Search

Technologies like machine learning in the current times, have emerged as capable domains of research in Computer Science. In Machine learning, the system is trained on the basis of the available dataset; the dataset may contain many redundant and irrelevant features which may require more memory for storage and also increases the cost of computation. Selection of best features enhances the accuracy of data classification along with working on smallest amount of features is considered as an optimization problem. Metaheuristic algorithms in current times have been used far and wide unravel various optimization problems. In this context, this study aims to discuss the solution of feature selection problem using metaheuristic algorithms and presents a population based comparison of four metaheuristic algorithms for extracting smallest feature subset with utmost accuracy.

In this research work, the growth of the fingernail plate does not affect the biometric authentication system. Now, the accuracy has been improved with FF-BPNN method and PCA algorithm. PCA algorithm is used for the extraction of the unique image features that depends on the valuable properties. The trained feature set forwards FF-BPNN model to train the feature set. If the feature set is true, then the transient finger nail is identified, if false, then transient fingernail is not found in the dataset. The performance metrics for each of the feature extraction method with Feed Forward-BPNN classifier is analyzed. The Comparison of Proposed works using Feed Forward-BPNN value is 98.4%. The existing algorithm used for comparison with Accuracy rate value is 90.2%.

Maximizing the duration of a warning system by arrangement procedures of devices is a successful solution to develop power successful instant warning networks. Following the arbitrary arrangement of devices in the goal region, the situation of locating the greatest amount of disjoint models of devices, with every collection to be able to totally protect the goal region, is nondeterministic polynomial-complete. That report proposes a cross strategy of mixing a genetic algorithm with routine move procedures, termed STHGA, to deal with that problem. Distinctive from different techniques in the literature, STHGA adopts a ahead selection system for chromosomes in the people and employs some efficient genetic and warning routine move operations. The uniqueness of the ahead selection system is that the most gene price of every chromosome is improved continually with the answer quality, which pertains to the amount of disjoint total protect sets. By exerting the constraint on chromosomes, the ahead selection system shows the architectural top features of probable schedules of devices and gives advice for more advancement. Complying with the selection needs, genetic procedures and routine move procedures in STHGA work to alter the imperfect protect collection in to a total one, while another models however keep total protection through the routine of unnecessary devices in the sets. Purposes for realizing several goal factors, termed point-coverage, and for your region, termed area-coverage, have already been useful for assessing the potency of STHGA. Besides the amount of devices and devices 'realizing stages, the effect of devices 'redundancy on the efficiency of STHGA has already been analyzed. Effects reveal that the planned algorithm is encouraging and outperforms another present strategy by equally optimization pace and answer quality.

Ultrasound images are difficult to segment due to presence of speckle noise and the boundaries of abnormal regions are also difficult to recognize due to similarity. It is important to segment the image for correct and effective diagnosis. Manual method of segmentation is good but not effective for segmentation of large data sets, due to this an automatic or computerized segmentation is motivated. An automatic region growing segmentation for ultrasound images is presented in this work. An automatic selection of seed is adopted because of time consumption, poor accuracy and need of human interaction in manual seed selection. In ultrasound images, identification of the boundaries of abnormal regions is impossible but automatic seed selection provides accurate location of abnormal regions. The proposed method outperforms the existing state-of-the-art techniques based on the texture features and visual results.