Feature selection intelligent algorithm with mutual information and steepest ascent strategy
This work addresses dimensionality reduction for hyperspectral image classification, which is an incremental improvement in remote sensing data mining.
The paper tackled the problem of reducing dimensionality in hyperspectral images by developing a feature selection algorithm that combines mutual information with a steepest ascent strategy to select relevant bands for classification, achieving results that differ from human decisions as demonstrated on the AVIRIS 92AV3C dataset.
Remote sensing is a higher technology to produce knowledge for data mining applications. In principle hyperspectral images (HSIs) is a remote sensing tool that provides precise classification of regions. The HSI contains more than a hundred of images of the ground truth (GT) map. Some images are carrying relevant information, but others describe redundant information, or they are affected by atmospheric noise. The aim is to reduce dimensionality of HSI. Many studies use mutual information (MI) or normalised forms of MI to select appropriate bands. In this paper we design an algorithm based also on MI, and we combine MI with steepest ascent algorithm, to improve a symmetric uncertainty coefficient-based strategy to select relevant bands for classification of HSI. This algorithm is a feature selection tool and a wrapper strategy. We perform our study on HSI AVIRIS 92AV3C. This is an artificial intelligent system to control redundancy; we had to clear the difference of the result's algorithm and the human decision, and this can be viewed as case study which human decision is perhaps different to an intelligent algorithm. Index Terms - Hyperspectral images, Classification, Fea-ture selection, Mutual Information, Redundancy, Steepest Ascent. Artificial Intelligence