Respiratory diseases are among the leading causes of morbidity worldwide, making timely and accurate diagnosis essential. However, interpreting chest X-rays is challenging due to the variability of pathological manifestations and the subjectivity of human analysis. In this study, we propose a multimodal approach that integrates automated image analysis with textual clinical data, leveraging a Visual Question Answering (VQA)based architecture and a text generation model for diagnostic report production. The use of Grad-CAM enhances the interpretability of the system by highlighting the most relevant image regions for diagnosis. The model was trained on a balanced dataset obtained by merging three sources-Lung X-ray Data, NIH Chest X-rays, and Chest X-Ray Images-ensuring fair classification across Normal and Pneumonia categories. The pipeline includes visual feature extraction using a Vision Transformer (ViT), automatic pathology classification, and diagnostic report generation with an advanced language model. Results indicate a significant improvement in diagnostic accuracy compared to traditional methods, supported by key performance metrics such as accuracy 95.3%, sensitivity, specificity, and F1-score. Furthermore, integrating the system into an interactive web app facilitates clinical adoption, enhancing diagnostic efficiency and supporting personalized management of pulmonary diseases.

The Internet of Things (IoT) is increasingly composed of numerous sensing devices with limited power availability, which rely on energy storage solutions such as batteries or supercapacitors to sustain their operation. To ensure a reliable power supply for continuous functioning and energy replenishment, energy harvesting systems have been proposed. However, energy harvesting is not without limitations, including high equipment costs and limited feasibility in certain environments. This paper investigates a star-connected IoT network, in which the central coordinator node is equipped with a solar energy harvesting system. The harvested energy is used not only to power the coordinator’s own operations but also to activate nearby end devices via Wireless Power Transmission (WPT). Based on the estimated amount of power each end device can receive, determined by its distance from the coordinator, we propose an algorithm to compute optimal task scheduling that maximizes overall quality while satisfying the energy neutrality condition. Simulation results demonstrate the feasibility of integrating energy harvesting with WPT to efficiently power IoT devices.

In the Internet of Things/Fog interplay we define a novel problem, namely Max Sustainable Scheduling, and propose an algorithm for its solution. This problem arises when an IoT device and a Fog node stipulate a service-level agreement that limits the computational power that the Fog node devotes to serve the IoT device and that defines the corresponding costs, which are dependent on the actual amount of computational power required and on the associated energy costs for the Fog node. As the cost of energy is variable over time, this agreement is an incentive for the IoT device to schedule its activities so to modulate the implied load on the Fog node, in order to take advantage of the variable costs of the energy and to maximize the overall quality of its output. We discuss the pragmatics of the solver and we propose an efficient algorithm to solve the problem on the IoT device itself.

The Internet of Things (IoT) has recently received a lot of attention from the information and communication technology community. It has turned out to be a crucial development for harnessing the incredible power of wireless media in the real world. The nature of IoT-Fog networks requires the use of defense techniques who are light and mobile-aware. The edge resources in such a distributed environment are open to various safety hazards. DDoS UDP flooding attacks are the most frequent threats to edge resources in IoT-Fog networks. It is crucial for sabotaging fog gateways and can overcome traditional data filtering techniques. This paper introduces M-RL, a lightweight intrusion detection system with mobility awareness that can detect DDoS UDP flooding attacks while taking into account adversarial IoT devices that engage in IP spoofing. To this end, this paper analyzes the malicious behaviors that result in anonymity against Rate Limiting and Received Signal Strength (RSS)-based approaches, combines their advantages, and addresses their vulnerabilities. We test our method in different contexts to achieve that goal, and we find that it may decrease the accuracy of the RL, RSS, and RSS-RL methods to 70%, 48.9%, and 64.3%, respectively. The outcomes demonstrate the proposed approach's resistance to software-based source address forgery, impersonation, and signal modification. It offers more than 99% accuracy and supports node mobility. In this case, the best possible accuracy of the previous methods is 77%.

Emerging technologies such as remote sensing from satellites and drones, internet of things (IoT), deep learning models, etc, could all be utilized to make informed and smart decisions aimed to increase crop production. We provide an overview of TEBAKA, an Italian national project on Smart Farming and discuss its relevance in the overall scenario of similar projects. We emphasize the project originality, in particular the research activity on new data-driven ML models that better extract relevant knowledge from observations. We presented the task of image semantic segmentation of olive trees or rows of grape plants and show an original self-supervised deep learning network that produce the segmentation with high accuracy. Furthermore, we discuss some idea that would be part of the project activities for the next year.

