Lorenzo Carnevale

An IoT Cloud System for Traffic Monitoring and Vehicular Accidents Prevention Based on Mobile Sensor Data Processing

The sudden traffic slowdown especially in fast scrolling roads and highways characterized by a scarce visibility is one of the major causes of accidents among motorized vehicles. It can be caused by other accidents, work-in-progress on roads, excessive motorized vehicles especially at peak times and so on. Typically, fixed traffic sensors installed on roads that interact with drivers’ mobile App through the 4G network can mitigate such a problem, but unfortunately not all roads and highways are equipped with such devices. In this paper, we discuss a possible alternative solution for addressing such an issue considering mobile traffic sensors directly installed in private and/or public transportation and volunteer vehicles. In this scenario a fast real-time processing of big traffic data is fundamental to prevent accidents. In particular, we discuss an IoT Cloud system for traffic monitoring and alert notification based on OpenGTS and MongoDB. Our IoT Cloud system, besides for private drivers, it is very useful for drivers of critical rescue vehicles such as ambulances. Experiments prove that our system provides acceptable response times that allows drivers to receive alert messages in useful time so as to avoid the risk of possible accidents.

A Watchdog Service Making Container-Based Micro-services Reliable in IoT Clouds

The integration of Internet of Things (IoT) and Cloud computing has brought the rising of IoT Clouds able to provide different kinds of IoT as a Service solutions consisting of various micro-services deployed in IoT devices (including sensors and actuators) interacting with different Infrastructure, Platform, and Software as Service (i.e., IaaS, PaaS, SaaS) running in the Clouds data centres. On the basis of IoT Clouds the container virtualisation is becoming an even more prominent technology that allows them to deploy and manage, in a flexible fashion, micro-services within IoT devices. In this paper, we specifically focus on micro-service reliability in IoT devices. In particular, we propose a system based on container virtualisation that allows IoT Clouds to carry out fault-tolerance when a micro-service running on an IoT device fails. Experiments prove that the overheard introduced in our system by container virtualisation does not negatively affect performances when a micro-service is replaced due to a failure.

A Cloud-Based System for Improving Retention Marketing Loyalty Programs in Industry 4.0: A Study on Big Data Storage Implications

Nowadays, the growing global economy and demand for customized products are bringing the manufacturing industry from a sellers’ market toward a buyers’ market. In this context, the smart manufacturing enabled by Industry 4.0 is changing the whole production cycle of companies specialized on different kinds of products. On one hand, the advent of cloud computing and social media makes the customers’ experience more and more inclusive, whereas on the other hand cyber-physical system technologies help industries to change in real time the cycle of production according to customers’ needs. In this context, “retention” marketing strategies aimed not only at the acquisition of new customers but also at the profitability of existing ones allow industries to apply specific production strategies so as to maximize their revenues. This is possible by means of the analysis of various kinds of information coming from customers, products, purchases, and so on. In this paper, we focus on customer loyalty programs. In particular, we propose cloud-based software as a service architecture that store and analyses big data related to purchases and products’ ranks in order to provide customers a list of recommended products. Experiments focus on a prototype of human to machine workflow for the pre-selection of customers deployed on both private and hybrid cloud scenarios.

How to enable clinical workflows to integrate big healthcare data

Nowadays, in order to enable future medical decision making, in the healthcare panorama there is the need of efficient Cloud-systems able to acquire and integrate Big e-health Data, coming from heterogeneous sources, through smart clinical workflows. Indeed, during the treatment at hospital, patients use medical devices generating a huge amount of data that have to be automatically stored into the Cloud storage system. In this paper, we specifically discuss an automated Machine-To-Machine clinical workflow able to manage the migration of Big e-health Data coming from medical devices to a Cloud NoSQL storage system. To validate our solution, we also present and test a real use case in which a clinical workflow is considered to manage big robotic rehabilitation datasets of the IRCCS Messina (Italy) Institute. Experiments prove the goodness of our approach in terms of data acquisition and integration.

