This page has only limited features, please log in for full access.
The use of ensemble methods for obtaining scalable solutions on complex multidimensional datasets has increased manifold in the field of advanced machine learning and analytics owing to the ensemble method's capabilities of combining multiple base estimators to generate a more robust estimator than any single estimator with a given algorithm. Bagging and boosting are the two widely used ensemble methods. This article presents a step‐by‐step approach to the applications of python in evaluating the performance of three bagging ensemble methods, namely, bagging, random forest, and extremely randomized trees for predicting the in‐bus carbon dioxide concentrations. The bagging ensemble model evaluation results from this study were compared with the results obtained from a prior study that evaluated the performance of four boosting (gradient boosting machine, light gradient boosting machine, extreme gradient boosting, adaptive boosting) ensemble methods using the same in‐bus database. Among the seven ensemble methods, the random forest ensemble method provided better results on the basis of predictive model evaluation with operational performance measures. The readers may adopt the bagging ensemble methods (inclusive of the python coding) discussed in this article to successfully address their own data science problems. © 2018 American Institute of Chemical Engineers Environ Prog, 2018
Akhil Kadiyala; Ashok Kumar. Applications of Python to Evaluate the Performance of Bagging Methods. Environmental Progress & Sustainable Energy 2018, 1 .
AMA StyleAkhil Kadiyala, Ashok Kumar. Applications of Python to Evaluate the Performance of Bagging Methods. Environmental Progress & Sustainable Energy. 2018; ():1.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2018. "Applications of Python to Evaluate the Performance of Bagging Methods." Environmental Progress & Sustainable Energy , no. : 1.
The use of ensemble methods for obtaining scalable solutions on complex multi‐dimensional datasets has increased manifold in the field of advanced machine learning and analytics owing to the ensemble method's capabilities of combining multiple base estimators to generate a more robust estimator than any single estimator with a given algorithm. Bagging and boosting are the two widely used ensemble methods. This paper presents a step‐by‐step approach to the applications of python in evaluating the performance of three bagging ensemble methods, namely, bagging, random forest, and extremely randomized trees for predicting the in‐bus carbon dioxide concentrations. The bagging ensemble model evaluation results from this study were compared with the results obtained from a prior study that evaluated the performance of four boosting (gradient boosting machine, light gradient boosting machine, extreme gradient boosting, adaptive boosting) ensemble methods utilizing the same in‐bus database. Among the seven ensemble methods, the random forest ensemble method provided better results on the basis of predictive model evaluation with operational performance measures. The readers may adopt the bagging ensemble methods (inclusive of the python coding) discussed in this article to successfully address their own data science problems. © 2018 American Institute of Chemical Engineers Environ Prog, 37: 1555–1559, 2018
Akhil Kadiyala; Ashok Kumar. Applications of python to evaluate the performance of bagging methods. Environmental Progress & Sustainable Energy 2018, 37, 1555 -1559.
AMA StyleAkhil Kadiyala, Ashok Kumar. Applications of python to evaluate the performance of bagging methods. Environmental Progress & Sustainable Energy. 2018; 37 (5):1555-1559.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2018. "Applications of python to evaluate the performance of bagging methods." Environmental Progress & Sustainable Energy 37, no. 5: 1555-1559.
There is a significant convergence of interests in the research community efforts to advance the development and application of software resources (capable of handling the relevant mathematical algorithms to provide scalable information) for solving data science problems. Anaconda is one of the many open source platforms that facilitate the use of open source programming languages (R, Python) for large-scale data processing, predictive analytics, and scientific computing. The environmental research community may choose to adapt the use of either of the R or the Python programming languages for analyzing the data science problems on the Anaconda platform. This study demonstrated the applications of using Scikit-learn (a Python machine learning library package) on Anaconda platform for analyzing the in-bus carbon dioxide concentrations by (i) importing the data into Spyder (Python 3.6) in Anaconda, (ii) performing an exploratory data analysis, (iii) performing dimensionality reduction through RandomForestRegressor feature selection, (iv) developing statistical regression models, and (v) generating regression decision tree models with DecisionTreeRegressor feature. The readers may adopt the methods (inclusive of the Python coding) discussed in this article to successfully address their own data science problems. © 2017 American Institute of Chemical Engineers Environ Prog, 36: 1580–1586, 2017
Akhil Kadiyala; Ashok Kumar. Applications of Python to evaluate environmental data science problems. Environmental Progress & Sustainable Energy 2017, 36, 1580 -1586.
