Search

In this paper, the modified Spider Monkey Optimization (SMO) with Multi-Layer Perceptron (MLP) is utilized to solve the classification problem on five different datasets. The MLP is a widely used Neural Network (NN) variant which requires training on specific application to tackle the slow convergence speed and local minima avoidance. The original SMO with MLP experiences the problem of finding the optimal classification result; due to that, the SMO is enhanced by other meta-heuristics algorithm to train the MLP. Based on the concept of no free lunch theorem, there is always a possibility to improve the algorithm. With the same expectation, the performance of the SMO algorithm is improved by using Differential Evolution (DE) and Grey Wolf Optimizer (GWO) algorithm to train the MLP. Likewise, the SMO-DE and SMO-GWO are two different concepts employed to improve efficiency. The results of proposed algorithms are compared with other well-known algorithms such as BBO, PSO, ES, SVM, KNN, and Logistic Regression. The results show that the proposed algorithm performs better than others or they are more competitive. [ABSTRACT FROM AUTHOR]

Distributed database servers are very popular as they provide data availability, reliability, replication, and partition for both homogeneous as well as heterogeneous software and hardware. In this paper, we analyze the previous works on load balancing of database servers. Further we also propose an algorithm for controlling job distribution at the database servers in different node partitions. We also formulate a methodology for load status evaluation of database servers to balance their loads for effective load status management. The load status of the database servers depends on three important parameters namely processor, RAM, and bandwidth. On the basis of load status, the clients'/users' requests can then be directed to another database in a distributed environment in order to balance the load effectively to meet user demands in an unobtrusive manner. [ABSTRACT FROM AUTHOR]

In software development, sometimes experienced programmers have difficulty determining before performing their tests, which algorithm will work best to solve a particular problem, and the answer to the question will always depend on the type of problem and nature of the data to be used, in this situation, it is necessary to identify which indicator is the most useful for a specific type of problem and especially in route optimization. Currently, there are techniques and algorithms used in Artificial Intelligence, which, however, cannot display their potential without a well-defined data set. The paper seeks to explain and propose an algorithm selection indicator to build a consistent data set, given the lack of availability of data that allows the best route size decision to be made. [ABSTRACT FROM AUTHOR]

Copyright of 3C Tecnologia is the property of Area de Innovacion y Desarrollo, SL and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)