A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Support Vector Machine Modeling Using Particle Swarm Optimization Approach for the Retrieval of Atmospheric Ammonia Concentrations
Abstract This study was performed in order to improve the estimation accuracy of atmospheric ammonia ($ NH_{3} $) concentration levels in the Greater Houston area during extended sampling periods. The approach is based on selecting the appropriate penalty coefficient C and kernel parameter σ2. These parameters directly influence the regression accuracy of the support vector machine (SVM) model. In this paper, two artificial intelligence techniques, particle swarm optimization (PSO) and a genetic algorithm (GA), were used to optimize the SVM model parameters. Data regarding meteorological variables (e.g., ambient temperature and wind direction) and the $ NH_{3} $ concentration levels were employed to develop our two models. The simulation results indicate that both PSO-SVM and GA-SVM methods are effective tools to model the $ NH_{3} $ concentration levels and can yield good prediction performance based on statistical evaluation criteria. PSO-SVM provides higher retrieval accuracy and faster running speed than GA-SVM. In addition, we used the PSO-SVM technique to estimate 17 drop-off $ NH_{3} $ concentration values. We obtained forecasting results with good fitting characteristics to a measured curve. This proved that PSO-SVM is an effective method for estimating unavailable $ NH_{3} $ concentration data at 3, 4, 5, and 6 parts per billion (ppb), respectively. A 4-ppb $ NH_{3} $ concentration had the optimum prediction performance of the simulation results. These results showed that the selection of the set-point values is a significant factor in compensating for the atmospheric $ NH_{3} $ dropout data with the PSO-SVM method. This modeling approach will be useful in the continuous assessment of $ NH_{3} $ sensor discrete data sources.
Support Vector Machine Modeling Using Particle Swarm Optimization Approach for the Retrieval of Atmospheric Ammonia Concentrations
Abstract This study was performed in order to improve the estimation accuracy of atmospheric ammonia ($ NH_{3} $) concentration levels in the Greater Houston area during extended sampling periods. The approach is based on selecting the appropriate penalty coefficient C and kernel parameter σ2. These parameters directly influence the regression accuracy of the support vector machine (SVM) model. In this paper, two artificial intelligence techniques, particle swarm optimization (PSO) and a genetic algorithm (GA), were used to optimize the SVM model parameters. Data regarding meteorological variables (e.g., ambient temperature and wind direction) and the $ NH_{3} $ concentration levels were employed to develop our two models. The simulation results indicate that both PSO-SVM and GA-SVM methods are effective tools to model the $ NH_{3} $ concentration levels and can yield good prediction performance based on statistical evaluation criteria. PSO-SVM provides higher retrieval accuracy and faster running speed than GA-SVM. In addition, we used the PSO-SVM technique to estimate 17 drop-off $ NH_{3} $ concentration values. We obtained forecasting results with good fitting characteristics to a measured curve. This proved that PSO-SVM is an effective method for estimating unavailable $ NH_{3} $ concentration data at 3, 4, 5, and 6 parts per billion (ppb), respectively. A 4-ppb $ NH_{3} $ concentration had the optimum prediction performance of the simulation results. These results showed that the selection of the set-point values is a significant factor in compensating for the atmospheric $ NH_{3} $ dropout data with the PSO-SVM method. This modeling approach will be useful in the continuous assessment of $ NH_{3} $ sensor discrete data sources.
Support Vector Machine Modeling Using Particle Swarm Optimization Approach for the Retrieval of Atmospheric Ammonia Concentrations
Zhang, Jiawei (author) / Tittel, Frank K. (author) / Gong, Longwen (author) / Lewicki, Rafal (author) / Griffin, Robert J. (author) / Jiang, Wenzhe (author) / Jiang, Bin (author) / Li, Mingbao (author)
2015
Article (Journal)
Electronic Resource
English
BKL:
43.00
Umweltforschung, Umweltschutz: Allgemeines
/
43.00$jUmweltforschung$jUmweltschutz: Allgemeines
RFID Anti-Collision Method Based on Particle Swarm Optimization and Support Vector Machine
| British Library Conference Proceedings | 2012
| Taylor & Francis Verlag | 2019