AMA StyleAkhil Kadiyala, Ashok Kumar. Applications of Python to evaluate environmental data science problems. Environmental Progress & Sustainable Energy. 2017; 36 (6):1580-1586.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2017. "Applications of Python to evaluate environmental data science problems." Environmental Progress & Sustainable Energy 36, no. 6: 1580-1586.
Open source programming languages and software platforms play a vital role in the progress of research towards developing new methods for addressing data science problems. R is one such platform that the research community may adapt and make the required changes to the codes in accordance with the requisite needs, specifically when analyzing data in different forms (structured, semistructured, unstructured). This study demonstrated the applications of R for analyzing in-bus carbon dioxide concentrations by: (i) importing the data into RStudio; (ii) performing an exploratory data analysis; (iii) developing statistical regression models; and (iv) developing tree models using machine learning methods. The readers may adopt the methods discussed in this paper to successfully address their own data science problems. © 2017 American Institute of Chemical Engineers Environ Prog, 36: 1358–1364, 2017
Akhil Kadiyala; Ashok Kumar. Applications of R to evaluate environmental data science problems. Environmental Progress & Sustainable Energy 2017, 36, 1358 -1364.
AMA StyleAkhil Kadiyala, Ashok Kumar. Applications of R to evaluate environmental data science problems. Environmental Progress & Sustainable Energy. 2017; 36 (5):1358-1364.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2017. "Applications of R to evaluate environmental data science problems." Environmental Progress & Sustainable Energy 36, no. 5: 1358-1364.
This paper contains an extensive review of life cycle assessment (LCA) studies on greenhouse gas emissions (GHG) from different material-based photovoltaic (PV) and working mechanism-based concentrating solar power (CSP) electricity generation systems. Statistical evaluation of the life cycle GHG emissions is conducted to assess the role of different PVs and CSPs in reducing GHG emissions. The widely-used parabolic trough and central receiver CSP electricity generation systems emitted approximately 50% more GHGs than the paraboloidal dish, solar chimney, and solar pond CSP electricity generation systems. The cadmium telluride PVs and solar pond CSPs contributed to minimum life cycle GHGs. Thin-film PVs are also suitable for wider implementation, due to their lower Energy Pay-Back Time (EPBT) periods, in addition to lower GHG emission, in comparison with c-Si PVs.
Raghava Kommalapati; Akhil Kadiyala; Tarkik Shahriar; Ziaul Huque. Review of the Life Cycle Greenhouse Gas Emissions from Different Photovoltaic and Concentrating Solar Power Electricity Generation Systems. Energies 2017, 10, 350 .
AMA StyleRaghava Kommalapati, Akhil Kadiyala, Tarkik Shahriar, Ziaul Huque. Review of the Life Cycle Greenhouse Gas Emissions from Different Photovoltaic and Concentrating Solar Power Electricity Generation Systems. Energies. 2017; 10 (3):350.
Chicago/Turabian StyleRaghava Kommalapati; Akhil Kadiyala; Tarkik Shahriar; Ziaul Huque. 2017. "Review of the Life Cycle Greenhouse Gas Emissions from Different Photovoltaic and Concentrating Solar Power Electricity Generation Systems." Energies 10, no. 3: 350.
Akhil Kadiyala; Ashok Kumar. Vector Time Series-Based Radial Basis Function Neural Network Modeling of Air Quality Inside a Public Transportation Bus Using Available Software. Environmental Progress & Sustainable Energy 2017, 36, 4 -10.
