Abstract: The invention relates to a method for training a model for predicting occurrence of an epileptic seizure, the method comprising performing a supervised training over a training dataset of a nonlinear binary classification model configured to receive as input the evaluation, by a patient, of the intensity of each prodromal symptom among a predefined set of prodromal symptoms, and to output a classification of said patient belonging either to a pre-ictal or inter-ictal state, and the training dataset comprises data inputs obtained from a plurality of epileptic patients, each data input comprising an evaluation, by a patient, of the intensity of each of the predefined set of prodromal symptoms, each data input being further associated to an indication of said patient belonging to a pre-ictal or inter-ictal state at the time of the evaluation. The invention also relates to a prediction model obtained accordingly, and a computing device for implementing said prediction model.

Abstract: The invention relates to a method for detecting a physiological state of a patient deviating from a reference physiological state, in which, after having determined, in each of Q frequency bands, R reference matrices PRq,r with qe[1 . . . Q] and r?[1 . . . R] which correspond to the reference physiological state, the following steps are repeated in a loop: carrying out measurements, in M time segments, of an electroencephalographic signal; filtering and centering the measurements in Q frequency bands to obtain and determine M×Q scaled matrices of spatial covariance; for each time segment m, calculating a deviation from the reference physiological state, and comparing each of the deviations from the reference physiological state to a predefined threshold. The invention also relates to a monitoring device applying said method.

Abstract: The invention relates to a method for detecting a physiological state of a patient deviating from a reference physiological state, in which, after having determined, in each of Q frequency bands, R reference matrices PRq,r with qe[1 . . . Q] and r?[1 . . . R] which correspond to the reference physiological state, the following steps are repeated in a loop: carrying out measurements, in M time segments, of an electroencephalographic signal; filtering and centering the measurements in Q frequency bands to obtain and determine M×Q scaled matrices of spatial covariance; for each time segment m, calculating a deviation from the reference physiological state, and comparing each of the deviations from the reference physiological state to a predefined threshold. The invention also relates to a monitoring device applying said method.

Abstract: A method for implementing a customizable interactive menu system with user interaction data analysis capability by executing computer-executable instructions stored on a non-transitory computer-readable medium is a digital replacement for paper restaurant menus with a customizable menu layout. The menu layout mimics traditional paper menus, displaying a plurality of menu pages on a personal computing device, including a menu start page, at least one menu items page, at least one advertisement page, and a menu end page. Users may select items on a menu items page or an advertisement page, and all user interactions are recorded and later analyzed with data mining and pattern recognition algorithms to produce sorted interaction data and layout suggestions, which the restaurant owner or manager may use to customize and optimize the menu layout.