Gene Selection in Microarray Datasets Using Progressively Refined PSO Scheme

Authors: Yamuna Prasad, K. Biswas

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on publicly available datasets, Colon, Leukemia and T2D show that our approach selects only a very small subset of genes while yielding substantial improvements in accuracy over state-of-the-art evolutionary methods.
Researcher Affiliation Academia Indian Institute of Technology Delhi New Delhi, India 110016 {yprasad, kkb}@cse.iitd.ac.in
Pseudocode Yes Algorithm 1: Progressively Refined PSO
Open Source Code No The paper does not provide any explicit statements about releasing source code or links to a code repository for the described methodology.
Open Datasets Yes We experiment with five publicly available benchmark microarray datasets, namely Colon, Lymphoma, Leukemia, RAOA and T2D (Ganesh K. et al. 2012).
Dataset Splits Yes We followed training and test splitting of (Li et al. 2008) and (Ganesh K. et al. 2012) for 10CV and LOOCV strategies respectively. ... The cost parameter C in SVM is tuned using 5-fold cross-validation on training dataset only for computing fitness of a particle in PSO.
Hardware Specification No The paper does not provide specific hardware details like CPU/GPU models, processor types, or memory amounts used for running experiments.
Software Dependencies No The paper mentions using Linear SVM (Fan et al. 2008) but does not provide specific version numbers for any software components or libraries.
Experiment Setup Yes For PSO implementation, we used C1 = 2, C2 = 2, ω =0.9, K=40 and T=100 (Li et al. 2008). The maximum number of iterative depth D is set to 20 in PRPSO method.