AMA StyleAkhil Kadiyala, Ashok Kumar. Vector Time Series-Based Radial Basis Function Neural Network Modeling of Air Quality Inside a Public Transportation Bus Using Available Software. Environmental Progress & Sustainable Energy. 2017; 36 (1):4-10.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2017. "Vector Time Series-Based Radial Basis Function Neural Network Modeling of Air Quality Inside a Public Transportation Bus Using Available Software." Environmental Progress & Sustainable Energy 36, no. 1: 4-10.
This paper evaluates life cycle greenhouse gas (GHG) emissions from the use of different biomass feedstock categories (agriculture residues, dedicated energy crops, forestry, industry, parks and gardens, wastes) independently on biomass-only (biomass as a standalone fuel) and cofiring (biomass used in combination with coal) electricity generation systems. The statistical evaluation of the life cycle GHG emissions (expressed in grams of carbon dioxide equivalent per kilowatt hour, gCO2e/kWh) for biomass electricity generation systems was based on the review of 19 life cycle assessment studies (representing 66 biomass cases). The mean life cycle GHG emissions resulting from the use of agriculture residues (N = 4), dedicated energy crops (N = 19), forestry (N = 6), industry (N = 4), and wastes (N = 2) in biomass-only electricity generation systems are 291.25 gCO2e/kWh, 208.41 gCO2e/kWh, 43 gCO2e/kWh, 45.93 gCO2e/kWh, and 1731.36 gCO2e/kWh, respectively. The mean life cycle GHG emissions for cofiring electricity generation systems using agriculture residues (N = 10), dedicated energy crops (N = 9), forestry (N = 9), industry (N = 2), and parks and gardens (N = 1) are 1039.92 gCO2e/kWh, 1001.38 gCO2e/kWh, 961.45 gCO2e/kWh, 926.1 gCO2e/kWh, and 1065.92 gCO2e/kWh, respectively. Forestry and industry (avoiding the impacts of biomass production and emissions from waste management) contribute the least amount of GHGs, irrespective of the biomass electricity generation system.
Akhil Kadiyala; Raghava Kommalapati; Ziaul Huque. Evaluation of the Life Cycle Greenhouse Gas Emissions from Different Biomass Feedstock Electricity Generation Systems. Sustainability 2016, 8, 1181 .
AMA StyleAkhil Kadiyala, Raghava Kommalapati, Ziaul Huque. Evaluation of the Life Cycle Greenhouse Gas Emissions from Different Biomass Feedstock Electricity Generation Systems. Sustainability. 2016; 8 (11):1181.
Chicago/Turabian StyleAkhil Kadiyala; Raghava Kommalapati; Ziaul Huque. 2016. "Evaluation of the Life Cycle Greenhouse Gas Emissions from Different Biomass Feedstock Electricity Generation Systems." Sustainability 8, no. 11: 1181.
This paper statistically quantifies the lifecycle greenhouse gas (GHG) emissions from six distinct reactor-based (boiling water reactor (BWR), pressurized water reactor (PWR), light water reactor (LWR), heavy-water-moderated reactor (HWR), gas-cooled reactor (GCR), fast breeder reactor (FBR)) nuclear power generation systems by following a two-step approach that included (a) performing a review of the lifecycle assessment (LCA) studies on the reactor-based nuclear power generation systems; and (b) statistically evaluating the lifecycle GHG emissions (expressed in grams of carbon dioxide equivalent per kilowatt hour, gCO2e/kWh) for each of the reactor-based nuclear power generation systems to assess the role of different types of nuclear reactors in the reduction of the lifecycle GHG emissions. Additionally, this study quantified the impacts of fuel enrichment methods (centrifuge, gaseous diffusion) on GHG emissions. The mean lifecycle GHG emissions resulting from the use of BWR (sample size, N = 15), PWR (N = 21), LWR (N = 7), HWR (N = 3), GCR (N = 1), and FBR (N = 2) in nuclear power generation systems are 14.52 gCO2e/kWh, 11.87 gCO2e/kWh, 20.5 gCO2e/kWh, 28.2 gCO2e/kWh, 8.35 gCO2e/kWh, and 6.26 gCO2e/kWh, respectively. The FBR nuclear power generation systems produced the minimum lifecycle GHGs. The centrifuge enrichment method produced lower GHG emissions than the gaseous diffusion enrichment method.
