A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

Traditional nursing interventions for children with Cerebral Palsy (CP) often lack active engagement and show limited improvement in motor function. Play interventions involving manipulative activities may better support motor skill development. Objectives: To evaluate the effect of structured play-based nursing interventions on hand motor skills in children with cerebral palsy. Methods: A quasi-experimental pre-test/post-test design with a control group was used. The study was conducted at the Paediatric Welfare Hospital in Baghdad from November 25, 2024, to February 13, 2025. A non-probability sample of 79 children was identified based on the study criteria; of these, 64 children met the eligibility criteria and agreed to particip

This paper presents a cognition path planning with control algorithm design for a nonholonomic wheeled mobile robot based on Particle Swarm Optimization (PSO) algorithm. The aim of this work is to propose the circular roadmap (CRM) method to plan and generate optimal path with free navigation as well as to propose a nonlinear MIMO-PID-MENN controller in order to track the wheeled mobile robot on the reference path. The PSO is used to find an online tune the control parameters of the proposed controller to get the best torques actions for the wheeled mobile robot. The numerical simulation results based on the Matlab package show that the proposed structure has a precise and highly accurate distance of the generated refere

Prediction of penetration rate (ROP) is important process in optimization of drilling due to its crucial role in lowering drilling operation costs. This process has complex nature due to too many interrelated factors that affected the rate of penetration, which make difficult predicting process. This paper shows a new technique of rate of penetration prediction by using artificial neural network technique. A three layers model composed of two hidden layers and output layer has built by using drilling parameters data extracted from mud logging and wire line log for Alhalfaya oil field. These drilling parameters includes mechanical (WOB, RPM), hydraulic (HIS), and travel transit time (DT). Five data set represented five formations gathered

Search Results at the International Journal of Science and Research (IJSR)

The x-ray fluorescence (XRF) of Znpc molecule with (flow of Ar) and Znpc molecule with (grow in N2) showed two peaks at (8.5and 9.5 Kv) referring to orbital transition ) K?-shell & K?-shell) respectively. The study of x-ray diffraction (XRD) where it was observed good growth of the crystal structure as a needle by the sublimation technique with a ?-phase of (monoclinic structure ) . Using Bragg equation the value of the interdistance of the crystalline plane (d-value) were calculated. We noticed good similarity with like once in the American Standards for Testing Material (ASTM) .Powder Diffraction File (PDF) Program was used to ensure the information obtained from (ASTM) . The output of (PDF) was compared with celn program, where the val