Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks
Imbalanced class is one of the challenges in classifying big data. Data disparity produces a biased output of a model regardless how recent the technology is. However, deep learning algorithms such as convolutional neural networks and deep belief networks showed promising results in many domains, es...
| Main Authors: | , , |
|---|---|
| Format: | Proceeding Paper |
| Language: | English |
| Published: |
2016
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/53436/ http://irep.iium.edu.my/53436/9/53436.pdf |
| _version_ | 1848784231208058880 |
|---|---|
| author | Amri, A’inur A’fifah Ismail, Amelia Ritahani Abdullah, Ahmad Zarir |
| author_facet | Amri, A’inur A’fifah Ismail, Amelia Ritahani Abdullah, Ahmad Zarir |
| author_sort | Amri, A’inur A’fifah |
| building | IIUM Repository |
| collection | Online Access |
| description | Imbalanced class is one of the challenges in classifying big data. Data disparity produces a biased output of a model regardless how recent the technology is. However, deep learning algorithms such as convolutional neural networks and deep belief networks showed promising results in many domains, especially in image processing. Therefore, in this paper, we will review the effect of imbalanced data disparity in classes using convolutional neural networks and deep belief networks as the benchmark model, and a modified MNIST handwritten dataset as the bench- mark dataset. The experiment shows that although the algorithm is stable and suitable for multiple domains, the imbalanced data distribution still manages to affect the outcome of the model. |
| first_indexed | 2025-11-14T16:33:57Z |
| format | Proceeding Paper |
| id | iium-53436 |
| institution | International Islamic University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T16:33:57Z |
| publishDate | 2016 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | iium-534362016-12-21T01:00:16Z http://irep.iium.edu.my/53436/ Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks Amri, A’inur A’fifah Ismail, Amelia Ritahani Abdullah, Ahmad Zarir QA75 Electronic computers. Computer science Imbalanced class is one of the challenges in classifying big data. Data disparity produces a biased output of a model regardless how recent the technology is. However, deep learning algorithms such as convolutional neural networks and deep belief networks showed promising results in many domains, especially in image processing. Therefore, in this paper, we will review the effect of imbalanced data disparity in classes using convolutional neural networks and deep belief networks as the benchmark model, and a modified MNIST handwritten dataset as the bench- mark dataset. The experiment shows that although the algorithm is stable and suitable for multiple domains, the imbalanced data distribution still manages to affect the outcome of the model. 2016-08 Proceeding Paper NonPeerReviewed application/pdf en http://irep.iium.edu.my/53436/9/53436.pdf Amri, A’inur A’fifah and Ismail, Amelia Ritahani and Abdullah, Ahmad Zarir (2016) Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks. In: The 3rd International Multi-Conference on Artificial Intelligence Technology (M-CAIT 2016), 23rd-24th August 2016, Malacca, Malaysia. (Unpublished) http://www.ftsm.ukm.my/mcait2016/ |
| spellingShingle | QA75 Electronic computers. Computer science Amri, A’inur A’fifah Ismail, Amelia Ritahani Abdullah, Ahmad Zarir Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks |
| title | Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks |
| title_full | Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks |
| title_fullStr | Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks |
| title_full_unstemmed | Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks |
| title_short | Exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks |
| title_sort | exploring imbalanced class issue in handwritten dataset using convolutional neural networks and deep belief networks |
| topic | QA75 Electronic computers. Computer science |
| url | http://irep.iium.edu.my/53436/ http://irep.iium.edu.my/53436/ http://irep.iium.edu.my/53436/9/53436.pdf |