Data Science and Internet of Things

Research and Applications at the Intersection of DS and IoT

herausgegeben von: Prof. Giancarlo Fortino, Prof. Antonio Liotta, Dr. Raffaele Gravina, Dr. Alessandro Longheu

Verlag: Springer International Publishing

Buchreihe : Internet of Things

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This book focuses on the combination of IoT and data science, in particular how methods, algorithms, and tools from data science can effectively support IoT. The authors show how data science methodologies, techniques and tools, can translate data into information, enabling the effectiveness and usefulness of new services offered by IoT stakeholders. The authors posit that if IoT is indeed the infrastructure of the future, data structure is the key that can lead to a significant improvement of human life. The book aims to present innovative IoT applications as well as ongoing research that exploit modern data science approaches. Readers are offered issues and challenges in a cross-disciplinary scenario that involves both IoT and data science fields. The book features contributions from academics, researchers, and professionals from both fields.

Inhaltsverzeichnis

Frontmatter

IoT Aided Smart Home Architecture for Anomaly Detection

Abstract

Internet of Things (IoT), and Information and Communication Technology (ICT) enhance the cities and homes with intelligence using various types of devices that are embedded for sensing purposes. The IoT nodes can collect time-series information for a given purpose, like measuring temperature, air pollution and traffic congestion, motion tracking etc. and provide node behavior and environment interaction. Besides the normal ritual events that happen according the measured parameters, some unusual states, called anomalies, can be detected by using the same measurements. The anomalies that happen at homes, such as fire, elderly people fall etc. are life-critical and their early detection and/or prevention can save lives. In this chapter, we propose an Anomaly Detection System Architecture for smart homes. The fire detection/prediction and fall detection of elderly people are examined as anomalies from the usual, everyday activities. An experimental study, as proof of concept for the fire emergence case, is run by using LSTM neural network architecture. One of the positive features of the proposed methodology is that the faulty readings and false positive alarms on specific parameters are not enough to rise an anomaly detection if those readings are not supported by other parameters.

Ibrahim Arif, Nevena Ackovska

Evolutionary Dynamics and Multiplexity for Mobile Edge Computing in a Healthcare Scenario

Abstract

Today, on the wake of the evolution of 5G towards 6G, the complex joining of existing communication systems and the socio-technical aspects of human interactions, acquire a growing scientific interest. In particular, this can become decisive to establish innovation in healthcare. Complex networks theory and evolutionary dynamics can play a key role in designing a smart healthcare system, and enable to provide statistical estimators to understand which measures and how would be needed to dynamically manage requirements and needs. Thus, following this approach, we propose a framework for a smart healthcare scenario, to design a cognitive ambient assisted living of frail people connected. We consider the multiplex networks to represent two interdependent networks, the mobile edge computing nodes network and the social network of frail people. In the case of a multi-services environment, we evaluate the impact of evolutionary dynamics of cooperation of mobile edge computing nodes in the system. Our findings show how the evolutionary dynamics of mobile edge computing nodes allow decreasing the blocking probability, with the increasing of cooperators in the considered scenario.

Barbara Attanasio, Alessandro Di Stefano, Aurelio La Corte, Marialisa Scatá

Correlations Among Game of Thieves and Other Centrality Measures in Complex Networks

Abstract

Social Network Analysis (SNA) is used to study the exchange of resources among individuals, groups, or organizations. The role of individuals or connections in a network is described by a set of centrality metrics which represent one of the most important results of SNA. Degree, closeness, betweenness and clustering coefficient are the most used centrality measures. Their use is, however, severely hampered by their computation cost. This issue can be overcome by an algorithm called Game of Thieves (GoT). Thanks to this new algorithm, we can compute the importance of all elements in a network (i.e. vertices and edges), compared to the total number of vertices. This calculation is done not in a quadratic time, as when we use the classical methods, but in polylogarithmic time. Starting from this we present our results on the correlation existing between GoT and the most widely used centrality measures. From our experiments emerge that a strong correlation exists, which makes GoT eligible as a centrality measure for large scale complex networks.

Annamaria Ficara, Giacomo Fiumara, Pasquale De Meo, Antonio Liotta

A LPWAN Case Study for Asset Tracking

Abstract

The industrial application of Internet Of Thing is rapidly growing leading to, so called, Industrial IoT. Moreover, the future spread of 5G make possible the application to many new fields. However, waiting for 5G, Low-Power Wide-Area Network (LPWAN) technologies permits company to already develop applications energy-efficient using current communication technologies. This paper presents the development of a project mainly aiming at providing tracking service starting from LPWAN protocol selection till the analysis of some implementation prototypes. The work focuses on energy saving when using GPS and cryptography routines.

