Dynamically adaptive bruxing suppression

Abstract

Apparatus and methods disclosed herein generally relate to a bruxing suppression apparatus configured to suppress bruxing feedback signals generated by false positive detection of bruxing events. In an illustrative example, a bruxing suppression apparatus may detect a false positive condition during a run-time operation of the bruxing suppression apparatus. The bruxing suppression apparatus may, for example, automatically interrupt bruxing-suppressing feedback in response to detecting the false positive. The bruxism prevention system may, for example, detect an elimination of the false positive condition and automatically resume the run-time operation without user intervention. Various embodiments may, for example, advantageously extend battery life and / or reduce habituation to feedback such as by, for example, reducing unnecessary feedback.

Description

DYNAMICALLY ADAPTIVE BRUXING SUPPRESSIONCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application Serial No. 63 / 612,854, titled “DYNAMICALLY ADAPTIVE BRUXING SUPPRESSION,” filed by Michael Duckwitz, et al., on December 20, 2023.

[0002] This application incorporates the entire contents of the foregoing application(s) herein by reference.TECHNICAL FIELD

[0003] Various embodiments pertain to methods and devices designed to effectively mitigate the adverse health effects arising from bruxism.BACKGROUND

[0004] Bruxism, a common dental condition, refers to the involuntary grinding or clenching of teeth, often occurring during sleep but can also manifest during waking hours. This parafunctional habit can lead to various dental issues, including worn tooth surfaces, jaw pain, headaches, and even damage to dental restorations. Bruxism is categorized into two types: awake bruxism, associated with conscious teeth clenching, and sleep bruxism, which happens unconsciously during sleep. The exact cause of bruxism is multifactorial, involving factors such as stress, anxiety, and malocclusion.SUMMARY

[0005] Apparatus and methods disclosed herein generally relate to a bruxing suppression apparatus configured to suppress bruxing feedback signals generated by false positive detection of bruxing events. In an illustrative example, a bruxing suppression apparatus may detect a false positive condition during a run-time operation of the bruxing suppression apparatus. The bruxing suppression apparatus may, for example, automatically interrupt bruxing-suppressing feedback in response to detecting the false positive. The bruxism prevention system may, for example, detect an elimination of the false positive condition and automatically resume the run-time operation without user intervention. Various embodiments may, for example, advantageously extend battery life and / or reduce habituation to feedback such as by, for example, reducing unnecessary feedback.

[0006] Apparatus and associated methods relate to a dynamically adjusted bruxing device. In an illustrative example, an anti-bruxing activation unit (ABAU) includes electrodes and a feedback module. For example, the ABAU may adaptively generate feedback signals to the feedback module based on signals received from the electrodes. The ABAU, for example, may include afalse positive detection engine configured to detect false positive signal patterns received from the electrodes. For example, the false positive detection engine may be configured to detect an electrode that is off position (e.g., lead off). In some implementations, the ABAU may, upon detecting a bruxing event of the user, dynamically increase / decrease an amplitude of a vibration pattern and / or change the vibration pattern activated at a feedback module based on a user’s response (e.g., lack of response, delay in response, change in response). Various embodiments may advantageously mitigate habituation to feedback and / or intervene with a user’s bruxing without waking the user from sleep.

[0007] The details of various embodiments are set forth in the accompanying drawings and the description below. Other features and advantages will be apparent from the description and drawings, and from the claims.BRIEF DESCRIPTION OF THE DRAWINGS|0008| FIG. 1 depicts an example Dynamic and Subtle Anti-Bruxing (DaSAB) Headband employed in an illustrative use-case scenario.

[0009] FIG. 2 is a block diagram depicting an example anti-bruxing activation unit (ABAU).

[0010] FIG. 3 is a flowchart illustrating an example bruxing detection training method.

[0011] FIG. 4 is a flowchart illustrating an example bruxing detection method.

[0012] FIG. 5 is a flowchart illustrating an example subtle brux intervention method.

[0013] FIG. 6 is a flowchart illustrating an example method to address an interruption in operation of a bruxing suppression apparatus.

[0014] FIG. 7 A shows a simplified block diagram of an AI / ML engine that may be included in an example bruxing suppression apparatus.

[0015] FIG. 7B is a flowchart illustrating an example method to generate training data that may be used to train an AI / ML engine of an example bruxing suppression apparatus.

[0016] FIG. 8A, FIG. 8B, FIG. 8C, FIG. 8D and FIG. 8E depict an example embodiment of a Dynamic and Subtle Anti-Bruxing (DaSAB) Headband.

[0017] FIG. 9 shows an example implementation of a bruxing suppression apparatus that includes one or more sensors incorporated into a pillow.

[0018] Like reference symbols in the various drawings indicate like elements. Objects shown in the various figures are not necessarily drawn to scale.DETAILED DESCRIPTION OF ILLUSTRATIVE EMBODIMENTS

[0019] FIG. 1 depicts an example Dynamic and Subtle Anti-Bruxing (DaSAB) Headband employed in an illustrative use-case scenario. In this example, a DaSAB headband 100 is worn byan individual, as illustrated in the form of a user 105. For example, the user 105 may be suffering from bruxing (e.g., grinding his / her teeth while sleeping). For example, the user 105 may, after waking up from his / her sleep, potentially suffer from tooth pain, tooth damage, tooth loss and / or other health problems (e.g., jaw joint pain, muscle tightness and / or weakness, headache, poor sleeping quality) due to bruxing.

[0020] The DaSAB headband 100 may relieve the user’s problems by detecting bruxing during his / her sleep, in some embodiments. For example, the DaSAB headband 100 may include multiple (e.g., 2, 3, 4, 8, 16) measurement electrodes to measure flexing biting muscles when the user 105 is grinding his teeth. For example, the measurement electrodes may receive electromyography (EMG) signals from predetermined muscles. In some implementations, the DaSAB headband 100 may provide a feedback signal to stop the user from grinding his teeth once bruxing is detected. For example, the DaSAB headband 100 may generate a dynamic haptic feedback signal (e.g., low amplitude vibration, low amplitude audio signal) to the user 105. For example, the dynamic haptic feedback signal may be generated adaptively as a function of intensity and / or duration of the detected bruxing.

