin and air using poly parameter linear free energy relationship (pp-LFER) and temperature. Machine learning algorithms showed good fitting and generalization abilities, with the random forest (RF) model performing the best. The models provide a useful tool for filling experimental data gaps and evaluating the environmental ecological risk of untested chemicals.

ENVIRONMENTAL POLLUTION (2022)

Article Computer Science, Interdisciplinary Applications

Deep neural network and whale optimization algorithm to assess flyrock induced by blasting

Hongquan Guo et al.

Summary: This study developed a deep neural network (DNN) model to predict flyrock induced by blasting, which showed a significant increase in prediction accuracy compared to an artificial neural network (ANN) model. The DNN model, optimized using the whale optimization algorithm (WOA), successfully minimized flyrock resulting from blasting and provided a suitable pattern for blasting operations in mines.

ENGINEERING WITH COMPUTERS (2021)

Article Chemistry, Multidisciplinary

QSPR models for water solubility of ammonium hexafluorosilicates: analysis of the effects of hydrogen bonds

Vladimir Gelmboldt et al.

Summary: In this study, QSAR models were developed to analyze the water solubility of some ammonium hexafluorosilicates, showing the influence of structural and physicochemical factors on solubility. The models can accurately predict the solubility of new compounds with satisfactory accuracy.

STRUCTURAL CHEMISTRY (2021)

Article Environmental Sciences

Identification of structural properties influencing the metabolism of polycyclic aromatic hydrocarbons by cytochrome P450 1A1

Chao Chen et al.

Summary: This study identified key structural properties affecting the metabolic capacity of PAHs by using a variety of computational methods. The findings shed new light on the structural mechanism of PAH metabolism and provide a useful tool for screening, classifying, and predicting the toxicities and risk assessment of PAHs in the environment.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

Article Engineering, Environmental

The value of human data annotation for machine learning based anomaly detection in environmental systems

Stefania Russo et al.

Summary: Anomaly detection is the process of identifying unexpected data samples in datasets, which can be done using supervised or unsupervised machine learning models. The research community focused on environmental systems lacks a comprehensive and objective comparative analysis, which is addressed for the first time in this study.

WATER RESEARCH (2021)

Review Engineering, Environmental

Machine learning in natural and engineered water systems

Ruixing Huang et al.

Summary: Machine learning has shown great potential in water resources management, being able to predict water quality indicators, solve emerging pollution problems, and effectively identify specific contaminants.

WATER RESEARCH (2021)

Article Engineering, Chemical

Evaluation of nine machine learning regression algorithms for calibration of low-cost PM2.5 sensor

Vikas Kumar et al.

Summary: This study compared nine machine learning algorithms for the calibration of low-cost sensors, with kNN, RF, and GB showing the best performance.

JOURNAL OF AEROSOL SCIENCE (2021)

Article Chemistry, Physical

Specific heat capacity of molten salt-based nanofluids in solar thermal applications: A paradigm of two modern ensemble machine learning methods

Mehdi Jamei et al.

Summary: The study developed two modern ensemble machine learning models based on 2384 datasets to accurately estimate the specific heat capacity of molten salt-based nanofluids. The models were validated and it was found that the specific heat capacity of the molten salt base fluid is the most significant factor in estimating the specific heat capacity of molten salt-based nanofluids.

JOURNAL OF MOLECULAR LIQUIDS (2021)

Article Green & Sustainable Science & Technology

Material Selection in Green Design: A Method Combining DEA and TOPSIS

Cheng Peng et al.

Summary: This study combines the methods of generalized Data Envelopment Analysis (DEA) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to establish a green material index system and successfully applies it to material selection in the furniture industry, providing a more rational and evidentiary basis for material selection in green design.

SUSTAINABILITY (2021)

Article Construction & Building Technology

Overall grouting compactness detection of bridge prestressed bellows based on RF feature selection and the GA-SVM model

Hongjin Liu et al.

Summary: The study proposes a longitudinal transmission detection method based on RF feature selection and GA-SVM model, which quickly detects the grouting compactness of bridge bellows by screening important features and optimizing parameters. Eight important features were selected out of 40, and the prediction effect was better compared to other optimization algorithms and models.

CONSTRUCTION AND BUILDING MATERIALS (2021)

Article Multidisciplinary Sciences

A Modified CRITIC Method to Estimate the Objective Weights of Decision Criteria

Anath Rau Krishnan et al.

Summary: This study developed the D-CRITIC method, which was validated to produce more valid criteria weights and ranks through distance correlation testing, and was found to be more stable with a larger decision matrix.

SYMMETRY-BASEL (2021)

Article Green & Sustainable Science & Technology

AI Methods for Modeling the Vacuum Drying Characteristics of Chlorococcum infusionum for Algal Biofuel Production

Phoebe Mae L. Ching et al.

Summary: AI methods, including ANN and XGB, demonstrate higher accuracy in optimizing the efficiency of a vacuum drying process for algal-based biofuels. These models outperform traditional regression methods and show notable improvement in approximating individual sample points, especially at high and low tail-ends of the dataset. This study suggests potential for further optimization and automation based on the AI models developed.

