Abstract: The present invention relates to a system (100) for determining the location of a number of animals in a group of animals, comprising a first number of first mobile devices (10A-10C) forming anchor devices, each configured to be attached to an animal of a first subgroup of the group of animals, each first mobile device (10A-10C) comprising a satellite positioning unit (11) for detecting a precise location of the first mobile device (10A-10C), and a first radio frequency (RF) unit (12) for transmitting a low power RF signal, a second number of second mobile devices (20A-20J) forming roaming devices, each configured to be attached an animal of a second subgroup of the group of animals, each second mobile device (20A-20J) comprising a second radio frequency (RF) unit (21) for receiving one or more RF signals transmitted by the first number of first mobile devices (10A-10C), and a second controller (22) configured to determine a location or relative location of the second mobile device (20A-20J) based on the one

Abstract: A method for determining a temperature of a component of an electric machine includes providing a plurality of trained neural networks, providing a current measurement of a plurality of operational parameters of the electric machine, and processing the operational parameters using the neural networks. The method further includes integrating output parameters issued by the neural networks over a time period, and issuing the integrated parameters as a temperature of the component.

Abstract: A method for determining a temperature of a component of an electric machine includes providing a plurality of trained neural networks, providing a current measurement of a plurality of operational parameters of the electric machine, and processing the operational parameters using the neural networks. The method further includes integrating output parameters issued by the neural networks over a time period, and issuing the integrated parameters as a temperature of the component.

Abstract: The invention relates to a method for determining a pathology in a subject, said method comprising: a) correlating N-N intervals with rate dependent fluctuations of electrocardiographic parameters derived from an electrocardiogram (ECG) of said subject or other recordings reflecting cardiac activity of said subject to derive electrocardiographic parameters correlation values, wherein said pathology is determined based on said correlation values.

Abstract: The invention relates to a method for determining a pathology in a subject, said method comprising: a) correlating N-N intervals with rate dependent fluctuations of electrocardiographic parameters derived from an electrocardiogram (ECG) of said subject or other recordings reflecting cardiac activity of said subject to derive electrocardiographic parameters correlation values, wherein said pathology is determined based on said correlation values.

Abstract: A method and a system for detecting cardiac arrhythmias that includes detecting RR intervals of the patient wherein each RR interval is an interval between two heart beats, and simulating standard probability density histograms of ?RRs by means of a suitable probability distribution calculated through at least one mathematical formulae, wherein ?RR is a difference between two successive RR intervals. Test probability density histograms of ?RRs of the patient are constructed from the detected RR intervals. Finally, the standard and test histograms are compared to detect whether the patient suffers from cardiac arrhythmia. As non limiting examples, the standard probability density histograms of ?RRs are modeled by a mathematical equation selected from the group consisting of: the Lorentzian distribution, the Gaussian distribution, the Student's t-distribution, and a probability distribution including a linear combination of the Lorentzian and Gaussian distribution.

Abstract: There are many different serious cardiac arrhythmias. The present invention uses measurements of RR intervals (interbeat intervals) to detect, in particular but not exclusively, atrial fibrillation of a patient. Atrial fibrilation is a serious ailment in which the heartbeat is generally rapid and irregular. Probability density histograms of ?RRs (difference between two successive RR intervals) collected during atrial fibrillation of a plurality of subjects are used as a template for the detection of atrial fibrillation. In one implementation, there are 16 standard probability density ?RRs histograms every 50 ms of mean RR interval of a certain number of beats, where the mean RR interval ranges from 350 ms to 1149 ms. Similarity between the standard probability density histograms and a test density probability histogram of ?RRs of a patient is estimated by the Kolmogorov-Smirnov test.

Abstract: There are many different serious cardiac arrhythmias. The present invention uses measurements of RR intervals (interbeat intervals) to detect, in particular but not exclusively, atrial fibrillation of a patient. Atrial fibrilation is a serious ailment in which the heartbeat is generally rapid and irregular. Probability density histograms of ?RRs (difference between two successive RR intervals) collected during atrial fibrillation of a plurality of subjects are used as a template for the detection of atrial fibrillation. In one implementation, there are 16 standard probability density ?RRs histograms every 50 ms of mean RR interval of a certain number of beats, where the mean RR interval ranges from 350 ms to 1149 ms. Similarity between the standard probability density histograms and a test density probability histogram of ?RRs of a patient is estimated by the Kolmogorov-Smirnov test.

Abstract: A method and a system for detecting cardiac arrhythmias that includes detecting RR intervals of the patient wherein each RR interval is an interval between two heart beats, and simulating standard probability density histograms of ?RRs by means of a suitable probability distribution calculated through at least one mathematical formulae, wherein ?RR is a difference between two successive RR intervals. Test probability density histograms of ?RRs of the patient are constructed from the detected RR intervals. Finally, the standard and test histograms are compared to detect whether the patient suffers from cardiac arrhythmia. As non limiting examples, the standard probability density histograms of ?RRs are modeled by a mathematical equation selected from the group consisting of: the Lorentzian distribution, the Gaussian distribution, the Student's t-distribution, and a probability distribution including a linear combination of the Lorentzian and Gaussian distribution.