[0021] As shown in FIG. 1, the DaSAB headband 100 includes an anti-bruxing activation unit (AB AU 110). The AB AU 110 is operably coupled with electrode(s) 115 and a feedback module 120. For example, the DaSAB headband 100 may adaptively generate feedback signals to the feedback module 120 based on signals received from the electrode(s) 115.

[0022] The electrode(s) 115, for example, may include multiple electrodes. For example, when the user 105 dons the DaSAB headband 100, the electrode(s) 115 may be positioned at specific location(s) of a head of the user 105. For example, the electrode(s) 115 may be configured to measure EMG signals from predetermined muscles relevant to a bruxing event.

[0023] As shown, the ABAU 110 includes a training engine 125, a bruxing detecting engine (BDE 130), a false positive detection engine (FPDE 135), and an actuation engine 140. For example, the actuation engine 140 may generate a feedback actuation signal to the feedback module 120. For example, the feedback actuation signal may activate the feedback module 120 to generate a feedback signal having a distinct vibration characteristic. In some implementations, the feedback actuation signal may activate the feedback module 120 to generate an audio signal. In some implementations, the feedback actuation signal may activate the feedback module 120 to generate a visual indication. In some implementations, the feedback actuation signal may activate the feedback module 120 to generate an electrical stimulation. In some implementations, the feedback actuation signal may activate the feedback module 120 to generate a combination of two or morefeedback signals that may include a vibration pattern, an audio, a visual indication, and / or an electrical stimulation.

[0024] For example, the training engine 125 may configure a baseline profile for the user 105 by training. In some implementations, the training engine 125 may be trained for a predetermined time (e.g., 1 minute, 3 minutes, 10 minutes) while the user 105 is in a relaxed state. For example, the training engine 125 may store the baseline response from the electrode(s) 115.

[0025] In some implementations, the training engine 125 may periodically request the user 105 to retrain the DaSAB headband 100. For example, the training engine 125 may generate a timely reminder to the user 105 to retrain the DaSAB headband 100 for three minutes during the day. As shown, the DaSAB headband 100 is operably connected to a smartphone 145. For example, the training engine 125 may generate the reminder at the smartphone 145. In some examples, the training engine 125 may generate the reminder at the DaSAB headband 100 (e.g., as a visual indicia at a status light embedded on a housing of the DaSAB headband 100, by vibrating with an indicative pattern, by generating a predetermined sound). In some examples, the training engine 125 may dynamically adjust the baseline profile based on user response.

[0026] In an illustrative example, the training engine 125 may measure an initial baseline EMG profile from one or more of the electrode(s) 115. For example, the training engine 125 may determine that a baseline EMG profile seems to be increased (e.g., because a muscle was used more intensively during the day) from the initial baseline EMG profile, leading to false positives if a static threshold is used to detect a bruxing event). In some implementations, the training engine 125 may dynamically adjust the baseline EMG profile when the biopotential increases by a certain amount based on real-time measurement signal from the electrode(s) 115.

[0027] In some implementations, the BDE 130 may generate a brux detection signal (BDS) based on measurement signals received from the electrode(s) 1 15 and the baseline response stored by the training engine 125. For example, the BDE 130 may generate the BDS when an amplitude of the measurement signals is larger than the baseline response by a predetermined threshold. For example, the BDE 130 may only generate the BDS when the amplitude of the measurement signals is larger than the baseline response by a predetermined threshold for over a predetermined duration. In some implementations, the BDE 130 may also use a responsive amplitude level for detecting the bruxing event. For example, the BDE 130 may increase the required amplitude level for a bruxing event when the baseline EMG profile is changed by the training engine 125.

[0028] The FPDE 135, for example, may inhibit generation of the feedback signal if movement is detected during sleep. For example, the electrode(s) 115 may include an accelerometer to detect the movement. In some implementations, the FPDE 135 may also be configured not to disable theDaSAB headband 100 when the user 105 is awake(e.g., even when movement is detected). For example, the FPDE 135 may determine that the user is awake based on a preset sleeping (or activation) clock of the user 105. For example, the present sleeping clock may be stored corresponding to a user profile of the user 105.

[0029] For example, the FPDE 135 may determine a sleep / wake state of the user by an orientation of the user’s head based on sensor measurements from the accelerometer (e.g., by detecting the direction of gravity). For example, when the user’s head is upright, the FPDE 135 may determine the user is awake. For example, when the user’s head is sideways, the FPDE 135 may determine that the user is sleeping. In some implementations, the FPDE 135 may allow continuous monitoring of the user when the user is awake with or without activating the feedback module 120. For example, the FPDE 135 may generate false positive signal when there is any non-bruxing movement and the user is sleeping. Various embodiments may advantageously inhibit feedback when there is movement during sleep.

[0030] As an illustrative example without limitation, the user 105 may set the DaSAB headband 100 to be activated between lam and 6am because the user 105 is very likely to be asleep at this time. In this case, the FPDE 135 may disregard all movement and disable the DaSAB headband 100 if the time is outside of the lam to 6am. In some implementations, the FPDE 135 may determine whether the user 105 is awake by detecting whether the user is lying down (e.g., using an accelerometer, a gyroscope, a tilt sensor, a magnetometer, a pressure sensor).

[0031] In some implementations, the FPDE 135 may also include a leads-off detection engine (LODE) (not shown). For example, the LODE may be configured to disable generation of the feedback signal for a short period of time after detection of the user 105 donning or doffing the device. In some implementations, the LODE may also prevent false positives by detecting a badly contacted electrode(s) 115 (e.g., when the electrode loses contact with the skin of the user 105 temporarily). In some implementations, the LODE may be configured by the training engine 125. Accordingly, for example, the FPDE 135 may advantageously filter false measurements from the DaSAB headband 100 not being worn by the user 105 and / or when the DaSAB headband 100 is worn but one or more electrodes loses contact with the skin. In some examples, the actuation engine 140 may generate the feedback actuation signal without using the filtered measurement (e.g., false positive bruxing events) to advantageously enhance an accuracy of the feedback actuation signal.

