Giovanni Pettorru Publications

This paper addresses the problem of data privacy in Human Activity Recognition (HAR) applications for eHealth. Cryptography, a proven privacy safeguard on the Internet, remains underutilized in the HAR context, as observed in the existing literature. This study highlights the importance of cryptographic practices by conducting a performance analysis, focusing on the accuracy of HAR with and without data en-cryption. This paper proves that even by introducing a very simple cryptographic mechanism, a potential eavesdropper would experience a reduction of more than 20% of accuracy in the activity recognition task as compared to the case where no encryption is used, at the price of a limited increase in the energy consumption for the involved sensors. Such preliminary results demonstrate the effectiveness of encryption for applications of this type, encouraging further exploration and refinement in this direction.

The Internet of Things (IoT) has revolutionized the world, connecting billions of devices that offer assistance in various aspects of users’ daily lives. Context-aware IoT applications exploit real-time environmental, user-specific, or situational data to dynamically adapt to users’ needs, offering tailored experiences. In particular, Location-Based Services (LBS) exploit geographical information to adapt to environmental settings or provide recommendations based on users’ and nodes’ positions, thus delivering efficient and personalized services. To this end, there is growing interest in developing IoT localization systems within the scientific community. In addition, due to the sensitivity and privacy inherent to precise location information, LBS introduce new security challenges. To ensure a more secure and trustworthy system, researchers are studying how to prevent vulnerabilities and mitigate risks from the early design stages of LBS-empowered IoT applications. The goal of this study is to carry out an in-depth examination of localization techniques for IoT, with an emphasis on both the signal-processing design and security aspects. The investigation focuses primarily on active radio localization techniques, classifying them into range-based and range-free algorithms, while also exploring hybrid approaches. Next, security considerations are explored in depth, examining the main attacks for each localization technique and linking them to the most interesting solutions proposed in the literature. By highlighting advances, analyzing challenges, and providing solutions, the survey aims to guide researchers in navigating the complex IoT localization landscape.

The last years have been characterized by strong market exploitation of the Internet of Things (IoT) technologies in different application domains, such as Industry 4.0, smart cities, and eHealth. All the relevant solutions should properly address the security issues to ensure that sensor data and actuators are not under the control of malicious entities. Additionally, many applications should at the same time provide low-latency communications, as in the case for instance of remote control of industrial robots. Low latency and security are two of the most important challenges to be addressed for the successful deployment of IoT applications. These issues have been analyzed by several scientific papers and surveys that appeared in the last decade. However, few of them consider the two challenges jointly. Moreover, the security aspects are primarily investigated only in specific application domains or protocol levels and the latency issues are typically investigated only at low layers (e.g., physical, access). This paper addresses this shortcoming and provides a systematic review of state-of-the-art solutions for providing fast and secure IoT communications. Although the two requirements may appear to be in contrast to each other, we investigate possible integrated solutions that minimize device connection and service provisioning. We follow an approach where the proposals are reviewed by grouping them based on the reference architectural layer, i.e., access, network, and application layers. We also review the works that propose promising solutions that rely on the exploitation of the QUIC protocol at the higher levels of the protocol stack.

This work addresses the problem of security and low latency in communications typical of several Internet of Things (IoT) scenarios, such as those in Industry 4.0 applications. In particular, we propose a WebSocket over QUIC (WS-QUIC) protocol for intra-network communications between the IoT devices and the gateway. In particular, low latency is achieved by combining the connection persistence of WebSocket (WS) with the reduced connection establishment time required by QUIC. Moreover, the use of QUIC implicitly exploit the security extensions of WS provided by the Transport Layer Security (TLS) protocol. We experimentally analyzed the performance of the proposed system and compare it with that provided by other Web-based secure protocols, such as HyperText Transfer Protocol Secure (HTTPS) and WebSocket Secure (WSS). Our results show that WS-QUIC outperforms HTTPS and WSS for medium-large file sizes. Moreover, the use of the so-called TLS ticket resumption makes WS-QUIC suitable also for medium-small file sizes. Finally, we also discuss the potential use of a single shared session ticket between different IoT devices in the same cluster to further decrease the latency.

Given the growing importance of Location-Based Services (LBS) in the broader Internet of Things (IoT) context, efficient and optimized location algorithms are essential. To address this, a hybrid WiFi/Bluetooth (BLT) localization algorithm is experimentally investigated in this paper. This approach uses Received Signal Strength (RSS) information to estimate target-anchors' distances, which are then fed at the input of a Least Squares (LS)-based localization algorithm to finally estimate the target position. The study relies on a dataset created by the authors with the goal of developing and evaluating RSS-based localization algorithms that incorporate the fusion of data from different technologies. The experimental results presented in this paper confirm that such an approach improves the accuracy, resilience, and robustness of location estimation and optimizes IoT services based on contextual information with respect to schemes based on a single technology.

