Abstract: Disclosed are a computing apparatus, a computer-readable medium and a method that enable a user to use subjective inputs to alter settings of a wearable automatic drug delivery system. A user input device is presented on a graphical user interface that enables input of a subjective insulin need parameter. In response to receiving the input, the processor may modify a subjective coefficient value. A specific factor useable by an automatic insulin delivery algorithm is set based on the subjective coefficient value. Physiological condition data related to the user and the set specific factor may be used to determine a dosage of insulin to be delivered to the user based on the collected physiological condition data of the user. The processor may cause the determined dosage of insulin to be delivered to the user based on an output of the automatic insulin delivery algorithm.

Abstract: A wearable drug delivery device, techniques, and computer-readable media that provide an application that implements a diabetes treatment plan for a user are described. The drug delivery device may include a controller operable to direct operation of the wearable drug delivery device. The controller may provide a selectable activity mode of operation for the user. Operation of the drug delivery device in the activity mode of operation may reduce a likelihood of hypoglycemia during times of increased insulin sensitivity for the user and may reduce a likelihood of hyperglycemia during times of increased insulin requirements for the user. The activity mode of operation may be manually activated by the user or may be activated automatically by the controller. The controller may automatically activate the activity mode of operation based on a detected activity level of the user and/or a detected location of the user.

Abstract: Exemplary embodiments may provide a user interface and logic for assisting a user in calculating a proper medicament bolus dosage. The user interface may be simple and easy to understand. The user interface may clearly specify needed inputs, such as a carbohydrates amount for a meal that is about to be ingested and the current glucose level reading for the user. Entered inputs may be displayed on the user interface. The user interface may depict key calculated values resulting from calculations that involve the inputs, including the total bolus dosage calculation. The user interface also may depict the values that contribute to the total bolus dosage calculation. Some of the input values, such as carbohydrates amount, may be prepopulated by the management device or medicament delivery device. The user interface may permit overriding of prepopulated input values.

Abstract: Disclosed are an audio processing method performed by an electronic device, a non-transitory computer-readable storage medium, and a computer program product. The method includes: sampling multiple fragments of audio data of a target object to obtain reference audio data of the target object; performing audio encoding on the reference audio data of the target object to obtain a reference embedding vector of the reference audio data; performing tone-based attention processing on the reference embedding vector of the reference audio data to obtain a tone embedding vector of the target object, wherein the tone embedding vector is independent from content of the audio data; and generating audio data of a target text that conforms to a tone of the target object according to the tone embedding vector of the target object.

Abstract: Disclosed herein are systems and methods for providing safeguards, in an automatic drug delivery system, to prevent or compensate for insufficient delivery of bolus doses of a liquid drug. The safeguards include, for example, features built into the medication delivery algorithm to allow the medication delivery algorithm to ensure that proper bolus doses are delivered, either manually by the user or automatically by the drug delivery system. In addition, various methods are described for providing the medication delivery algorithm with a means for determining when a meal has been ingested and, in some embodiments, for providing an automatic bolus dose of the liquid drug in response to the determination.

Abstract: Disclosed are techniques to establish a modified pump rate that mitigates the effects of a pump occlusion and enables a recommended dosage of insulin to be output by a pump mechanism over the course of a control cycle. In an example, the pump rate may be reduced by adding a calculated time interval between application of actuation commands to extend the amount of time over which insulin may be output by the pump mechanism.

Abstract: Disclosed are a system, methods and computer-readable medium products that provide safety constraints for an insulin-delivery management program. Various examples provide safety constraints for a control algorithm-based drug delivery system that provides automatic delivery of a drug based on sensor input. Glucose measurement values may be received at regular time intervals from a sensor. A processor may predict future glucose values based on prior glucose measurement values. The safety constraints assist in safe operation of the drug delivery system during various operational scenarios. In some examples, predicted future glucose values may be used to implement safety constraints that mitigate under-delivery or over-delivery of the drug while not overly burdening the user of the drug delivery system and without sacrificing performance of the drug delivery system. Other safety constraints are also disclosed.