[0032] In some implementations, the electrode(s) 1 15 may include built-in LODE hardware for removing measurement signals from a fault contact electrode. For example, the electrode(s) 115may include an analog high pass filter and a digital notch filter for filtering 50 Hz and / or 60 Hz noise arising due to a faulty contact (e.g., a loose contact, for example).

[0033] As shown, the AB AU 110 may also include other sensor(s) 150. For example, the sensor(s) 150 may include a temperature sensor. For example, the BDE 130 may use the temperature sensor to measure a temperature of the user’s skin to detect bruxing. In some implementations, the FPDE 135 may also use the temperature sensor to determine whether the user 105 is sleeping. For example, the training engine 125 may use the measurement signals from the sensor(s) 150 as part of the baseline profile of the user 105.

[0034] In some embodiments the feedback module 120 may vary the feedback vibration pattern based on an activation pattern stored in an activation pattern definitions 155 to mitigate habituation (the diminishing of a response to a frequently repeated stimulus). For example, the activation pattern definitions 155 may include various feedback vibration types, including, for example, humming, clicking, and / or buzzing. In some implementations, the activation pattern definitions 155 may also include other feedback vibrations in temporal patterns (e.g., double click, pulsing, ramp up, and ramp down). In some examples, the activation pattern definitions 155 may define amplitude variations (e.g., a medium / strong, smooth / sharp in the amplitude progression from low to high). In some implementations, the actuation engine 140 may step the feedback signal amplitude up a little at a time if the user 105 responds negatively (e.g., without response). For example, the actuation engine 140 may advantageously search and save a responsive amplitude range unique to the user 105. For example, the responsive amplitude range may effectively attenuate the bruxism event without waking the user 105. For example, the DaSAB headband 100 may include a user interface (e.g., on the housing or at the smartphone 145) to allow the user 105 to set or fine-tune an upper limit of the feedback amplitude if the automatic tuning algorithms still wake them.

[0035] In some implementations, the actuation engine 140 may, based on the measurement signals received from the electrode(s) 115 and the sensor(s) 150, vary a feedback signal amplitude automatically. In some implementations, the actuation engine 140 may include fine adjustment in the feedback amplitude. For example, the actuation engine 140 may reduce the amplitude each time the user responds favorably (e.g., stop or reduce bruxing) to the feedback.

[0036] For example, the actuation engine 140 may be configured to retrieve and generate a feedback signal continuously when a bruxing event is detected by the BDE 130. For example, based on a response from the user 105 to the feedback signal, the actuation engine 140 may increase / decrease an amplitude a small amount. When the user does not respond, for example, the actuation engine 140 may increase the amplitude amount. In some implementations, when theamplitude reaches a predetermined threshold (e.g., defined in the activation pattern definitions 155), the actuation engine 140 may retrieve another activation pattern. In various examples, the continuous variation may be advantageously controlled such that the amplitude would not wake the user 105.

[0037] The smartphone 145, for example, may receive historical data from the DaSAB headband 100 to be displayed on a report user interface (RUI 160). In some implementations, the historical data may be filtered with the false positive measurement detected by the FPDE 135. For example, based on the displayed habituation data, the user 105 may interactively use the RUI 160 to select vibration / activation patterns that are more effective. For example, the user 105 may deactivate one or more of the activation patterns because they will wake him up.

[0038] In this example, the smartphone 145 is also connected to a central analysis server 165. For example, the central analysis server 165 may be a cloud storage for saving the historical data. In some embodiments, the central analysis server 165 may include a machine learning model to update the activation pattern definitions 155 based on historic data of one or more users. For example, the machine learning model may receive parameters including, for example, patient data, real response to activation patterns, bruxing patterns. For example, the central analysis server 165 may train the machine learning model to classify various users. For example, based on the classification, the central analysis server 165 may simulate (e.g., generate and test) a recommended type of activation pattern for the user 105. In some implementations, the historical data used may include correlation between bruxing events, pre -bruxing measurements corresponding to the bruxing events, and / or various physiological attributes (e.g., EKG, skin temperature, humidity). As shown, the DaSAB headband 100 is supported in power by a battery 170. In some implementations, the DaSAB headband 100 may draw power from a wall socket. In some embodiments, the smartphone 145 may include a similar machine learning model. For example, the machine learning model may include regression. For example, the machine learning model may include support vector machine. For example, the machine learning model may include artificial neural network.

[0039] FIG. 2 is a block diagram depicting an example anti-bruxing activation unit (ABAU). In this example, the ABAU 110 includes a processor 205. The processor 205 may, for example, include one or more processing units. In some implementations, the processor 205 may include a low-power sensor processor and a high-power processor. For example, the low-power sensor processor may be active in processing signals received from the electrode(s) 115 and the sensor(s) 150. For example, the high-power processing may be in low-power mode (e.g., in a stand-by mode) most of the time until woken up by the low-power processor upon detection of a bruxing event.For example, the dual processing structure may advantageously extend the battery life of the DaSAB headband 100.

[0040] The processor 205 is operably coupled to a communication module 210. The communication module 210 may, for example, include wired communication. The communication module 210 may, for example, include wireless communication. In the depicted example, the communication module 210 is operably coupled to a cloud network 215 (e.g., the Internet), the electrode(s) 115, an actuator(s) 218 (e.g., the feedback module 120), and a user interface 220. For example, the ABAU 110 may access the cloud network 215 to determine a time. For example, the AB AU 110 may access the cloud network 215 to transmit and receive data to and from the smartphone 145. For example, the ABAU 1 10 may receive updates (e.g., activation patterns update) from the central analysis server 165. For example, the actuator(s) 218 may include a vibration actuator to provide vibration feedback. For example, the actuator(s) 218 may include a (e.g., low amplitude) speaker to provide audio feedback. For example, the actuator(s) 218 may include a visual actuator to provide visual feedback. For example, the actuator(s) 218 may include an electric actuator to provide an electrical stimulation.

