Approximate reinforcement learning to control beaconing congestion in distributed networks.

In vehicular communications, the increase of the channel load caused by excessive periodical messages (beacons) is an important aspect which must be controlled to ensure the appropriate operation of safety applications and driver-assistance systems. To date, the majority of congestion control solutions involve including additional information in the payload of the messages transmitted, which may jeopardize the appropriate operation of these control solutions when channel conditions are unfavorable, provoking packet losses. This study exploits the advantages of non-cooperative, distributed beaconing allocation, in which vehicles operate independently without requiring any costly road infrastructure. In particular, we formulate the beaconing rate control problem as a Markov Decision Process and solve it using approximate reinforcement learning to carry out optimal actions. Results obtained were compared with other traditional solutions, revealing that our approach, called SSFA, is able to keep a certain fraction of the channel capacity available, which guarantees the delivery of emergency-related notifications with faster convergence than other proposals. Moreover, good performance was obtained in terms of packet delivery and collision ratios.

Determination of progesterone in saliva using an electrochemical immunosensor and a COTS-based portable potentiostat.

This paper describes the reliable determination of progesterone (P4) in undiluted saliva making use of a disposable amperometric immunosensors implemented on low-cost and portable device/potentiostat constructed with commercial-off-the-shelf (COTS) components. The immunosensor allows the fast (45 min), selective and sensitive determination (5 pg mL-1 LOD) of P4 using amperometry in stirred solutions. The immunosensor was coupled to the COTS-based potentiostat and amperometry was made into drops of quiescent solutions. No significant differences were apparent between the analytical performance achieved with the immunosensor for P4 using both a conventional and the COST-based potentiostats. The practical applicability of the immunosensor coupled with the COTS-based potentiostat was demonstrated by determining the endogenous P4 content in different undiluted saliva samples with highly variable endogenous contents of the target hormone. The obtained results were in good agreement with those provided by the conventional ELISA methodology and with the contents reported in the literature for samples with similar characteristics. This validated the combined device for the reliable and minimally invasive determination of the target hormone involving a very simple protocol and taking only 45 min.