Abstract:
Linear discriminant analysis (LDA) is a classical statistical machine-learning method that finds a linear data transformation that increases class discrimination in an optimal discriminant subspace. LDA assumes Gaussian class distributions and single-label data annotations. We propose a new LDA variant for dimensionality reduction on original data in multilabel classification tasks to improve classifier performance. A probabilistic class saliency estimation method computes saliency-based weights for all instances. Weights are used to redefine between-class and within-class scatter matrices for projection matrix calculation. Six saliency-based multilabel LDA (SMLDA) variants are based on different prior information on the importance of each instance for their class(es) extracted from labels and features. Our experiments show that the proposed SMLDA outperforms several dimensionality reduction methods in multilabel classification problems.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