Energy neutrality of Internet of Things devices powered with energy harvesting is a concept introduced to let these devices operate uninterruptedly. A method to achieve it is by letting the device scheduling different tasks characterized by different energy costs (and quality), depending on the current energy production of the energy harvesting subsystem and on the residual battery charge. In this context, we propose a novel scheduling problem that aims at keeping the energy neutrality of the scheduling while maximizing the overall quality of the executed tasks and minimizing the leaps of quality among consecutive tasks, so to improve the stability of the output of the device itself. We propose for this problem an algorithm based on a dynamic programming approach that can be executed even on low-power devices. By simulation we show that, with respect to the state of the art, the scheduling by our algorithm greatly improve the stability of the device with a minor penalty in terms of overall quality.

Unmanned aerial vehicles (UAVs) are autonomous devices employed as data collectors in precision agriculture to support a large number of applications. These UAVs gather data from on-the-ground wireless sensor networks, especially in scenarios that lack any kind of fixed communication infrastructure or where the available infrastructure does not fit the application requirements. Sensors on the ground can store sensing data, and in scenarios that do not require a real-time observation and analysis of the data, like in smart farming, a drone can be used maybe once or two times each day to collect and report the data to a command-and-control center that use them directly, without any other infrastructure (cloud or edges). In this article, we study analytically how close the drone, that uses a LoRa radio, needs to fly over the sensors to collect data with a given quality of data collection. This can be used to properly spacing the sensors on the field at deployment time, to select among different type of drones, and to properly solve some tradeoff related to field size vs autonomy of the drones and the path used by the latter when collecting the data.

The Internet of Things (IoT) paradigm poses a great variety of application domains where million of devices work uninterruptedly to improve some aspect of our lives. To support the continuous execution of the applications working on the devices, energy harvesting systems enable to extract the energy found naturally in the environment (for instance from the sun or from the wind) and convert it into energy able to either sustain the device's operation and recharge its batteries which, in conjunction with an appropriate scheduling strategy, led to the device to an electrically sustainable state (i.e. an energy-neutral state). Most of the works found in literature oriented to achieve energy neutrality are however evaluated by means of simulation which means that, in spite of precisely modeling hardware features and energy productions, lack of the realism that we find in a real deployment. A minor part of the works are based on a real deployment but do not share the collected data that permit to replicate the analysis. With this purpose in mind, in this article we describe a testbed designed for outdoor monitoring purposes in the IoT context, equipped with several sensors for weather conditions monitoring and with a solar panel to provide application lifetimes potentially infinite. The testbed was deployed on the roof of a building and it executed uninterruptedly an application able to generate a dataset with the collected information over a period of more than two months. This dataset has been online published to be used for different researching purposes, as for instance, prediction models of the energy production.

To make sustainable large IoT deployments in smart cities, a promising approach is to develop a new generation of solar energy harvesting IoT devices based on the concept of energy neutrality. Key to this concept are the models for the forecast of energy production, which provide input to the energy-neutral schedulers governing the activities of the IoT devices. The development of such models however need to be validated against real-world conditions. To this purpose we propose a testbed aimed at the collection of real-world dataset about the energy parameters of energy harvesting IoT devices, and, on the base of such a dataset, we perform a comparative assessment of state of the art and novel energy production forecast models.

Scheduling tasks appropriately in an IoT device powered by multiple energy-harvesting sources is a challenging problem. In this paper, we model this problem, and we present a scheduling algorithm that optimally sets the overall node power consumption based on the utility, and on the energy required by tasks. The algorithm schedules high-level tasks, it uses the weather forecast informations available at the beginning of each scheduling period (typically a day), and the level of the battery, to define an optimal schedule. The main goal is to find a schedule that is energy neutral on average, over a period longer than the single scheduling window, for example a week. We test our scheduler on a simulated platform with the same specs of an Arduino node, equipped with a small (portable) solar panel, and attached to a small wind turbine. We see from the simulations that the scheduler performs as expected and that the utility of the scheduling improves as the error between the expected forecast and the real harvested energy is reduced.

Outdoor Internet of Things (IoT) applications usually exploit energy harvesting systems to guarantee virtually uninterrupted operations. However, the use of energy harvesting poses issues concerning the optimization of the utility of the application while guaranteeing energy neutrality of the devices. In this context, we propose a new dynamic programming algorithm for the optimization of the scheduling of the tasks in IoT devices that harvest energy by means of a solar panel. We show that the problem is NP-hard and that the algorithm finds the optimum solution in a pseudo-polynomial time. Furthermore, we show that the algorithm can be executed with a small overhead on three popular IoT platforms (namely TMote, Raspberry PI, and Arduino) and, by simulation, we show the behavior of the algorithm with different settings and at different conditions of energy production.

