Publications Lists     [ all BibTeX ]  

Faulty operations of Heating, Ventilation and Air Conditioning (HVAC) chiller systems can lead to discomfort for the occupants, energy wastage, unreliability and shorter equipment life. Such faults need to be detected early to prevent further escalation and energy losses. Commonly, data regarding unforeseen phenomena and abnormalities are rare or are not available at the moment of HVAC systems installation: for this reason in this paper an unsupervised One-Class SVM classifier employed as a novelty detection system to identify unknown status and possible faults is presented. The approach, that exploits Principal Component Analysis to accent novelties w.r.t. normal operations variability, has been tested on a HVAC literature dataset.

In recent years, Visual Sensor Networks (VSNs) have emerged as an interesting category of distributed sensor- actor systems to retrieve data from the observed scene and produce information. Indeed, the request for accurate 3D scene reconstruction in several applications is leading to the development of very large systems and more specifically to large scale motion capture systems. When dealing with such huge amount of data from a large number of cameras it becomes very hard to make real time reconstruction on a single machine.
Within this context, a distributed approach for reconstruc- tion on large scale camera networks is proposed. The approach is based on geometric triangulation performed in a distributed fashion on the computational grid formed by the camera net- work organized into a tree structure. Since the computational performance of the algorithm strongly depends on the order in which cameras are paired, to optimize the efficiency of the reconstruction a pairing strategy is designed that relies on an affinity score among cameras. This score is computed from a probabilistic perspective by studying the variance of the 3D target reconstruction error and resorting to a normalized cut graph partitioning.
The scaling laws and the results obtained in simulation suggest that the proposed optimization strategy allows to obtain a significant reduction of the computational time.

Process monitoring and Predictive Maintenance (PdM) are gaining increasing attention in most manufacturing environments as a means of reducing maintenance related costs and downtime. This is especially true in industries that are data intensive such as semiconductor manufacturing. In this paper an adaptive PdM based flexible maintenance scheduling decision support system, which pays particular attention to associated opportunity and risk costs, is presented. The proposed system, which employs Machine Learning and regularized regression methods, exploits new information as it becomes available from newly processed components to refine remaining useful life estimates and associated costs and risks. The system has been validated on a real industrial dataset related to an Ion Beam Etching process for semiconductor manufacturing.

We consider the problem of building a transitional model of an initially uncalibrated camera network. More specifically, we discuss an Hidden Markov Model (HMM) based strategy in which the model’s statespace is defined in terms of a partition of the physical network coverage. Transitions between any two such states are modeled by the distribution of the underlying Markov Process. Extending previous work in (Cenedese et al., 2010), we show how it is possible to infer the model structure and parameters from coordinate free observations and introduce a novel performance index that is used for model validation. We moreover show the predictive power of this HMM approach in simulated and real settings that comprise Pan-Tilt- Zoom (PTZ) cameras.

In this paper, we consider the problem of designing a distributed strategy to estimate the channel parameters for a generic Wireless Sensor-Actor Network. To this aim, we present a distributed least-square algorithm that complies with the constraint of transmitting only integer data through the wireless communication, which often characterizes Wireless Sensor-Actor Network embedded architectures. In this respect, we propose a quantized consensus strategy that mitigates the effects of the rounding operations applied to the wireless exchanged floating data. Moreover, the approach is based on a symmetric random gossip strategy, making it suitable for the actual deployment in multiagent networks. Finally, the effectiveness of the proposed algorithm and of its implementation as an open-source application is assessed and the employment of the procedure is illustrated through the application to radio-frequency localization experiments in a real world testbed.

