Self-learning verification method for data authenticity
AssigneeKoninklijke Philips N.V.
InventorsMUSTAFA GHASSAN RADHA, LUCAS JACOBUS FRANCISCUS GEURTS, MARK ANTHONY HENNESSY, MARK THOMAS JOHNSON
Life of this patent
Estimating the term…
Abstract
A user device that receives plural strings of data corresponding to physiological data, generated from a training model trained in an unsupervised manner using concurrently implemented loss functions, and using a distance metric, relative to a threshold, applied between the plural strings to provide an indication of authenticity.
Claims20
A device, comprising:
- a memory comprising instructions;
- and
- one or more processors configured by the instructions to:
- receive plural strings of data corresponding to plural sets of user data, the plural sets of user data comprising physiological data, each of the plural strings of data generated based on a learning model, the learning model trained in unsupervised manner using concurrently implemented loss functions that generate each of the plural strings of data in a manner that satisfies the loss functions;
- apply a distance metric between the plural strings of data;
- and
- provide an indication of authenticity corresponding to a user based on application of the distance metric relative to a threshold.
A method implemented by one or more computational nodes of a neural network, the method comprising:
- generating plural strings of data corresponding to plural sets of user data, the plural sets of user data comprising physiological data, each of the plural strings of data generated based on a learning model, the learning model trained in unsupervised manner using concurrently implemented loss functions that generate each of the plural strings of data in a manner that satisfies the loss functions;
- applying a distance metric between the plural strings of data;
- and
- providing an indication of authenticity corresponding to a user based on application of the distance metric relative to a threshold.
A non-transitory, computer readable storage medium that, when executed by one or more processors, causes the one or more processors to:
- receive plural strings of data corresponding to plural sets of user data, the plural sets of user data comprising physiological data, each of the plural strings of data generated based on a learning model, the learning model trained in unsupervised manner using concurrently implemented loss functions that generate each of the plural strings of data in a manner that satisfies the loss functions;
- apply a distance metric between the plural strings of data;
- and
- provide an indication of authenticity corresponding to a user based on application of the distance metric relative to a threshold.
Dependencies are inferred from the claim text.