Fabrizio Formosa, Michele Malgeri, Marco Vigo

Implementing an Integrated Internet of Things System (IoT) for Hydroponic Agriculture

Abstract

This chapter presents ongoing work in the development of a hydroponics monitoring system by using IoT technology. Hydroponics is a method of growing plants in water based nutrient rich solution system, instead of soil. By monitoring the parameters of the solution in parallel with the environmental parameters inside the greenhouse, farmers can increase the production while decreasing the need for manual labor. Multiple networked sensors can measure these parameters and send all the necessary information to an Internet of things (IoT) platform (i.e., Thingsboard) in order the farmer or agronomist to be able to control and adjust current operating conditions (e.g. environmental controls) and plan the nutrition schedule. Furthermore Machine Learning (ML) can be used, so the system will provide recommendations to agronomists. The novelty presented in our system is that data contributed by multiple farming sites can be used to improve the quality of predictions and recommendations for all parties involved.

Georgios Georgiadis, Andreas Komninos, Andreas Koskeris, John Garofalakis

A Collaborative BSN-Enabled Architecture for Multi-user Activity Recognition

Abstract

Human activity plays a significant role in various fields, such as manufacturing, healthcare, and public safety; therefore, recognizing human activity is crucial to enable smart innovative services. The development of ubiquitous sensing and pervasive computing allows studying what humans perform in real time and mobility. Single- and multi-user activity recognition (AR) differ by the number of involved users. With recent developments of multi-sensor and multi-information fusion, multi-user activity recognition is gradually becoming an emerging and relevant research frontier. In this paper, we propose a software architecture which combines cloud and edge computing with collaborative body sensor networks (CBSNs) to support the development of CBSNs-enabled services and in particular we provide its case-study in the context of multi-user AR.

Qimeng Li, Raffaele Gravina, Congcong Ma, Weilin Zang, Ye Li, Giancarlo Fortino

Collaborative Solutions for Unmanned Aerial Vehicles

Abstract

In the coming years, regulation changes and market pushing are expected to relax existing restrictions to UAV flights. In this new scenario, we expect to encounter a greater number of UAVs over our cities, citizens, and critical infrastructures. Such changes impose new requirements in terms of safety, coordination, and operations management that must be properly addressed. In this chapter, we provide an overview of the main challenges that UAVs of the vertical takeoff and landing (VTOL) type are still facing, detailing their key application areas. Afterward, we discuss some solutions where wireless communications between UAVs enable achieving advanced collaborative solutions such as flight coordination and collision avoidance.

Francisco Fabra, Julio A. Sanguesa, Willian Zamora, Carlos T. Calafate, Juan-Carlos Cano, Pietro Manzoni

Graph and Network Theory for the Analysis of Criminal Networks

Abstract

Social Network Analysis is the use of Network and Graph Theory to study social phenomena, which was found to be highly relevant in areas like Criminology. This chapter provides an overview of key methods and tools that may be used for the analysis of criminal networks, which are presented in a real-world case study. Starting from available juridical acts, we have extracted data on the interactions among suspects within two Sicilian Mafia clans, obtaining two weighted undirected graphs. Then, we have investigated the roles of these weights on the criminal networks properties, focusing on two key features: weight distribution and shortest path length. We also present an experiment that aims to construct an artificial network which mirrors criminal behaviours. To this end, we have conducted a comparative degree distribution analysis between the real criminal networks, using some of the most popular artificial network models: Watts-Strogats, Erdős-Rényi, and Barabási-Albert, with some topology variations. This chapter will be a valuable tool for researchers who wish to employ social network analysis within their own area of interest.

Lucia Cavallaro, Ovidiu Bagdasar, Pasquale De Meo, Giacomo Fiumara, Antonio Liotta

A Data Mining Approach for Indoor Navigation Systems in IoT Scenarios

Abstract

Indoor positioning is an important aspect in internet of things which plays a crucial role in various scenarios. Meanwhile, depending on the scenario, Indoor Navigation Systems (INS) generates considerable amount of data which can be used in navigation as a data-driven approach. In this paper, a navigation method has been proposed based on data mining techniques which enables value added services for end-users in different IoT scenarios such as airports, shopping mall and hospitals. The proposed heuristic algorithm is based on combining the greedy and random forest algorithms. Toward that end, we have collected data from a real world scenario (a large hospital) and used them to our implementation. According to our results regarding passage of time and accumulated history in the central server, we were able to suggest better routes while the proposed method shows reduction in both traveled distance and elapsed time. It also improved routing by decreasing the number of turns and encounters with obstacles. Thus, the proposed method provides better solution as an intelligent indoor navigation.

Mahbubeh Sattarian, Javad Rezazadeh, Reza Farahbakhsh, Omid Ameri Sianaki

Titel: Data Science and Internet of Things
herausgegeben von: Prof. Giancarlo Fortino
Prof. Antonio Liotta
Dr. Raffaele Gravina
Dr. Alessandro Longheu
Verlag: Springer International Publishing
Electronic ISBN: 978-3-030-67197-6
Print ISBN: 978-3-030-67196-9
DOI: https://doi.org/10.1007/978-3-030-67197-6