Abstract: A method for generating stimulation parameters, an electrical stimulation control apparatus and an electrical stimulation system are provided. After receiving a brainwave signal, the brainwave signal is decomposed to obtain a first sub-signal and a second sub-signal. Then, the first sub-signal is analyzed to obtain an intrinsic frequency series, and the second sub-signal is converted to a Boolean signal. Subsequently, the intrinsic frequency series and the Boolean signal, which serve as a set of stimulation parameters, are outputted to the stimulator, enabling the stimulator to generate a stimulus signal.

Abstract: The present invention discloses a brain activity analysis method and apparatus, which is based on a nonlinear waveform decomposition technology, wherein the changes of the intrinsic features in brain waves are decomposed and demodulated to extract the modulation signals of the components, including the frequency-modulation signals and the amplitude-modulation signals. The present invention further uses a feature mask to determine whether to proceed further decomposition and demodulation of the extracted modulation signals. If not, the multidimensional changes of the intrinsic features are obtained according to the feature mask. Then, quantitation and identification is performed to obtain the status of brain function. The present invention not only effectively increases the accuracy of the identification but also uses the feature mask to obviously reduce the complexity and the load of computation.

Abstract: A method and a system for processing an electroencephalogram (EEG) signal are provided. The method for processing the EEG signal includes: performing a spike detection on the EEG signal to obtain a spike distribution waveform, performing an instantaneous frequency oscillation energy analysis on the EEG signal to obtain multiple energy distribution waveforms; performing a complexity analysis on the EEG signal to obtain a complexity change waveform, obtaining a determination result of a specified neural waveform based on the spike distribution waveform, the energy distribution waveforms, and the complexity change waveform, and outputting the determination result.

Abstract: A method for generating stimulation parameters, an electrical stimulation control apparatus and an electrical stimulation system are provided. After receiving a brainwave signal, the brainwave signal is decomposed to obtain a first sub-signal and a second sub-signal. Then, the first sub-signal is analyzed to obtain an intrinsic frequency series, and the second sub-signal is converted to a Boolean signal. Subsequently, the intrinsic frequency series and the Boolean signal, which serve as a set of stimulation parameters, are outputted to the stimulator, enabling the stimulator to generate a stimulus signal.

Abstract: A method and a system for processing an electroencephalogram (EEG) signal are provided. The method for processing the EEG signal includes: performing a spike detection on the EEG signal to obtain a spike distribution waveform, performing an instantaneous frequency oscillation energy analysis on the EEG signal to obtain multiple energy distribution waveforms; performing a complexity analysis on the EEG signal to obtain a complexity change waveform, obtaining a determination result of a specified neural waveform based on the spike distribution waveform, the energy distribution waveforms, and the complexity change waveform, and outputting the determination result.

Abstract: An electrical stimulation controlling device and an electrical stimulation system are provided. In which, the electrical stimulation controlling device includes a receiving circuit and a controller coupled to the receiving circuit. The receiving circuit is configured to receive an ictal neural signal which is a signal obtained by a detector when a neural event has been occurring. The controller is further coupled to a stimulator and configured to: determine a time point to start an electrical stimulation according to the ictal neural signal after an onset of the neural event has been determined; and generate and transmit a control signal to the stimulator for providing the electrical stimulation according to the determined time point.

Abstract: Non-limiting examples describe sharing of bundled content through an application/service. A first input may be received, through a user interface of the email service. The first input is associated with a selection of a user interface element for sharing of a bundle of emails that comprises a grouping of at least two separate email threads. A second input is received indicating one or more other users for sharing the bundle of emails. The bundle of emails is shared with the one or more other users. Sharing of the bundle of emails creates a sharing permission that enables multi-directional sharing between the user and the one or more other users for current content of the shared bundle of emails and future content added to the shared bundle of emails. The shared bundle of emails is displayed inline with other emails of an email mailbox of the user through the user interface.