Abstract: The present invention discloses a waveform file processing method, storage medium, and device, wherein the method comprises a storage step, and such storage step comprises the following sub-steps: obtain a waveform file that comprises at least one waveform signal; assign a basic index value based on the waveform signal, and adopt the variable-length encoding method to, in a memory, encode the said waveform file as a resolvable serialized structure; when the memory consumed by the serialized structure reaches the threshold, trigger the compression and persistence for the current serialized structure, and obtain the waveform processing file. The present invention uses a unique organization mode to locally or remotely generate a waveform file of a specific format so that the efficiency of subsequent storage, reading, and debugging based on the waveform database file of the said format is significantly improved.

Abstract: Disclosed herein is a method for execution by a drug delivery device for determining an optimal dose of a liquid drug for current cycle of a medication delivery algorithm, the method utilizing a stepwise evaluation of a model and a cost function across a coarse search space consisting of coarse discrete quantities of the drug and a refined search space consisting of refined discrete quantities of the drug.

Abstract: A wearable drug delivery device, techniques, and computer-readable media that provide an application that implements a diabetes treatment plan for a user are described. The drug delivery device may include a controller operable to direct operation of the wearable drug delivery device. The controller may provide a selectable activity mode of operation for the user. Operation of the drug delivery device in the activity mode of operation may reduce a likelihood of hypoglycemia during times of increased insulin sensitivity for the user and may reduce a likelihood of hyperglycemia during times of increased insulin requirements for the user. The activity mode of operation may be manually activated by the user or may be activated automatically by the controller. The controller may automatically activate the activity mode of operation based on a detected activity level of the user and/or a detected location of the user.

Abstract: Disclosed are techniques and devices that are operable to receive one or a number of generalized parameters of an automated insulin delivery algorithm. An input of at least one generalized parameter corresponding to a user may be used to set one or more of the number of specific parameters of the automated insulin delivery algorithm based on the inputted at least one generalized parameter. Physiological condition data related to the user may be collected. The automated insulin delivery algorithm may determine a dosage of insulin to be delivered based on the collected physiological condition. Signals may be output to cause a liquid drug to be delivered to the user based on an output of the automated insulin delivery algorithm related to the determined dosage of insulin.

Abstract: Disclosed are techniques to establish initial settings for an automatic insulin delivery device. An adjusted total daily insulin (TDI) factor usable to calculate a TDI dosage may be determined. The adjusted TDI factor may be a TDI per unit of a physical characteristic of the user (e.g., weight) times a reduction factor. The adjusted TDI factor may be compared to a maximum algorithm delivery threshold. Based on the comparison result, the application or algorithm may set a TDI dosage and output a control signal. Blood glucose measurement values may be collected from a sensor over a period of time. A level of glycated hemoglobin of the blood may be determined based on the obtained blood glucose measurement values. In response to the level of glycated hemoglobin, the set TDI dosage may be modified. A subsequent control signal including the modified TDI dosage may be output to actuate delivery of insulin.

Abstract: A speech synthesis method includes: converting a text input sequence into a text feature representation sequence; inputting the text feature representation sequence into an encoder including N encoding layers; the N encoding layers including an encoding layer Ei and an encoding layer Ei+1; the encoding layer Ei+1 including a first multi-head self-attention network; acquiring a first attention matrix and a historical text encoded sequence outputted by the encoding layer Ei, and generating a second attention matrix of the encoding layer Ei+1 according to residual connection between the first attention matrix and the first multi-head self-attention network and the historical text encoded sequence; and generating a target text encoded sequence of the encoding layer Ei+1 according to the second attention matrix and the historical text encoded sequence, and generating synthesized speech data matched with the text input sequence based on the target text encoded sequence.

Abstract: The exemplary embodiments may account for a change in potency of a medicament and adjust the dosage of medicament delivered to a user via a medicament delivery device to compensate for the change in potency. The medicament delivery device may determine the amount of change in the potency in the medicament and may make the adjustment in dosage of the medicament delivered to the user automatically without user input. The net result in that the dosage of medicament delivered to the user is better matched to the user's true need for the medicament.