PROCESS INTEGRATION AND OPTIMIZATION FOR SUSTAINABILITY (2021)

Article Environmental Sciences

Predicting acute contact toxicity of organic binary mixtures in honey bees (A. mellifera) through innovative QSAR models

Edoardo Carnesecchi et al.

SCIENCE OF THE TOTAL ENVIRONMENT (2020)

Article Chemistry, Multidisciplinary

QSPR studies on water solubility, octanol-water partition coefficient and vapour pressure of pesticides

P. R. Duchowicz

SAR AND QSAR IN ENVIRONMENTAL RESEARCH (2020)

Article Mining & Mineral Processing

Predicting the electrical conductivity of brine-saturated rocks using machine learning methods

Tuan Nguyen-Sy et al.

JOURNAL OF APPLIED GEOPHYSICS (2020)

Review Chemistry, Analytical

State of the art and prospects of methods for determination of lipophilicity of chemical compounds

Dagmara Kempinska et al.

TRAC-TRENDS IN ANALYTICAL CHEMISTRY (2019)

Article Engineering, Civil

Further investigation on water-hammer control inline strategy in water-supply systems

Ali Triki

JOURNAL OF WATER SUPPLY RESEARCH AND TECHNOLOGY-AQUA (2018)

Article Green & Sustainable Science & Technology

A Voting TOPSIS Approach for Determining the Priorities of Areas Damaged in Disasters

Yanjin He et al.

SUSTAINABILITY (2018)

Article Engineering, Environmental

Comparison of Machine Learning Approaches with a General Linear Model To Predict Personal Exposure to Benzene

Noel J. Aquilina et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2018)

Article Medicine, Research & Experimental

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets

Alexandru Korotcov et al.

MOLECULAR PHARMACEUTICS (2017)

Article Chemistry, Multidisciplinary

Prediction of Hydrate and Solvate Formation Using Statistical Models

Khaled Taldeddin et al.

CRYSTAL GROWTH & DESIGN (2016)

Article Automation & Control Systems

Be aware of error measures. Further studies on validation of predictive QSAR models

Kunal Roy et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2016)

Article Chemistry, Multidisciplinary

Better prediction of aqueous solubility of chlorinated hydrocarbons using support vector machine modeling

Behnoosh Bahadori et al.

ENVIRONMENTAL CHEMISTRY LETTERS (2016)

Article Environmental Sciences

Effect of compositional heterogeneity on dissolution of non-ideal LNAPL mixtures

M. Vasudevan et al.

JOURNAL OF CONTAMINANT HYDROLOGY (2016)

Article Engineering, Environmental

QSPR prediction of the hydroxyl radical rate constant of water contaminants

Tohid Nejad Ghaffar Borhani et al.

WATER RESEARCH (2016)

Article Chemistry, Multidisciplinary

QSAR modeling of antimalarial activity of urea derivatives using genetic algorithm-multiple linear regressions

Abolghasem Beheshti et al.

JOURNAL OF SAUDI CHEMICAL SOCIETY (2016)

Article Computer Science, Interdisciplinary Applications

Comparing lazy and eager learning models for water level forecasting in river-reservoir basins of inundation regions

Chih-Chiang Wei

ENVIRONMENTAL MODELLING & SOFTWARE (2015)

Article Chemistry, Medicinal

In silico Prediction of Aqueous Solubility: a Comparative Study of Local and Global Predictive Models

Oleg A. Raevsky et al.

MOLECULAR INFORMATICS (2015)

Review Engineering, Environmental

Applications of Polyparameter Linear Free Energy Relationships in Environmental Chemistry

Satoshi Endo et al.

ENVIRONMENTAL SCIENCE & TECHNOLOGY (2014)

Article Biochemical Research Methods

3D-MoRSE descriptors explained

Oleg Devinyak et al.

JOURNAL OF MOLECULAR GRAPHICS & MODELLING (2014)

Article Chemistry, Medicinal

Assessment of Methods To Define the Applicability Domain of Structural Alert Models

C. M. Ellison et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2011)

Article Automation & Control Systems

QSPR studies on the aqueous solubility of PCDD/Fs by using artificial neural network combined with stepwise regression

Long Jiao et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2010)

Article Chemistry, Medicinal

QSAR prediction of D2 receptor antagonistic activity of 6-methoxy benzamides

Mohammad H. Fatemi et al.

EUROPEAN JOURNAL OF MEDICINAL CHEMISTRY (2010)

Article Mathematics, Applied

Asymptotic stability of impulsive high-order Hopfield type neural networks

Bingji Xu et al.

COMPUTERS & MATHEMATICS WITH APPLICATIONS (2009)

Article Multidisciplinary Sciences

Reducing the dimensionality of data with neural networks

G. E. Hinton et al.

SCIENCE (2006)

Article Chemistry, Medicinal

General melting point prediction based on a diverse compound data set and artificial neural networks

M Karthikeyan et al.

JOURNAL OF CHEMICAL INFORMATION AND MODELING (2005)

Article Chemistry, Multidisciplinary

General and class specific models for prediction of soil sorption using various physicochemical descriptors

PL Andersson et al.

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES (2002)

Review Chemistry, Multidisciplinary

Structurally diverse quantitative structure-property relationship correlations of technologically relevant physical properties

AR Katritzky et al.

JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES (2000)