Deep learning (DL) plays a significant role in several tasks, especially classification and prediction. Classification tasks can be efficiently achieved via convolutional neural networks (CNN) with a huge dataset, while recurrent neural networks (RNN) can perform prediction tasks due to their ability to remember time series data. In this paper, three models have been proposed to certify the evaluation track for classification and prediction tasks associated with four datasets (two for each task). These models are CNN and RNN, which include two models (Long Short Term Memory (LSTM)) and GRU (Gated Recurrent Unit). Each model is employed to work consequently over the two mentioned tasks to draw a road map of deep learning mod

Background: Myasthenia gravis is an autoimmune disease of the neuromuscular junction that results in fluctuating muscle weakness as well as significant fatigue. Disease exacerbation is a critical condition, and the predisposing factors for it need to be identified to improve preventive measures.

Objectives:  Our study aims to determine the predisposing factors for myasthenia gravis exacerbations in a group of Iraqi patients.

Subjects and Methods: A total number of 30 myasthenia gravis patients were admitted to the hospital with an exacerbation of their symptoms, determined as the development of functional disability, dysphagia, or respiratory fai

Background: Sonographic examination is an important tool in assessment of normal and abnormal cervical lymph nodes. The aim of the study is to assess the distribution and the characteristic features of normal cervical lymph nodes in a sample of Syrian population. Materials and Methods: Fifty healthy Syrian subjects (25 men and 25 women) with an age of 20 -60years old, who had their cervical lymph nodes examined by ultrasound. Three hundred and two lymph nodes were detected. Lymph nodes were evaluated for their number, size, site, echogenic hilus, shape, as well as for the border sharpness. The subjects were categorized by age into four groups, (20 -30, 31 - 40 , 41 - 50 , 51- 60 years ). Statistical analysis of data was done using SP

SUMMARY. – Nanocrystalline thin fi lms of CdS are deposited on glass substrate by chemical bath deposited technique using polyvinyl alcohol (PVA) matrix solution. Crystallite size of the nanocrystalline films are determining from broading of X-ray diffraction lines and are found to vary from 0.33-0.52 nm, an increase of molarity the grain size decreases which turns increases the band gap. The band gap of nanocrystalline material is determined from the UV spectrograph. The absorption edge and absorption coefficient increases when the molarity increases and shifted towards the lower wavelength.

In vivo study revealed that ZnO nanoparticles treatment of Streptococcus SPP contaminated injured skin showed good prognosis and good healing process include complete regeneration of the epithelial cells of the epidermis and increase of cellulartiy of the dermal content compared with untreated group. In conclusion, treatment of S. pyogenes infected skin with Zinc oxide nanoparticles concentration (2 mg/ml) limit the skin damage and localized the lesion to the incision site with good healing process

This study concerns the role of activated carbon (AC) from palm raceme as a support material for the enhancement of lipase-catalyzed reactions in an aqueous solution, with deep eutectic solvent (DES) as a co-solvent. The effects of carbonization temperature, impregnation ratio, and carbonization time on lipase activity were studied. The activities of Amano lipase from Burkholderia cepacia (AML) and lipase from the porcine pancreas (PPL) were used to investigate the optimum conditions for AC preparation. The results showed that AC has more interaction with PPL and effectively provides greater enzymatic activity compared with AML. The optimum treatment conditions of AC samples that yield the highest enzymatic activity were 0.5 (NaOH (

This paper considers a new Double Integral transform called Double Sumudu-Elzaki transform DSET. The combining of the DSET with a semi-analytical method, namely the variational iteration method DSETVIM, to arrive numerical solution of nonlinear PDEs of Fractional Order derivatives. The proposed dual method property decreases the number of calculations required, so combining these two methods leads to calculating the solution's speed. The suggested technique is tested on four problems. The results demonstrated that solving these types of equations using the DSETVIM was more advantageous and efficient