Improved particle swarm optimisation to estimate bone age

Advanced Particle Swarm Optimization Algorithm with Improved Velocity Update Strategy

“…PSO is an intelligent computational dependent approach which is not primarily influence by the nonlinear nature and size of the problem, and can easily be converged to an optimal point in most of the problems where other techniques fail to provide an optimal solution [4]. Hence, it can be used efficiently to various optimization tasks in engineering and other related fields.…”

Optimization of Feedforward Neural Networks Using an Improved Flower Pollination Algorithm for Short-Term Wind Speed Prediction

“…In this situation, the local search power becomes stronger, while the global search power weakens. To avoid a repeated oscillation near the extreme point from a larger moving step size [26][27][28][29], four inertia weights, i.e., ω 1 , ω 2 , ω 3 and ω 4 , are selected to improve FPA, where ω 1 is a fixed inertia weight, ω 2 is a linear inertia weight, ω 3 is an exponential decreasing inertia weight and ω 4 is a dynamic inertia weight. Each inertia weight is shown as follows:…”

Lung tumour detection by fusing extended local binary patterns and weighted orientation of difference from computed tomography

“…Besides the statistical features, texture‐based features have been widely used in the CAD systems in order to detect abnormalities and deformities in medical images [17]. This is, therefore, texture‐based features mostly provide discriminative features for image segmentation image classification [18–22] and image retrieval systems [23, 24]. In the past two decades, several texture‐based features were proposed for tumour detection such as the grey level difference method (GLDM), the grey level run‐length method (GLRLM) and the spatial grey level dependent method (SGLDM) [25].…”