کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
507684 865138 2013 8 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Improvement of the multilayer perceptron for air quality modelling through an adaptive learning scheme
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر نرم افزارهای علوم کامپیوتر
پیش نمایش صفحه اول مقاله
Improvement of the multilayer perceptron for air quality modelling through an adaptive learning scheme
چکیده انگلیسی


• The behavior of PM10 was modeled by a time-varying multilayer perceptron model.
• The time-varying model overperformed the conventional MLP counterpart.
• The adaptive learning scheme can address the uncertainty of the prediction.

Multilayer perceptron (MLP), normally trained by the offline backpropagation algorithm, could not adapt to the changing air quality system and subsequently underperforms. To improve this, the extended Kalman filter is adopted into the learning algorithm to build a time-varying multilayer perceptron (TVMLP) in this study. Application of the TVMLP to model the daily averaged concentration of the respirable suspended particulates with aerodynamic diameter of not more than 10 µm (PM10) in Macau shows statistically significant improvement on the performance indicators over the MLP counterpart. In addition, the adaptive learning algorithm could also address explicitly the uncertainty of the prediction so that confidence intervals can be provided. More importantly, the adaptiveness of the TVMLP gives prediction improvement on the region of higher particulate concentrations that the public concerns.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Computers & Geosciences - Volume 59, September 2013, Pages 148–155
نویسندگان
, , ,