Abstract: The insulin to carbohydrate ratio (ICR) and the correction factor for a user of a medicament delivery device may be automatically adjusted. The automatic adjustments may tailor the values to the user's actual insulin needs. Various factors may be examined to determine how to adjust the ICR and the correction factor. The identified factors are weighed with the processor to decide whether to increase or decrease the insulin to carbohydrate ratio or the correction factor. The insulin to carbohydrate ratio or the correction factor for the user are adjusted based on the weights of the identified factors. In addition or in the alternative, automatic adjustments of user-requested insulin boluses may be made to requested dosages and timing of deliveries of the insulin boluses. In some instances, the exemplary embodiments may deliver a percentage of the insulin bolus dosage initially and deliver the remaining percentage after a delay to reduce the risk of hypoglycemia for the user.

Abstract: Disclosed are processes and techniques for a drug delivery system to maintain optimal drug delivery for a patient according to a treatment plan. The disclosed techniques enable a drug delivery system to delivery adjusted drug dosages and/or drug delivery cost function aggressiveness factors modified based on clusters or patterns of patient drug dosages and/or response event probabilities. For example, a controller for operating a drug delivery device may operate to determine a plurality of dosage clusters for a patient based on drug dosage patient information, determine an adjustment profile for each of the dosage clusters, determine a current cluster for a dosage cycle, determine an adjusted dosage for the dosage cycle by applying the adjustment profile to a default dosage, and provide a signal to the drug delivery device to deliver the adjusted dosage to the patient for the dosage cycle. Other embodiments are described.

Abstract: Disclosed are a system, methods and computer-readable medium products that provide safety constraints for an insulin-delivery management program. Various examples provide safety constraints for a control algorithm-based drug delivery system that provides automatic delivery of a drug based on sensor input. Glucose measurement values may be received at regular time intervals from a sensor. A processor may predict future glucose values based on prior glucose measurement values. The safety constraints assist in safe operation of the drug delivery system during various operational scenarios. In some examples, predicted future glucose values may be used to implement safety constraints that mitigate under-delivery or over-delivery of the drug while not overly burdening the user of the drug delivery system and without sacrificing performance of the drug delivery system. Other safety constraints are also disclosed.

Abstract: Provided are techniques, devices and systems that include monitoring a trend of blood glucose measurement values over a series of measurement cycles. A processor may identify a potential excursion outside a range of a target blood glucose measurement value setting of a user based on the monitored trend. In response to the identified potential excursion, an alert may be generated to the user to consume rescue carbohydrates. In addition, the disclosed techniques may include a processor that assesses the factors related to a potential impending hypoglycemic event for a user. Based on a result of the assessment of the factors, the processor may determine whether the user is approaching the potential impending hypoglycemic event for the user. In response to a determination that the user is approaching the potential impending hypoglycemic event for the user, a number of rescue carbohydrates to suggest for consumption by the user may be determined.

Abstract: Exemplary embodiments described herein relate to a closed loop artificial pancreas system. The artificial pancreas system seeks to automatically and continuously control the blood glucose level of a user by emulating the endocrine functionality of a healthy pancreas. The artificial pancreas system uses a closed loop control system with a cost function. The penalty function helps to bound the infusion rate of insulin to attempt to avoid hypoglycemia and hyperglycemia. However, unlike conventional systems that use a generic or baseline parameter for a user's insulin needs in a cost function, the exemplary embodiments may use a customized parameter in the cost function that reflects the individualized insulin needs of the user. The use of the customized parameter causes the cost function to result in insulin dosages over time better suited to the individualized insulin needs of the user. This helps to better avoid hypoglycemia and hyperglycemia.

Abstract: The switchover between an expiring on-body medicament delivery device and a replacement on-body medicament is made to eliminate or significantly decrease the time where an on-body medicament delivery device is operational to deliver medicament to a user. The replacement on-body medicament device is attached to the user and prepped for operation while the expiring on-body medicament delivery device is still operational. The switchover between on-body sensors also may be improved. Methods for calibrating a replacement on-body sensor while the expiring on-body sensor is still operative are provided. The calibrating may be performed quickly so that there is no gap in operation between expiration of the expiring on-body sensor and full operation of the replacement on-body sensor.