In the past two decades, the growth of social data on the web has rapidly increased. This leads to researchers to access the data and information for many academic research and commercial uses. Social data on the web contains many real life events that occurred in daily life, today the global COVID-19 disease is spread worldwide. Many individuals including media organizations and government agencies are presenting the latest news and opinions regarding the coronavirus. In this study, the twitter data has been pulled out from Twitter social media, through python programming language, using Tweepy library, then by using TextBlob library in python, the sentiment analysis operation has been done. After the measuring sentiment analysis, the graphical representation has been provided on the data. The data we have collected on twitter are based on two specified hashtag keywords, which are (“COVID-19, coronavirus”). The date of searching data is seven days from 09-04-2020 to 15-04-2020. In the end a visualized presentation regarding the results and further explanation are provided.

Recently, it has emerged that both Internet of Things (IoT), and Software Defined Network (SDN) are becoming popular technologies. The main goal of IoT is to link electronic devices via the internet, meanwhile SDN facilitates network arrangement for management of a network by distinguishing the control layer and the data layer from each other. The number of electronic devices over the internet is increasing constantly, therefore it is a complicated process to manage and control especially over the huge distributed network. IoT network can be reasonably flexible and programmable through The SDN without introducing any trouble to the previously implemented network infrastructure. This paper reviews various IoT domains and applications such as cellular network, wireless Sensor, IoT management, security and smart city framework and common IoT SDN solutions. Moreover, The IoT and SDN notion has been explored critically, with assessing the current contributions in the research field. Lastly, analyzing current available solutions for SDN-based IoT implementations comparatively helps easily understanding the emerging trends view.

As a result of the rapid growth of the world population, traffic signaling systems for monitoring and controlling the roads have turned to be an important issue facing humanity. To effectively overcome this problem, an accurate method for congestion reduction on the roads should be used which has a direct relation between the population and the cars’ usage. Various approaches derived from deep and transfer learning have been investigated in this context. This research implemented an optimized transfer learning approach for densely connected convolutional neural network (DenseNet201) models for multiple classifications (non-emergency cars, ambulance, police, and firefighter). Due to the non-availability of public datasets, a customized dataset has been created. This paper aims to improve the performance accuracy of vehicle classification using certain preprocessing algorithms on the input images and testing various optimization methods. The performance accuracy of the proposed model is evaluated using k-folds cross-validation 20:80 for the test and training, respectively. The metrics which are used for comparison with other deep learning techniques are based on exactness, recall, accuracy and F1-score. Test outcomes specify that the proposed transfer model-based optimization outperforms alternative deep learning algorithms regarding vehicle accuracy in classifying and reaches 98.6%.

Due to the rapid increase of the population in the world, traffic signal controlling and monitoring has become an important issue to be solved with regard to the direct relation between the number of populations and the cars’ usage. In this regard, an intelligent traffic signaling with a rapid urbanization is required to prevent the traffic congestions, cost reduction, minimization in travel time, and CO2 emissions to atmosphere. This paper provides a comprehensive review of computer vision techniques for autonomic traffic control and monitoring. Moreover, recent published articles in four related topics including density estimation investigation, traffic sign detection and recognition, accident detection, and emergency vehicle detection are investigated. The conducted survey shows that there is no fair comparison and performance evaluation due to the large number of involved parameters in the abovementioned four topics which can control the traffic signal controlling system such as (computation time, dataset availability, and an accuracy).

The rapid growth and development of AI-based applications introduce a wide range of deep and transfer learning model architectures. Selecting an optimal optimizer is still challenging to improve any classification type's performance efficiency and accuracy. This paper proposes an intelligent optimizer selection technique using a new search algorithm to overcome this difficulty. A dataset used in this work was collected and customized for controlling and monitoring roads, especially when emergency vehicles are approaching. In this regard, several deep and transfer learning models have been compared for accurate detection and classification. Furthermore, DenseNet201 layers are frizzed to choose the perfect optimizer. The main goal is to improve the performance accuracy of emergency car classification by performing the test of various optimization methods, including (Adam, Adamax, Nadam, and RMSprob). The evaluation metrics utilized for the model’s comparison with other deep learning techniques are based on classification accuracy, precision, recall, and F1-Score. Test results show that the proposed selection-based optimizer increased classification accuracy and reached 98.84%. Szybki wzrost i rozwój aplikacji opartych na sztucznej inteligencji wprowadzają szeroki zakres architektur modeli głębokiego uczenia i uczenia transferowego. Wybór optymalnego optymalizatora wciąż stanowi wyzwanie w celu poprawy wydajności i dokładności każdego rodzaju klasyfikacji. W niniejszej pracy proponowana jest inteligentna technika wyboru optymalizatora, wykorzystująca nowy algorytm wyszukiwania, aby pokonać to wyzwanie. Zbiór danych użyty w tej pracy został zebrany i dostosowany do celów kontroli i monitorowania dróg, zwłaszcza w sytuacjach, gdy zbliżają się pojazdy ratunkowe. W tym kontekście porównano kilka modeli głębokiego uczenia i uczenia transferowego w celu dokładnej detekcji i klasyfikacji. Ponadto, warstwy DenseNet201 zostały zamrożone, aby wybrać optymalizatora idealnego. Głównym celem jest poprawa dokładności klasyfikacji samochodów ratunkowych poprzez przeprowadzenie testów różnych metod optymalizacji, w tym (Adam, Adamax, Nadam i RMSprob). Metryki oceny wykorzystane do porównania modelu z innymi technikami głębokiego uczenia opierają się na dokładności klasyfikacji, precyzji, czułości i miarze F1. Wyniki testów pokazują, że zaproponowany optymalizator oparty na wyborze zwiększył dokładność klasyfikacji i osiągnął wynik na poziomie 98,84%.

In the context of today's digital system applications, content-based image retrieval (CBIR) is an essential tool for managing large visual repositories. Current CBIR systems, however, face a trade-off between retrieval accuracy and computational efficiency, caused by high-dimensional representations and their heavy memory and query-time requirements. To address this problem, this paper proposes an efficient CBIR system based on deep metric learning. The system integrates the MobileNetV2 network for feature extraction, a trainable linear projection head, and triplet-loss optimization. The aim of this integration is to learn compact, discriminative embeddings that improve retrieval accuracy while maintaining a fast search time. The system was trained and tested with the Corel-1K database, and tested with 200 query images. The results show that training the projection head with triplet loss improves embedding quality while reducing the embedding dimensionality from 1280 to 512. This reduction not only improves retrieval accuracy, but also reduces query latency by more than 59%. The proposed model achieved a precision at 10 (P@10) of 97.65% and an average precision at 10 (AP@10) of 97.11%. Moreover, the framework maintained performance at greater retrieval depth, achieving P@20 and AP@20 scores of 97.30% and 96.74%, respectively, exceeding those of several more complex methods. The learned embeddings are also robust across image classes, as further confirmed by the qualitative and class-wise analyses. Overall, the results confirm that compact metric-learning representations provide a practical, scalable, and efficient approach for contemporary CBIR applications.