[0041] The communication module 210, for example, may be used to receive measurement signals from the electrode(s) 115. For example, the ABAU 110 may transmit control signals to the actuator(s) 218 to generate the feedback vibration when a bruxism event is detected.

[0042] The user interface 220, for example, may allow the user 105 to control an operation mode of the ABAU 110. For example, the user 105 may select the ABAU 110 into a training mode for training the baseline profile. For example, the user 105 may select the ABAU 110 into a deactivation mode when he is awake. For example, the user 105 may activate the ABAU 110 using the user interface 220 when he begins to sleep.

[0043] The processor 205 is operably coupled to a memory module 225. The memory module 225 may, for example, include one or more memory modules (e.g., random-access memory (RAM)). The processor 205 includes a storage module 230. The storage module 230 may, for example, include one or more storage modules (e.g., non-volatile memory). In the depicted example, the storage module 230 includes the training engine 125. For example, the training engine 125 may generate a baseline profile based on measurement signals received in the training mode of the ABAU 110.

[0044] In this example, the BDE 130 includes the FPDE 135 and a LODE 235. For example, the BDE 130 may generate a bruxing detection event based on measurement signals received from the electrode(s) 115, filtered by the FPDE 135 and the LODE 235. In some implementations, the FPDE135 may filter false positive events. In some implementations, the LODE 235 may remove measurement signals received from badly contacted electrodes.

[0045] The storage module 230 also includes the actuation engine 140 and a reporting engine 240. For example, the actuation engine 140 may generate control signals to control the actuator(s) 218. For example, the control signals may cause the feedback actuator(s) 218 to vibrate at a predetermined pattern and magnitude specified by the control signals.

[0046] The reporting engine 240, for example, may transmit historical data to a destination device via the cloud network 215. For example, the reporting engine 240 may generate the historical data in JSON format, xml format, and / or other data format.

[0047] The processor 205 is further operably coupled to a data store 245. The data store 245 includes a dynamic bruxing detection pattern (DBDP 250), a Dynamic Anti-Brux Pattern Selection Profile (DABPSP 255), a user profile 260, and a historical brux activity data 265. For example, the historical brux activity data 265 may include time and intensity of each bruxing event for a user within a predetermined time period (e.g., 1 day, 7 days, 1 month, previous 100 hours of active time of the DaSAB headband 100). For example, the reporting engine 240 may use the historical brux activity data 265 to generate the historical data to be transmitted to the smartphone 145.

[0048] The DBDP 250 may, for example, include a baseline profile for detecting a bruxing event. In some implementations, the DBDP 250 may be dynamically updated by the training engine 125 and / or the BDE 130. For example, the training engine 125 may set an initial baseline profile to the DBDP 250 after a training configuration is completed. For example, based on real-time measurements, the BDE 130 may further adjust the DBDP 250 to reflect a current physio-condition of the user 105.

[0049] Using the DBDP 250, the BDE 130 may generate a bruxing event signal to the actuation engine 140. For example, the actuation engine 140 may use the DABPSP 255 to intervene with the bruxism of the user 105. In some implementations, the actuation engine 140 may select a vibration pattern to control the actuator(s) 218 based on the user profile 260. For example, the user profile 260 may specify an effective intervention pattern for reducing bruxing intensity of the user 105. For example, based on the DABPSP 255, the actuation engine 140 may dynamically increase or decrease a magnitude of a vibration in real-time based on user response received from the electrode(s) 115 and / or the sensor(s) 150.

[0050] In an example embodiment, the processor 205 may configure the actuation engine 140 to perform operations that are directed at mitigating habituation by the user 105. Habituation may lead to the user 105 becoming accustomed to a first type of feedback signal (a vibration signal, for example) and ignoring the first type of feedback signal after a period of time, thereby failing tostop bruxing events. The actuation engine 140 may be configured to generate one or more of various types of feedback signals over one or more periods of time in order to mitigate habituation. In an example configuration, the actuation engine 140 may generate a first feedback signal that may be characterized by a first pattern (a first frequency, a first pulse duration, and / or a first repetition rate, for example) and is persisted for a first period of time in order to address a first bruxing event. The actuation engine 140 may then generate a second feedback signal that may be characterized by a second pattern (a second frequency, a second pulse duration, and / or a second repetition rate, for example) and is persisted for either the first period of time or a second period of time in order to address a second bruxing event. The actuation engine 140 may then subsequently generate various other feedback signals. A sequence of feedback signals used for mitigating habituation by the user 105 may include, for example, vibration signals and / or audio signals in the form of various patterns having various characteristics (a long buzz, a short buzz, a series of beeps, a series of clicks, etc.), various amplitudes and / or various waveshapes (ramp, exponential, saw tooth, etc.). In some implementations, the feedback signals may include audio patterns of a buzz, a beep, a click, a bump, fuzz, an alert, a tick, a pulse, hum, and / or a ramp.

[0051] In an example implementation, the AB AU 110 may detect a bruxing event and respond to the detection by applying a feedback signal to the user 105. Detecting a start of the bruxing event may involve evaluating a signal received from the electrode(s) 115 and / or sensor(s) 150 for identifying a clenching or grinding operation of the teeth of the user 105. In an example scenario, the bruxing event may be caused due to habituation and the AB AU 110 may modify trigger signals provided to the user 105 when subsequent bruxing events are detected and / or when a bruxing event does not terminate successfully in response to a first type of trigger signal. The AB AU 110, may, for example, provide trigger signals of varying patterns. In one case, the trigger signals may conform to a first pattern (a buzzing, for example), followed by a second pattern (a series of clicks, for example), followed by a third pattern (variations in amplitudes, for example), followed by a fourth pattern (buzz, click, buzz, click..., for example), and so on. The trigger signals may conform to a preset format such as, for example, a first schedule (“Pattern 2, Pattern 1, Pattern 4, Pattern 4, Pattern 1, Pattern 1 , Pattern 1, Pattern 3”), a second schedule (“Pattern 1, Pattern 2, Pattern 3, Pattern 1, Pattern 2, Pattern 3...”), a third schedule (random patterns, for example), and so on. The trigger signals may conform to a preset time format such as, for example, a trigger signal that is used upon detection of a bruxism event on a first night may conform to a first pattern, a trigger signal that is used upon detection of a bruxism event on a second night may conform to a second pattern, and so on.100521 FIG. 3 is a flowchart illustrating an example bruxing detection training method 300. For example, the training engine 125 may perform the example bruxing detection training method 300 to generate a baseline profile corresponding to a user profile. In this example, the example bruxing detection training method 300 begins in step 305 when a signal is received to start training. For example, the training engine 125 may receive a start training signal from the smartphone 145 through a mobile application.

