The involvement of maxillofacial tissues in SARS‐CoV‐2 infections ranges from mild dysgeusia to life‐threatening tissue necrosis, as seen in SARS‐CoV‐2‐associated mucormycosis. Angiotensin‐converting enzyme 2 (ACE2) which functions as a receptor for SARS‐CoV‐2 was reported in the epithelial surfaces of the oral and nasal cavities; however, a complete understanding of the expression patterns in deep oral and maxillofacial tissues is still lacking.

This research studies the comparison of deep neural network models and performance evaluation to predict the gold prices of time series, where the gold prices contain high fluctuations and non-linear patterns that are difficult to capture using traditional models, which makes predicting them a significant challenge. Therefore, the focus was on using deep learning models represented by (LSTM), (Bi-LSTM), (GRU) and (Bi-GRU). The results showed the superiority of the (Bi-GRU) model according to comparison criteria (MSE), (RMSE), (MAE), and (R∧2) compared to other models because it was able to understand the time patterns better by processing the data in both directions and provided superior performance, which indicates its effectiveness, eff

Sequence covering array (SCA) generation is an active research area in recent years. Unlike the sequence-less covering arrays (CA), the order of sequence varies in the test case generation process. This paper reviews the state-of-the-art of the SCA strategies, earlier works reported that finding a minimal size of a test suite is considered as an NP-Hard problem. In addition, most of the existing strategies for SCA generation have a high order of complexity due to the generation of all combinatorial interactions by adopting one-test-at-a-time fashion. Reducing the complexity by adopting one-parameter- at-a-time for SCA generation is a challenging process. In addition, this reduction facilitates the supporting for a higher strength of

Sequence covering array (SCA) generation is an active research area in recent years. Unlike the sequence-less covering arrays (CA), the order of sequence varies in the test case generation process. This paper reviews the state-of-the-art of the SCA strategies, earlier works reported that finding a minimal size of a test suite is considered as an NP-Hard problem. In addition, most of the existing strategies for SCA generation have a high order of complexity due to the generation of all combinatorial interactions by adopting one-test-at-a-time fashion. Reducing the complexity by adopting one-parameter- at-a-time for SCA generation is a challenging process. In addition, this reduction facilitates the supporting for a higher strength of cove

The paper discusses the structural and optical properties of In 2 O 3 and In 2 O 3-SnO 2 gas sensor thin films were deposited on glass and silicon substrates and grown by irradiation of assistant microwave on seeded layer nucleated using spin coating technique. The X-ray diffraction revealed a polycrystalline nature of the cubic structure. Atomic Force Microscopy (AFM) used for morphology analysis that shown the grain size of the prepared thin film is less than 100 nm, surface roughness and root mean square for In 2 O 3 where increased after loading SnO 2 , this addition is a challenge in gas sensing application. Sensitivity of In 2 O 3 thin film against NO 2 toxic gas is 35% at 300 o C. Sensing properties were improved after adding Tin Oxi

Its well known that understanding human facial expressions is a key component in understanding emotions and finds broad applications in the field of human-computer interaction (HCI), has been a long-standing issue. In this paper, we shed light on the utilisation of a deep convolutional neural network (DCNN) for facial emotion recognition from videos using the TensorFlow machine-learning library from Google. This work was applied to ten emotions from the Amsterdam Dynamic Facial Expression Set-Bath Intensity Variations (ADFES-BIV) dataset and tested using two datasets.

The convolutional neural networks (CNN) are among the most utilized neural networks in various applications, including deep learning. In recent years, the continuing extension of CNN into increasingly complicated domains has made its training process more difficult. Thus, researchers adopted optimized hybrid algorithms to address this problem. In this work, a novel chaotic black hole algorithm-based approach was created for the training of CNN to optimize its performance via avoidance of entrapment in the local minima. The logistic chaotic map was used to initialize the population instead of using the uniform distribution. The proposed training algorithm was developed based on a specific benchmark problem for optical character recog