Abstract: A computer-implemented method and device for determining trajectories from a set of trajectories for measurements on a technical system. A predictive model of the technical system includes a measure of uncertainty of the prediction of the predictive model, wherein the measure depends on trajectories from the set, wherein the trajectories from the set for which the measure indicates a greater or equal uncertainty than the measure for others of the trajectories from the set are determined.

Abstract: A monitoring device for monitoring inactive behavior of a monitored person in a monitored zone includes a plurality of monitoring sensors configured to record sensor data. The monitoring sensors are positioned in at least two spatially separated monitored subzones of the monitored zone. The monitoring device further includes an evaluation device including a model module and a test module. The model module produces a first inactivity model in a spatially anonymized manner for a first time period with reference to sensor data in the first time period. The model module produces a second inactivity model for a second time period. At least portions of the second time period are formed later than the first time period. The test module compares the first inactivity model and the second inactivity model and provides a change notification if there is a deviation between the first inactivity model and the second inactivity model.

Abstract: A method of monitoring a position of a moveable entity includes equipping a moveable entity with a position sensor that outputs position signals indicating current geographical positions of the sensor, and using a machine learning system to process the position signals in accordance with a machine learning algorithm to identify reference positions indicated by the position signals corresponding to a first type of activity performed by the entity. Rules are defined based on the identified reference positions. The computer processor then monitors the position signals and apply the rules to the position signals to identify positions that violate the rules.

Abstract: A method for monitoring at least one interior space of a building includes comparing recorded image data, which represent the at least one interior space, with reference data, which represent a reference situation, in order to generate monitoring information dependent on a comparison result. The monitoring information represents a monitoring-relevant situation in the at least one interior space.

Abstract: A monitoring device for monitoring inactive behavior of a monitored person in a monitored zone includes a plurality of monitoring sensors configured to record sensor data. The monitoring sensors are positioned in at least two spatially separated monitored subzones of the monitored zone. The monitoring device further includes an evaluation device including a model module and a test module. The model module produces a first inactivity model in a spatially anonymized manner for a first time period with reference to sensor data in the first time period. The model module produces a second inactivity model for a second time period. At least portions of the second time period are formed later than the first time period. The test module compares the first inactivity model and the second inactivity model and provides a change notification if there is a deviation between the first inactivity model and the second inactivity model.

Abstract: A method for a personal emergency response system includes receiving output signals of a nonintrusive load monitoring (NILM)system coupled to an electrical supply of an person's residence, the output signals indicating switching events of appliances connected to the electrical supply. A computer processor is then used to process the output signals in accordance with a machine learning algorithm to identify appliance activation routines. Rules are defined based on the identified appliance activation routines, and the computer processor is used to monitor the output signals and apply the rules to the output signals to identify appliance switching conditions that violate the rules.

Abstract: A method of monitoring a position of a moveable entity includes equipping a moveable entity with a position sensor that outputs position signals indicating current geographical positions of the sensor, and using a machine learning system to process the position signals in accordance with a machine learning algorithm to identify reference positions indicated by the position signals corresponding to a first type of activity performed by the entity. Rules are defined based on the identified reference positions. The computer processor then monitors the position signals and apply the rules to the position signals to identify positions that violate the rules.

Abstract: A calibration method is provided for a motion sensor, in particular a pedometer, a first acceleration signal being measured as a function of an acceleration parallel to a first direction in a first calibration step, a second acceleration signal being measured as a function of an acceleration parallel to a second direction in a second calibration step, and an acceleration vector being ascertained from the angle between the first and the second acceleration signal in a third calibration step, and a phase angle between the acceleration vector and the first direction being determined in a fourth calibration step for determining a calibration signal.

Abstract: An echo-signal monitoring device having a plurality of transceiver units for transmitting signals and receiving the echoes reflected by an external object and an analyzer unit for estimating the distance from the monitoring device to the external object on the basis of the received echoes is characterized in that the device has an operating mode for calculating the relative position of the transceiver units from one another on the basis of the reflected echoes.

Abstract: In a device for bistatic radar applications, at least two spaced-apart radar sensors having separate carrier-frequency oscillators are provided, which do not require phase synchronization. The pulse modulation is carried out time-synchronously for all transmitter and receiver pairs. The cross-echo signals can be analyzed in an analyzing unit, in which a mixing of the transmitted and received signals takes place.

Abstract: In a device for bistatic radar applications, at least two spaced-apart radar sensors having separate carrier-frequency oscillators are provided, which do not require phase synchronization. The pulse modulation is carried out time-synchronously for all transmitter and receiver pairs. The cross-echo signals can be analyzed in an analyzing unit, in which a mixing of the transmitted and received signals takes place.

Abstract: An echo-signal monitoring device having a plurality of transceiver units for transmitting signals and receiving the echoes reflected by an external object and an analyzer unit for estimating the distance from the monitoring device to the external object on the basis of the received echoes is characterized in that the device has an operating mode for calculating the relative position of the transceiver units from one another on the basis of the reflected echoes.

Abstract: A sensor array with a pulse echo radar system with which a carrier signal of a microwave transmitter oscillator is transmitted in the form of pulses with a specified pulse repetition frequency in a transmission window. This radar signal is reflected from a target object and the position of the target object is calculated in a mixer from the times of transmission of the pulse to the arrival of the reflected radiation. An array of several transmitter and receiver units with switches are constructed in which the stochastic pulse sequences of each transmission window in each receiver branch are known and the transmitter and receiver units are linked to one another so that in each of the receiver branches the stochastic pulse sequences of each transmission window are detected separately and thereby the cross echoes may also be analyzed.

Abstract: The signal echo monitoring device includes a transmitting unit (5) for broadcasting a transmitted signal (s(t)) which is a group of randomly generated pulses, a receiving unit (6) for receiving an echo signal (e(t)), reflected by an object (12), of the transmitted signal and a combined control and evaluation unit (2) including a device (10) for jointly evaluating the transmitted signal (s(t)) and the echo signal (e(t)) with an integrated adaptive filter (14). The adaptive filter (14) automatically calibrates its impulse response b(t) and may be a digital filter.

Abstract: A sensor array with a pulse echo radar system with which a carrier signal of a microwave transmitter oscillator (2) is transmitted in the form of pulses with a specified pulse repetition frequency in a transmission window. This radar signal is reflected from a target object and the position of the target object is calculated in a mixer (7) from the times of transmission of the pulse to the arrival of the reflected radiation. An array of several transmitter and receiver units (11, 20, 30, 40) with switches (R1, R2, R3, R4) can be constructed in which the stochastic pulse sequences of each transmission window in each receiver branch (7, 9, 10) are known and the transmitter and receiver units (11, 20, 30, 40) are linked to one another in such a way that in each of the receiver branches (7, 9, 10) the stochastic pulse sequences of each transmission window are detected separately and thereby the cross echoes can also be analyzed.

Abstract: Artificial Intelligence (AI) techniques are used for processing data having multiple possible values, for example, gray-scale values of pixels of an image. This is useful in scanning of digitally-coded image data to detect anomalies, for example defects in some of a series of manufactured products. The preferred processing apparatus has either one processing channel or multiple parallel processing channels. The apparatus samples or scans incoming signals to produce a matrix of scan values, selects subsets of the scan values to define samples, extracts at least one feature, such as mean image brightness (MM), activity (MA), gradient absolute value (MG) and/or gradient direction (MD) from each sample, uses the at least one feature as an address to retrieve, from a table, a corresponding probability-of-occurrence value, derives, from the probability-of-occurrence values of a plurality of the samples, a decision value, and compares the decision value with a predetermined threshold value.