In this study, the kinematic analysis including the forward and inverse kinematic developed for a 5 degree of freedom robotic arm. The forward kinematic is elaborated using Denavit-Hartenberg (DH) convention. Inverse Kinematic is established using Deep Neural Network (DNN) model with five hidden layer each contain 50 neurons fully connected using ReLu activation. A data of inputs and outputs are created and trained. The inputs are the end-effector position and orientation. The outputs are the joint angles of the manipulator. The data is generated by the forward kinematics, where a set of joint angles that limited by their corresponding ranges are inserted to the forward kinematic equations to result the end-effector positions and orientations. The results of the DNN are tested and show an accuracy of the approach with a Mean Square Error of 0.0002569 which means the approach is highly accurate.
KE Sharquie, AA Noaimi, MR Al-Karhi, Journal of Cosmetics, Dermatological Sciences and Applications, 2014 - Cited by 2
Most vegetation’s are Land cover (LC) for the globe, and there is an increased attention to plants since they represent an element of balance to natural ecology and maintain the natural balance of rapid changes due to systematic and random human uses, including the subject of the current study (Bassia eriophora ) Which represent an essential part of the United Nations system for land cover classification (LCCS), developed by the World Food Organization (FAO) and the world Organization for environmental program (UNEP), to observe basic environmental elements with modern techniques. Although this plant is distributed all over Iraq, we found that this plant exists primarily in the middle
... Show MoreIn the present study, five derivatives have been designed to be synthesized as possible mutual prodrugs for 5-Fluorouracil (5-FU) and non steroidal anti-inflammatory drugs (NSAIDs) to selectively deliver the drugs into the cancer cells. The synthesis of the target compounds were accomplished following multistep reaction procedures, the chemical reaction followed up and the purity of the products were checked by TLC. The structure of the final compounds and their intermediates were confirmed by their melting points, infrared spectroscopy and elemental microanalysis, the hydrolysis of compound III was studied using HPLC technique. According to the results mentioned above, compounds (I−V) can be good candidates as possible mutual prod
... Show MoreRetreatment Efficacy of Continuous Rotation Versus Reciprocation Kinematic Movements in Removing Gutta-Percha with Calcium Silicate-Based Sealer: SEM Study, Raghad Noori Nawaf*, Ra
Objective This study aims to investigate the impact of integrated training on kinematics variables and defensive accuracy in volleyball, focusing on enhancing balance and muscle tension control through proprioceptive neuromuscular facilitation (PNF) exercises. Methods The sample consisted of 14 male volleyball athletes from the first volleyball league of Al-Jaish Sports Club were divided into experimental (n=7) and control group (n=7). In the pre- and post-intervention periods, dynamic balance, muscle tension control and kinematic variables (during a lateral reaching task) as well as defensive performance accuracy upon fatigue onset of recoil laser strikes were assessed. Exposure the intervention program was carried out for six weeks, and t
... Show MoreAbstract
In this research we study the wavelet characteristics for the important time series known as Sunspot, on the aim of verifying the periodogram that other researchers had reached by the spectral transform, and noticing the variation in the period length on one side and the shifting on another.
A continuous wavelet analysis is done for this series and the periodogram in it is marked primarily. for more accuracy, the series is partitioned to its the approximate and the details components to five levels, filtering these components by using fixed threshold on one time and independent threshold on another, finding the noise series which represents the difference between
... Show MoreData scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for