Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.20532/cit.2017.1003294

Hybrid Feature Selection Approach Based on GRASP for Cancer Microarray Data

Arpita Nagpal ; Department of Computer Science and Engineering, School of Engineering and Technology, The NorthCap University, Gurugram, Haryana, India
Deepti Gaur ; Department of Computer Science and Engineering, School of Engineering and Technology, The NorthCap University, Gurugram, Haryana, India


Puni tekst: engleski pdf 337 Kb

str. 133-148

preuzimanja: 656

citiraj


Sažetak

Microarray data usually contain a large number of genes, but a small number of samples. Feature subset selection for microarray data aims at reducing the number of genes so that useful information can be extracted from the samples. Reducing the dimension of data sets further helps in improving the computational efficiency of the learning model. In this paper, we propose a modified algorithm based on the tabu search as local search procedures to a Greedy Randomized Adaptive Search Procedure (GRASP) for high dimensional microarray data sets. The proposed Tabu based Greedy Randomized Adaptive Search Procedure algorithm is named as TGRASP. In TGRASP, a new parameter has been introduced named as Tabu Tenure and the existing parameters, NumIter and size have been modified. We observed that different parameter settings affect the quality of the optimum. The second proposed algorithm known as FFGRASP (Firefly Greedy Randomized Adaptive Search Procedure) uses a firefly optimization algorithm in the local search optimzation phase of the greedy randomized adaptive search procedure (GRASP). Firefly algorithm is one of the powerful algorithms for optimization of multimodal applications. Experimental results show that the proposed TGRASP and FFGRASP algorithms are much better than existing algorithm with respect to three performance parameters viz. accuracy, run time, number of a selected subset of features. We have also compared both the approaches with a unified metric (Extended Adjusted Ratio of Ratios) which has shown that TGRASP approach outperforms existing approach for six out of nine cancer microarray datasets and FFGRASP performs better on seven out of nine datasets.

Ključne riječi

feature selection; microarray; classification; GRASP; hill climbing; firefly algorithm; tabu search

Hrčak ID:

183329

URI

https://hrcak.srce.hr/183329

Datum izdavanja:

26.6.2017.

Posjeta: 1.404 *