Big data analytics in genomics: The point on Deep Learning solutions

Nowadays, Next Generation Sequeencing (NGS) is a catch-all term used to describe different modern DNA sequencing applications that produce big genomics data that can be analysed in a faster fashion than in the past. For this reason, NGS requires more and more sophisticated algorithms and high-performance parallel processing systems able to analyse and extract knowledge from a huge amount of genomics and molecular data. In this context, researchers are beginning to look at emerging deep learning algorithms able to perform efficient big data analytics. In this paper, we analyse and classify the major current deep learning solutions that allow biotechnology researchers to perform big genomics data analytics. Moreover, by means of a taxonomic analysis, we provide a clear picture of the current state of the art also discussing future challenges.

A Cloud Computing Workflow for Managing Oceanographic Data

Ocean data management plays an important role in the oceanographic problems, such as ocean acidification. These data, having different physical, biological and chemical nature, are collected from all seas and oceans of the world, generating an international networks for standardizing data formats and facilitating global databases exchange. Cloud computing is therefore the best candidate for oceanographic data migration on a distributed and scalable platform, able to help researchers for performing future predictive analysis. In this paper, we propose a new Cloud based workflow solution for storing oceanographic data and ensuring a good user experience about the geographical data visualization. Experiments prove the goodness of the proposed system in terms of performance.

Heart Disorder Detection with Menard Algorithm on Apache Spark

Nowadays, healthcare is facing Big Data processing in order to support medical staff by means of decision making tools. In this context, a challenging topic is the storing and analysis of data in the cardiology field. Electrocardiogram produces signals about the heart health that need to be processed in order to detect a possible disorder. In this paper, we discuss an Apache Spark based tool and that uses the Menard algorithm. In order to validate our solution, we performed experiments on a use case in which the algorithm has been implemented in order to detect heart disorder. Experiments prove the goodness of our approach in terms of performance.

An approach for the secure management of hybrid cloud–edge environments

Abstract The Cloud-of-Things (CoT) paradigm is a challenging approach to manage IoT applications exploiting Cloud resources and services. In order to avoid latency in Cloud–IoT communications, the management of time-sensitive services has to be moved to the edge of the CoT. To this aim, a secure Cloud-to-Edge environment for seamless management of IoT applications is necessary. The realization of a performing and secure Cloud-to-Edge middleware solution is a very strategic goal for future business CoT services. Thus, it needs to be deeply investigated, as highlighted by the Cloud Security Alliance (CSA). A valuable approach to develop an efficient Cloud-to-Edge system is based on an instant-message communication solution. In current Cloud environments, a Message Oriented Middleware (MOM) based on an Instant Message Protocol (IMP) provides good performance, but overlook security requirements. In this paper, we aim at overcoming such a gap following the CSA guidelines. In particular, we discuss the involved issues for improving such a kind of Cloud-to-Edge system in order to achieve data confidentiality, integrity, authenticity and non-repudiation. Moreover, we analyze a real case of study considering a MOM architectural model. Experimental results performed on a real testbed show how the introduced secure capabilities do not affect the overall performances of the whole middleware.

An innovative methodology for big data visualization in oceanographic domain

Nowadays, thanks to new technologies, we are observing an explosion of data in different fields such as clinical, environmental and so on. In this context, a typical example of the well-known Big Data problem is represented by visualization. In this work, we propose an innovative platform for managing the oceanographic acquisitions. More specifically, we present two innovative visualization techniques: general overview and site specific observation. Experiments prove the goodness of the proposed system in terms both of performance and user experience.

Applying Artificial Intelligence in Healthcare Social Networks to Identity Critical Issues in Patients' Posts.

Nowadays, the possibility of using social media in the healthcare field is attracting the attention of clinical professionals and of the whole healthcare industry. In this panorama, many Healthcare Social Networking (HSN) platforms are emerging with the purpose to enhance patient care and education. However, they also present potential risks for patients due to the possible distribution of poor-quality or wrong information. On one hand doctors want to promote the exchange of information among patients about a specific disease, but on the other hand they do not have the time to read patients’ posts and moderate them when required. In this paper, we propose an Artificial Intelligence (AI) approach based on a combination of stemming, lemmatization and Machine Learnign (ML) algorithms that allows to automatically analyse the patients’ posts of a HSN platform and identify possible critical issues so as to enable doctors to intervene when required. In particular, after a discussion of advantages and disadvantages of using a HSN platform, we discuss in detail an architecure that allows to analyse big data consisting of patients’ posts. In the end, real case studies are discussed highlighting