Akhil Kadiyala; Raghava Kommalapati; Ziaul Huque. Quantification of the Lifecycle Greenhouse Gas Emissions from Nuclear Power Generation Systems. Energies 2016, 9, 863 .
AMA StyleAkhil Kadiyala, Raghava Kommalapati, Ziaul Huque. Quantification of the Lifecycle Greenhouse Gas Emissions from Nuclear Power Generation Systems. Energies. 2016; 9 (11):863.
Chicago/Turabian StyleAkhil Kadiyala; Raghava Kommalapati; Ziaul Huque. 2016. "Quantification of the Lifecycle Greenhouse Gas Emissions from Nuclear Power Generation Systems." Energies 9, no. 11: 863.
This study evaluated the life cycle greenhouse gas (GHG) emissions from different hydroelectricity generation systems by first performing a comprehensive review of the hydroelectricity generation system life cycle assessment (LCA) studies and then subsequent computation of statistical metrics to quantify the life cycle GHG emissions (expressed in grams of carbon dioxide equivalent per kilowatt hour, gCO2e/kWh). A categorization index (with unique category codes, formatted as “facility type-electric power generation capacity”) was developed and used in this study to evaluate the life cycle GHG emissions from the reviewed hydroelectricity generation systems. The unique category codes were labeled by integrating the names of the two hydro power sub-classifications, i.e., the facility type (impoundment (I), diversion (D), pumped storage (PS), miscellaneous hydropower works (MHPW)) and the electric power generation capacity (micro (µ), small (S), large (L)). The characterized hydroelectricity generation systems were statistically evaluated to determine the reduction in corresponding life cycle GHG emissions. A total of eight unique categorization codes (I-S, I-L, D-µ, D-S, D-L, PS-L, MHPW-µ, MHPW-S) were designated to the 19 hydroelectricity generation LCA studies (representing 178 hydropower cases) using the proposed categorization index. The mean life cycle GHG emissions resulting from the use of I-S (N = 24), I-L (N = 8), D-µ (N = 3), D-S (N = 133), D-L (N = 3), PS-L (N = 3), MHPW-µ (N = 3), and MHPW-S (N = 1) hydroelectricity generation systems are 21.05 gCO2e/kWh, 40.63 gCO2e/kWh, 47.82 gCO2e/kWh, 27.18 gCO2e/kWh, 3.45 gCO2e/kWh, 256.63 gCO2e/kWh, 19.73 gCO2e/kWh, and 2.78 gCO2e/kWh, respectively. D-L hydroelectricity generation systems produced the minimum life cycle GHGs (considering the hydroelectricity generation system categories with a representation of at least two cases).
Akhil Kadiyala; Raghava Kommalapati; Ziaul Huque. Evaluation of the Life Cycle Greenhouse Gas Emissions from Hydroelectricity Generation Systems. Sustainability 2016, 8, 539 .
AMA StyleAkhil Kadiyala, Raghava Kommalapati, Ziaul Huque. Evaluation of the Life Cycle Greenhouse Gas Emissions from Hydroelectricity Generation Systems. Sustainability. 2016; 8 (6):539.
Chicago/Turabian StyleAkhil Kadiyala; Raghava Kommalapati; Ziaul Huque. 2016. "Evaluation of the Life Cycle Greenhouse Gas Emissions from Hydroelectricity Generation Systems." Sustainability 8, no. 6: 539.
The development of valid air quality models (adressing the complex interrelationships between air contaminants and influential variables) is an integral component to developing good indoor air quality (IAQ) management strategies. With an increase in the capabilities of computational resources to process large datasets utilizing the hybrid mathematical calculations, environmentalists are now better equipped to develop and use hybrid IAQ models. This software review paper presents the development and evaluation of one such hybrid IAQ model, referred to as the multivariate time series based radial basis function neural network models (multivariate time series + radial basis function neural networks) for the monitored contaminants of carbon dioxide and carbon monoxide inside a public transportation bus using available software. © 2016 American Institute of Chemical Engineers Environ Prog, 2016
Akhil Kadiyala; Ashok Kumar. Multivariate time series based radial basis function neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy 2016, 35, 931 -935.
