An experiment was conducted in the Date Palm Research Units labs / College of Agricultural Engineering Sciences / University of Baghdad to assess the tolerance toward salinity stress in potato after two mutagens treatments in vitro. Potato cv. Arizona and Rivera nodal segments were irradiated with four dosages of gamma rays at 0, 10, 20, and 30 Gray and immersed in (EMS) with four concentrations included 0, 10, 20, and 30 mM. The survival rates after mutagenesis treatments were calculated and 449 lines were obtained. The lines were tested for salinity tolerance by growing in MS medium supplemented with four concentrations of NaCl at 0, 100, 150, and 200 mM and data were analyzed according to the CRD with 10 replicates and means were

This study was aimed to determine the impact of Conocarpus erectus L. compost fertilizer, and some micronutrients on growth and production of potato. This research was conducted at one of the fields of the College of Agricultural Engineering Sciences - University of Baghdad. The experiment was implemented using factorial arrangement (4X3X3) within randomized complete block design with three replicates. Conocarpus fertilizer was represented the first factor with three levels (7.5, 15, 30 ton.ha-1), which symbolized (C2, C3, C4). Chemical fertilizer as recommended dose as a control, which symbolized (C1). The second factor was foliar spraying with three levels of iron (0, 100, 200 mg.L-1), which symbolized (F0, F1, F2). The third fact

Support vector machine (SVM) is a popular supervised learning algorithm based on margin maximization. It has a high training cost and does not scale well to a large number of data points. We propose a multiresolution algorithm MRH-SVM that trains SVM on a hierarchical data aggregation structure, which also serves as a common data input to other learning algorithms. The proposed algorithm learns SVM models using high-level data aggregates and only visits data aggregates at more detailed levels where support vectors reside. In addition to performance improvements, the algorithm has advantages such as the ability to handle data streams and datasets with imbalanced classes. Experimental results show significant performance improvements in compa