Improving Classification Performance with Statistically Weighted Dimensions and Dimensionality Reduction
Source abstract
Abstract
In image classification, various techniques have been developed to enhance the performance of principal component analysis (PCA) dimension reduction techniques with guiding weighting features to remove redundant and irrelevant features. This study proposes the statistically weighted dimension technique based on three distribution-related class behaviors; collection-class, inter-class, and intra-class to enhance the feature-extraction ability before using PCA for feature selection. The data from the statistics-weighted dimension spaces is utilized to reduce dimensionality by reducing the large index data into smaller index data using PCA. The new principal component from the weighted training part by an unlabeled dataset is constructed and then the image is classified efficiently. Additionally, the weighting direction investigates the pros and cons of promoting and demoting to determine the worst or best option utilizing the exponents of three proposed weighted scheme. The experiment is conducted using three datasets, MNIST, E-MNIST, and F-MNIST, along with three image classification algorithms, logistic Regression, KNN, and SVM (RBF). The results clearly demonstrate that the statistically weighted dimension feature can improve the conventional classification accuracy in lower dimensions with an appropriate combination of weighting nearly 3% for the best solution on dimensionality reduction by more than 50%.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Face and Expression Recognition · Remote-Sensing Image Classification · Image Retrieval and Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Science and Arts, Chanthaburi Campus, Burapha University, Chanthaburi 22170, Thailand
Department of Electrical and Computer Engineering, Assumption University, Samut Prakan 10570, Thailand
Funding
Burapha University
References (34)
Show source-provided references
1. Xing, H., Chen, B., Feng, Y., Ni, Y., Hou, D., Wang, X., and Kong, Y. (2022). Mapping irrigated, rainfed and paddy croplands from time-series sentinel-2 images by integrating pixel-based classification and image segmentation on google earth engine. Geocarto Int., 1–20.10.1080/10106049.2022.2076923 ↗
2. Sparse principal component analysis for natural language processing10.1007/s40745-020-00277-x ↗
3. Gupta, D., Bansal, P., and Choudhary, K. (2018). Speech and Language Processing for Human-Machine Communications, Springer.
4. 3D cnn-pca: A deep-learning-based parameterization for complex geomodels10.1016/j.cageo.2020.104676 ↗
5. Multimodal medical image fusion based on ihs and pca10.1016/j.proeng.2010.11.045 ↗
6. Pca-based edge-preserving features for hyperspectral image classification10.1109/TGRS.2017.2743102 ↗
7. Combining variable selection with dimensionality reduction10.1109/CVPR.2005.103 ↗
8. Puyati, W., and Walairacht, A. (2008, January 17–20). Efficiency improvement for unconstrained face recognition by weightening probability values of modular pca and wavelet pca. Proceedings of the 2008 10th International Conference on Advanced Communication Technology, Phoenix Park, Republic of Korea.10.1109/ICACT.2008.4494037 ↗
9. Feature extraction and selection of kidney ultrasound images using glcm and pca10.1016/j.procs.2020.03.382 ↗
10. Probabilistic principal component analysis with expectation maximization (ppca-em) facilitates volume classification and estimates the missing data
11. Digital image recognition based on fractional-order-pca-svm coupling algorithm10.1016/j.measurement.2019.02.006 ↗
12. A low effort approach to structured cnn design using pca10.1109/ACCESS.2019.2961960 ↗
13. Shah, F.P., and Patel, V. (2016, January 23–25). A review on feature selection and feature extraction for text classification. Proceedings of the 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, India.10.1109/WiSPNET.2016.7566545 ↗
14. Ting, G., Moydin, K., and Hamdulla, A. (2018, January 29–30). An overview of feature extraction methods for handwritten image retrieval. Proceedings of the 2018 3rd International Conference on Smart City and Systems Engineering (ICSCSE), Xiamen, China.10.1109/ICSCSE.2018.00181 ↗
15. Xing, H., Chen, B., and Lu, M. (2022). A sub-seasonal crop information identification framework for crop rotation mapping in smallholder farming areas with time series sentinel-2 imagery. Remote. Sens., 14.10.3390/rs14246280 ↗
16. Yumeng, C., and Yinglan, F. (2020, January 23–25). Research on pca data dimension reduction algorithm based on entropy weight method. Proceedings of the 2020 2nd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), Osaka, Japan.10.1109/MLBDBI51377.2020.00084 ↗
17. Zhang, S., Chen, X., Li, P., and Cai, Q. (2019, January 17–19). Data dimensionality reduction method combining intra-class and inter-class distance. Proceedings of the 2019 International Conference on Artificial Intelligence and Advanced Manufacturing, Dublin, Ireland.10.1145/3358331.3358348 ↗
18. Buatoom, U., Kongprawechnon, W., and Theeramunkong, T. (2020). Document clustering using k-means with term weighting as similarity-based constraints. Symmetry, 12.10.3390/sym12060967 ↗
19. Hernandez, W., Mendez, A., and Göksel, T. (2018). Statistics-Growing Data Sets and Growing Demand for Statistics, IntechOpen.
20. Principal component analysis in medical image processing: A study10.1504/IJIM.2015.070024 ↗
21. Li, X., Zhang, L., and You, J. (2019). Locally weighted discriminant analysis for hyperspectral image classification. Remote. Sens., 11.10.3390/rs11020109 ↗
22. Weighted principal component extraction with genetic algorithms10.1016/j.asoc.2011.08.030 ↗
23. Toward more efficient wmsn data search combined fjlt dimension expansion with pca dimension reduction10.1109/ACCESS.2020.2999484 ↗
24. Tavoli, R., Kozegar, E., Shojafar, M., Soleimani, H., and Pooranian, Z. (2013, January 2–4). Weighted pca for improving document image retrieval system based on keyword spotting accuracy. Proceedings of the 2013 36th International Conference on Telecommunications and Signal Processing (TSP), Rome, Italy.10.1109/TSP.2013.6614043 ↗
25. Feature extraction using evolutionary weighted principal component analysis10.1109/ICSMC.2005.1571170 ↗
26. Improved results on frequency-weighted balanced truncation and error bounds10.1002/rnc.1745 ↗
27. Adaptive entropy weighted picture fuzzy clustering algorithm with spatial information for image segmentation10.1016/j.asoc.2019.105888 ↗
28. Improving seeded k-means clustering with deviation-and entropy-based term weightings10.1587/transinf.2019IIP0017 ↗
29. Pilarczyk, R., and Skarbek, W. (2019). On intra-class variance for deep learning of classifiers. arXiv.10.2478/fcds-2019-0015 ↗
30. Facial expression recognition by inter-class relational learning10.1109/ACCESS.2019.2928983 ↗
31. Venkataramanan, A., Laviale, M., Figus, C., Usseglio-Polatera, P., and Pradalier, C. (2021, January 22–24). Tackling inter-class similarity and intra-class variance for microscopic image-based classification. Proceedings of the International Conference on Computer Vision Systems, Virtual.10.1007/978-3-030-87156-7_8 ↗
32. Hameed, Z., Rehman, W.U., Khan, W., Ullah, N., and Albogamy, F.R. (2021). Weighted hybrid feature reduction embedded with ensemble learning for speech data of parkinson’s disease. Mathematics, 9.10.3390/math9243172 ↗
33. Cohen, G., Afshar, S., Tapson, J., and Schaik, A.V. (2017, January 14–19). Emnist: Extending mnist to handwritten letters. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.10.1109/IJCNN.2017.7966217 ↗
34. Xiao, H., Rasul, K., and Vollgraf, R. (2017). Fashion-mnist: A novel image dataset for benchmarking machine learning algorithms. arXiv.