Artificial Intelligence-Based Prediction Models for Environmental Engineering

Yetilmezsoy, Kaan; Özkaya, Bestamin; Çakmakçı, Mehmet

doi:10.14311/nnw.2011.21.012

Cited by 99 publications

(45 citation statements)

References 95 publications

(150 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several models have been proposed in the literature. Those models range from simple (average based models) [34][35][36][37][38][39][40] to very complex (Artificial Intelligence based tools such as deep learning-based techniques).…”

Section: Future Developments: Sote and Lcamentioning

confidence: 99%

Sustainable Overall Throughputability Effectiveness (S.O.T.E.) as a Metric for Production Systems

2018

View full text Add to dashboard Cite

This paper proposes a new index for a comprehensive and systematic measurement of sustainability and throughput performance in production systems. The proposed index, called Sustainable Overall Throughput Effectiveness (S.O.T.E.), is designed on the basis of a comparison of the environmental and operational factors. Specifically, it integrates the following four dimensions: availability, utilization, performance, and environmental sustainability. The way each dimension is measured is explained and justified. This index uses the overall environmental equipment effectiveness (OEEE) index, which is based on the Overall Equipment Effectiveness (OEE) index. However, such metrics are lacking at the factory level, because OEEE, as well as the OEE, is devoted to equipment-level. Its application and potential contribution to the analysis of sustainable throughput is demonstrated through a case study in an actual crushing plant. Through examining several hypotheses concerning the relationship between operational and environmental performance, a series of useful conclusions could be raised. The main difference and advantage of the proposed S.O.T.E. is that S.O.T.E., as it is based on the Overall Throughput Effectiveness (OTE), measures factory-level sustainability and operational performance. S.O.T.E. allows us to relate the impact of the overall effectiveness of each one of the components of the index to each piece of equipment that makes a part of the production systems. Furthermore, S.O.T.E., as OTE, take into account the production system configuration (series, parallel, assembly, etc.).

show abstract

Section: Future Developments: Sote and Lcamentioning

confidence: 99%

Sustainable Overall Throughputability Effectiveness (S.O.T.E.) as a Metric for Production Systems

2018

View full text Add to dashboard Cite

show abstract

“…The weighted sum of the inputs are transferred to the hidden neurons, where it is transformed using an activation function, such as a tangent sigmoid activation function. In turn, the outputs of the hidden neurons act as inputs to the output neuron where they undergo another transformation (Yetilmezsoy et al 2011).…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

“…When the learning is complete, the neural network is used for prediction. The primary goal of training is to minimize an error function by searching for a set of connection strengths and biases that causes the ANN to produce outputs equal or close to the targets (Yetilmezsoy et al 2011).…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

Forecasting Hazardous Waste Generation Using Short Data Sets: Case Study of Lithuania / Pavojingųjų Atliekų Susidarymo Prognozavimas Naudojant Trumpas Duomenų Imtis: Lietuvos Atvejis

Karpušenkaitė

Денафас

Ruzgas

2016

Mokslas – Lietuvos Ateitis

View full text Add to dashboard Cite

and development of effective hazardous waste utilization methods or the establishment of certain facilities.The overview of previously conducted research on waste matter in general showed that various mathematical forecasting methods were used to predict solid waste generation. Only a few published research papers that were able to be found using a wide access to scientific journals and subscribed scientific databases uncovered successful application of mathematical prognostic methods applicable for few types of hazardous waste, but not hazardous waste in general. This paper will only overview those research papers that showed the most promising forecasting results.A study conducted by Abdol et al. (2011) presented the approach to unravel the interpolating problem of various structures of artificial neural networks (ANN) for the long-term prediction of solid waste generation (SWG). Results indicate that the multilayer perception approach has more advantages in comparison with traditional methods, like MLR, in predicting the municipal SWG (Abdol et al. 2011).Artificial neural networks (ANNs) and multiple linear regression (MLR) were applied to predict the total rate of medical waste generation and in different types of sharp, infectious and general waste. ANNs showed high performance measure values (R 2 = 0,99 Abstract. Due to inefficient waste sorting in primary and secondary waste generation sources Lithuania fails in trying to meet EU requirements for waste management sector regarding the amount of waste flow that reaches landfills. Especially sensitive situation is with hazardous waste, which often are disposed along with municipal solid waste and with it reaches landfills and due to the fact that mechanical and biological treatment plant are only now being established in the biggest cities of Lithuania, landfills becomes a big issue. The main purpose of this research is to find out which mathematical modelling methods could be fitted and if it is possible to forecast annual hazardous waste generation by using automotive, medical and daylight lamps waste generation statistical data. This is part of a research of medical, automotive and daylight lamps waste generation forecasting possibilities. Tests on the performance of artificial neural networks, multiple linear regression, partial least squares, support vector machines and four nonparametric regression methods were conducted on two developed data sets. The best and most promising results in both cases were demonstrated by generalized additives method (R 2 = 0.99) and kernel regression (R 2 = 0.99).

show abstract

“…Successful application of ANN based models for environmental problems in past decades stands for its reliability, robustness and adjustability [16][17][18]. These properties stem from the ability of learning complex nonlinear relationships within multiple variables particularly in situations where the explicit form of the relations is unknown [19].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Multivariate Model for the Optical Detection of Total Organic Carbon

Kokya

Mehrdadi

Ardestani

et al. 2016

J. Chil. Chem. Soc.

View full text Add to dashboard Cite

UV inactivity and fluorescence irradiance of various organic substances are the major drawbacks for a wide applicability of UV based TOC assessment models, especially in drinking water utilities and environmental fields. The adoption of an intelligent model is the key factor to access a reliable and effective detection. The accurate training of the artificial neural network model and backward elimination of less significant parameters, conferred more predictive properties to TOC detection. This led to an efficient optimal TOC detection model based on turbidity, UV 254 absorbance and true color. The validation of model performance was investigated through application of untrained scenarios. The outcome of the validation analysis showed a correlation coefficient of 0.87 and root mean square error of 0.48 while the training performance of the model showed 0.95 and 0.33 respectively. The results indicated that the trained ANN model was efficiently capable for TOC detection in water resources based on the main drivers.

show abstract

Artificial Intelligence-Based Prediction Models for Environmental Engineering

Cited by 99 publications

References 95 publications

Sustainable Overall Throughputability Effectiveness (S.O.T.E.) as a Metric for Production Systems

Sustainable Overall Throughputability Effectiveness (S.O.T.E.) as a Metric for Production Systems

Forecasting Hazardous Waste Generation Using Short Data Sets: Case Study of Lithuania / Pavojingųjų Atliekų Susidarymo Prognozavimas Naudojant Trumpas Duomenų Imtis: Lietuvos Atvejis

Intelligent Multivariate Model for the Optical Detection of Total Organic Carbon

Contact Info

Product

Resources

About