Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97–100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with

Cerium oxide (CeO2), or ceria, has gained increasing interest owing to its excellent catalytic applications. Under the framework of density functional theory (DFT), this contribution demonstrates the eect that introducing the element nickel (Ni) into the ceria lattice has on its electronic, structural, and optical characteristics. Electronic density of states (DOSs) analysis shows that Ni integration leads to a shrinkage of Ce 4f states and improvement of Ni 3d states in the bottom of the conduction band. Furthermore, the calculated optical absorption spectra of an Ni-doped CeO2 system shifts towards longer visible light and infrared regions. Results indicate that Ni-doping a CeO2 system would result in a decrease of the band gap. Finally,

In this research project, a tip-tilting angle of a photovoltaic solar cell was developed to increase generated electrical power output. An active, accurate, and simple dual-axis tracking system was designed by using an Arduino Uno microprocessor. The system consisted of two sections: software and apparatus (hardware). It was modified by using a group of light-dependent resistor sensors, and two DC servo motors were utilized to rotate the solar panel to a location with maximum sunlight. These components were arranged in a mechanical configuration with the gearbox. The three locations of the solar cell were chosen according to the tilt angle values, at zero angles, which included an optimal 33-degree angle for the Baghdad location and

Autism Spectrum Disorder, also known as ASD, is a neurodevelopmental disease that impairs speech, social interaction, and behavior. Machine learning is a field of artificial intelligence that focuses on creating algorithms that can learn patterns and make ASD classification based on input data. The results of using machine learning algorithms to categorize ASD have been inconsistent. More research is needed to improve the accuracy of the classification of ASD. To address this, deep learning such as 1D CNN has been proposed as an alternative for the classification of ASD detection. The proposed techniques are evaluated on publicly available three different ASD datasets (children, Adults, and adolescents). Results strongly suggest that 1D

Fetal growth restriction is a significant contributor to fetal morbidity and mortality. In addition, there are heightened maternal risks associated with surgical operations and their accompanying dangers. Monitoring fetal development is a crucial objective of prenatal care and effective methods for early diagnosis of Fetal growth restriction, allowing prompt management and timely intervention to improve the outcomes. Screening for Fetal growth restriction can be achieved via many modalities; it can be medical, biochemical, or radiological. Some recommended combining more than one for better outcomes. Currently, there is inconsistency about the best method of Fetal growth restriction screening.   In this review, a comprehensive