Abstract: Non-limiting examples describe enhanced searching and filtering of message content by an application/service. Processing operations described herein are applicable to any type of message content including but not limited to bundled content of an email service. A search input may be received through a user interface of an email service. The search input may be for searching emails associated with a mailbox the email service. Email results may be retrieved based on the received search input. The retrieved email results may be categorized into one or more categories. A smart filter may be generated for filtering the retrieved email results. An exemplary smart filter may comprise at least one filter field that corresponds to category specific content extracted from emails of a category of the one or more categories. The email results and the smart filter may be displayed through the user interface of the email service.

Abstract: Non-limiting examples describe automated management of rich content previews associated with bundled content of an application/service. As an example, a bundle of content may be a bundle of emails created within an email service. Email content associated with a bundle of emails may be accessed. The email content may be evaluated based on application of machine learning model that: determines an entity type associated with the bundle of emails based on the tag, identifies a state associated with the bundle of emails, and determines relevancy of specific email content in association with a determined entity type and the identified state associated with the bundle of emails. A rich content preview for the bundle of emails may be generated based on an evaluation of the email content.

Abstract: Non-limiting examples describe automated bundling of content on behalf of a user by an application/service. As an example, a bundle of content may be a bundle of emails created on behalf of a user by an email service. Email data associated with a user account of an email service may be accessed. The email data may be evaluated by applying a bundle generation model that that evaluates the emails for bundling associations. An exemplary bundle generation model may evaluate the email data based on: user signal data from actions pertaining to categorization of specific emails, content and metadata corresponding with the email data, and server side metric analysis of activity corresponding with the user account. A bundle of emails may be automatically generated based on an evaluation result from applying the bundle generation model. The bundle of emails may be transmitted for display in a mailbox of the user account.

Abstract: An electrical stimulation controlling device and an electrical stimulation system are provided. In which, the electrical stimulation controlling device includes a receiving circuit and a controller coupled to the receiving circuit. The receiving circuit is configured to receive an ictal neural signal which is a signal obtained by a detector when a neural event has been occurring. The controller is further coupled to a stimulator and configured to: determine a time point to start an electrical stimulation according to the ictal neural signal after an onset of the neural event has been determined; and generate and transmit a control signal to the stimulator for providing the electrical stimulation according to the determined time point.

Abstract: The present invention discloses a brain activity analysis method and apparatus, which is based on a nonlinear waveform decomposition technology, wherein the changes of the intrinsic features in brain waves are decomposed and demodulated to extract the modulation signals of the components, including the frequency-modulation signals and the amplitude-modulation signals. The present invention further uses a feature mask to determine whether to proceed further decomposition and demodulation of the extracted modulation signals. If not, the multidimensional changes of the intrinsic features are obtained according to the feature mask. Then, quantitation and identification is performed to obtain the status of brain function. The present invention not only effectively increases the accuracy of the identification but also uses the feature mask to obviously reduce the complexity and the load of computation.

Abstract: The present invention discloses a brain activity analysis method and apparatus, which is based on a nonlinear waveform decomposition technology, wherein the changes of the intrinsic features in brain waves are decomposed and demodulated to extract the modulation signals of the components, including the frequency-modulation signals and the amplitude-modulation signals. The present invention further uses a feature mask to determine whether to proceed further decomposition and demodulation of the extracted modulation signals. If not, the multidimensional changes of the intrinsic features are obtained according to the feature mask. Then, quantitation and identification is performed to obtain the status of brain function. The present invention not only effectively increases the accuracy of the identification but also uses the feature mask to obviously reduce the complexity and the load of computation.

Abstract: A method for neurological event detection is provided and include: obtaining a neural oscillation signal and extracting a plurality of features from the neural oscillation signal; obtaining a plurality of classification results corresponding to a plurality of times according to the plurality of features by using a classification model constructed based on a plurality of training data, wherein whether a neurological event occurs is known in each training data; and calculating a final determination result corresponding to each of a plurality of evaluation time windows according to a preset time window width and the plurality of classification results and displaying the final determination result. The final determination result indicates whether the neurological event occurs. Each evaluation time window corresponds to a plurality of classification results and one single final determination result.

