Abstract: This specification describes systems, apparatus and methods for deploying Tsetlin machine models on resource-constrained devices. According to a first aspect of this specification, there is described apparatus comprising: one or more sensors; at least one processor; and at least one memory with storing instructions that, when executed by the at least one processor, cause the apparatus at to at least: collect one or more sets of sensor data using the one or more sensors; classify the one or more sets of sensor data using an encoded Tsetlin machine. The encoded Tsetlin machine comprises a compressed representation of a trained Tsetlin machine. The compressed representation is based on a number of exclude decisions of the trained Tsetlin machine being greater than a number of include decisions of the trained Tsetlin machine.

Abstract: An apparatus, method and computer program is described comprising: obtaining first sensor data from a first earphone of a pair of earphones; obtaining second sensor data from a second earphone of the pair of earphones; operating in a first mode in the event that the pair of earphones is determined to be worn or used by a single user; and operating in a second mode in the event that the pair of earphones is determined to be worn or used by different users.

Abstract: An apparatus comprising: at least one photoplethysmography sensor configured to determine pulse information of a user; at least one audio sensor configured to determine heart sound information of the user; and means for determining, based, at least in part, on the pulse information and the heart sound information, blood pressure information of the user, wherein the at least one photoplethysmography sensor and the at least one audio sensor are comprised in an ear-worn device.

Abstract: An apparatus, method and computer program is described for: receiving, over a period of time, a signal indicative of a pressure measured by a pressure sensor of an earpiece, the earpiece comprising an ear tip configured for insertion into an ear canal of a user, wherein the pressure sensor is arranged to measure a pressure within the ear canal whilst the ear tip is inserted into the ear canal; determining one or more characteristics of the signal; and determining a measure of a quality of a seal between the earpiece and the ear canal based on the one or more characteristics.

Abstract: An apparatus, method and computer program is described comprising: degrading an acquired data signal, using a source coding module, to generate a degraded signal having a fidelity dependent on a first measure of available energy, wherein the acquired data signal is degraded based on a scalar dependent on said first measure of available energy; and generating an output based on the degraded data signal, wherein the output is generated using an inference module that has parameters dependent on a second measure of available energy, wherein the inference module is configured to output degradable inferences dependent on the degraded signal received by the inference module from the source coding module.

Abstract: A method is provided that includes determining a quality of a data portion of an input sensor data stream based, at least in part, on data of a first data type and determining between, at least, generation of two or more streams of a second, different data type including at least one synthesised data stream of the second data type. Determining between generation of two or more streams of a second, different data type is based, at least in part, on the determined quality. The synthesis is based, at least in part, on the data of the first data type. The method further includes causing generation of at least one stream of the second, different data type based, at least in part, on the determination between generation of two or more streams of the second, different data type.

Abstract: This relates to the use of sensor evaluation in a multi-sensor environment. In a first aspect, this specification describes apparatus comprising: at least one processor; and at least one memory including computer program code. The at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: receive sensor data from a plurality of sensors collected during a first time period; process the received sensor data through a plurality of layers of a neural network to generate an output indicative of the sensing quality of each of the plurality of sensors for a task; and cause a subset of the plurality of sensors to collect data during a second time period based on the output indicative of the suitability of each of the plurality of sensors for the task.

Abstract: An apparatus comprising means for: receiving information from at least one inertial measurement unit configured to be worn on a user's head; and causing, at least in part, determining facial expression information in dependence on at least the received information.

Abstract: An apparatus, method and computer program is described comprising: determining an initial performance of a first model, wherein determining the initial performance comprises deploying the first model at a first device; determining one or more operations for modifying the first model based on at least the initial performance of the first model and one or more user requirements; modifying the first model by performing the one or more operations; determining whether a performance of the modified first model satisfies the one or more user requirements, wherein the determining comprises deploying the modified first model at the first device; and in the event that the modified first model does not satisfy the one or more user requirements, further modifying the first model by performing one or more further operations until the performance of the modified first model satisfies the one or more user requirements, wherein the determining further one or more operations based on at least the performance of the modified f

Abstract: A capability for privacy-aware personal data storage is presented. The capability for privacy-aware personal data storage enables secure storage of data within a personal data store. The data stored in the personal data store may be data produced by a set of connected end devices associated with an entity for which the personal data store stores data of the set of connected end devices. The capability for privacy-aware personal data storage may support visualization of and control over privacy level for data of a connected end device(s) that is stored in the personal data store. The visualization of and control over data stored in the personal data store may be supported by a privacy meter, which may be an object or device that may be integrated with or independent of the connected end device(s) for which the visualization of and control over data stored in the personal data store is supported.