The knowledge of the size of a network, i.e.\ of the number of nodes composing it, is important for maintenance and organization purposes. In networks where the identity of the nodes or is not unique or cannot be disclosed for privacy reasons, the size-estimation problem is particularly challenging since the exchanged messages cannot be uniquely associated with a specific node. In this work, we propose a totally distributed anonymous strategy based on statistical inference concepts. In our approach, each node starts generating a vector of independent random numbers from a known distribution. Then nodes compute a common function via some distributed consensus algorithms, and finally they compute the Maximum Likelihood (ML) estimate of the network size exploiting opportune statistical inferences. In this work we study the performance that can be obtained following this computational scheme when the consensus strategy is either the maximum or the average. In the max-consensus scenario, when data come from absolutely continuous distributions, we provide a complete characterization of the ML estimator. In particular, we show that the squared estimation error decreases as $1/M$, where $M$ is the amount of random numbers locally generated by each node, independently of the chosen probability distribution. Differently, in the average-consensus scenario, we show that if the locally generated data are independent Bernoulli trials, then the probability for the ML estimator to return a wrong answer decreases exponentially in $M$. Finally, we provide a discussion as how the numerical errors may affect the estimators performance under different scenarios.

Technological advances and the ever-growing human quest for improving the resolution of telescope observations are motivating the design of larger and larger ground telescopes: indeed, the larger is the telescope lens diameter, the better is the diffraction limited resolution of the telescope. Unfortunately, the terrestrial atmospheric turbulence, if not properly compensated, negatively affects the telescope observations, limiting its real resolution. Adaptive Optics (AO) systems are used in large ground telescopes in order to compensate the effect of the atmosphere, and hence to make the real telescope resolution be determined by the diffraction properties of the lens.

Technological advances and the ever-growing human quest for improving the resolution of telescope observations are motivating the design of larger and larger ground telescopes: indeed, the larger is the telescope lens diameter, the better is the diffraction limited resolution of the telescope. Unfortunately, the terrestrial atmospheric turbulence, if not properly compensated, negatively affects the telescope observations, limiting its real resolution. Adaptive Optics (AO) systems are used in large ground telescopes in order to compensate the effect of the atmosphere, and hence to make the real telescope resolution be determined by the diffraction properties of the lens. AO systems exploit the measurements of wavefront sensors to estimate the current values of the atmospheric turbulence, and compensate its effect by properly adapting the shape of a set of deformable mirrors. As the size of the telescope lenses is increasing, then the size of the AO system (e.g. the number of deformable mirror actuators and the size of the wavefront sensor) is increasing as well. This causes the increase of the computational burden needed to compute a proper compensation of the effect of the atmosphere. Consequently, as the potential telescope resolution increases, the task of the AO systems becomes more challenging. Motivated by the need of providing AO solutions useful for the next generations of ground telescopes, then a number of efficient algorithms have been recently considered in the literature to solve the problems related to the AO system. This paper considers the combination of a recently proposed very efficient phase reconstruction method, namely the CuRe, with a properly defined Kalman filter in order to obtain a dynamic compensation of the atmospheric turbulence. The performance of the proposed approach is investigated in some simulations.

In the semiconductor manufacturing environment it is very important to understand which factors have the most impact on process outcomes and to control them accordingly. This is usually achieved through design of experiments at process start-up and long term observation of production. As such it relies heavily on the expertise of the process engineer. In this work, we present an automatic approach to extracting useful insights about production processes and equipment based on state-of-the-art Machine Learning techniques. The main goal of this activity is to provide tools to process engineers to accelerate the learning-by-observation phase of process analysis. Using a Metal Deposition process as an example, we highlight various ways in which the extracted information can be employed.

We propose a new modeling paradigm for large dimensional aggregates of stochastic systems by Generalized Factor Analysis (GFA) models. These models describe the data as the sum of a flocking plus an uncorrelated idiosyncratic component. The flocking component describes a sort of collective orderly motion  which admits a much simpler   mathematical description than the whole ensemble while the idiosyncratic component describes weakly correlated noise. We first discuss static GFA representations and characterize in a rigorous way the properties of the two components. For wide-sense stationary sequences the character and existence of GFA models is completely clarified. The extraction of the flocking component of a random field is discussed for a simple class of separable random fields.

