This paper solves the dynamic traveling salesman problem (DTSP) using dynamic Gaussian Process Regression (DGPR) method. The problem of varying correlation tour is alleviated by the nonstationary covariance function interleaved with DGPR to generate a predictive distribution for DTSP tour. This approach is conjoined with Nearest Neighbor (NN) method and the iterated local search to track dynamic optima. Experimental results were obtained on DTSP instances. The comparisons were performed with Genetic Algorithm and Simulated Annealing. The proposed approach demonstrates superiority in finding good traveling salesman problem (TSP) tour and less computational time in nonstationary conditions.

Malware threats have become increasingly dynamic and complex, and, accordingly, artificial intelligence techniques have become the focal point for cybersecurity, as they are viewed as being more suited to tackling modern malware incidents. Specifically, neural networks, with their strong generalisation performance capability, are able to address a wide range of cyber threats. This article outlines the development and testing of a neural network ensemble approach to malware detection, based on a hybrid search mechanism. In this mechanism, the optimising of individual networks is done by an adaptive memetic algorithm with tabu search, which is also used to improve hidden neurons and weights of neural networks. The adaptive memetic algorithm combines global and local search optimisation techniques in order to overcome premature convergence and obtain an optimal search outcome. The results from the testing prove that the proposed method is strongly adaptive and efficient in its detection of a range of malware threats, and that it generates better results than other existing methods.

In recent years, there have been an increasing number of automobiles in cities around the world. This is due to more people living and working in cities as a result of urbanization. Street parking remains a common option for motorists, due to it being cheap and convenient. However, this option leads to a high concentration of vehicles causing congestion and obstruction of traffic. This problem is compounded as motorists wait for others to pull out of parking bays or look for empty parking spaces. In order to provide relief to this problem, an intelligent approach is proposed that generates an optimal parking space based on the vehicle location and desired destination. The proposed approach applies its operators adaptively and it derives optimality from the synergy between genetic algorithm and a local search technique in the search optimization process. The proposed method exhibits superior performance when compared with the existing methods over multiple iterations.

No abstract

A generic self-evolving multi-agent approach is proposed in this chapter. Most of the existing security approaches are custom designed for specific threats and attacks. However, the fusion of technologies and systems in the fourth industrial revolution and therefore the nature of its current cyber environment increasingly attracts multiple cyber threats in a single interface. In order to solve this problem, a generic self-evolving multi-agent approach is proposed. Multiple agents interact with each other in light of their reactions towards the environment and its inherent changes. Information from individual agents is collected and integrated to form the abstract compartment of the structure. The important aspects are analyzed including demonstrating how the abstract domain can be obtained from the custom interactions at the low-level domain of the proposed approach. The analysis explores the existing works in the area and how they have been advanced in the fourth industrial revolution.