Abstract: Non-limiting examples describe automated bundling of content on behalf of a user by an application/service. As an example, a bundle of content may be a bundle of emails created on behalf of a user by an email service. Email data associated with a user account of an email service may be accessed. The email data may be evaluated by applying a bundle generation model that that evaluates the emails for bundling associations. An exemplary bundle generation model may evaluate the email data based on: user signal data from actions pertaining to categorization of specific emails, content and metadata corresponding with the email data, and server side metric analysis of activity corresponding with the user account. A bundle of emails may be automatically generated based on an evaluation result from applying the bundle generation model. The bundle of emails may be transmitted for display in a mailbox of the user account.

Abstract: Non-limiting examples describe automated bundling of content on behalf of a user by an application/service. As an example, a bundle of content may be a bundle of emails created on behalf of a user by an email service. Email data associated with a user account of an email service may be accessed. The email data may be evaluated by applying a bundle generation model that that evaluates the emails for bundling associations. An exemplary bundle generation model may evaluate the email data based on: user signal data from actions pertaining to categorization of specific emails, content and metadata corresponding with the email data, and server side metric analysis of activity corresponding with the user account. A bundle of emails may be automatically generated based on an evaluation result from applying the bundle generation model. The bundle of emails may be transmitted for display in a mailbox of the user account.

Abstract: The present invention discloses a brain activity analysis method and apparatus, which is based on a nonlinear waveform decomposition technology, wherein the changes of the intrinsic features in brain waves are decomposed and demodulated to extract the modulation signals of the components, including the frequency-modulation signals and the amplitude-modulation signals. The present invention further uses a feature mask to determine whether to proceed further decomposition and demodulation of the extracted modulation signals. If not, the multidimensional changes of the intrinsic features are obtained according to the feature mask. Then, quantitation and identification is performed to obtain the status of brain function. The present invention not only effectively increases the accuracy of the identification but also uses the feature mask to obviously reduce the complexity and the load of computation.

Abstract: Non-limiting examples describe automated bundling of content on behalf of a user by an application/service. As an example, a bundle of content may be a bundle of emails created on behalf of a user by an email service. Email data associated with a user account of an email service may be accessed. The email data may be evaluated by applying a bundle generation model that that evaluates the emails for bundling associations. An exemplary bundle generation model may evaluate the email data based on: user signal data from actions pertaining to categorization of specific emails, content and metadata corresponding with the email data, and server side metric analysis of activity corresponding with the user account. A bundle of emails may be automatically generated based on an evaluation result from applying the bundle generation model. The bundle of emails may be transmitted for display in a mailbox of the user account.

Abstract: Non-limiting examples describe automated management of rich content previews associated with bundled content of an application/service. As an example, a bundle of content may be a bundle of emails created within an email service. Email content associated with a bundle of emails may be accessed. The email content may be evaluated based on application of machine learning model that: determines an entity type associated with the bundle of emails based on the tag, identifies a state associated with the bundle of emails, and determines relevancy of specific email content in association with a determined entity type and the identified state associated with the bundle of emails. A rich content preview for the bundle of emails may be generated based on an evaluation of the email content.

Abstract: Non-limiting examples describe sharing of bundled content through an application/service. A first input may be received, through a user interface of the email service. The first input is associated with a selection of a user interface element for sharing of a bundle of emails that comprises a grouping of at least two separate email threads. A second input is received indicating one or more other users for sharing the bundle of emails. The bundle of emails is shared with the one or more other users. Sharing of the bundle of emails creates a sharing permission that enables multi-directional sharing between the user and the one or more other users for current content of the shared bundle of emails and future content added to the shared bundle of emails. The shared bundle of emails is displayed inline with other emails of an email mailbox of the user through the user interface.