Underwater communications through acoustic modems rise several networking challenges for the Underwater Acoustic Sensor Networks (UASN). In particular, opportunistic routing is a novel but promising technique that can remarkably increase the reliability of the UASN, but its use in this context requires studies on the nature of mobility in UASN. Our goal is to study a real-world mobility dataset obtained from the Argo project. In particular, we observe the mobility of 51 free-drifting floats deployed on the Mediterranean Sea for approximately one year and we analyze some important properties of the underwater network we built. Specifically, we analyze the contact-time, inter-contact time as well density and network degree while varying the connectivity degree of the whole dataset. We then consider three known routing algorithms, namely Epidemic, PROPHET and Direct Delivery, with the goal of measuring their performance in real conditions for USAN. We finally discuss the opportunities arising from the adoption of opportunistic routing in UASN showing that, even in a very sparse and strongly disconnected network, it is still possible to build a limited but working networking framework.

Underwater mobile acoustic sensor networks are promising tools for the exploration of the oceans. These networks require new robust solutions for fundamental issues such as: localization service for data tagging and networking protocols for communication. All these tasks are closely related with connectivity, coverage and deployment of the network. A realistic mobility model that can capture the physical movement of the sensor nodes with ocean currents gives better understanding on the above problems. In this paper, we propose a novel physically-inspired mobility model which is representative of underwater environments. We study how the model affects a range-based localization protocol, and its impact on the coverage and connectivity of the network under different deployment scenarios.

We consider the problem of routing with guaranteed delivery in wireless sensor networks where physical locations of the sensors are not known. We propose a naming protocol which defines a 2-dimensional coordinate system and a routing protocol (Ibrid) which ensures guaranteed delivery of packets. We show by means of simulation that in realistic settings where the network includes voids and obstacles, Ibrid finds routess hortest than those obtained with existing geographic routing algorithms over physical coordinates.

System-level diagnosis aims at the identification of faulty units in a system by the analysis of the system syndrome, that is, the outcomes of a set of interunit tests. For any given syndrome, it is possible to produce a correct (although possibly incomplete) diagnosis of the system if the number of faults is below a syndrome-dependent bound and the degree of diagnosis completeness, that is, the number of correctly diagnosed units, is also dependent on the actual syndrome sigma. The worst-case diagnosis completeness is a syndrome-independent bound that represents the minimum number of units that the diagnosis algorithm correctly diagnoses for any syndrome. This paper provides a lower bound to the worst-case diagnosis completeness for regular graphs for which vertex- isoperimetric inequalities are known and it shows how this bound can be applied to toroidal grids. These results prove a previous hypothesis about the influence of two topological parameters of the diagnostic graph, that is, the bisection width and the diameter, on the degree of diagnosis completeness.

In this paper we consider the problem of constructing a coordinate system in a sensor network where location information is not available. To this purpose we introduce the virtual coordinate assignment protocol (VCap) which defines a virtual coordinate system based on hop distances. As compared to other approaches, VCap is simple and have very little requirements in terms of communication and memory overheads. We compare by simulations the performances of greedy routing using our virtual coordinate system with the one using the physical coordinates. Results show that the virtual coordinate system can be used to efficiently support geographic routing.

The problem of identifying the faulty units in regularly interconnected systems is addressed. The diagnosis is based on mutual tests of units, which are adjacent in the "system graph" describing the interconnection structure. This paper evaluates an algorithm named EDARS (Efficient Diagnosis Algorithm for Regular Structures). The diagnosis provided by this algorithm is provably correct and almost complete with high probability. Diagnosis correctness is guaranteed if the cardinality of the actual fault set is below a "syndrome-dependent bound," asserted by the algorithm itself along with the diagnosis. Evaluation of EDARS relies upon extensive simulation which covered grids, hypercubes, and cube-connected cycles (CCC). Simulation experiments showed that the degree of the system graph has a strong impact over diagnosis completeness and affects the "syndrome-dependent bound," ensuring correctness. Furthermore, a comparative analysis of the performance of EDARS, with hypercubes and CCCs on one side and grids of the same size and degree on the other side, showed that diameter and bisection width of the system graph also influence the diagnosis correctness and completeness.

Introduces EDARS (Efficient Diagnosis Algorithm for Regular Structures). The algorithm provides a diagnosis which is correct, but possibly incomplete, if the cardinality of the actual fault set is below a "syndrome-dependent bound" asserted by the algorithm itself. The time complexity of EDARS is O(nt) when executed on t-regular structures of size n. The correctness and the completeness degree of EDARS were evaluated by means of simulation. Grids, hypercubes and cube-connected cycle (CCC) structures were considered. Simulation results with grid structures showed a strong influence of structure degree over diagnosis performance. Furthermore, comparisons of simulation results obtained with hypercubes, CCCs and grids of the same size and degree showed that diameter and bisection width also appear to influence the performance of EDARS, particularly with respect to diagnosis completeness.