Computer-aided diagnosis (CAD) systems are considered a powerful tool for physicians to support identification of the novel Coronavirus Disease 2019 (COVID-19) using medical imaging modalities. Therefore, this article proposes a new framework of cascaded deep learning classifiers to enhance the performance of these CAD systems for highly suspected COVID-19 and pneumonia diseases in X-ray images. Our proposed deep learning framework constitutes two major advancements as follows. First, complicated multi-label classification of X-ray images have been simplified using a series of binary classifiers for each tested case of the health status. That mimics the clinical situation to diagnose potential diseases for a patient. Second, the cascaded architecture of COVID-19 and pneumonia classifiers is flexible to use different fine-tuned deep learning models simultaneously, achieving the best performance of confirming infected cases. This study includes eleven pre-trained convolutional neural network models, such as Visual Geometry Group Network (VGG) and Residual Neural Network (ResNet). They have been successfully tested and evaluated on public X-ray image dataset for normal and three diseased cases. The results of proposed cascaded classifiers showed that VGG16, ResNet50V2, and Dense Neural Network (DenseNet169) models achieved the best detection accuracy of COVID-19, viral (Non-COVID-19) pneumonia, and bacterial pneumonia images, respectively. Furthermore, the performance of our cascaded deep learning classifiers is superior to other multi-label classification methods of COVID-19 and pneumonia diseases in previous studies. Therefore, the proposed deep learning framework presents a good option to be applied in the clinical routine to assist the diagnostic procedures of COVID-19 infection.

Air pollution is a major issue resulting from the excessive use of conventional energy sources in developing countries and worldwide. Particulate Matter less than 2.5 µm in diameter (PM_2.5) is the most dangerous air pollutant invading the human respiratory system and causing lung and heart diseases. Therefore, innovative air pollution forecasting methods and systems are required to reduce such risk. To that end, this paper proposes an Internet of Things (IoT) enabled system for monitoring and predicting PM_2.5 concentration on both edge devices and the cloud. This system employs a hybrid prediction architecture using several Machine Learning (ML) algorithms hosted by Nonlinear AutoRegression with eXogenous input (NARX). It uses the past 24 h of PM_2.5, cumulated wind speed and cumulated rain hours to predict the next hour of PM_2.5. This system was tested on a PC to evaluate cloud prediction and a Raspberry P_i to evaluate edge devices’ prediction. Such a system is essential, responding quickly to air pollution in remote areas with low bandwidth or no internet connection. The performance of our system was assessed using Root Mean Square Error (RMSE), Normalized Root Mean Square Error (NRMSE), coefficient of determination (R²), Index of Agreement (IA), and duration in seconds. The obtained results highlighted that NARX/LSTM achieved the highest R² and IA and the least RMSE and NRMSE, outperforming other previously proposed deep learning hybrid algorithms. In contrast, NARX/XGBRF achieved the best balance between accuracy and speed on the Raspberry P_i.

Nowadays, deep learning achieves higher levels of accuracy than ever before. This evolution makes deep learning crucial for applications that care for safety, like self-driving cars and helps consumers to meet most of their expectations. Further, Deep Neural Networks (DNNs) are powerful approaches that employed to solve several issues. These issues include healthcare, advertising, marketing, computer vision, speech processing, natural language processing. The DNNs have marvelous progress in these different fields, but training such DNN models requires a lot of time, a vast amount of data and in most cases a lot of computational steps. Selling such pre-trained models is a profitable business model. But, sharing them without the owner permission is a serious threat. Unfortunately, once the models are sold, they can be easily copied and redistributed. This paper first presents a review of how digital watermarking technologies are really very helpful in the copyright protection of the DNNs. Then, a comparative study between the latest techniques is presented. Also, several optimizers are proposed to improve the accuracy against the fine-tuning attack. Finally, several experiments are performed with black-box settings using several optimizers and the results are compared with the SGD optimizer.

Text plagiarism has greatly spread in the recent years, it becomes a common problem in several fields such as research manuscripts, textbooks, patents, academic circles, etc. There are many sentence similarity features were used to detect plagiarism, but each of them is not discriminative to differentiate the similarity cases. This causes the discovery of lexical, syntactic and semantic text plagiarism types to be a challenging problem. Therefore, a new plagiarism detection system is proposed to extract the most effective sentence similarity features and construct hyperplane equation of the selected features to distinguish the similarity cases with the highest accuracy. It consists of three phases; the first phase is used to preprocess the documents. The second phase is depended on two paths, the first path is based on traditional paragraph level comparison, and the second path is based on the computed hyperplane equation using Support Vector Machine (SVM) and Chi-square techniques. The third phase is used to extract the best plagiarized segment. The proposed system is evaluated on several benchmark datasets. The experimental results showed that the proposed system obtained a significant superiority in the performance compared to the systems with a higher ranking in the recent years. The proposed system achieved the best values 89.12% and 92.91% of the Plagdet scores, 89.34% and 92.95% of the F-measure scores on the complete test corpus of PAN 2013 and PAN 2014 datasets, respectively.

In a world where humanity’s interests come first, the environment is flooded with pollutants produced by humans’ urgent need for expansion. Air pollution and climate change are side effects of humans’ inconsiderate intervention. Particulate matter of 2.5 µm diameter (PM_2.5) infiltrates lungs and hearts, causing many respiratory system diseases. Innovation in air pollution prediction is a must to protect the environment and its habitants, including those of humans. For that purpose, an enhanced method for PM_2.5 prediction within the next hour is introduced in this research work using nonlinear autoregression with exogenous input (NARX) model hosting a convolutional neural network (CNN) followed by long short-term memory (LSTM) neural networks. The proposed enhancement was evaluated by several metrics such as index of agreement (IA) and normalized root mean square error (NRMSE). The results indicated that the CNN–LSTM/NARX hybrid model has the lowest NRMSE and the best IA, surpassing the state-of-the-art proposed hybrid deep-learning algorithms.

The phenomenon of scientific burglary has seen a significant increase recently due to the technological development in software. Therefore, many types of research have been developed to address this phenomenon. However, detecting lexical, syntactic, and semantic text plagiarism remains to be a challenge. Thus, in this study, we have computed and recorded all the features that reflect different types of text similarities in a new database. The created database is proposed for intelligent learning to solve text plagiarism detection problems. Using the created database, a reliable plagiarism detection system is also proposed, which depends on intelligent deep learning. Different approaches to deep learning, such as convolution and recurrent neural network architectures, were considered during the construction of this system. A comparative study was implemented to evaluate the proposed intelligent system on the two benchmark datasets: PAN 2013 and PAN 2014 of the PAN Workshop series. The experimental results showed that the proposed system based on long short-term memory (LSTM) achieved the first rank compared to up-to-date ranking systems.