HTH Ali Tarik Abdulwahid , Ahmed Dheyaa Al-Obaidi , Mustafa Najah Al-Obaidi, eNeurologicalSci, 2023

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

Background: The association between facial types and dental arches forms has considerable implications in orthodontic diagnosis and treatment planning. The aim was to establish the maxillary and mandibular dental arches width and length in skeletal and dental class II division 1 and class III malocclusion groups, find out the most frequent dental arch form and facial type and the association between them and to check the gender differences. Materials and Methods: Frontal and lateral facial photographs and maxillary and mandibular occlussal photographs for 90 iraqi subjects with age 18-25 years old (45 males and 45 females) divided equally into three groups, the 1st group with class II division 1malocclusion (overjet more than 3mm but less t

Emotion recognition has important applications in human-computer interaction. Various sources such as facial expressions and speech have been considered for interpreting human emotions. The aim of this paper is to develop an emotion recognition system from facial expressions and speech using a hybrid of machine-learning algorithms in order to enhance the overall performance of human computer communication. For facial emotion recognition, a deep convolutional neural network is used for feature extraction and classification, whereas for speech emotion recognition, the zero-crossing rate, mean, standard deviation and mel frequency cepstral coefficient features are extracted. The extracted features are then fed to a random forest classifier. In

Artificial roughness applied to a Solar Air Heater (SAH) absorber plate is a popular technique for increasing its total thermal efficiency (ηt−th). In this paper, the influence of geometrical parameters of V-down ribs attached below the corrugated absorbing plate of a SAH on the ηt−th was examined. The impacts of key roughness parameters, including relative pitch p/e (6–12), relative height e/D (0.019–0.043), angles of attack α (30–75°), and Re (1000–20,000), were examined under real weather conditions. The SAH ηt−th roughened by V-down ribs was predicted using an in-house developed conjugate heat-transfer numerical model. The maximum SAH ηt−th was shown to be 78.8% as predicted under the steady-state condition

Solar collectors, in general, are utilized to convert the solar energy into heat energy, where it is employed to generate electricity. The non-concentrating solar collector with a circular shape was adopted in the present study. Ambient air is heated under a translucent roof where buoyant air is drawn from outside periphery towards the collector center (tower base). The present study is aimed to predict and visualize the thermal-hydrodynamic behavior for airflow under inclined roof of the solar air collector, SAC. Three-dimensional of the SAC model using the re-normalization group, RNG, k−ε turbulence viscus model is simulated. The simulation was carried out by using ANSYS-FLUENT 14.5. The simulation