MuG: A Multilevel Graph Representation for Big Data Interpretation

Abstract

Our society is oriented towards data production. The increasingly massive spread of mobile devices and the Internet of Things is transforming our society into a data factory. Data, however, does not immediately lead to knowledge and, in fact we can become overwhelmed with a mass of information that is difficult to understand: often the desire to predict the future from data analysis turns into the nightmare of data overload. There are numerous approaches, automatic and manual, present in the literature that try to interpret data by extracting information. Among the various methodologies proposed, none seems to have resolved the problem in a definitive and universal way, perhaps because every data analysis problem needs to be faced from a different point of view. This paper introduces an approach for the interpretation of data from sensors located within a city. Three graphs (Ontologies, Context Dimension Tree and Bayesian Networks) were chosen for the representation of the scenarios both from the point of view of the sensors involved and of the services and events connected to the data. Through the Ontologies and the Context Dimension Tree it is possible to analyze the scenario from a syntactic and semantic point of view constructing Bayes networks that enable the estimation of the probability that some events happen. A first empirical analysis conducted on some districts of London seems to confirm the effectiveness of the proposed method.

A multilevel graph approach for rainfall forecasting: A preliminary study case on London area

“…The purpose of this work was to evaluate the application of an innovative approach, such as the Multilevel Graph Approach to the hydrological filed, in an attempt to use this methodology at the service of Early Warning Systems. The presented approach, which involves the use of three graphs such as the Bayes Networks, Ontologies, and the Context Dimension Tree, is a method that has already produced reasonable results in the prediction of the road accident risks within a specific borough of London …”

“…The presented approach, which involves the use of three graphs such as the Bayes Networks, Ontologies, and the Context Dimension Tree, is a method that has already produced reasonable results in the prediction of the road accident risks within a specific borough of London. 20 Regarding the attempt to apply this methodology to the hydrological field, we first proceeded to evaluate the data set available through classical methodologies such as Linear Correlation, Cross-Correlation, and Multiple Linear Regression. The results obtained from these analyses are not entirely satisfactory.…”

“…In this section will be introduced the Multilevel Graph Approach (MuG), which has been used with other purposes providing acceptable results; in addition, the architecture of the proposed system will be presented with its details.…”

Smart Traffic Management System for Metropolitan Cities of Kingdom Using Cutting Edge Technologies

“…However, some of the most cutting-edge technologies, such as IoT and cloud computing, may help to improve traffic monitoring systems in major cities. To leverage the potential benefits of modern cutting-edge technologies in getting context awareness and providing real-time traffic updates [25,26], this paper proposes an IoT-based architecture to provide mobile users with real-time traffic updates via roadside message agents and Google Maps. This smart traffic management is required in metropolitan areas to avoid congestion, control delays, and comfort end-users daily, especially during peak hours.…”

An Internet of Things approach for Cultural Heritage enhancement

“…Different enabling technologies, such as wireless sensor networks, Bluetooth Low Energy, radio frequency identification, Near Field Communication, and QR-codes, enable the development of these environments [21]. There are several possible applications, and the most interesting solutions concern the automatic management of knowledge integrated with context-aware data for tourism [22,23,24]. In addition, the most common solutions concern the design of an appropriate network of museum sensors designed to monitor the presence, location, and integrity of the works of art on display, and used to measure other parameters such as temperature, humidity, and light intensity inside the rooms.…”