Andrea Proietti

An Accurate Algorithm for the Identification of Fingertips Using an RGB-D Camera

RGB-D cameras and depth sensors have made possible the development of an uncountable number of applications in the field of human-computer interactions. Such applications, varying from gaming to medical, have made possible because of the capability of such sensors of elaborating depth maps of the placed ambient. In this context, aiming to realize a sound basis for future applications relevant to the movement and to the pose of hands, we propose a new approach to recognize fingertips and to identify their position by means of the Microsoft Kinect technology. The experimental results exhibit a really good identification rate, an execution speed faster than the frame rate with no meaningful latencies, thus allowing the use of the proposed system in real time applications. Furthermore, the scored identification accuracy confirms the excellent capability of following also little movements of the hand and it encourages the real possibility of successive implementations in more complex gesture recognition systems.

A New Dusts Sensor for Cultural Heritage Applications Based on Image Processing

In this paper, we propose a new sensor for the detection and analysis of dusts (seen as powders and fibers) in indoor environments, especially designed for applications in the field of Cultural Heritage or in other contexts where the presence of dust requires special care (surgery, clean rooms, etc.). The presented system relies on image processing techniques (enhancement, noise reduction, segmentation, metrics analysis) and it allows obtaining both qualitative and quantitative information on the accumulation of dust. This information aims to identify the geometric and topological features of the elements of the deposit. The curators can use this information in order to design suitable prevention and maintenance actions for objects and environments. The sensor consists of simple and relatively cheap tools, based on a high-resolution image acquisition system, a preprocessing software to improve the captured image and an analysis algorithm for the feature extraction and the classification of the elements of the dust deposit. We carried out some tests in order to validate the system operation. These tests were performed within the Sistine Chapel in the Vatican Museums, showing the good performance of the proposed sensor in terms of execution time and classification accuracy.

Fuzzy clustering using the convex hull as geometrical model

A new approach to fuzzy clustering is proposed in this paper. It aims to relax some constraints imposed by known algorithms using a generalized geometrical model for clusters that is based on the convex hull computation. A method is also proposed in order to determine suitable membership functions and hence to represent fuzzy clusters based on the adopted geometrical model. The convex hull is not only used at the end of clustering analysis for the geometric data interpretation but also used during the fuzzy data partitioning within an online sequential procedure in order to calculate the membership function. Consequently, a pure fuzzy clustering algorithm is obtained where clusters are fitted to the data distribution by means of the fuzzy membership of patterns to each cluster. The numerical results reported in the paper show the validity and the efficacy of the proposed approach with respect to other well-known clustering algorithms.

Fuzzy membership functions based on point-to-polygon distance evaluation

In this paper, a new approach is presented for the evaluation of membership functions in fuzzy clustering algorithms. Starting from the geometrical representation of clusters by polygons, the fuzzy membership is evaluated through a suited point-to-polygon distance estimation. Three different methods are proposed, either by using the geometrical properties of clusters in the data space or by using Gaussian or cone-shaped kernel functions. They differ from the basic trade-off between computational complexity and approximation accuracy. By the proposed approach, fuzzy clusters of any geometrical complexity can be used, since there is no longer required to impose constraints on the shape of clusters resulting from the choice of computationally affordable membership functions. The methods illustrated in the paper are validated in terms of speed and accuracy by using several numerical simulations.

Multimedia and Gaming Technologies for Telerehabilitation of Motor Disabilities [Leading Edge]

Rehabilitation for chronic conditions resulting from acute or progressive disease might be delivered in an outpatient facility as in the case of telerehabilitation, self rehabilitation and, more generally, in the context of home-based rehabilitation to improve the patients’ quality of life. Here we present the emerging field of home-based applications for continuous digital health, focusing in particular on low-cost rehabilitation systems for motor disabilities based on multimedia and gaming technologies. Innovative technologies for telerehabilitation are illustrated. We also present recent advances in telerehabilitation, considering the most relevant projects that best represent new trends for research and development of new technologies and applications in this context.

Improved online fuzzy clustering based on unconstrained kernels

A novel fuzzy clustering algorithm is presented in this paper, which removes the constraints generally imposed to the cluster shape when a given model is adopted for membership functions. An on-line, sequential procedure is proposed where the cluster determination is performed by using suited membership functions based on geometrically unconstrained kernels and a point-to-shape distance evaluation. Since the performance of on-line algorithms suffers from the pattern presentation order, we also consider the problem of cluster validity aiming at proving the minimal dependence and the robustness with respect to the initialization of inner parameters in the proposed algorithm. The numerical results reported in the paper prove that the proposed approach is able to improve the performances of well-known algorithms on some reference benchmarks.

A higher-order fuzzy neural network for modeling financial time series

This work investigates on the widespread use of fuzzy neural networks in time series forecasting, concerning in particular the energy commodity markets. We propose a new learning strategy suited to any neural model. The proposed approach is further assessed in the case of higher-order Sugeno-type fuzzy rules, which are able to replicate the daily data and to reproduce the same statistical features for various Commodity time series. The data used are obtained from the daily return series of specific energy commodities, such as coal, natural gas, crude oil and electricity, over the period 2001-2010 for both the European and US markets. We will prove that our approach can obtain interesting results in terms of prediction accuracy and volatility estimation, compared to well-known neural and fuzzy neural models and to the ARMA-GARCH statistical paradigm.

Energy saving project for heating system with ZigBee wireless control network

An energy saving system able to optimize power management and energy efficiency of an home heating plant is proposed. Thanks to an advanced interface and control architecture based on ZigBee wireless devices, a continuous control of temperature is warranted making efficient the heating plant. The system uses a sensor and actuator combination to control and guarantee the desired system parameters; the information is transferred point-by-point using ZigBee communication network and its sent to a central unit used to check the peripheral devices state and to take appropriate measures in case of failure or alarm.

Classification of Dust Elements by Spatial Geometric Features

Management of air quality is an important task in many human activities. It is carried out mainly by installing ventilation and filtering facilities. In order to ensure efficiency, these systems must be designed after the knowledge of key environmental parameters, such as size and type of particles and fibres present in the air. In this paper, we propose a new method for the classification of dust particles and fibres based on a minimal set of geometric features extracted from binary images of dust elements, captured by a very cheap imaging system. The proposed technique is discussed and tested. Experimental results obtained by real- measured data are presented, showing satisfactory performance by using several well-known classifiers.

A genetic algorithm for feature selection in gait analysis

This paper deals with the opportunity of extracting useful information from medical data retrieved directly from a stereophotogrammetric system applied to gait analysis, which aims at controlling movements of patients affected by neurological diseases. The proposed approach is intended to a feature selection procedure as an optimization strategy based on genetic algorithms, where the misclassification error of healthy/diseased patients is adopted as the fitness function. This procedure will be used for estimating the performance of widely used classification algorithms, whose performance has been ascertained in many real-world problems with respect to well-known classification benchmarks, both in terms of number of selected features and classification accuracy. Moreover, the technique herein described will provide a useful tool in the context of medical diagnosis. In fact, we will prove that for the classification problem at hand the whole set of features is redundant and it can be significantly pruned. The obtained results on a real dataset acquired in our biomechanics laboratory show a very interesting classification accuracy using six features only among the sixteen acquired by the stereophotogrammetric system.