Turbulence simulation methods are of fundamental importance for evaluating the performance of control strategies for Adaptive Optics (AO) systems. In order to obtain a reliable evaluation of the performance a statistically accurate turbulence simulation method has to be used. This work generalizes a previously proposed method for turbulence simulation based on the use of a multiscale stochastic model. The main contributions of this work are: first, a multiresolution local PCA representation is considered. In typical operating conditions, the computational load for turbulence simulation is reduced approximately by a factor of 4, with respect to the previously proposed method, by means of this PCA representation. Second, thanks to a different low resolution method, based on a moving average model, the wind velocity can be in any direction (not necessarily that of the spatial axes). Finally, this paper extends the simulation procedure to generate, if needed, turbulence samples by using a more general model than that of the frozen flow hypothesis.

The property of single prediction predictive control in the form of dynamic matrix control is studied within internal model control framework. The sensitivity function and integral squared error are used as performance evaluation criteria in the frequency and time domain respectively, to quantitativelyanalyze single prediction strategy, especially on controller with the prediction and control horizon P = M = 1. We present the correlation between system performance and model mismatch in this case. The performance limitation for tracking unit step signal is obtained through derivation and simulation.

This paper investigates an original system for wireless control and monitoring of an agricultural machine. The system is implemented by means of an IEEE 802.11-based soft realtime communication architecture which enables the connection of the machine with off-the-shelf mobile devices, like widespread tablet PCs, that could hence replace traditional ad-hoc developed operator panels. The harsh surrounding environment, however, introduces severe requirements. Hence, focusing on the wireless communication behavior, the paper yields a thorough performance analysis derived by extensive experimental campaigns. By investigating the outcomes of these measurement sessions, the paper assesses some causes of performance degradation, and provides viable and easy to implement solutions to improve the overall system behavior.

Classification methods with embedded feature selection capability are very appealing for the analysis of complex processes since they allow the analysis of root causes even when the number of input variables is high. In this work, we investigate the performance of three techniques for classification within a Monte Carlo strategy with the aim of root cause analysis. We consider the naive Bayes classifier and the logistic regression model with two different implementations for controlling model complexity, namely, a LASSO-like implementation with a l1 norm regularization and a fully Bayesian implementation of the logistic model, the so called relevance vector machine. Several challenges can arise when estimating such models mainly linked to the characteristics of the data: a large number of input variables, high correlation among subsets of variables, the situation where the number of variables is higher than the number of available data points and the case of unbalanced datasets. Using an ecological and a semiconductor manufacturing dataset, we show advantages and drawbacks of each method, highlighting the superior performance in term of classification accuracy for the relevance vector machine with respect to the other classifiers. Moreover, we show how the combination of the proposed techniques and the Monte Carlo approach can be used to get more robust insights into the problem under analysis when faced with challenging modelling conditions.

The diffusion of visual sensor networks, and in particular of smart camera networks, is motivating an increasing interest on the research of distributed solutions for several vision problems. Specifically, in this paper we propose a distributed solution to the problem of reconstructing target positions in large Motion Capture (MoCap) systems. Real time reconstruction by means of centralized procedures is practically unfeasible for very large systems, while the use of distributed computation allows to significantly reduce the computational time required for reconstruction, thus allowing the development of real time solutions.
Then the proposed distributed reconstruction procedure is optimized by exploiting information about the structure of the system: the visibility matrix states which objects in the scene are somehow measurable by a sensor (sensor-object matrix). Often, the typical localization of data from real application scenarios induces an underlying structure on the visibility matrix, that can be exploited to improve the performance of the system in understanding the surrounding environment. Unfortunately, usually these data are not properly organized in the visibility matrix: for instance, listing the sensors in a pseudo-random order can hide the underlying structure of the matrix. This paper considers the problem of recovering such underlying structure directly from the visibility matrix and designs an algorithm to perform this task.
Our simulations show that the distributed reconstruction algorithm optimized by means of the estimation of the structure of the visibility matrix allows a particularly relevant computational time reduction with respect to the standard (centralized) reconstruction algorithm.