[0053] In step 310, measurement signals are received from electrodes. For example, the training engine 125 may receive measurement signals from the electrode(s) 115. Next, in a decision point 315, it is determined whether the received signals are valid. For example, the training engine 125 may invoke the FPDE 135 to validate whether the received signals are valid. If the received signals are not valid, the step 310 is repeated.

[0054] If the received signals are valid, in step 320, sensor data is received from other sensor(s). For example, the training engine 125 may receive sensor data from the sensor(s) 150. In a decision point 325, it is determined whether a predetermined training duration is reached. For example, the predetermined training duration may be 3 minutes. If the predetermined training duration is not reached, the step 310 is repeated. If the predetermined training duration is reached, in step 330, a baseline profile is generated to be stored in a database. For example, the training engine 125 may generate a baseline profile to be stored in the data store 245.

[0055] In a decision point 335, it is determined whether a number of training sessions is larger than a predetermined threshold. For example, the training engine 125 may include a training session threshold of 3, meaning that three training sessions are needed to generate a DBDP 250. If the predetermined threshold is reached, the DBDP 250 is updated using the saved baseline profile in step 340, and the example bruxing detection training method 300 ends. For example, the training engine 125 may generate the DBDP 250. If the predetermined threshold is not reached, in step 345, a timely reminder is generated to remind a user to train again tomorrow, and the example bruxing detection training method 300 ends. For example, the training engine 125 may save a reminder at the mobile application of the smartphone 145 to remind the user 105 to train again the next day.

[0056] FIG. 4 is a flowchart illustrating an example bruxing detection method 400. For example, the example bruxing detection method 400 may be performed by the BDE 130 to detect bruxing of the user 105. In this example, the example bruxing detection method 400 begins in step 405 when an activation signal is received. For example, the activation signal may be received when the DaSAB headband 100 is turned on. For example, the activation signal may be received whenan activation button is selected at the smartphone 145. For example, the activation signal may be received when a time is reached at a predetermined timer.

[0057] In a decision point 410, it is determined whether any lead off is detected. For example, the LODE 235 may be used to detect whether any leads of the DaSAB headband 100 is off. If any lead off is detected, in step 415, the off leads are disabled. For example, the LODE 235 may disable the badly contacted leads. If no off lead is detected in the decision point 410 or after the step 415, measurement signals are continuously recorded from electrodes. For example, the BDE 130 may receive measurement signals from the electrode(s) 115.

[0058] In a decision point 425, it is determined whether bruxing detection time is reached. For example, the BDE 130 may include a predetermined time period for the user to fall asleep, so that any movement detected may be classified as bruxing. If the bruxing detection time is not reached, the decision point 410 is repeated. If the bruxing detection time is reached, a dynamic bruxing detection pattern is retrieved from the data store based on a user profile in step 430. For example, the BDE 130 may retrieve the DBDP 250 from the data store 245 based on the user profile 260.

[0059] Next, in a decision point 435, it is determined whether a measurement signal pattern is bruxing. For example, the BDE 130 may determine whether a measurement signal pattern is bruxing based on the DBDP 250. If the measurement signal pattern is not bruxing, the step 420 is repeated. If the measurement signal pattern is bruxing, in a decision point 440, it is determined whether a false positive is detected. For example, the BDE 130 may use the FPDE 1 5 to determine whether it is a false positive by, for example, detecting whether the user is moving and lying down using a gyroscope and / or accelerometer data. If a false positive is detected, the step 420 is repeated. If a false positive is not detected, in step 445, a bruxing event is generated, and the method 400 ends.

[0060] FIG. 5 is a flowchart illustrating an example subtle brux intervention method 500. For example, the actuation engine 140 may perform the example subtle brux intervention method 500 when a bruxing event (e.g., at the step 445) is generated. In this example, the example subtle brux intervention method 500 begins in step 505 when a bruxing event signal is received. For example, the actuation engine 140 may receive the bruxing event signal from the BDE 130. In step 510, a dynamic anti-brux pattern selection profile is retrieved from a data store. For example, the actuation engine 140 may retrieve the DAB PSP 255 from the data store 245. Next, a control signal is generated in step 515 to a feedback module based on the DABPSP. For example, the actuation engine 140 may generate a control signal to the feedback module 120 based on the DABPSP 255.

[0061] In a decision point 520, it is determined whether a positive response from a user is detected. For example, the actuation engine 140 may directly receive measurement signals from theelectrode(s) 115. In some implementations, the actuation engine 140 may determine a level of bruxism by calculating a root mean square of measured EMG signals.

[0062] If a positive response is not detected, in step 525, amplitude of the vibration of the DABPSP is increased. Next, in a decision point 530, it is determined whether the amplitude reaches a predetermined maximum. For example, the DABPSP 255 may include a predetermined maximum amplitude based on safety. For example, the predetermined maximum amplitude may be selected by the user through the connection to the smart phone 145. For example, the DABPSP 255 may include a predetermined maximum amplitude based on efficiency.

[0063] If the maximum amplitude is not reached, the step 515 is repeated. If the maximum amplitude is reached, in step 535, another DABPSP is retrieved from the data store, and the step 515 is repeated. For example, the actuation engine 140 may use another vibration pattern to intervene the user’s bruxing.

[0064] In the decision point 520, if a positive response is detected, an amplitude of vibration of the DABPSP is reduced in step 540. For example, the actuation engine 140 may advantageously adjust the amplitude dynamically to a minimum effective amplitude to avoid waking up the user. In a decision point 545, it is determined whether bruxing stops. For example, the actuation engine 140 may receive whether the bruxing stops from the BDE 130 (e.g., performing the example bruxing detection method 400). If the bruxing does not stop, the decision point 520 is repeated.

