![]() | 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 ”Oreochromis niloticus” sh liver and gills can also represent the adaptation strategies to maintain some physiological functions or to assess acute and chronic exposure to chemicals found in water and sediments. This thesis provides an automatic system for assessing water pollution ; in Sharkia governorate- Egypt, based on microscopic images of sh gills and liver. The proposed system used 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 dierent histopathological changes in sh gills and liver microscopic images. Various performance evaluation metrics; namely, retrieval accuracy, Receiver Operating characteristic (ROC) curves, F-measure, and Gmean, have been used in order to objectively indicate the true performance of the system considering the unbalanced data. Experimental results showed that the proposed hybrid biomarker CBR based system achieved water quality prediction accuracy of 97.9 % using cosine distance similarity measure. Also, it outperformed both SVMs and LDA classifiers for the tested microscopic images data set. |