Indoor localization systems have already wide applications mainly for providing localized information and directions. The majority of them focus on commercial applications providing information such us advertisements, guidance and asset tracking. Medical oriented localization systems are uncommon. Given the fact that an individual’s indoor movements can be indicative of his/her clinical status, in this paper we present a low-cost indoor localization system with room-level accuracy used to assess the frailty of older people. We focused on designing a system with easy installation and low cost to be used by non technical staff. The system was installed in older people houses in order to collect data about their indoor localization habits. The collected data were examined in combination with their frailty status, showing a correlation between them. The indoor localization system is based on the processing of Received Signal Strength Indicator (RSSI) measurements by a tracking device, from Bluetooth Beacons, using a fingerprint-based procedure. The system has been tested in realistic settings achieving accuracy above 93% in room estimation. The proposed system was used in 271 houses collecting data for 1–7-day sessions. The evaluation of the collected data using ten-fold cross-validation showed an accuracy of 83% in the classification of a monitored person regarding his/her frailty status (Frail, Pre-frail, Non-frail).

No abstract

No abstract

Cognitive radio networks are a promising technology for the improvement of the spectrum utilisation. The basic idea is to maximise the utilisation of the available spectrum by dynamically assigning available channels to secondary users. This problem known as the spectrum allocation problem is non-deterministic polynomial-time hard (NP-hard). Chaotic biogeographybased optimisation (CBBO) is a recently proposed evolutionary algorithm that can be applied to the above-mentioned problem. The authors compare CBBO with other popular algorithms in different spectrum allocation problem cases. The results show that CBBO performs in general better or similar to the other algorithms. 8 IET Netw.