Search results for: Vida Jodaeian

3 The Role of Thermo Priming on Improving Seedling Production Technology (Ispt) in Soybean [Glycine max (L.) Merrill] Seeds

Abstract:

In order to determine the impact of thermo priming on germination of soybean seeds, an experiment was conducted as a completely randomized design with three replications. The factors of studied included different time thermo priming (control, 5 and 10 minutes) through the placing seeds were exposed to oven. The results showed that the effect of thermo priming was significant on germination percentage, seedling dry weight and seedling vigour in P ≤ 0.05. Mean comparison showed that the highest germination percentage (77%), seedling dry weight (1.39 g) and seedling vigour (107.03) were achieved by 10 minutes thermo priming.

Keywords: Thermo priming, seedling, seedling production, seedling growth, soybean.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2362

2 A New Algorithm to Stereo Correspondence Using Rank Transform and Morphology Based On Genetic Algorithm

Authors: Razagh Hafezi, Ahmad Keshavarz, Vida Moshfegh

Abstract:

This paper presents a novel algorithm of stereo correspondence with rank transform. In this algorithm we used the genetic algorithm to achieve the accurate disparity map. Genetic algorithms are efficient search methods based on principles of population genetic, i.e. mating, chromosome crossover, gene mutation, and natural selection. Finally morphology is employed to remove the errors and discontinuities.

Keywords: genetic algorithm, morphology, rank transform, stereo correspondence

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2123

1 Hybrid Machine Learning Approach for Text Categorization

Authors: Nerijus Remeikis, Ignas Skucas, Vida Melninkaite

Abstract:

Text categorization - the assignment of natural language documents to one or more predefined categories based on their semantic content - is an important component in many information organization and management tasks. Performance of neural networks learning is known to be sensitive to the initial weights and architecture. This paper discusses the use multilayer neural network initialization with decision tree classifier for improving text categorization accuracy. An adaptation of the algorithm is proposed in which a decision tree from root node until a final leave is used for initialization of multilayer neural network. The experimental evaluation demonstrates this approach provides better classification accuracy with Reuters-21578 corpus, one of the standard benchmarks for text categorization tasks. We present results comparing the accuracy of this approach with multilayer neural network initialized with traditional random method and decision tree classifiers.

Keywords: Text categorization, decision trees, neural networks, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1763