Monocular 3D head tracking to detect falls of elderly people.

Faced with the growing population of seniors, Western societies need to think about new technologies to ensure the safety of elderly people at home. Computer vision provides a good solution for healthcare systems because it allows a specific analysis of people behavior. Moreover, a system based on video surveillance is particularly well adapted to detect falls.

Sequence design and software environment for real-time navigation of a wireless ferromagnetic device using MRI system and single echo 3D tracking.

Software architecture for the navigation of a ferromagnetic untethered device in a 1D and 2D phantom environment is briefly described. Navigation is achieved using the real-time capabilities of a Siemens 1.5 T Avanto MRI system coupled with a dedicated software environment and a specially developed 3D tracking pulse sequence.

Microdevice's susceptibility difference based MRI positioning system, a preliminary investigation.

A positioning technique for an endovascular microdevice propelled by magnetic force inside a magnetic resonance imaging (MRI) system is being developed. Positioning options are presented and a magnetic positioning technique is described in more details. Since a magnetic positioning system is deeply dependent on the quality of the measurement modality, we describe the main magnetic field measurement techniques that can be used inside an MRI.

Adapting MRI systems to propel and guide microdevices in the human blood circulatory system.

Magnetic resonance imaging (MRI) systems are widely used to gather noninvasively images of the interior of the human body. This paper suggests that an MRI system can be seen beyond being just a tool for imaging purpose but one that can propel and guide special microdevices in the human body to perform specific medical tasks. More specifically, an MRI system can potentially be used to image the region of interest, propel a microdevice through the generation of magnetic gradients, determine the location of the device, compute the corrective actions through feedback control algorithms and adjust the generation of the magnetic gradients accordingly to navigate such a microdevice in a preplanned path.

Input-output HMMs for sequence processing.

We consider problems of sequence processing and propose a solution based on a discrete-state model in order to represent past context. We introduce a recurrent connectionist architecture having a modular structure that associates a subnetwork to each state. The model has a statistical interpretation we call input-output hidden Markov model (IOHMM).

Ultrasonic texture motion analysis: theory and simulation.

A theoretical model was previously developed to evaluate the relationship between the dynamics of ultrasonic speckle and its underlying tissue. The model is divided into an instrumental part represented by the point spread function (in the far field) of the ultrasonic apparatus and a moving tissue component described by a collection of scatterers. By computing the convolution of these terms and then the envelope, one obtains a simulated ultrasonic speckle pattern sequence which shows speckle motions closely linked to the tissue dynamics when small motion amplitudes are involved.

Learning long-term dependencies with gradient descent is difficult.

Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in the input/output sequences span long intervals. We show why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases.

A neural network image reconstruction technique for electrical impedance tomography.

Reconstruction of images in electrical impedance tomography requires the solution of a nonlinear inverse problem on noisy data. This problem is typically ill-conditioned and requires either simplifying assumptions or regularization based on a priori knowledge. The authors present a reconstruction algorithm using neural network techniques which calculates a linear approximation of the inverse problem directly from finite element simulations of the forward problem.