Ensemble Learning for Overall Power Conversion Efficiency of the All-Organic Dye-Sensitized Solar Cells
Authors:
Open Access
- 25 June 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 34118-34126
Abstract
Ensemble learning breaks the bottleneck of weak learners and is usually significantly more accurate than base learners. The overall power conversion efficiency of all-organic dye-sensitized solar cells is difficult to obtain by either calculations or experiments. To achieve high accurate models, various ensemble learning methods are investigated. Three types of global ensemble models, including homogeneous and heterogeneous ensembles, are constructed, which outperformed the best single base learner, a support vector machine model (MAE: 0.52; Q2: 0.76); in particular, a novel local heterogeneous ensemble model (MAE: 0.34 and Q2: 0.91) achieved high accuracy and generalization. This study shows ensemble learning model is capable of exploring complicated quantitative structure activity relationship, where the features are distant from targets.Keywords
Funding Information
- National Natural Science Foundation of China (21473025)
- Science and Technology Development Planning of Jilin Province (20150204041GX, 20160204044GX)
This publication has 28 references indexed in Scilit:
- Prediction and Identification of Krüppel-Like Transcription Factors by Machine Learning MethodCombinatorial Chemistry & High Throughput Screening, 2017
- Comparing decision tree algorithms to estimate intercity trip distributionTransportation Research Part C: Emerging Technologies, 2017
- Recent Development of Graphene-Based Cathode Materials for Dye-Sensitized Solar CellsJournal of Nanomaterials, 2016
- Predicting human intestinal absorption of diverse chemicals using ensemble learning based QSAR modeling approachesComputational Biology and Chemistry, 2016
- A cascaded QSAR model for efficient prediction of overall power conversion efficiency of all-organic dye-sensitized solar cellsJournal of Computational Chemistry, 2015
- Donor/Acceptor Indenoperylene Dye for Highly Efficient Organic Dye-Sensitized Solar CellsJournal of the American Chemical Society, 2015
- Applying Ant Colony Optimization to configuring stacking ensembles for data miningExpert Systems with Applications, 2014
- QSPR studies of impact sensitivity of nitro energetic compounds using three-dimensional descriptorsJournal of Molecular Graphics and Modelling, 2012
- Principles of QSAR models validation: internal and externalQSAR & Combinatorial Science, 2007
- The Weighted Majority AlgorithmInformation and Computation, 1994