Browsing by Author "Dasanayake, D"

Now showing 1 - 2 of 2

Embargo
Classification of Documents and Images Using an Enhanced Genetic Algorithm
(IEEE, 2022-12-09) Athuraliya, N; De Silva, H; Dasanayake, D; Fernando, K; Haddela, P.S; Gunarathne, A
In 1975, John Holland proposed the Genetic Algorithm (GA). The algorithm is widely used to provide superior solutions for optimization and search problems by relying on biologically inspired operators including mutation, crossover, and selection. The fittest individuals are chosen for reproduction in this algorithm to generate the next generation’s offspring. Classification is a technique used in data mining to analyze the collected data and to divide them into different classes. The relationship between a known class assignment and the properties of the entity to be classed may serve as the foundation for the classification procedure. Through this research, it has mainly consider classification for documents and images using GA. In order to enhance the accuracy and to reduce the error rate of traditional models, a new approach is proposed which is based on GA. The primary benefit of using GA in conjunction with classification is the efficiency in which it can address optimization issues. The experiment results are used to verify the suggested algorithm using benchmark data sets gathered from the UCI machine learning repository.
Embargo
Genetic Algorithm Based Hybrid Clustering Technique for the Retinal Blood Vessels Segmentation
(IEEE, 2022-12-09) Dasanayake, D; Athuraliya, N; De Silva, H; Fernando, K; Haddela ., P.S
Important details about the visual anomaly can be found in the retinal fundus imaging. The segmentation of the blood vessels is crucial and necessary for diagnosing different ocular fundus. The primary and most common causes of blindness are diabetic retinopathy and its effects on the retinal vascular structures. The study suggested a genetic algorithm combined with the K-means clustering technique for unsupervised retinal segmentation. An essential pre-processing step for vessel identification applications is vessel enhancement. The CLAHE filtering method is employed in this work as a preprocessing step for vessel improvement. The improved vessels were grouped together using a genetic approach, and K-means clustering was applied for superior clustering outcomes. DRIVE and IOSTAR databases that are accessible to the public are used to evaluate the suggested strategy. According to the experimental findings, the proposed algorithm successfully separates clusters that are more dense and well-separated than those of other previous findings. Both the Calinski-Harabasz I ndex S core and the Silhouette Index Score are used to validate the proposed algorithm.