[0065] If bruxing stops, in the step 550, the vibration amplitude is saved to the data store. For example, the DABPSP 255 may be updated with the current vibration amplitude so that an initial vibration amplitude will be the same as the current vibration amplitude next time. In step 555, a signal is generated to stop vibration and return to a detection mode, and the method 500 ends. For example, the actuation engine 140 may generate a signal to the feedback module 120 to stop vibrating and return the DaSAB headband 100 is returned to a detection mode (e.g., to perform the example bruxing detection method 400).

[0066] FIG. 6 is a flowchart illustrating an example method 600 to address an interruption in operation of a bruxing suppression apparatus. In an example implementation, the method 600 may be executed by an electronic circuit of a bruxing suppression apparatus such as embodied by the DaSAB headband 100. The electronic system may include a biofeedback module (the biofeedback module 120, for example) one or more electrodes (electrode(s) 115, for example), a data store (the data store 245, for example), and a processor (the processor 205, for example) that is operably coupled to the bio-feedback module, the electrode(s), and the data store. The processor may execute computer-executable instructions stored in the data store for performing the examplemethod 600 that may automatically detect and mitigate bruxing in a user (the user 105, for example).

[0067] In step 605, an activation signal may be received to activate a bruxing suppression apparatus. For example, the activation signal may be received when the DaSAB headband 100 is turned on. For example, the activation signal may be received when an activation button is selected at the smartphone 145. For example, the activation signal may be received when a time is reached at a predetermined timer. In an example implementation, the bruxing suppression apparatus may be turned operational in response to the activation signal and may start operating successfully to detect and mitigate bruxing in the user 105 of the bruxing suppression apparatus.

[0068] In step 610, a bruxing event in the user 105 is detected. Detecting the bruxing event may be based at least in part on evaluating a detection signal received from the electrode(s) 115. As indicated above, the electrode(s) 115 may be positioned at specific location(s) of a head of the user 105. For example, the electrode(s) 115 may be configured to measure EMG signals from predetermined muscles relevant to a bruxing event.

[0069] In step 615 an anti-bruxing actuation pattern model may be retrieved from the data store 245. The anti-bruxing actuation pattern model may, for example, conform to a series of clicks, a series of buzzes, and / or a combination of clicks and buzzes.

[0070] In step 620, the biofeedback module 120 of the bruxing suppression apparatus may be configured to generate a feedback signal based on the anti-bruxing actuation pattern model. In an example implementation, the actuation engine 140 may generate a feedback actuation signal to the feedback module 120. For example, the feedback actuation signal may activate the feedback module 120 to generate a feedback signal having a distinct vibration characteristic. In some implementations, the feedback actuation signal may activate the feedback module 120 to generate an audio signal. In some implementations, the feedback actuation signal may activate the feedback module 120 to generate a visual indication. In some implementations, the feedback actuation signal may activate the feedback module 120 to generate an electrical stimulation signal. In some implementations, the feedback actuation signal may activate the feedback module 120 to generate a combination of two or more feedback signals that may include a vibration pattern, an audio signal, a visual indication, and / or an electrical stimulation signal.

[0071] In step 625, the bruxing suppression apparatus may operate to mitigate the bruxing event based on application of the feedback signal to the user 105. In an example scenario, the user 105 may stop bruxing in response to the feedback signal. In another example scenario, the user 105 may continue bruxing in spite of application of the feedback signal, such as, for example, when the user 105 is habituated to the feedback signal.100721 In step 630, an interruption in operation of the bruxing suppression apparatus may be detected. In one case, the interruption may be attributable to a false positive condition caused by an improper contact between a portion of the bruxing suppression apparatus (such as, for example, the electrode(s) 115) and a body portion of the user. In another case, the interruption may be attributable to a false positive condition caused by an action performed by the individual such as, for example, doffing of the bruxing suppression apparatus by the user 105. In an example scenario, the doffing may be accidental such as, for example, due to the user 105 turning his / her head on a pillow when asleep. In another example scenario, the doffing may be intentional such as, for example, due to the user 105 doffing the DaSAB headband 100 when visiting a toilet in the middle of the night. In another example scenario, the doffing may be intentional such as, for example, due to the user 105 doffing the DaSAB headband 100 when awake. The user 105 may have donned the DaSAB headband 100 to mitigate bruxing during the day (clenching his / her jaw during the day, for example).

[0073] In another case, the interruption may be attributable to a false positive condition caused by an action performed by the user 105 such as, for example, donning of the bruxing suppression apparatus by the user 105. In an example scenario, the user 105 may intentionally disable the DaSAB headband 100 when / after doffing the DaSAB headband 100 to visit a toilet in the middle of the night and may don the DaSAB headband 100 upon returning to bed thereafter.

[0074] In step 625, elimination of the false positive condition may be detected. In an example case, elimination of the false positive condition may be detected when the user 105 dons the DaSAB headband 100 once again after having previously doffed the DaSAB headband 100 such as, for example, in order to visit a toilet in the middle of the night.

[0075] In step 640, the bruxing suppression apparatus may automatically resume operations without intervention by the user 105, such as, for example, by automatically repeating step 610- 640 in a recursive manner.

[0076] In an example embodiment, the electronic circuit described above with reference to bruxing suppression apparatus (DaSAB headband 100, for example) may further include a training engine and the processor may be operably coupled to the training engine to execute operations such as, for example, generating a baseline profile of the user 105 based on a training procedure. The training procedure may include steps such as, for example, conveying to the user 105, a first request to train the bruxing suppression apparatus, followed by training the bruxing suppression apparatus based at least in part on input received from the user in response to the first request.

[0077] The training procedure may further include steps such as, for example, conveying to the user, a second request to retrain the bruxing suppression apparatus, and retraining the bruxingsuppression apparatus based at least in part on input received from the user over at least a first time period. The retraining may include modifying at least one characteristic of the feedback signal such as, for example, changing a pattern of the feedback signal).

