الفهرس | Only 14 pages are availabe for public view |
Abstract Water pollution by organic materials or metals is one of the problems that threaten humanity, both nowadays and over the next decades. Morphological changes in Nile Tilapia 3Oreochromis niloticus3 {uFB01}sh liver and gills can also represent the adaptation strategies to main- tain some physiological functions or to assess acute and chronic expo- sure to chemicals found in water and sediments. This thesis provides an automatic system for assessing water pollution; in Sharkia gover- norate - Egypt, based on microscopic images of {uFB01}sh gills and liver. The proposed system used {uFB01}sh gills and liver as hybrid biomarker to detect water pollution. It utilized case based reasoning (CBR) for indicating the degree of water pollution based on the di{uFB00}erent histopathological changes in {uFB01}sh gills and liver microscopic images. Various performance evaluation metrics; namely, retrieval accuracy, Receiver Operating characteristic (ROC) curves, F-measure, and G- mean, have been used in order to objectively indicate the true perfor- mance of the system considering the unbalanced data. Experimental results showed that the proposed hybrid biomarker CBR based sys- tem achieved water quality prediction accuracy of 97.9 % using cosine distance similarity measure. Also, it outperformed both SVMs and LDA classi{uFB01}ers for the tested microscopic images data set |