An Optimal Stacked Ensemble Deep Learning Model for Predicting Time-Series Data Using a Genetic Algorithm-An Application for Aerosol Particle Number Concentrations

Näytä kaikki kuvailutiedot



Pysyväisosoite

http://hdl.handle.net/10138/325340

Lähdeviite

Surakhi , O M , Zaidan , M A , Serhan , S , Salah , I & Hussein , T 2020 , ' An Optimal Stacked Ensemble Deep Learning Model for Predicting Time-Series Data Using a Genetic Algorithm-An Application for Aerosol Particle Number Concentrations ' , Computers , vol. 9 , no. 4 , 89 . https://doi.org/10.3390/computers9040089

Julkaisun nimi: An Optimal Stacked Ensemble Deep Learning Model for Predicting Time-Series Data Using a Genetic Algorithm-An Application for Aerosol Particle Number Concentrations
Tekijä: Surakhi, Ola M.; Zaidan, Martha Arbayani; Serhan, Sami; Salah, Imad; Hussein, Tareq
Tekijän organisaatio: Institute for Atmospheric and Earth System Research (INAR)
Global Atmosphere-Earth surface feedbacks
Air quality research group
Päiväys: 2020-12
Kieli: eng
Sivumäärä: 26
Kuuluu julkaisusarjaan: Computers
ISSN: 2073-431X
DOI-tunniste: https://doi.org/10.3390/computers9040089
URI: http://hdl.handle.net/10138/325340
Tiivistelmä: Time-series prediction is an important area that inspires numerous research disciplines for various applications, including air quality databases. Developing a robust and accurate model for time-series data becomes a challenging task, because it involves training different models and optimization. In this paper, we proposed and tested three machine learning techniques—recurrent neural networks (RNN), heuristic algorithm and ensemble learning—to develop a predictive model for estimating atmospheric particle number concentrations in the form of a time-series database. Here, the RNN included three variants—Long-Short Term Memory, Gated Recurrent Network, and Bi-directional Recurrent Neural Network—with various configurations. A Genetic Algorithm (GA) was then used to find the optimal time-lag in order to enhance the model’s performance. The optimized models were used to construct a stacked ensemble model as well as to perform the final prediction. The results demonstrated that the time-lag value can be optimized by using the heuristic algorithm; consequently, this improved the model prediction accuracy. Further improvement can be achieved by using ensemble learning that combines several models for better performance and more accurate predictions.Time-series prediction is an important area that inspires numerous research disciplines for various applications, including air quality databases. Developing a robust and accurate model for time-series data becomes a challenging task, because it involves training different models and optimization. In this paper, we proposed and tested three machine learning techniques-recurrent neural networks (RNN), heuristic algorithm and ensemble learning-to develop a predictive model for estimating atmospheric particle number concentrations in the form of a time-series database. Here, the RNN included three variants-Long-Short Term Memory, Gated Recurrent Network, and Bi-directional Recurrent Neural Network-with various configurations. A Genetic Algorithm (GA) was then used to find the optimal time-lag in order to enhance the model's performance. The optimized models were used to construct a stacked ensemble model as well as to perform the final prediction. The results demonstrated that the time-lag value can be optimized by using the heuristic algorithm; consequently, this improved the model prediction accuracy. Further improvement can be achieved by using ensemble learning that combines several models for better performance and more accurate predictions.
Avainsanat: 113 Computer and information sciences
112 Statistics and probability
Vertaisarvioitu: Kyllä
Tekijänoikeustiedot: cc_by
Pääsyrajoitteet: openAccess
Rinnakkaistallennettu versio: publishedVersion


Tiedostot

Latausmäärä yhteensä: Ladataan...

Tiedosto(t) Koko Formaatti Näytä
computers_09_00089.pdf 22.73MB PDF Avaa tiedosto

Viite kuuluu kokoelmiin:

Näytä kaikki kuvailutiedot