[0078] In an example implementation, the processor may dynamically modify the baseline profile of the user 105 based on one or more signals received from the electrode(s) 115 (and / or other electrodes) during retraining. In one case, the signal(s) may be received when the user 105 is in an awake state. The retraining procedure may be periodically repeated, randomly repeated, or performed over a subsequent time period when the user 105 is in an awake state.

[0079] In an example implementation, the processor may dynamically modify the baseline profile of the user 105 based on one or more signals received from the electrode(s) 115 (and / or other electrodes) when the user is in a sleeping state.

[0080] FIG. 7 shows a simplified block diagram of an AI / ML engine 705 that may be included in a bruxing suppression apparatus such as embodied by the DaSAB headband 100. In the illustrated example implementation, the AI / ML engine 705 is configured to perform bruxing event detection. In another example implementation, the AI / ML engine 705 may be configured to perform other operations in addition to, or in lieu of, performing bruxing event detection such as, for example, to perform some or all of the operations illustrated in one or more of the various flowcharts described above.

[0081] In an example implementation, the AI / ML engine 705 may include one or more of a generative Al model, a regenerative Al model, a deep learning model, a linear regression block, and / or one or more decision trees. In an example implementation, the AI / ML engine 705 may perform artificial intelligence (Al) operations that may use various types of algorithms and techniques to replicate human intelligence. In another example implementation, the AI / ML engine 705 may perform machine-language (ML) to perform various operations based on information provided in the form of training data. The training data may be generated by historic operations performed by the multi-dimensional index generation engine 130 and / or other engines. In another example implementation, the AI / ML engine 705 may perform AI / ML operations that include a combination of Al operations and ML operations.

[0082] The illustrated example AI / ML engine 705 may be provided with one or more inputs 710. In an example implementation, the one or more inputs 710 may be provided to the AI / ML engine 705 by one or more elements of the DaSAB headband 100, such as, for example, the electrode(s) 115, sensor(s) 140, and / or an activation element (on / off switch, power button, etc.). In an example implementation, the AI / ML engine 705 may be provided with training patterns 715 that may be operated upon by the AI / ML engine 705 for generating an output 725 in the form of one or morefeedback signal patterns. The training patterns 715 may, for example, be provided in the form of one or more pattern templates. In this case, the AI / ML engine 705 may provide an output 720 in the form of a feedback signal that may be used by the actuation engine 140 for various purposes (bruxing mitigation, training, retraining, etc.). The AI / ML engine 705 may also provide an output in the form of training data 725. In one case, the training data 725 may be stored in the data store 245 for future use. In another case, the training data 725 may be used as training input for other AI / ML engines in other bruxing suppression apparatus

[0083] In an example implementation, the AI / ML engine 705 may be provided with an input(s) 710 that may be operated upon by the AI / ML engine 705 to generate an output 720 in the form of a bruxing event detection. In an example implementation, the AI / ML engine 705 may be provided with an input(s) 710 that may be operated upon by the AI / ML engine 705 to generate an output 720 in the form of a false positive condition detection.

[0084] In an example implementation, the AI / ML engine 705 may replace, supplement, complement, and / or independently perform one or more of the example operational blocks shown in FIG. 1, such as, for example, one or more of the training engine 125, the bruxing detection engine 130, the false positive detection engine 135, or the actuation engine 140.

[0085] FIG. 7B is a flowchart 750 illustrating an example method to generate training data that may be used to train the AI / ML engine 705. In an example implementation, some, or all steps of the flowchart 750 may be performed by a processor such as may be included in the central analysis server 165 and / or in other devices. For example, the processor 205 included in the AB AU 110 shown in FIG. 2, may execute a program of instructions retrieved from the data store 245 to perform the steps of the flowchart 750.

[0086] At step 755, any of various types of historical data may be received. In the illustrated example step, the historical data may be associated with one or more users of one or more bruxing suppression apparatus . The historical data may, for example, include various types of responses by various users to various feedback signals that may be generated upon detection of various bruxing actions.

[0087] At step 760, one or more training patterns may be determined based on evaluating the received historical data. In an example scenario, a training pattern may be determined based on evaluating one or more characteristics of one or more feedback signals produced in response to bruxing actions performed by one or more users over a selected period of time during nights.

[0088] At step 765, one or more training patterns may be validated based on applying the training patterns to test data. In an example case, the test data may be obtained from a data store or may be obtained from one or more sensors attached to a user.|0089| At step 775, a determination may be made whether the training pattem(s) have been validated.

[0090] If not validated, at step 770, additional test data may be obtained, followed by performing step 775. Alternatively, or additionally, one or more training patterns may be modified and step 775 carried out.

[0091] If, at step 775, the training pattern(s) have been validated, at step 780, the training pattem(s) may be stored. In an example implementation, the training pattern(s) may be stored in the data store 245 and used for executing the AI / ML engine 705 shown in FIG. 7B.

[0092] FIG. 8A, FIG. 8B, FIG. 8C, FIG. 8D and FIG. 8E depict an example embodiment of a Dynamic and Subtle Anti-Bruxing (DaSAB) Headband. As shown in FIG. 8A, DaSAB headband 100 may include a printed circuit board (PCB 805) included in a housing 820.

[0093] As shown in FIG. 8B, the housing 820 may include a layer 825 that is configured to provide contact with the skin of the user 105. The layer 825 may be extra thin and may extend out farther from the edges of the other layers. For example, the thin layer 825 may soften the transition at the edge of the housing 820. In some examples, the thin layer 825 may advantageously solve a problem of marks left on a forehead of the user 105 from the housing 805.

[0094] In this example, the housing 820 is coupled to a substrate 835. For example, the substrate 835 may include an elastic material. In some implementations, the substrate 835 may be shaped as a "tongue."For example, the substrate 835 may be coupled to (e.g., attached with) the electrode(s) 115. For example, the electrode(s) 115 may be printed on the substrate 835.

