A Genetic Programming Based Pollutant Concentration Predictor Design for Urban Pollution Monitoring Based on Multi-Sensor Electronic Nose

Ari, Davut; Alagöz, Barış Baykant

doi:10.1109/icit52682.2021.9491122

Cited by 2 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Especially, the low MRE performance is significant for precise measurement of low-level CO concentrations. The MRE of the optimal ANN with EA-GWO is lower than the MRE of other methods in the literature (automatic Bayesian regularization (De Vito et al, 2009) and the genetic programming model (Ari and Alagoz, 2021)).…”

Section: Experimental Studymentioning

confidence: 79%

“…The calibration errors could be confined within the range ±1 mg/m 3 for a 10-day estimation period. The MRE of the optimal ANN model with EA-GWO was obtained 0.084, which indicates more than 20% reduction in MREs of automatic Bayesian regularization (De Vito et al, 2009) method and genetic programming (Ari and Alagoz, 2021).…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, ANNs have been widely implemented for automated detection and classification of odors, vapors, and gasses in various applications (Jamal et al, 2010). ANN estimation models have been also implemented for the calibration of pollutant concentration sensors (Ari and Alagoz, 2021; De Vito et al, 2008). A survey of the recent progresses in e-nose technology and their implemented machine learning methods were summarized in the work of Ye et al (2021).…”

Section: Introductionmentioning

confidence: 99%

“…There are several works demonstrating the use of other computational intelligence methods in e-nose applications: concentration estimation problems are usually solved by developing regression models (Carotta et al, 2001). Genetic programming was used for estimation of pollutant concentrations based on multi-sensor array measurements (Ari and Alagoz, 2021). Various methods such as feature extraction methods, k -means clustering, neural networks, and support vector machines (Capelli et al, 2014; Wilson, 2012) have been used in e-nose applications for the gas and odor recognition.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Optimal architecture artificial neural network model design with exploitative alpha gray wolf optimization for soft calibration of CO concentration measurements in electronic nose applications

Simsek

Alagöz

2022

Transactions of the Institute of Measurement and Control

Self Cite

View full text Add to dashboard Cite

The low-cost and small size solid-state sensor arrays are suitable to implement a wide-area electronic nose (e-nose) for real-time air quality monitoring. However, accuracy of these low-cost sensors is not adequate for precise measurements of pollutant concentrations. Artificial neural network (ANN) estimation models are used for the soft calibration of low-cost sensor array measurements and significantly improve the accuracy of low-cost multi-sensor measurements. However, optimality of neural architecture affects the performance of ANN estimation models, and optimization of the ANN architecture for a training data set is essential to improve data-driven modeling performance of ANNs to reach optimal neural complexity and improved generalization. In this study, an optimal architecture ANN estimator design scheme is suggested to improve the estimation performance of ANN models for e-nose applications. To this end, a gray wolf optimization (GWO) algorithm is modified, and an exploitative alpha gray wolf optimization (EA-GWO) algorithm is suggested. This modification enhances local exploitation skill of the best alpha gray wolf search agent, and thus allows the fine-tuning of ANN architectures by minimizing a multi-objective cost function that implements mean error search policy. Experimental study demonstrates the effectiveness of optimal architecture ANN models to estimate CO concentration from the low-cost multi-sensor data.

show abstract

Section: Experimental Studymentioning

confidence: 79%

Section: Discussionmentioning

confidence: 99%