Selection of Sustainable Process and Essential Indicators for Decision Making Using Machine Learning Algorithms

Mukherjee, Rabindra Nath

doi:10.1007/s41660-017-0011-4

Cited by 18 publications

(11 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms usually produce accurate results, at high computational costs, which may even improve if data are scattered. Therefore, this method has been used to treat uncertainty in studies, such as [ 83 , 84 ].…”

Section: Computational Methods For Decision-making Under Uncertaintymentioning

confidence: 99%

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Alzate-Mejía

Santos-Boada

Amazonas

2021

Sensors

View full text Add to dashboard Cite

Among the several emerging dimensioning, control and deployment of future communication network paradigms stands out the human-centric characteristic that creates an intricate relationship between telematics and human activities. The hard to model dynamics of user behavior introduces new uncertainties into these systems that give rise to difficult network resource management challenges. According to this context, this work reviews several decision-making computational methods under the influence of uncertainties. This work, by means of a systematic literature review, focuses on sensor-based Internet of Things scenarios such as Smart Spaces and Industry 4.0. According to our conclusions, it is mandatory to establish a means for modeling the human behavior context in order to improve resource assignment and management.

show abstract

Section: Computational Methods For Decision-making Under Uncertaintymentioning

confidence: 99%

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Alzate-Mejía

Santos-Boada

Amazonas

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Supervised learning algorithms are widely studied in many fields of engineering and sciences primarily in classification and regression-type problems for predicting either a categorical output or a continuous output, respectively [ 24 , 26 – 32 ]. Classification is the problem of finding the categorical output of a new observation and distinguishing between different classes of information via statistical recognition of patterns in a training data set.…”

Section: Methodsmentioning

confidence: 99%

“…Feature selection or variable selection is one of the key processes in machine learning model building, where the aim is to identify a subset of features among many others that are uncorrelated and the most informative set of descriptors, for a given data-driven modeling problem. There is a growing interest within various fields of engineering and sciences for developing computationally efficient feature selection algorithms that enable the identification of the minimum number of features for maximum predictive capabilities in data-driven models [21][22][23][24][25]. Here, the feature selection is done in two steps: (1) Through hierarchical clustering for identifying the groups of similar and correlated features, and (2) Through a heuristic feature selection step, in which a single feature is selected from each cluster based on the ER pathway model presented in [6].…”

Section: Er Data Normalmentioning

confidence: 99%

“…In this work, the training set is a balanced subset of the active compounds that contain both agonist and antagonist chemicals and their corresponding 4 technical replicates, whereas the testing set is the remaining unseen active compounds with their corresponding 4 technical replicates, not used in the training phase. Supervised learning algorithms are widely studied in many fields of engineering and sciences primarily in classification and regression-type problems for predicting either a categorical output or a continuous output, respectively [24,[26][27][28][29][30][31][32]. Classification is the problem of finding the categorical output of a new observation and distinguishing between different classes of information via statistical recognition of patterns in a training data set.…”

Section: Plos Computational Biologymentioning

confidence: 99%

See 1 more Smart Citation

Classification of estrogenic compounds by coupling high content analysis and machine learning algorithms

et al. 2020

Self Cite

View full text Add to dashboard Cite

Environmental toxicants affect human health in various ways. Of the thousands of chemicals present in the environment, those with adverse effects on the endocrine system are referred to as endocrine-disrupting chemicals (EDCs). Here, we focused on a subclass of EDCs that impacts the estrogen receptor (ER), a pivotal transcriptional regulator in health and disease. Estrogenic activity of compounds can be measured by many in vitro or cellbased high throughput assays that record various endpoints from large pools of cells, and increasingly at the single-cell level. To simultaneously capture multiple mechanistic ER endpoints in individual cells that are affected by EDCs, we previously developed a sensitive high throughput/high content imaging assay that is based upon a stable cell line harboring a visible multicopy ER responsive transcription unit and expressing a green fluorescent protein (GFP) fusion of ER. High content analysis generates voluminous multiplex data comprised of minable features that describe numerous mechanistic endpoints. In this study, we present a machine learning pipeline for rapid, accurate, and sensitive assessment of the endocrine-disrupting potential of benchmark chemicals based on data generated from high content analysis. The multidimensional imaging data was used to train a classification model to ultimately predict the impact of unknown compounds on the ER, either as agonists or antagonists. To this end, both linear logistic regression and nonlinear Random Forest classifiers were benchmarked and evaluated for predicting the estrogenic activity of unknown compounds. Furthermore, through feature selection, data visualization, and model discrimination, the most informative features were identified for the classification of ER agonists/antagonists. The results of this data-driven study showed that highly accurate and generalized classification models with a minimum number of features can be constructed PLOS COMPUTATIONAL BIOLOGY

show abstract

“…One approach is to use an augmented metric that combines economic, environmental, and other sustainability objectives (Sikdar et al 2012;El-Halwagi 2017b). In this case, due to the multivariate nature of the problem, it is important to find the contribution of different sustainability objectives in finding the optimal solution (Mukherjee et al 2013;Mukherjee 2017). Alternatively, a multi-objective optimization approach can be used.…”

Section: Problem Formulationmentioning

confidence: 99%

Optimal Design of Water Distribution Networks with Incorporation of Uncertainties and Energy Nexus

Mukherjee¹,

González-Bravo

Nápoles‐Rivera

et al. 2017

Process Integr Optim Sustain

Self Cite

View full text Add to dashboard Cite

The reliability of water distribution networks is susceptible to large impacts resulting from uncertainties. Several factors may contribute to such uncertainties. These include nodal demands, reservoir/tank levels, and availability of system components. Additional sources of uncertainties arise when water-energy nexus is considered. For instance, when water desalination systems that are coupled with power plants are incorporated in the water distribution networks, uncertainties in energy demand influence the design of the water network system. In this work, a multi-objective optimization framework is developed for the design of water networks that involve dual-purpose power plants for simultaneous water desalination and power generation. The multi-objective model accounts for sustainability goals through environmental, economic, and societal metrics such as greenhouse gas emissions, net profit, and number of jobs created, respectively. Fossil fuels, as well as renewable biofuels and solar power, are considered as candidate sources of energy. Water resources include multiple systems such as dams, lakes, rivers, aquifers, and artificial storage lakes. Demands from agricultural, industrial as well as domestic needs in the region are considered. In order to incorporate uncertainty in the proposed approach, a stochastic optimization model is formulated with a probabilistic objective function and constraints. The network has multiple sources as well as demands with varied distributions. In order to find an overall distribution for probability density estimation, a decomposition scheme is applied where each scenario is solved separately as a sub-problem. The solution from sub-problem is used to find the probability using kernel density estimator. The modified model equations lead to a stochastic MINLP problem. The proposed framework and optimization formulations are applied to a case study in the Mexican state of Sonora. From the demand and natural resource distribution, 12 scenarios have been identified and the model is weighted by their probability of occurrence. The results are compared with the deterministic solution to obtain the cost associated with uncertainty.

show abstract

Selection of Sustainable Process and Essential Indicators for Decision Making Using Machine Learning Algorithms

Cited by 18 publications

References 19 publications

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Decision-Making under Uncertainty for the Deployment of Future Hyperconnected Networks: A Survey

Classification of estrogenic compounds by coupling high content analysis and machine learning algorithms

Optimal Design of Water Distribution Networks with Incorporation of Uncertainties and Energy Nexus

Contact Info

Product

Resources

About