This paper compares two statistical models of location within a smart flat during the day. The location is then identified with a task executed normally or repeated pathologically, e.g., in case of Alzheimer disease (AD), whereas a task persistence parameter assesses tendency to perseverate. Compared with a Pólya's urns derived approach, the Markovian one is more effective and offers up to 98 percent of good prediction using only the last known location but distinguishing days of week. To extend these results to a multisensor context, some difficulties must be overcome. An external knowledge is made from a set of observable random variables provided by body sensors and organized either in a Bayesian network or in a reference knowledge base system (KBS) containing the person's actimetric profile. When data missed or errors occurred, an estimate of the joint probabilities of these random variables and hence the probability of all events appearing in the network or the KBS was developed and corrects the bias of the Lancaster and Zentgraf classical approach which in certain circumstances provides negative estimates. Finally, we introduce a correction corresponding to a possible loss of the person's synchronization with the nycthemeral (day versus night) zeitgebers (synchronizers) to avoid false alarms.

Free of most social constraints, elderly people tend to perform activities of daily living following the same sequence. This paper proposes a method for medical telesurveillance to detect and quantify a nycthemeral shift in this daily routine. While this common phenomenon is mostly mild, in acute cases, however, it may reveal a pathological behavior requiring a rapid medical examination. This method allows to compare two sequences of activities using the Hamming distance and to interpret the result according to the Gumbel distribution. It may be used to compare either consecutive sequences thereby taking into account evolution in the habits or a sequence to the person's individual activity profile to detect dementia's onset. In this early stage, only elementary activities were considered. That is the reason why location data were used to monitor the person's nycthemeral rhythm of activity. IR sensors placed in her own flat allowed us to follow-up the inhabitant's successive activities. Improvements of this method have already been planned. They include the use of a multi-sensors network to monitor both actimetric (location, movement, posture) and physiological nycthemeral rhythms (ECG, respiratory frequency) and to detect the use of particular items (fridge, chairs, bed). This more sophisticated sensors network will allow us to monitor more complex tasks execution and then to detect pathological behaviors such as perseveration in a task or wandering. On the other hand, multiplying sensors will require more storage capacities and the use of time-consuming data fusion tools. Therefore, a classification phase will be necessary to reduce as possible the number of relevant sensors.