The integration of social networking concepts into the Internet of things has led to the Social Internet of Things (SIoT) paradigm, according to which objects are capable of establishing social relationships in an autonomous way with respect to their owners with the benefits of improving the network scalability in information/service discovery. Within this scenario, we focus on the problem of understanding how the information provided by members of the social IoT has to be processed so as to build a reliable system on the basis of the behavior of the objects. We define two models for trustworthiness management starting from the solutions proposed for P2P and social networks. In the subjective model each node computes the trustworthiness of its friends on the basis of its own experience and on the opinion of the friends in common with the potential service providers. In the objective model, the information about each node is distributed and stored making use of a distributed hash table structure so that any node can make use of the same information. Simulations show how the proposed models can effectively isolate almost any malicious nodes in the network at the expenses of an increase in the network traffic for feedback exchange.

The integration of social networking concepts into the Internet of Things (IoT) has led to the so called Social Internet of Things (SIoT) paradigm, according to which the objects are capable of establishing social relationships in an autonomous way with respect to their owners. The benefits are those of improving scalability in information/service discovery when the SIoT is made of huge numbers of heterogeneous nodes, similarly to what happens with social networks among humans. In this paper we focus on the problem of understanding how the information provided by the other members of the SIoT has to be processed so as to build a reliable system on the basis of the behavior of the objects. We define a subjective model for the management of trustworthiness which builds upon the solutions proposed for P2P networks. Each node computes the trustworthiness of its friends on the basis of its own experience and on the opinion of the common friends with the potential service providers. We employ a feedback system and we combine the credibility and centrality of the nodes to evaluate the trust level. Preliminary simulations show the benefits of the proposed model towards the isolation of almost any malicious node in the network.

As the world becomes increasingly interconnected, emerging and innovative sensing technologies are shaping the future of agriculture, with a special focus on sustainability-related issues. In this context, we envision the possibility to exploit Social Internet of Things for sensing of environmental conditions (solar radiation, humidity, air temperature, and soil moisture) and communications, deep learning for plant disease detection, and crowdsourcing for images collection and classification, engaging farmers and community garden owners and experts. Through, data fusion and deep learning, the designed system can exploit the collected data and predict when a plant would (or not) get a disease, with a specific degree of precision, with the final purpose to render agriculture more sustainable. We here present the architecture, the deep learning model, and the responsive Web app. Finally, some experimental evaluations and usability/engagement tests are reported and discussed, together with final remarks, limitations, and future work.

This paper presents Lysis, which is a cloud-based platform for the deployment of Internet of Things (IoT) applications. The major features that have been followed in its design are the following: each object is an autonomous social agent; the platform as a service (PaaS) model is fully exploited; reusability at different layers is considered; the data is under control of the users. The first feature has been introduced by adopting the social IoT concept, according to which objects are capable of establishing social relationships in an autonomous way with respect to their owners with the benefits of improving the network scalability and information discovery efficiency. The major components of PaaS services are used for an easy management and development of applications by both users and programmers. The reusability allows the programmers to generate templates of objects and services available to the whole Lysis community. The data generated by the devices is stored at the object owners cloud spaces. This paper also presents a use-case that illustrates the implementation choices and the use of the Lysis features.

In this paper, we analyze the combination of Vehicular Ad-hoc NETworks (VANETs) with the Social Internet of Things (SIoT), i.e., the Social Internet of Vehicles (SIoV). In the SIoV every vehicle is capable of establishing social relationships with other vehicles in an autonomous way with the intent of creating an overlay social network that can be exploited for information search and dissemination in VANET applications. The contribution of this paper is two-fold: firstly, we define some relationships which can be established between the vehicles and between the vehicles and the road side units (RSUs); secondly, we propose a SIoV middleware which extends the functionalities of the Intelligent Transportation Systems Station Architecture (ITS SA), defined by ISO and ETSI standards, to take into account the elements needed to integrate VANETs in the SIoT. Additionally, we present results of software simulations analyzing realistic vehicular mobility trace in order to study the characteristics of the resulting social network structure.

Smart buildings use Internet of Things (IoT) sensors for monitoring indoor environmental parameters, such as temperature, humidity, luminosity, and air quality. Due to the huge amount of data generated by these sensors, data analytics and machine learning techniques are needed to extract useful and interesting insights, which provide the input for the building optimization in terms of energy-saving, occupants’ health and comfort. In this paper, we propose an IoT-based smart building (SB) solution for indoor environment management, which aims to provide the following main functionalities: monitoring of the room environmental parameters; detection of the number of occupants in the room; a cloud platform where virtual entities collect the data acquired by the sensors and virtual super entities perform data analysis tasks using machine learning algorithms; a control dashboard for the management and control of the building. With our prototype, we collected data for 10 days, and we built two prediction models: a classification model that predicts the number of occupants based on the monitored environmental parameters (average accuracy of 99.5%), and a regression model that predicts the total volatile organic compound (TVOC) values based on the environmental parameters and the number of occupants (Pearson correlation coefficient of 0.939).