Determining the face of wearing a mask from not wearing a mask from visual data such as video and still, images have been a fascinating research topic in recent decades due to the spread of the Corona pandemic, which has changed the features of the entire world and forced people to wear a mask as a way to prevent the pandemic that has calmed the entire world, and it has played an important role. Intelligent development based on artificial intelligence and computers has a very important role in the issue of safety from the pandemic, as the Topic of face recognition and identifying people who wear the mask or not in the introduction and deep education was the most prominent in this topic. Using deep learning techniques and the YOLO (”You only look once”) neural network algorithm, which is an efficient real-time object identification algorithm, an intelligent system was developed in this thesis to distinguish which faces are wearing a mask and who is not wearing a wrong mask. The proposed system was developed based on data preparation, preprocessing, and adding a multi-layer neural network, followed by extracting the detection algorithm to improve the accuracy of the system. Two global data sets were used to train and test the proposed system and worked on it in three models, where the first contains the AIZOO data set, the second contains the MoLa RGB CovSurv data set, and the third model contains a combined data set for the two in order to provide cases that are difficult to identify and the accuracy results that were obtained. obtained from the merging datasets showed that the face mask (0.953) and the face recognition system were the most accurate in detecting them (0.916).
(7)
(2)
A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an
... Show More
(1)
The rise of edge-cloud continuum computing is a result of the growing significance of edge computing, which has become a complementary or substitute option for traditional cloud services. The convergence of networking and computers presents a notable challenge due to their distinct historical development. Task scheduling is a major challenge in the context of edge-cloud continuum computing. The selection of the execution location of tasks, is crucial in meeting the quality-of-service (QoS) requirements of applications. An efficient scheduling strategy for distributing workloads among virtual machines in the edge-cloud continuum data center is mandatory to ensure the fulfilment of QoS requirements for both customer and service provider. E
... Show More
(5)
(2)
In this work, the detection of zinc (Zn) ions that cause water pollution is studied using the CSNPs- Linker-alkaloids compound that was prepared by linking extracted alkaloids from Iraqi Catharanthus roseus plant with Chitosan nanoparticles (CSNPs) using maleic anhydride. This compound is characterized by an X-ray diffractometer (XRD) which shows that it has an orthorhombic structure with crystallite size in the nano dimension. Zeta Potential results show that the CSNPs-Linker-alkaloids carried a positive charge of 54.4 mV, which means it possesses high stability. The Fourier transform infrared spectroscopy (FTIR) shows a new distinct band at 1708.93 cm-1 due to C=O esterification. Scanning electron microscope (SEM) image
... Show More
(1)
(1)
(18)
(20)
Evolutionary algorithms are better than heuristic algorithms at finding protein complexes in protein-protein interaction networks (PPINs). Many of these algorithms depend on their standard frameworks, which are based on topology. Further, many of these algorithms have been exclusively examined on networks with only reliable interaction data. The main objective of this paper is to extend the design of the canonical and topological-based evolutionary algorithms suggested in the literature to cope with noisy PPINs. The design of the evolutionary algorithm is extended based on the functional domain of the proteins rather than on the topological domain of the PPIN. The gene ontology annotation in each molecular function, biological proce
... Show More
(5)
(3)
(14)
(8)
DeepFake is a concern for celebrities and everyone because it is simple to create. DeepFake images, especially high-quality ones, are difficult to detect using people, local descriptors, and current approaches. On the other hand, video manipulation detection is more accessible than an image, which many state-of-the-art systems offer. Moreover, the detection of video manipulation depends entirely on its detection through images. Many worked on DeepFake detection in images, but they had complex mathematical calculations in preprocessing steps, and many limitations, including that the face must be in front, the eyes have to be open, and the mouth should be open with the appearance of teeth, etc. Also, the accuracy of their counterfeit detectio
... Show More
(7)
(5)