ABSTRACT
Complexity, heterogeneity, schemaless-ness, data visualization, and extraction of consistent knowledge from Big Data are the biggest challenges in NoSQL databases. This paper presents a general semantic NoSQL Application Program Interface that integrates and converts NoSQL databases to semantic representation. The generated knowledge base is suitable for visualization and knowledge extraction from different Big Data sources. The authors use a case study of the COVID-19 pandemic prediction and other weather occurrences in various parts of the world to illustrate the suggested API. The Authors find a correlation between COVID-19 spread and deteriorating weather. According to the experimental findings, the API's performance is enough for heterogeneous Big Data.
ABSTRACT
Complexity, heterogeneity, schemaless-ness, data visualization, and extraction of consistent knowledge from Big Data are the biggest challenges in NoSQL databases. This paper presents a general semantic NoSQL Application Program Interface that integrates and converts NoSQL databases to semantic representation. The generated knowledge base is suitable for visualization and knowledge extraction from different Big Data sources. The authors use a case study of the COVID-19 pandemic prediction and other weather occurrences in various parts of the world to illustrate the suggested API. The Authors find a correlation between COVID-19 spread and deteriorating weather. According to the experimental findings, the API's performance is enough for heterogeneous Big Data.
ABSTRACT
COVID-19 is a coronavirus-caused viral disease that had spread worldwide. Within over six months after its spread in China at the end of 2019, it infected over 10 million persons worldwide and more than 519,000 had perished. Drones are important in decreasing the range of COVID-19 disease outbreaks in most general applications, and especially in medical applications. This paper presents a new application of an autonomous Drone in fast detecting medical face masks by using Deep Learning to classify people based on their mask-wearing with high accuracy by using a classifier implemented based on MobileNetV2 architecture. The training carried out on an artificially created using Tensorflow, Opencv, and Keras. The autonomous Drone controlled by a smart mobile app with help of IoT technology such as the TeamViewer app, which controls the mobile, and the Qground control app to control the Drone through the MAV-link protocol. The objective of this paper is to use intelligent technology to decrease the spread of coronavirus to protecting people. © 2021 IEEE.
ABSTRACT
Nowadays, the world suffers a Coronavirus mutation in 2019 (COVID-19). The COVID-19 data sources possess three main characteristics: big volume, velocity, and variety. These challenges have compelled the authors to employ Big Data technology, data mining techniques, and Ontology-based approaches instead of using a statistics hypothesis. Big Data Frameworks are involved in most data-related activities, such as storing, processing, analyzing, and sharing. Nevertheless, most of them miss having a semantic layer that is required for meaning-related activities, such as decision support, reasoning, and event detection. A semantic layer is based on Ontology, Semantic Query Engine, Association Rule Mining, and Fuzzy Logic. Therefore, this research aims to build Ontology and transform Big Data from Big Data Frameworks to semantic environments. This paper presents Onto-NoSQL, a Protégé plug-in that supports the creation of Ontology and transformation of a column-oriented NoSQL datastore like Hbase into Protégé. Besides, the whole process of transformation is carried out automatically without any external intervention. It demonstrates the proposed plug-in through a case study of air pollution and weather phenomena’s data. The proposed plug-in is utilized to predict COVID-19 prevalence and the relationship between COVID-19 prevalence and weather factors. Moreover, the plug-in handles many challenges due to Big Data size and time processing. The time consumption to import up to 64 GB data is 17 minutes. The data prediction accuracy is 96.9% applying association rules discovery on Ontology creation. © 2020. All Rights Reserved.