Synergistic Study of Reduced Graphene Oxide as Interfacial Buffer Layer in HTL-free Perovskite Solar Cells with Carbon Electrode
The application of machine learning algorithms to the detection of fraudulent credit card transactions is a challenging problem domain due to the high imbalance in the datasets and confidentiality of financial data. This implies that legitimate transactions make up a high majority of the datasets s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nigerian Society of Physical Sciences
2022-08-01
|
| Series: | Journal of Nigerian Society of Physical Sciences |
| Subjects: | |
| Online Access: | https://journal.nsps.org.ng/index.php/jnsps/article/view/909 |
| _version_ | 1828148894034296832 |
|---|---|
| author | Sherifdeen O. Bolarinwa Eli Danladi Andrew Ichoja Muhammad Y. Onimisia Christopher U. Achem |
| author_facet | Sherifdeen O. Bolarinwa Eli Danladi Andrew Ichoja Muhammad Y. Onimisia Christopher U. Achem |
| author_sort | Sherifdeen O. Bolarinwa |
| collection | DOAJ |
| description |
The application of machine learning algorithms to the detection of fraudulent credit card transactions is a challenging problem domain due to the high imbalance in the datasets and confidentiality of financial data. This implies that legitimate transactions make up a high majority of the datasets such that a weak model with 99% accuracy and faulty predictions may still be assessed as high-performing. To build optimal models, four techniques were used in this research to sample the datasets including the baseline train test split method, the class weighted hyperparameter approach, and the undersampling and oversampling techniques. Three machine learning algorithms were implemented for the development of the models including the Random Forest, XGBoost and TensorFlow Deep Neural Network (DNN). Our observation is that the DNN is more efficient than the other 2 algorithms in modelling the under-sampled dataset while overall, the three algorithms had a better performance in the oversampling technique than in the undersampling technique. However, the Random Forest performed better than the other algorithms in the baseline approach. After comparing our results with some existing state-of-the-art works, we achieved an improved performance using real-world datasets.
|
| first_indexed | 2024-04-11T21:23:06Z |
| format | Article |
| id | doaj.art-7a58e75ad8124cddab53713dfa6e4ed4 |
| institution | Directory Open Access Journal |
| issn | 2714-2817 2714-4704 |
| language | English |
| last_indexed | 2024-04-11T21:23:06Z |
| publishDate | 2022-08-01 |
| publisher | Nigerian Society of Physical Sciences |
| record_format | Article |
| series | Journal of Nigerian Society of Physical Sciences |
| spelling | doaj.art-7a58e75ad8124cddab53713dfa6e4ed42022-12-22T04:02:33ZengNigerian Society of Physical SciencesJournal of Nigerian Society of Physical Sciences2714-28172714-47042022-08-014310.46481/jnsps.2022.909Synergistic Study of Reduced Graphene Oxide as Interfacial Buffer Layer in HTL-free Perovskite Solar Cells with Carbon ElectrodeSherifdeen O. Bolarinwa0Eli Danladi1Andrew Ichoja2Muhammad Y. Onimisia3Christopher U. Achem4Department of Physics, Nigerian Defence Academy, Kaduna, NigeriaNigerian Defence Academy, KadunaDepartment of Physics, Federal University of Health Sciences, Otukpo, Benue State, NigeriaDepartment of Physics, Nigerian Defence Academy, Kaduna, NigeriaCentre for Satellite Technology Development-NASRDA, Abuja, Nigeria The application of machine learning algorithms to the detection of fraudulent credit card transactions is a challenging problem domain due to the high imbalance in the datasets and confidentiality of financial data. This implies that legitimate transactions make up a high majority of the datasets such that a weak model with 99% accuracy and faulty predictions may still be assessed as high-performing. To build optimal models, four techniques were used in this research to sample the datasets including the baseline train test split method, the class weighted hyperparameter approach, and the undersampling and oversampling techniques. Three machine learning algorithms were implemented for the development of the models including the Random Forest, XGBoost and TensorFlow Deep Neural Network (DNN). Our observation is that the DNN is more efficient than the other 2 algorithms in modelling the under-sampled dataset while overall, the three algorithms had a better performance in the oversampling technique than in the undersampling technique. However, the Random Forest performed better than the other algorithms in the baseline approach. After comparing our results with some existing state-of-the-art works, we achieved an improved performance using real-world datasets. https://journal.nsps.org.ng/index.php/jnsps/article/view/909Perovskite Solar CellsReduced Graphene Oxidebuffer layerHTM |
| spellingShingle | Sherifdeen O. Bolarinwa Eli Danladi Andrew Ichoja Muhammad Y. Onimisia Christopher U. Achem Synergistic Study of Reduced Graphene Oxide as Interfacial Buffer Layer in HTL-free Perovskite Solar Cells with Carbon Electrode Journal of Nigerian Society of Physical Sciences Perovskite Solar Cells Reduced Graphene Oxide buffer layer HTM |
| title | Synergistic Study of Reduced Graphene Oxide as Interfacial Buffer Layer in HTL-free Perovskite Solar Cells with Carbon Electrode |
| title_full | Synergistic Study of Reduced Graphene Oxide as Interfacial Buffer Layer in HTL-free Perovskite Solar Cells with Carbon Electrode |
| title_fullStr | Synergistic Study of Reduced Graphene Oxide as Interfacial Buffer Layer in HTL-free Perovskite Solar Cells with Carbon Electrode |
| title_full_unstemmed | Synergistic Study of Reduced Graphene Oxide as Interfacial Buffer Layer in HTL-free Perovskite Solar Cells with Carbon Electrode |
| title_short | Synergistic Study of Reduced Graphene Oxide as Interfacial Buffer Layer in HTL-free Perovskite Solar Cells with Carbon Electrode |
| title_sort | synergistic study of reduced graphene oxide as interfacial buffer layer in htl free perovskite solar cells with carbon electrode |
| topic | Perovskite Solar Cells Reduced Graphene Oxide buffer layer HTM |
| url | https://journal.nsps.org.ng/index.php/jnsps/article/view/909 |
| work_keys_str_mv | AT sherifdeenobolarinwa synergisticstudyofreducedgrapheneoxideasinterfacialbufferlayerinhtlfreeperovskitesolarcellswithcarbonelectrode AT elidanladi synergisticstudyofreducedgrapheneoxideasinterfacialbufferlayerinhtlfreeperovskitesolarcellswithcarbonelectrode AT andrewichoja synergisticstudyofreducedgrapheneoxideasinterfacialbufferlayerinhtlfreeperovskitesolarcellswithcarbonelectrode AT muhammadyonimisia synergisticstudyofreducedgrapheneoxideasinterfacialbufferlayerinhtlfreeperovskitesolarcellswithcarbonelectrode AT christopheruachem synergisticstudyofreducedgrapheneoxideasinterfacialbufferlayerinhtlfreeperovskitesolarcellswithcarbonelectrode |