AMA StyleAkhil Kadiyala, Ashok Kumar. Multivariate time series based radial basis function neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy. 2016; 35 (4):931-935.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2016. "Multivariate time series based radial basis function neural network modeling of air quality inside a public transportation bus using available software." Environmental Progress & Sustainable Energy 35, no. 4: 931-935.
Modern indoor air quality (IAQ) management plans integrate the use of valid air quality models that accurately predict the dynamics of air quality variations within a considered environment. With rapid advancements in the field of computer sciences that helped improve the capabilities of computational resources and the availability of a wide-ranging spectrum of methodologies that address different aspects of the nonlinearity in a multi-dimensional information domain, there is ample scope for environmental professionals to develop and use hybrid IAQ models. This software review paper presents one such methodology that combines the use of the univariate time series and the radial basis function neural network methods in the development and evaluation of univariate time series based radial basis function neural network hybrid IAQ models for the monitored contaminants of carbon dioxide and carbon monoxide inside a public transportation bus using available software. © 2016 American Institute of Chemical Engineers Environ Prog, 2016
Akhil Kadiyala; Ashok Kumar. Univariate time series based radial basis function neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy 2016, 35, 320 -324.
AMA StyleAkhil Kadiyala, Ashok Kumar. Univariate time series based radial basis function neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy. 2016; 35 (2):320-324.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2016. "Univariate time series based radial basis function neural network modeling of air quality inside a public transportation bus using available software." Environmental Progress & Sustainable Energy 35, no. 2: 320-324.
This software review article describes the development of hybrid indoor air quality (IAQ) models by integrating the use of vector time series (VTS) and back propagation neural network (BPNN) modeling approaches. BPNNs are the most widely adopted artificial neural networks that serve as universal approximators and provide a flexible computational platform to integrate conventional modeling approaches like time series in developing hybrid environmental prediction (or forecasting) models. The hybrid VTS-based BPNN IAQ prediction models developed and validated in this study using available software are based on the monitoried in-bus contaminants of carbon dioxide and carbon monoxide. © 2015 American Institute of Chemical Engineers Environ Prog, 2015
Akhil Kadiyala; Ashok Kumar. Vector-time-series-based back propagation neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy 2015, 35, 7 -13.
AMA StyleAkhil Kadiyala, Ashok Kumar. Vector-time-series-based back propagation neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy. 2015; 35 (1):7-13.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2015. "Vector-time-series-based back propagation neural network modeling of air quality inside a public transportation bus using available software." Environmental Progress & Sustainable Energy 35, no. 1: 7-13.
Time series and artificial neural networks (ANNs) are two distinct methodologies that present environmental researchers and managers with the resources to develop reliable and accurate indoor air quality (IAQ) models. The development of valid IAQ models is a fundamental component in the development of risk assessment and mitigation plans that ensure an occupant's exposure to indoor air contaminants are within the permissible IAQ guidelines. This software review paper provides a detailed step-by-step description of the methodology on how one may integrate the use of the multivariate time series and the back propagation neural network (widely used ANN) methods simultaneously in the development of valid in-bus carbon dioxide and carbon monoxide models using available software. © 2015 American Institute of Chemical Engineers Environ Prog, 34: 1259–1266, 2015
Akhil Kadiyala; Ashok Kumar. Multivariate time series based back propagation neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy 2015, 34, 1259 -1266.
AMA StyleAkhil Kadiyala, Ashok Kumar. Multivariate time series based back propagation neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy. 2015; 34 (5):1259-1266.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2015. "Multivariate time series based back propagation neural network modeling of air quality inside a public transportation bus using available software." Environmental Progress & Sustainable Energy 34, no. 5: 1259-1266.
