Giuseppe Marcone

RF propagation analysis for ZigBee Sensor Network using RSSI measurements

The scope of this work is to investigate the RF behavior of ZigBee devices operating within a real environment. On this purpose a Wireless Sensor Network (WSN) ZigBee based has been deployed in a specific indoor context. Three different RSSI measurement campaigns have been carried out to characterize the main propagation features. On the basis of the experimental results it has been possible to analyze the different factors that affect the measurements, such as external factors (e.g. multipath, fading) or internal ones (e.g. hardware device, integrated antennas). The first campaign, made nearby the transmitter, was performed to study the internal and external factor effects, the second one to extend the range of the first experiment, and the latter to investigate the propagation trying to isolate the external phenomena. Furthermore to deeply analyze the ZigBee behavior we have compared the measurements with a suitable propagation model. This work allows the definition of the main performance requirements for a ZigBee Sensor Network deployed in real building environment.

Neural clustering for optimal KLT image compression

A multiple class approach is proposed for improving the performance of the Karhunen-Loeve transform (KLT) image compression technique. The classification is adaptively performed by suitable neural networks. Several examples are presented in order to show that the proposed method performs much better than the classical discrete cosine transform (DCT). >

Eye Tracking in Image Sequences by Competitive Neural Networks

An automatic algorithm is presented for the eye tracking within face image sequences. It is based on the property of local Gabor filters to efficiently determine the location of eyes in face images. The proposed algorithm is implemented by a competitive neural network, that locates and tracks the eyes in a reliable manner as shown by experimental results.

ZigBee Sensor Network propagation analysis for health-care application

The goal of the work is to investigate the Radio Frequency (RF) propagation of ZigBee devices operating within a hospital environment to analyze their real indoor behaviour to design healthcare systems. Different Received Signal Strength Inidcation (RSSI) measurement campaigns have been carried out to characterize the main propagation features. On the basis of the experimental results it has been possible to analyze the different factors that affect the measurements, such as external factors (e.g. multipath, fading) or internal ones (e.g. hardware device, integrated antennas). Furthermore to deeply define the ZigBee behavior we have compared the measurements with a suitable propagation model. This preliminary study permitted us to include the main measurements outcomes in a planning simulator which emulates the radio propagation in hospital environments. Specifically the planning model proposed is useful to design a “Smart Hospital” and thus to define main performance requirements for a ZigBee Sensor Network deployed in real hospital environment.