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

Image is an important digital information that used in many internet of things (IoT) applications such as transport, healthcare, agriculture, military, vehicles and wildlife. etc. Also, any image has very important characteristic such as large size, strong correlation and huge redundancy, therefore, encrypting it by using single key Advanced Encryption Standard (AES) through IoT communication technologies makes it vulnerable to many threats, thus, the pixels that have the same values will be encrypted to another pixels that have same values when they use the same key. The contribution of this work is to increase the security of transferred image. This paper proposed multiple key AES algorithm (MECCAES) to improve the security of the tran

Seepage through earth dams is one of the most popular causes for earth dam collapse due to internal granule movement and seepage transfer. In earthen dams, the core plays a vital function in decreasing seepage through the dam body and lowering the phreatic line. In this research, an alternative soil to the clay soil used in the dam core has been proposed by conducting multiple experiments to test the permeability of silty and sandy soil with different additives materials. Then the selected sandy soil model was used to represent the dam experimentally, employing a permeability device to measure the amount of water that seeps through the dam's body and to represent the seepage line. A numerical model was adopted using Geo-Studio software i

In this research, porous silicon (PS) prepared by anodization etching on surface of single crystalline p-type Si wafer, then Gold nanoparticle (AuNPs) prepared by pulsed laser ablation in liquid. NPs deposited on PS layer by drop casting. The morphology of PS, AuNPs and AuNPs/PS samples were examined by AFM. The crystallization of this sample was characterized by X-ray diffraction (XRD). The electrical properties and sensitivity to CO2 gas were investigated to Al/AuNPs/PS/c-Si/Al, we found that AuNPs plays crucial role to enhance this properties.

Many isolated rural communities are located in regions where there is an abundant and reliable supply of solar energy, but where the distance to the nearest power station is many tens or even hundreds of kilometre. It is therefore mainly in these areas that rural electrification is now being provided by PV generators. since Stand-Alone PV generator can offer the most cost-effective and reliable option for providing power needed in remote places. Accordingly these isolated rural canters are fitted with PV for lighting, a refrigerator, a television and socket to supply kitchen appliances

The sensors based on Nickel oxide doped chromic oxide (NiO: Cr2O3) nanoparticals were fabricated using thick-film screen printing of sol-gel grown powders. The structural, morphological investigations were carried out using XRD, AFM, and FESEM. Furthermore, the gas responsivity were evaluated towards the NH3 and NO2 gas. The NiO0.10: Cr2O3 nanoparticles exhibited excellent response of 95 % at 100oC and better selectivity towards NH3 with low response and recovery time as compared to pure Cr2O3 and can stand as reliable sensor element for NH3 sensor related applications.

The intelligent buildings provided various incentives to get highly inefficient energy-saving caused by the non-stationary building environments. In the presence of such dynamic excitation with higher levels of nonlinearity and coupling effect of temperature and humidity, the HVAC system transitions from underdamped to overdamped indoor conditions. This led to the promotion of highly inefficient energy use and fluctuating indoor thermal comfort. To address these concerns, this study develops a novel framework based on deep clustering of lagrangian trajectories for multi-task learning (DCLTML) and adding a pre-cooling coil in the air handling unit (AHU) to alleviate a coupling issue. The proposed DCLTML exhibits great overall control and is