1,721,121 research outputs found
Decentralised learning for Intelligent Control Systems
No full textThis manuscript represents a collection of the most important research activities
carried out by the candidate during his three years of PhD studies.
This work leverages on the concept of Intelligent Control Systems, defined as
a framework where control methods attempt to emulate important characteristics
of human intelligence to generate control actions. Being referred to as a point of
contact between the scientific fields of control theory and artificial intelligence, they
aim to combine the mathematical rigor of the former with the representativeness of
the latter in order to exploit the potential of both of them.
While classical control theory model-based approaches commonly used to examine
the characteristics of a given system in terms of its stability, safety and optimality,
may fail to include environmental uncertainties and are subject to modelling errors,
data-driven controller design techniques aim to capture such stochasticities and
nonlinearities. This idea is behind the development of the first work which develops
neural-based control solution which envisages the use of deep neural networks within
the model predictive control framework with the aim to derive the optimal control law
in a distributed fashion by means of a cascading combination of one-step predictors.
The second work focuses on the learning processes of data-driven methodologies,
with particular attention to neural networks, whose approximation capabilities make
them of one of the most important tools in the approximation of system dynamics.
The research activity, carried out by the candidate in the scope of the POR FESR
FedMedAI project, develops a decentralised framework based on consensus-theory
aimed at allowing the training of a neural network over decentralised scenarios,
namely on data belonging to multiple actors who communicate with each other and
collaborate for the learning of a data-driven model aimed at solving an approximation
task. The specifications of this framework were defined during the course of the
project through interactions with the Italian Istituto Superiore di Sanità, allowing
the realization of a platform aimed at enhancing a privacy-preserving collaboration
among clinical institutions, without any exchange of clinical data.
The investigation of the mechanisms underpinning the interaction between different
actors is examined within the third work in the context of multi-agent systems.
Since communication is one of the tools used by agents to collaborate, a learningbased
strategy allowing agents to limit their communication while still achieving
their objective is proposed leveraging on the multi-agent reinforcement learning framework. The proposed approach allows to cope with real-world scenarios where
communication-related costs cannot be neglected.
The fourth work discusses multi-agent scenarios where each agent attempts to
accomplish its own objective independently of other agents’ cooperation. Numerous
settings find use for these non-cooperative scenarios, one of which being telecommunications.
In this context, the convergence properties of a class of load-balancing
strategies towards a set of approximate non-cooperative equilibria are examined. The
candidate also explores non-cooperative approaches in the domains of mobile edge
computing and automotive, whereby decentralised policy broadcasting mechanisms
and decision-making processes based on reinforcement learning are proposed.
All the studies incorporated into this work addresses various issues and challenges
that may arise when intelligent control systems are employed in multi-agent context.
In particular, control systems of this type find application in the control of complex
systems, such as health-related ones, in which the interaction with the human being
constitutes the most critical aspect. With respect to this issue, the high-level architecture
of the PON CADUCEO, POR FESR FedMedAI and Allenamente project is
described.
Every study under consideration is predicated on the use of various control theory
arguments and data-driven approaches, whose choice and combination is justified
and validated over different scenarios
Tecniche di misura nel dominio del tempo per la caratterizzazione di sistemi di trasmissione wireless
No full text
A University Space Technology Program to Design and Validate New and Potentially Cost-Effective Hardware
No full textThe evolution of the aerospace field has pushed the importance of cost-effective development of space platform. The high-risk levels related to new technology allow universities to have an important role in improving the cost effectiveness of the hardware design, development and testing. In this frame, the Second University of Naples space technology program is described, outlining benefits and drawbacks of the program from both industrial, research. and educational points of view. The R&D approach and relative laboratory are described, presenting the results obtained in terms of the developed hardware and the educational improvements. An overview of the budget needed in these few years to develop the program is given. and the potential achievements, along with the main critical points are outline
Treatment of atherosclerotic renal artery stenosis
No full textThe increasing prevalence of atherosclerotic renal artery stenosis (ARAS) has prompted in recent years a more aggressive treatment of this condition for reducing BP and for preserving the jeopardized renal function. Percutaneous transluminal renal angioplasty (PTRA), alone or in conjunction with stent implantation, may be useful for both these goals. However, despite the methodological improvements that make this procedure much safer than surgery, caution must be applied before PTRA is extended to all patients with ARAS. Indeed, PTRA is associated with a 23% rate of major/minor complications and with a 20% rate of restenosis, even in arteries implanted with stent. Moreover the cure rate of hypertension achievable with PTRA is, at best, around 10%, with a 40% rate of improvements. Even for rescuing the ischemic kidney, PTRA/stem implantation are not always effective; only 35% of patients with ARAS have some improvement in renal function. These data indicate that there is an urgent need of rigorous criteria for selecting among the many patients with ARAS those who may actually benefit from the dilation procedure
Avionics Integration and Test for Rover Applications
No full textRover systems are currently attracting an increasing interest, both for planetary exploration and terrestrial missions. Regardless of the considered applications, avionics design and integration present some common threads, related to sensor fusion, subsystems modularity, and low cost/mass/dimensions requirements. This paper deals with a customized system based on a radio-controlled car model and equipped with an integrated GNC/communication system. This rover is being developed as a multi-purpose test bed for concepts, algorithms and/or prototype subsystems. GNC system is based on GPS/INS integration and MEMS sensors. Communication with ground station is implemented by Wi-Fi and UDP protocol. Integration of EO sensors for stereo vision is under way. Hardware and software elements of the system are described in detail, regarding both rover and ground station. Results from laboratory and open tests are reported which put into evidence real time navigation capability and communication link reliability, in terms of small and constant latency and no loss of messages
- …
