Alexia Gouin

Health smart home for elders - a tool for automatic recognition of activities of daily living

Elders live preferently in their own home, but with aging comes the loss of autonomy and associated risks. In order to help them live longer in safe conditions, we need a tool to automatically detect their loss of autonomy by assessing the degree of performance of activities of daily living. This article presents an approach enabling the activities recognition of an elder living alone in a home equipped with noninvasive sensors.

Makespan minimisation on parallel batch processing machines with non-identical job sizes and release dates

The problem we study in this paper arises from the washing step of hospital sterilisation services. Washers in the washing step are capable of handling more than one medical device set as long as their capacity is not exceeded. The medical device set sizes and arrival times to the sterilisation service may be different, but they all have the same washing duration. Thus, we model the washing step as a batch scheduling problem where medical device sets are treated as jobs with non-identical sizes and release dates, but equal processing times. The main findings we present in this paper are the following. First, we study two special cases for which polynomial algorithms are presented. We then develop a 2-approximation algorithm for the general problem. Finally, we develop a MILP model and compare it with another MILP model from the literature. Computational results show that our MILP model outperforms the model from the literature.

A generic simulation model to assess the performance of sterilization services in health establishments.

The work presented here is with a view to improving performance of sterilization services in hospitals. We carried out a survey in a large number of health establishments in the Rhône-Alpes region in France. Based on the results of this survey and a detailed study of a specific service, we have built a generic model. The generic nature of the model relies on a common structure with a high level of detail. This model can be used to improve the performance of a specific sterilization service and/or to dimension its resources. It can also serve for quantitative comparison of performance indicators of various sterilization services.

Optimizing the makespan of washing operations of medical devices in hospital sterilization services

In this paper, we deal with the problem of minimizing the makespan of washing operations in hospitals sterilization services. After use in operating blocs, reusable medical devices (RMD) are sent to the sterilization service which is composed of various processes. In the washing step, different sets of RMD, used for different operations, may be washed together without exceeding washer capacity. An RMD set must be washed in one cycle and so, we are not allowed to split RMD sets. In this case, we consider a batch scheduling problem where RMD sets may have different sizes and different release dates for washing. Note that if all release dates are equal, the problem is reduced to a bin packing problem. We provide a mixed integer linear programming model which aims at minimizing the makespan of washing operations. We provide and also experiment some heuristics based on classical bin packing algorithms.

Diagnosis architecture reconfiguration for a networked mobile robot

Wireless networked robots are mobile systems communicating to a control station via a wireless network. These robots move in a distributed infrastructure while receiving orders from control stations to reach their target. A distributed and collaborative diagnosis architecture is a good solution to monitor and diagnose the different components behavior of such distributed system due to the unreliability of wireless networks. Modular Bayesian Network (MBN), as a distributed Bayesian Network, can manage causal uncertain factors (stochastic failures dependencies) and infer information coming from different environments and from devices having memory and calculation limitations. MBN was proposed in our previous work for distributed and collaborative diagnosis. However, the robots can receive orders to switch to autonomous operating mode or to a good performing network (a new control station) to avoid system performance degradation. The robot is no more connected to the station of origin. The diagnosis strategy must consequently be updated. This paper proposes a procedure to reconfigure the diagnosis architecture and the MBN when the mobile robot changes its operating mode i.e, switching from embedded controller to distant controller.

Distributed to embedded Bayesian Network for diagnosis of a networked robot

Mobile networked robots are distributed systems controlled by a distant station i.e, the controller is implemented on a control station. The main mission of the mobile robot is reaching a target position starting from an initial one while receiving the instructions from the control station via a wireless network. The wireless network is characterized by a stochastic behavior and is sensitive to perturbations. The unreliability of wireless networks does not guarantee data transmission between system components (the robot and the station) which can cause system performance degradation. A distributed Bayesian Network (BN) was proposed in previous work to monitor and diagnose the system performance and to model causal uncertainties between failures. The developed BN is a modular Bayesian Network (MBN) which is composed of three Bayesian modules shared between the robot and the control station. In the case of system performance degradation because of a bad network state, the robot switches to embedded controller implemented on-board (autonomous behavior). The distributed diagnosis architecture must be updated and the diagnosis tool becomes embedded on the robot. A procedure of BNs assembly is described in this work in order to implement one monolithic BN on-board. The obtained monolithic BN is the result of combining two Bayesian modules from the modular Bayesian Network: the control and the operative Bayesian modules.