The development of reliable and accurate indoor air quality (IAQ) models is essential to predict occupant exposures within a considered microenvironment, in addition to the assessment of ventilation design characteristics (influencing air flow rates) to ensure indoor air contaminant levels are within the permissible IAQ guidelines. Time series and artificial neural networks (ANNs) are two distinct methodologies that present environmentalists with the resources in developing valid IAQ models. Over the years, the simple structure and robustness in prediction made the use of time series attractive to environmentalists in modeling their respective databases; while, the ease of modeling complex nonlinear multivariate environmental databases made ANNs gain prominence in the last 2 decades. The use of time series and ANNs together though has not been extensively examined in the field of environmental engineering and science. This software review article presents a methodology that combines the use of univariate time series and back propagation neural network (widely used ANN) methods in the development and evaluation of IAQ models for the monitored contaminants of carbon dioxide and carbon monoxide inside a public transportation bus using available software. © 2015 American Institute of Chemical Engineers Environ Prog, 34: 319–323, 2015
Akhil Kadiyala; Ashok Kumar. Univariate time series based back propagation neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy 2015, 34, 319 -323.
AMA StyleAkhil Kadiyala, Ashok Kumar. Univariate time series based back propagation neural network modeling of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy. 2015; 34 (2):319-323.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2015. "Univariate time series based back propagation neural network modeling of air quality inside a public transportation bus using available software." Environmental Progress & Sustainable Energy 34, no. 2: 319-323.
Tarkik Shahriar; Akhil Kadiyala; Raghava Kommalapati; Ziaul Huque. A Review of Ozone Studies in the Houston−Galveston−Brazoria Nonattainment Area. ACS Symposium Series 2015, 37 -50.
AMA StyleTarkik Shahriar, Akhil Kadiyala, Raghava Kommalapati, Ziaul Huque. A Review of Ozone Studies in the Houston−Galveston−Brazoria Nonattainment Area. ACS Symposium Series. 2015; ():37-50.
Chicago/Turabian StyleTarkik Shahriar; Akhil Kadiyala; Raghava Kommalapati; Ziaul Huque. 2015. "A Review of Ozone Studies in the Houston−Galveston−Brazoria Nonattainment Area." ACS Symposium Series , no. : 37-50.
Akhil Kadiyala; Ashok Kumar. Vector time series models for prediction of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy 2014, 33, 1069 -1073.
AMA StyleAkhil Kadiyala, Ashok Kumar. Vector time series models for prediction of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy. 2014; 33 (4):1069-1073.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2014. "Vector time series models for prediction of air quality inside a public transportation bus using available software." Environmental Progress & Sustainable Energy 33, no. 4: 1069-1073.
Ashok Kumar; Akhil Kadiyala; Dipsikha Sarmah. Evaluation of Geographic Information Systems-Based Spatial Interpolation Methods Using Ohio Indoor Radon Data. The Open Environmental Engineering Journal 2014, 7, 1 -9.
AMA StyleAshok Kumar, Akhil Kadiyala, Dipsikha Sarmah. Evaluation of Geographic Information Systems-Based Spatial Interpolation Methods Using Ohio Indoor Radon Data. The Open Environmental Engineering Journal. 2014; 7 (1):1-9.
Chicago/Turabian StyleAshok Kumar; Akhil Kadiyala; Dipsikha Sarmah. 2014. "Evaluation of Geographic Information Systems-Based Spatial Interpolation Methods Using Ohio Indoor Radon Data." The Open Environmental Engineering Journal 7, no. 1: 1-9.
