Abstract:The ageing of the population, and their increasing wish of living independently, are motivating the development of welfare and healthcare models. Existing approaches based on the direct heath-monitoring using body sensor networks (BSN) are precise and accurate. Nonetheless, their intrusiveness causes non-acceptance. New approaches seek the indirect monitoring through monitoring activities of daily living (ADLs), which proves to be a suitable solution. ADL monitoring systems use many heterogeneous sensors, are less intrusive, and are less expensive than BSN, however, the deployment and maintenance of wireless sensor networks (WSN) prevent them from a widespread acceptance. In this work, a novel technique to monitor the human activity, based on non-intrusive load monitoring (NILM), is presented. The proposal uses only smart meter data, which leads to minimum intrusiveness and a potential massive deployment at minimal cost. This could be the key to develop sustainable healthcare models for smart homes, capable of complying with the elderly people' demands. This study also uses the Dempster-Shafer theory to provide a daily score of normality with regard to the regular behavior. This approach has been evaluated using real datasets and, additionally, a benchmarking against a Gaussian mixture model approach is presented.

No abstract

No abstract

Ultra-Wideband (UWB) has a high interest in research and industry for accurate indoor positioning. This technology comprises signals with a bandwidth of at least 500 MHz at a power decay of -10dB. This large bandwidth conferes the capability of resolving multipath, penetrating through obstacles and accurate ranging. However, NLOS (Non-Line-Of-Sight) conditions produced by obstacles in indoor environments severely degrade performance, as they introduce a positive bias in ranging estimation. In this paper we present a robust UWB indoor positioning which is able to accurately operate in a highly complex indoor scenario, where NLOS condition is predominant. For that purpose, the system uses a NLOS detection algorithm based on the skewness of the estimated channel impulse response and it mitigates NLOS by using an Extended Kalman Filter. The use of this detection/mitigation algorithm shows an improvement of the RMSE in positioning about 67%.

This paper presents a flexible deployment of ultrasonic position sensors and a novel positioning algorithm suitable for the navigation of mobile robots (MRs) in extensive indoor environments. Our proposal uses several independently-referenced local positioning systems (LPS), which means that each one of them operates within its own local reference system. In a typical layout, an indoor extensive area can be covered using just a reduced set of globally-referenced LPS (GRLPS), whose beacon positions are known to the global reference system, while the rest of the space can be covered using locally-referenced LPSs (LRLPS) that can be distributed arbitrarily. The number of LRLPS and their position can be also changed at any moment. The algorithm is composed of several Bayesian filters running in parallel, so that when an MR is under the GRLPS coverage area, its position is updated by a global filter, whereas when the MR is inside the LRLPS area, its position is updated using position increments within a local filter. The navigation algorithm has been tested by simulation and with actual data obtained using a real set of ultrasonic LPSs.