No abstract

The network field has been very popular in recent times and has aroused much of the attention of researchers. The network must keep working with the varying infrastructure and must adapt to rapid topology changes. Graphical representation of the networks with a series of edges varying over time can help in analysis and study. This paper presents a novel adaptive and dynamic network routing algorithm based on a Regenerate Genetic Algorithm (RGA) with the analysis of network delays. With the help of RGA at least a very good path, if not the shortest one, can be found starting from the origin and leading to a destination. Many algorithms are devised to solve the shortest path (SP) problem for example Dijkstra algorithm which can solve polynomial SP problems. These are equally effective in wired as well as wireless networks with fixed infrastructure. But the same algorithms offer exponential computational complexity in dealing with the real-time communication for rapidly changing network topologies. The proposed genetic algorithm (GA) provides more efficient and dynamic solutions despite changes in network topology, network change, link or node deletion from the network, and the network volume (with numerous routes).

Today, botnets are the most common threat on the Internet and are used as the main attack vector against individuals and businesses. Cybercriminals have exploited botnets for many illegal activities, including click fraud, DDOS attacks, and spam production. In this article, we suggest a method for identifying the behavior of data traffic using machine learning classifiers including genetic algorithm to detect botnet activities. By categorizing behavior based on time slots, we investigate the viability of detecting botnet behavior without seeing a whole network data flow. We also evaluate the efficacy of two well-known classification methods with reference to this data. We demonstrate experimentally, using existing datasets, that it is possible to detect botnet activities with high precision.

No abstract

In the sales business, the ultimate goal is to derive more sales and increase the profits for interested stakeholders. Maximizing profit margins from highly demanding products is one of their major objectives. Nowadays, there are varieties of intelligent systems available, which can guide the business owners, entrepreneurs, or managers to make smart decision and lead their business towards success. Out of different options, this research study explores the possibility and elaborates on how their objectives can be achieved through a genetic algorithm? The proposed approach can be adopted by businesses to increase their profits by enhancing low profit yielding products sales using optimized Genetic Algorithm. Initially groups are defined by adding products with high and low sales. After applying the proposed genetic algorithm, a “bundle of three” offers are traced out, to promote the product with poor sales history This study helps the businesses with a decision support model to maximize sales resulting in high profits. In this research, optimization algorithm is used along with variety of operations and methods, by the businesses, in order to reach their respective target goals. This can be achieved by applying an optimization method that has stable and reliable functions, selection methods, population size and mutation rate. The final result is to improve the overall profit of different businesses in the marketplace.