Ricerc@Sapienza

In this paper, we model manufacturing processes and facilities as transducers (automata with output). The problem of whether a given manufacturing process can be realized by a given set of manufacturing resources can then be stated as an orchestration problem for transducers. We first consider the conceptually simpler case of uni-transducers (transducers with a single input and a single output port), and show that synthesizing orchestrations for uni-transducers is EXPTIME-complete.

Planning domains represent what an agent assumes or be- lieves about the environment it acts in. In the presence of non- determinism, additional temporal assumptions, such as fair- ness, are often expressed as extra conditions on the domain. Here we consider environment specifications expressed in ar- bitrary LTL, which generalize many forms of environment specifications, including classical specifications of nondeter- ministic domains, fairness, and other forms of linear-time constraints on the domain itself.

There has recently been increasing interest in using reactive synthesis techniques to automate the production of manufacturing process plans. Previous work has assumed that the set of manufacturing resources is known and fixed in advance. In this paper, we consider the more general problem of whether a controller can be synthesized given sufficient resources.

In this article, we study the completion time of the PUSH-PULL variant of rumor spreading, also known as randomized broadcast.We show that if a network has n nodes and conductance φ then, with high probability, PUSH-PULL will deliver themessage to all nodes in the graph within O(logn/φ) many communication rounds. This bound is best possible. We also give an alternative proof that the completion time of PUSH-PULL is bounded by a polynomial in logn/φ, based on graph sparsification.

Mobile biometrics technologies are nowadays the new frontier for secure use of data and services, and are considered particularly important due to the massive use of handheld devices in the entire world. Among the biometric traits with potential to be used in mobile settings, the iris/ocular region is a natural candidate, even considering that further advances in the technology are required to meet the operational requirements of such ambitious environments. Aiming at promoting these advances, we organized the Mobile Iris Challenge Evaluation (MICHE)-I contest.

The paper presents experiments with the home-made, low-cost prototype of a sensor-equipped pen for handwriting-based biometric authentication. The pen allows to capture the dynamics of user writing on normal paper, while producing a kind of password (passphrase) chosen in advance. The use of a word of any length instead of the user's signature makes the approach more robust to spoofing, since there is no repetitive pattern to steal. Moreover, if the template gets violated, this is much less harmful than signature catch.

Mobile biometrics represent the new frontier of authentication. The most appealing feature of mobile devices is the wide availability and the presence of more and more reliable sensors for capturing biometric traits, e.g., cameras and accelerometers. Moreover, they more and more often store personal and sensitive data, that need to be protected. Doing this on the same device using biometrics to enforce security seems a natural solution. This makes this research topic attracting and generally promising.

We consider the problem of approximating a given matrix by a low-rank matrix so as to minimize the entry-wise ?p-approximation error, for any P ? 1; the case p = 2 is the classical SVD problem. We obtain the first provably good approximation algorithms for this version of low-rank approximation that work for every value of p ? 1, including p = ?. Our algorithms are simple, easy to implement, work well in practice, and illustrate interesting tradeoffs between the approximation quality, the running time, and the rank of the approximating matrix.

The principles on how neurons encode and process information from low-level stimuli are still open questions in neuroscience. Neuron models represent useful tools to answer this question but a sensitive method is needed to decode the input information embedded in the neuron spike sequence. In this work, we developed an automatic decoding procedure based on the SNR spectrum improved by low-pass homomorphic filtering. The procedure was applied to a stochastic Hodgkin Huxley neuron model forced by a low-level sinusoidal signal in the range 50 Hz-300 Hz.

The encoding of the spatial-temporal archeological, historical and anthropological records can be considered an ideal-typical representation of the human reasoning and thus also an artificial membrane interposed between the researcher and the past. These membranes are here considered artificial networks and can undergo interrogation processes through the most advanced analytical tools for learning and modeling complex configurations.