Image segmentation with a multilevel threshold using backtracking search optimization algorithm

Image segmentation is an important process in image processing. Though, there are many applications are affected by the segmentation methods and algorithms, unfortunately, not one technique, but the threshold is the popular one. Threshold technique can be categorized into two ways either simple threshold which has one threshold or multi- thresholds separated which has more than two thresholds . In this paper, image segmentation is used simple threshold method which is a simple and effective technique. Therefore, to calculate the value of threshold solution which is led to increase exponentially threshold that gives multi-thresholds image segmentation present a huge challenge. This paper is considered the multi-thresholds segmentation model for the optimization problem in order to overcome the problem of excessive calculation. The objective of this paper proposed an slgorithmto solve the optimization problem and realize multi-thresholds image segmentation. The proposed multi-thresholds segmentation algorithm should be segmented the raw image into pieces, and compared with other algorithms results. The experimental results that show multi-thresholds image segmentation based on backtracking search optimization algorithm are feasible and have a good segmentation. http://dx.doi.org/10.25130/tjps.25.2020.036

A health management system for large vertical mill

The large vertical mill has complicated structure and tens of thousands of parts, which is a critical grinding equipment for slag and cinder. As large vertical mill always works in severe conditions, the on-line monitoring, timely fault diagnosis, and trend prediction are very important guarantees for the safe service and saving maintaining costs. To address this issue, the health management system for large vertical mill is developed. More specifically, in order to manage reservoirs of state-related running data, the intrinsic physic data, and diagnosis knowledge base, an entity-relationship-model-based database is first constructed. Based on the fault diagnosis reasoning of experts, the fault tree is developed and the fault diagnosis rules are derived. Especially, a hybrid condition prognosis method based on backtracking search optimization algorithm and neural network is developed, and in comparison with traditional back propagation neural network and ant colony neural network, the developed backtracking search optimization algorithm and neural network gets superior hybrid prediction performance in prediction accuracy and training efficiency. Finally, the health management system, including the functions of condition monitoring, fault diagnosis, and trend prediction for large vertical mill is implemented using Microsoft Visual Studio C # and Microsoft SQL Server.

Deep-Mining Backtracking Search Optimization Algorithm Guided by Collective Wisdom

The backtracking search optimization algorithm (BSA) is a recently proposed evolutionary algorithm with simple structure and well global exploration capability, which has been widely used to solve optimization problems. However, the exploitation capability of the BSA is poor. This paper proposes a deep-mining backtracking search optimization algorithm guided by collective wisdom (MBSAgC) to improve its performance. The proposed algorithm develops two learning mechanisms, i.e., a novel topological opposition-based learning operator and a linear combination strategy, by deeply mining the winner-tendency of collective wisdom. The topological opposition-based learning operator guides MBSAgC to search the vertices in a hypercube about the best individual. The linear combination strategy contains a difference vector guiding individuals learning from the best individual. In addition, in order to balance the overall performance, MBSAgC simulates the clusterity-tendency strategy of collective wisdom to develop another difference vector in the above linear combination strategy. The vector guides individuals to learn from the mean value of the current generation. The performance of MBSAgC is tested on CEC2005 benchmark functions (including 10-dimension and 30-dimension), CEC2014 benchmark functions, and a test suite composed of five engineering design problems. The experimental results of MBSAgC are very competitive compared with those of the original BSA and state-of-the-art algorithms.