Activity recognition plays a key role in providing activity assistance and care for users in smart homes. In this work, we present an activity recognition system that classifies in the near real-time a set of common daily activities exploiting both the data sampled by sensors embedded in a smartphone carried out by the user and the reciprocal Received Signal Strength (RSS) values coming from worn wireless sensor devices and from sensors deployed in the environment. In order to achieve an effective and responsive classification, a decision tree based on multisensor data-stream is applied fusing data coming from embedded sensors on the smartphone and environmental sensors before processing the RSS stream. To this end, we model the RSS stream, obtained from a Wireless Sensor Network (WSN), using Recurrent Neural Networks (RNNs) implemented as efficient Echo State Networks (ESNs), within the Reservoir Computing (RC) paradigm. We targeted the system for the EvAAL scenario, an international competition that aims at establishing benchmarks and evaluation metrics for comparing Ambient Assisted Living (AAL) solutions. In this paper, the performance of the proposed activity recognition system is assessed on a purposely collected real-world dataset, taking also into account a competitive neural network approach for performance comparison. Our results show that, with an appropriate configuration of the information fusion chain, the proposed system reaches a very good accuracy with a low deployment cost.

SUMMARYEffective primary prevention of congenital toxoplasmosis requires up to date information on locally relevant risk factors for infection in pregnant women. In Naples, risk factors for toxoplasma infection were compared in recently infected women (as assessed by detection of specific IgM in serum) and susceptible, IgG negative women. Recent infection was strongly associated with frequency of consumption of cured pork and raw meat. Eating cured pork or raw meat at least once a month increased the risk of toxoplasma infection threefold.This simple study design for determining locally relevant sources of toxoplasma infection is the first report of cured pork as a risk factor for infection. Further research is required to determine cyst viability in cured pork products. Our findings suggest that in southern Italy, cured pork and raw meat should be avoided by susceptible pregnant women.

The role of ear-piercing, tattooing, attendance at chiropodist or manicurist and barber shop shaving in transmitting hepatitis B and hepatitis non-A, non-B was evaluated. Data reported here were collected from 1985 to 1993 by the National Viral Hepatitis Surveillance System. The association between parenterally transmitted hepatitis and the considered risk factors was estimated, comparing 6,395 hepatitis B and 2,558 hepatitis non-A, non-B cases with 4,789 hepatitis A cases, using the case-control method. Of the non-A, non-B cases tested from 1991 to 1993, 56.6% were anti-HCV positive. The incidence of parenterally transmitted hepatitis cases reporting specific beauty treatments was also evaluated. Tattooing, ear-piercing and barber shop shaving were associated with both parenterally transmitted hepatitides, while attendance at a chiropodist or manicurist was associated only with hepatitis B. During the study period the incidence of acute hepatitis B and non-A, non-B cases reporting beauty treatments declined by 49%. In spite of this decline, considering that a large part of the general population is exposed to the considered risk factors, the role of beauty treatments in transmitting hepatitis B and hepatitis non-A, non-B should not be underestimated.