Recurrent neural network (RNN) has been widely used as a tool in the data classification. This network can be educated with gradient descent back propagation. However, traditional training algorithms have some drawbacks such as slow speed of convergence being not definite to find the global minimum of the error function since gradient descent may get stuck in local minima. As a solution, nature...

This paper presents an improved harmony search metaheuristic for the multi-mode resource-constrained project scheduling problem (MRCPSP). The hybrid metaheuristic presented is an improved version of the forbidden set oriented “Sounds of Silence” harmony search metaheuristic. In the original approach a simple but efficient "rule of thumb" was applied to eliminate the hidden resource conflicts. T...

This paper introduces a new social metaheuristic for the Max-Cut problem applied to a weighted undirected graph. This problem consists in finding a partition of the nodes into two subsets, such that the sum of the weights of the edges having endpoints in different subsets is maximized. This NP-hard problem for non planar graphs has several application areas such as VLSI and ASICs CAD. The hiera...

Bucket elimination (BE) is an exact technique based on variable elimination. It has been recently used with encouraging results as a mechanism for recombining solutions in a memetic algorithm (MA) for the still life problem, a hard constraint optimization problem based on Conway’s game of life. This paper studies expanded multi-level models in which this exact/metaheuristic hybrid is further hy...

High power consumption efficiency in wireless sensor networks is always desirable. One way to deal with this issue is using a linear integer programming model based upon a schedule of sensor allocation plans in multiple time intervals subject to coverage and connectivity constraints. The Generate-and-Solve (GS) methodology is a hybrid approach that combines a metaheuristic component with an exa...

The human has always been to up to the best in everything, And this perfectionism has led to the creation of optimization methods. The goal of optimization is to determine the variables to find the best acceptable answer to the limitations in a problem, so that the objective function is a minimum or a maximum. Metaheuristic algorithms are one of inaccurate optimization methods that inspired by ...

Slope stability assessment is a critical research area in civil engineering. Disastrous consequences of slope collapse necessitate better tools for predicting their occurrences. This research proposes a hybrid Artificial Intelligence (AI) for slope stability assessment based on metaheuristic and machine learning. The contribution of this study to the body of knowledge is multifold. First, advan...

This work proposes an attempt to control the navigation of a wall following mobile robot using a hybrid metaheuristic which is a combination of two different population-based heuristics such as Gravitational Search (GS) and Particle Swarm Optimization (PSO). The hybrid metaheuristic is called GSPSO which is used to train a multi-layered Artificial Neural Network (ANN) with the available benchma...

The Traveling Salesman Problem (TSP) is a classical NPhard combinatorial problem that has been intensively studied through several decades. A large amount of literature is dedicated to this problem. TSP can be directly applied to some real life problems, and to be generalized to some other set of important combinatorial problems. Nowadays, a large collection of TSP instances can be found such a...