Machine learning models have recently provided great promise in diagnosis of several ophthalmic disorders, including keratoconus (KCN). Keratoconus, a noninflammatory ectatic corneal disorder characterized by progressive cornea thinning, is challenging to detect as signs may be subtle. Several machine learning models have been proposed to detect KCN, however most of the models are supervised and thus require large well-annotated data. This paper proposes a new unsupervised model to detect KCN, based on adapted flower pollination algorithm (FPA) and the k-means algorithm. We will evaluate the proposed models using corneal data collected from 5430 eyes at different stages of KCN severity (1520 healthy, 331 KCN1, 1319 KCN2, 1699 KCN3 a

The estimation of the regular regression model requires several assumptions to be satisfied such as "linearity". One problem occurs by partitioning the regression curve into two (or more) parts and then joining them by threshold point(s). This situation is regarded as a linearity violation of regression. Therefore, the multiphase regression model is received increasing attention as an alternative approach which describes the changing of the behavior of the phenomenon through threshold point estimation. Maximum likelihood estimator "MLE" has been used in both model and threshold point estimations. However, MLE is not resistant against violations such as outliers' existence or in case of the heavy-tailed error distribution. The main goal of t

This study was conducted to know some Immune responses in women with vaginal candidias is by Candidia species. Hemoglubin (Hb) was decreased significantly in patient women comparing with control group. The differential count of Blood cells revealed that neutrophils and monocytcs were increased significantly in patient women comparing with control group. The percentage of the Phagocytosis index was decreased significantly in patient women (66.45 + 15.05) comparing with control group (73.72 + 3.77) and the T- lymphocytes were decreased also in patient women (57.75 + 18.787) comparing with control group (74.25 + 7.759).

          In this paper, magnesium oxide nanoparticles (MgO NPS) have been prepared and characterized and its concentration effect has been studied on polymers surface (MgO NPS). The results showed that the degradation of poly methyl methacrylate increased when using such metal oxide. The results also showed that the metal oxide increased the degradation of poly methyl methacrylate. X-ray diffraction, scanning electron microscopy, atomic force microscopy were used to study the morphological characteristics and size of nano MgO particles analysis.  Films were prepared by mixing the different masses of MgO NPS (0.025, 0.05, 0.1, 0.2 and 0.4) % with a polymer solution ratio (W/V) 7 %. Photo-

MO Khudhair, 2020

The newly synthesized Schiff base ligand (E)-2-((2-phenylhydrazono)methyl)naphthalen-1-ol (phenyl hydrazine derivative), is allowed to react with each of the next mineral ion: Ni2+, Cu2+, Zn2+andCd2+successfully resulting to obtain new metal complexes with different geometric shape. The formation of Schiff base complexes and also the origin Schiff base is indicated using LC-Mass that manifest the obtained molar mass, FT-IR proved the occurrence of coordination through N of azobenzene and O of OH by observing the shifting in azomethines band and appearing of M-N and N-O bands. Moreover, we can also detect by such apparatus, the presence of aquatic water molecule inside the coordination sphere. UV-Vis spectra of all resultants reveale

The objective of this study is to apply Artificial Neural Network for heat transfer analysis of shell-and-tube heat exchangers widely used in power plants and refineries. Practical data was obtained by using industrial heat exchanger operating in power generation department of Dura refinery. The commonly used Back Propagation (BP) algorithm was used to train and test networks by divided the data to three samples (training, validation and testing data) to give more approach data with actual case. Inputs of the neural network include inlet water temperature, inlet air temperature and mass flow rate of air. Two outputs (exit water temperature to cooling tower and exit air temperature to second stage of air compressor) were taken in ANN.

Steady natural convection in a square enclosure with wall length (L= 20 cm) partially filled by saturated porous medium with same fluid (lower layer) and air (upper layer) is investigated. The conceptual study of the achievements of the heat transfer is performed under effects of bottom heating by constant heat flux (q=150,300,450,600W/m2 ) for three heaters size (0.2,0.14,0.07)m with symmetrically cooling with constant temperature on two vertical walls and adiabatic top wall. The relevant filled studied parameters are four different porous medium heights (Hp=0.25L,0.5L, 0.75L, L), Darcey number (Da1) 3.025×10-8 and (Da2) 8.852×10-4 ) and Rayleigh number range (60.354 - 241.41), (1.304×106 – 5.2166×106 ) for Da1 and Da2 cases respecti