Abstract: A method for determining a driving intention of a user in a vehicle using electroencephalography (EEG) signals, comprising: acquiring (100) a plurality of EEG signals on a user in the vehicle, determining (101, . . . , 104) a plurality of features of the EEG signals, for each feature of the EEG signals, performing (111, . . . , 114?) a respective preliminary soft classification process, so as to obtain a plurality of preliminary soft predictions of driving intention each based on a feature of the EEG signals, performing (120) a soft classification process based on the plurality of preliminary soft predictions so as to obtain the driving intention of the user.

Abstract: A system for brain-based digital menu selection includes an acquisition device to obtain one or more electrical signals corresponding to an operator's brain response, a stimulation generation device to generate a first stimulus with one or more target options based on the operator triggering the system, a first database including a first classification model, and processor. The processor receives a first response from the acquisition device corresponding to an operator's brain response to the first stimulus with the one or more target options, determines a probability of intended target, when the probability of intended target option is higher than a predefined confidence threshold value, selecting the intended target option and presenting a second stimulus, or executing a final action, according to the selected target option, and storing the first response and the selected target option in the first database with a classification identifier identifying the operator.

Abstract: A method for determining the intention of a user of a vehicle to brake or accelerate, comprising: acquiring (100) a plurality of EEG signals on the user, applying (101) a predetermined spatial filter on the plurality of EEG signals so as to obtain a target EEG component, detecting (102) a spectral pattern in the EEG component corresponding to an intention to brake or detecting a phase pattern in the EEG component corresponding to an intention to accelerate.

Abstract: A system for brain-based digital menu selection includes an acquisition device to obtain one or more electrical signals corresponding to an operator's brain response, a stimulation generation device to generate a first stimulus with one or more target options based on the operator triggering the system, a first database including a first classification model, and processor. The processor receives a first response from the acquisition device corresponding to an operator's brain response to the first stimulus with the one or more target options, determines a probability of intended target, when the probability of intended target option is higher than a predefined confidence threshold value, selecting the intended target option and presenting a second stimulus, or executing a final action, according to the selected target option, and storing the first response and the selected target option in the first database with a classification identifier identifying the operator.

Abstract: A computer-based method for simulating a human-like decision in an environmental context, comprising: capturing environmental data with at least one sensor, realising a computer based method for realising a bi-directional compression of high dimensional data by compressing the data into a lower-dimensional map, if environmental data are captured during a learning phase of a computer-based model, evaluate the map of compressed data by determining the quality of the map by how well it separates data with different properties, the captured data corresponding to known pre-recorded data that have been pre-evaluated, if environmental data are captured after the learning phase, add new point to the compressed data and generate a signal indicating which human-like decision to use to correspond to the state of the operator.

Abstract: This invention relates to an artificial memory system and a method of continuous learning for predicting and anticipating human operator's action as response to ego-intention as well as environmental influences during machine operation. More specifically the invention relates to an architecture with artificial memory for interacting with dynamic behaviors of a tool and an operator, wherein the architecture is a first neural network having structures and mechanisms for abstraction, generalization and learning, the network implementation comprising an artificial hierarchical memory system.

Abstract: A method for determining a driving intention of a user in a vehicle using electroencephalography (EEG) signals, comprising: acquiring (100) a plurality of EEG signals on a user in the vehicle, determining (101, . . . , 104) a plurality of features of the EEG signals, for each feature of the EEG signals, performing (111, . . . , 114?) a respective preliminary soft classification process, so as to obtain a plurality of preliminary soft predictions of driving intention each based on a feature of the EEG signals, performing (120) a soft classification process based on the plurality of preliminary soft predictions so as to obtain the driving intention of the user.

Abstract: A method for determining the intention of a user of a vehicle to brake or accelerate, comprising: acquiring (100) a plurality of EEG signals on the user, applying (101) a predetermined spatial filter on the plurality of EEG signals so as to obtain a target EEG component, detecting (102) a spectral pattern in the EEG component corresponding to an intention to brake or detecting a phase pattern in the EEG component corresponding to an intention to accelerate.

Abstract: Method for the video inspection of a pantograph (100) along an overhead contact line, including the steps of: detecting passage of the pantograph (100) in a plurality of monitoring stations (2); in each monitoring station (2), in response to the detection of the passage of the pantograph (100), illuminating a first overhead zone in which a portion of the pantograph (100) passes; in each monitoring station (2), during the step of illuminating the first overhead zone, acquiring images of the first overhead zone by way of at least one pair of stereo video cameras (5a, 5b); calculating the disparity between the images acquired; reconstructing a three-dimensional model of the portion of the pantograph (100).

Abstract: A computer-based method for simulating a human-like decision in an environmental context, comprising: capturing environmental data with at least one sensor, realising a computer based method for realising a bi-directional compression of high dimensional data by compressing the data into a lower-dimensional map, if environmental data are captured during a learning phase of a computer-based model, evaluate the map of compressed data by determining the quality of the map by how well it separates data with different properties, the captured data corresponding to known pre-recorded data that have been pre-evaluated, if environmental data are captured after the learning phase, add new point to the compressed data and generate a signal indicating which human-like decision to use to correspond to the state of the operator.

Abstract: A measurement system (1) of the relative position between two structural parts (2a, 2b) of a building, that have separated for example following the formation of a crack, comprising a cylindrical permanent magnet (3) adapted to generate a magnetic field (B) and a sensor (5), the sensor (5) being fixed and the magnet (3) being moveable according to a direction perpendicular to its axis of symmetry (h) so as to vary the direction of the lines of force of the magnetic field B which cross the sensor 5.