Indoor air pollution predictions, if reliable and accurate, could play an important role in managing indoor air quality (IAQ). Accurate predictions of the air contaminants inside a transit microenvironment could assist vehicle manufacturers in the design of optimal ventilation systems by facilitating adequate air exchange rate that can prevent the buildup of in‐vehicle contaminants beyond recommended IAQ guidelines. The predictions can also be of particular interest to the public in understanding the possible levels of exposure when commuting during different time periods of a day. Due to the simple structure and the robustness in prediction, the use of time series models is greatly encouraged. This study demonstrates the methodology to develop and validate the multivariate time series transfer function models (ARMAX/ARIMAX) for the in‐bus contaminant concentrations of carbon dioxide and carbon monoxide using available software. © 2014 American Institute of Chemical Engineers Environ Prog, 33: 337–341, 2014
Akhil Kadiyala; Ashok Kumar. Multivariate time series models for prediction of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy 2014, 33, 337 -341.
AMA StyleAkhil Kadiyala, Ashok Kumar. Multivariate time series models for prediction of air quality inside a public transportation bus using available software. Environmental Progress & Sustainable Energy. 2014; 33 (2):337-341.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2014. "Multivariate time series models for prediction of air quality inside a public transportation bus using available software." Environmental Progress & Sustainable Energy 33, no. 2: 337-341.
Akhil Kadiyala; Ashok Kumar. Development of a pollution prevention tool for sustainable management of hospital wastes. Environmental Progress & Sustainable Energy 2013, 32, 872 -876.
AMA StyleAkhil Kadiyala, Ashok Kumar. Development of a pollution prevention tool for sustainable management of hospital wastes. Environmental Progress & Sustainable Energy. 2013; 32 (4):872-876.
Chicago/Turabian StyleAkhil Kadiyala; Ashok Kumar. 2013. "Development of a pollution prevention tool for sustainable management of hospital wastes." Environmental Progress & Sustainable Energy 32, no. 4: 872-876.
The present study developed a novel approach to modeling indoor air quality (IAQ) of a public transportation bus by the development of hybrid genetic-algorithm-based neural networks (also known as evolutionary neural networks) with input variables optimized from using the regression trees, referred as the GART approach. This study validated the applicability of the GART modeling approach in solving complex nonlinear systems by accurately predicting the monitored contaminants of carbon dioxide (CO2), carbon monoxide (CO), nitric oxide (NO), sulfur dioxide (SO2), 0.3-0.4 microm sized particle numbers, 0.4-0.5 microm sized particle numbers, particulate matter (PM) concentrations less than 1.0 microm (PM10), and PM concentrations less than 2.5 microm (PM2.5) inside a public transportation bus operating on 20% grade biodiesel in Toledo, OH. First, the important variables affecting each monitored in-bus contaminant were determined using regression trees. Second, the analysis of variance was used as a complimentary sensitivity analysis to the regression tree results to determine a subset of statistically significant variables affecting each monitored in-bus contaminant. Finally, the identified subsets of statistically significant variables were used as inputs to develop three artificial neural network (ANN) models. The models developed were regression tree-based back-propagation network (BPN-RT), regression tree-based radial basis function network (RBFN-RT), and GART models. Performance measures were used to validate the predictive capacity of the developed IAQ models. The results from this approach were compared with the results obtained from using a theoretical approach and a generalized practicable approach to modeling IAQ that included the consideration of additional independent variables when developing the aforementioned ANN models. The hybrid GART models were able to capture majority of the variance in the monitored in-bus contaminants. The genetic-algorithm-based neural network IAQ models outperformed the traditional ANN methods of the back-propagation and the radial basis function networks.
Akhil Kadiyala; Devinder Kaur; Ashok Kumar. Development of hybrid genetic-algorithm-based neural networks using regression trees for modeling air quality inside a public transportation bus. Journal of the Air & Waste Management Association 2012, 63, 205 -218.
AMA StyleAkhil Kadiyala, Devinder Kaur, Ashok Kumar. Development of hybrid genetic-algorithm-based neural networks using regression trees for modeling air quality inside a public transportation bus. Journal of the Air & Waste Management Association. 2012; 63 (2):205-218.
Chicago/Turabian StyleAkhil Kadiyala; Devinder Kaur; Ashok Kumar. 2012. "Development of hybrid genetic-algorithm-based neural networks using regression trees for modeling air quality inside a public transportation bus." Journal of the Air & Waste Management Association 63, no. 2: 205-218.