Natural ecosystem conservation is a topical issue that is receiving increasing attention from different branches of the scientific community. Forests and woodlands are major contributors to climate change mitigation, able to absorb significant amounts of carbon dioxide. The conservation of tree areas has been addressed through the adoption of different solutions. This paper proposes a new monitoring system and the use of artificial intelligence (AI) for real-time fire detection. The system is based on intelligent Digital Mobile Radio (DMR) nodes and a Social Internet of Things (SIoT) platform on which AI algorithms have been implemented. The results obtained show the ability to detect the slightest change in observed environmental parameters, determining the direction and speed of fire propagation.

The preservation of the natural ecosystem is a topical issue that is receiving increasing attention not only from the scientific community but from the entire world population. Forests and woodlands are the main actors responsible for mitigating climate change, able to absorb significant amounts of carbon dioxide. The preservation of the arboreal areas has been addressed through the adoption of various solutions. This paper proposes a new real-time fire monitoring and detection system based on Digital Mobile Radio (DMR) nodes and a Social Internet of Things (SIoT) platform on which artificial intelligence algorithms have been implemented. The results obtained show the ability to detect the slightest variation in the observed parameters, determining the direction and speed of fire propagation.

Monitoring and control of natural environments is becoming increasingly sensitive in the face of climate change. This work proposes a solution for the protection to safeguard forests and woodlands against natural or arson fires. Currently, existing solutions have critical issues in terms of early detection of outbreaks, or rely on expensive solutions if implemented on a large scale. Electronic noses for fire smoke detection have been developed. The data is transmitted in real time to a Social Internet of Things (SIoT) cloud platform that analyzes the data and detects potential critical situations. Preliminary results obtained show the effectiveness of the system in detecting the change in detected parameters during the occurrence of a fire front.

This paper presents an innovative vehicle monitoring system based on Wi-Fi sniffing devices and real-time data processing using machine learning techniques. Our solution involves the construction of a neural network-based multiclass classifier that can classify the incoming Wi-Fi signal from many sources based on the received signal strength. The solution was carried out by training the neural network to predict different output classes corresponding to different vehicular (0-30 Km/h, 30-60 Km/h, 60-90 Km/h, 90-120 Km/h) and several pedestrian speed ranges among 0-15 Km/h.

This paper presents an innovative vehicle monitoring system based on Wi-Fi sniffing devices and real-time data processing using machine learning techniques. Our solution involves the construction of a neural network-based multiclass classifier that can classify the incoming Wi-Fi signal from many sources based on the received signal strength. The solution was carried out by training the neural network to predict different output classes corresponding to different vehicular (0-30Km/h,30-60Km/h, 60-90Km/h, 90-120Km/h) and several pedestrian speed ranges among 0-15Km/h.

This paper addresses the issue of monitoring and tracking people and vehicles within smart cities. The actors in this work jointly cooperate in sensing, sensible data processing, anonymized data delivery, and data processing, with the final goal of providing real-time mapping of vehicular and pedestrian concentration conditions. The classification of conditions can bring out critical situations that can be communicated in real-time to citizens. Tests were conducted in the city of Cagliari, Italy.

The time lost looking for a free parking spot in a city impacts negatively not only on the mood of the drivers but also on the environment in terms of air quality and fuel consumption. The vehicle detection can be considered as the most important task in Smart Parking systems as it allows to automatically monitor the occupancy state of the parking spots in a city. In this paper, we implement and test a vehicle detection system based on a magnetometer sensor, which is part of a complete Smart Parking system under development at the University of Cagliari. After a preliminary analysis conducted to test the performance of the magnetometer, we conducted two specific experiments to investigate the suitability of the magnetometer as the mean to detect the presence of a vehicle in the parking spots. The first experiment, involving 15 different vehicles, has demonstrated that the magnetometer can be used to reliably detect the presence of a vehicle in a parking spot if it is placed under the front or rear axle of the vehicle. From the second experiment it resulted that, when considering 3 adjacent parking spots and only one magnetometer placed in the central spot, it is not possible to reliably detect the vehicles parked on the adjacent spots. Therefore, one magnetometer for each considered parking spot is needed.