[0095] As shown in FIG. 8C, the substrate 835 includes a layer 845 configured to provide skin contact with the user 105. In some implementations, the layer 845 may cover an inner surface of the substrate 835. For example, the layer 845 may be extra thin. As shown in FIG. 8D, the layer 845 may extend out farther from edges 850 of the substrate 835. For example, the thin layer 845 may soften the transition at the edges of 850 the substrate. In some examples, the thin layer 845 may advantageously solve a problem of marks left on a forehead of the user 105 from the substrate 835.

[0096] As shown in FIG. 8E, in some embodiments, the substrate 835 may include a curved (e.g., a tongue shaped) housing. In this example, the substrate 835 may include a curved edge 850B. For example, the curved edge 850B may be shaped to curve away from the skin of the user 105. The curved edge 850B may, for example, advantageously provide a smooth transition to mitigate marks left on the skin by wearing the DaSAB headband 100. In some implementations, the substrate 835 may include the curved edge 850B, the layer 845, or both.100971 In some implementations, the housing 820 and / or the substrate 835 may be shaped to curve away from the skin at the edges. For example, the curved edges may soften the transition at the edges of the housing 820. In some examples, the curved housing 820 may advantageously solve a problem of marks left on a forehead of the user 105 from the housing 820 . In some implementations, the substrate 835 may be shaped to curve away from the skin at the edges. For example, the curved edges may soften the transition at the edges of the substrate 835. In some examples, the curved edges of the substrate 835 may advantageously solve a problem of marks left on the forehead of the user 105.

[0098] As shown in FIG. 8 A, the pogo pins 815 protrudes through a top surface of the housing 820. For example, the pogo pins 815 may be configured to make electrical contact with (external) conductive traces of the electrode(s) 115 and with the internal PCB 805 (using, e.g., gold pads on the PCB). For example, the DaSAB headband 100 may include a substrate band (not shown) configured to wrap around a user’s head when the user is wearing the DaSAB headband 100. For example, the elastic band may thread up through the housing 820 (e.g., so that it runs along the top of the housing 820). For example, the pogo pins 815 may electrically couple conductive traces disposed or printed on the elastic band through the top surface of the housing 820.

[0099] For example, the pogo pins 815 may conduct an EMG signal via the conductive traces to the PCB 805. The EMG signal may, for example, be conducted from the skin to the electrodes that are not isolated from the skin, via the conductive traces that are isolated from the skin, and through the pogo pins 815 to the PCB 805. For example, the pogo pins 815 may advantageously make connecting and disconnecting the electrode(s) 115 quick and / or convenient. For example, the substrate headband may be made of fabric (e.g., woven, non-woven, knitted). For example, the fabric headband may advantageously be cleaned easily and / or replaced easily. For example, the substrate 835 with attached electrodes 115 may be cleaned easily and / or replaced easily.

[0100] The DaSAB headband 100 can include a removable, molded silicone cover that fits over the housing 820. For example, the molded silicone cover may be integrated with the conductive traces and the electrode(s) 115 as a single unit. The molded silicone cover, the conductive ink traces, and the electrode(s) 115 combination may facilitate easy removal and replacement, for example. In some implementations, the molded silicone cover, the conductive ink traces, and the electrode(s) 115 combination may, for example, be attached to a fabric of, for example, a baseball cap using snapback-like plastic fasteners to complete the headband structure.

[0101] In some implementations, the PCB 805 may include the communication module 210 shown in FIG. 2. In some implementations, the PCB 805 may be implemented without the communication module 210. For example, the PCB 805 may include an analog front-end. For example, usingcircuit filtering circuits, pulse-width-modulation circuits, and vibratory circuits, the PCB 805 may be configured to detect and intervene a user’s bruxing.

[0102] The DaSAB headband 100 may include a higher conductivity material for connecting the electrode(s) 115 to a printed circuit board (PCB). In this example, electrode(s) 115 are connected to the with conductive ink traces to the pogo pins 815. In various implementations, the conductive ink traces may be selected to advantageously increase the lifespan of the electrode(s) 115.

[0103] In an example implementation, the conductive ink traces are screen-printed on a silicone substrate 835, such as, for example, a silicone strip. A non-conductive layer may be provided for preventing the skin from contacting the conductive ink traces, but allows the electrode(s) 115 to contact the skin through cutouts.

[0104] In an example implementation, the DaSAB headband 100 includes three electrodes (electrode(s) 115) as used in a traditional EKG measurement: lead 1 and lead 2 provide the measurement and RLD (“right leg drive”) is the common which may also be biased to negate the half-cell potential and low frequency noise. Lead 1 and lead 2 contact the skin directly over the muscle of interest that provides an indication of a bruxing event. The RLD electrode may be arranged to make contact the skin located away from the muscle of interest, ideally over a bony area.

[0105] In an example implementation, the silicone substrate 835 (with the adhesive layer attached) and the headband together thread through the housing 820 in a manner such that an external top surface of the housing 820 is covered by the headband and substrate.

[0106] In some implementations, the DaSAB headband 100 may include a breakaway headband. For example, the breakaway headband may mitigate a strangulation risk while sleeping. In some implementations, the DaSAB headband 100 may include a breakaway buckle to be worn while sleeping. In some implementations, the DaSAB headband 100 may include a Velcro strip that is releasably coupled to a circuit (e.g., the PCB 805) of the DaSAB headband 100. In some implementations, the DaSAB headband 100 may include a length adjustable strap.

[0107] Although various embodiments have been described with reference to the figures, other embodiments are possible. Such embodiments may be deployed in various types of industrial, scientific, medical, commercial, and / or residential applications.

[0108] For example, in some implementations, the feedback module 120 may be used for other purposes. For example, as the vibration model 120 may be configured as an alarm clock to wake the user at a particular time without waking a bed partner. In some implementations, the feedback module 120 may be used to sooth the user to encourage, for example, the user to fall asleep. In some examples, the vibration model 120 may be used to improve the quality of sleep. In anotherexample, the feedback module 120 may be used to awaken the user when the device (e.g., based on a classification result from the machine learning model, or other predetermined rules) determines that it is beneficial to awaken the user. For example, the vibration model 120 may be activated to awaken the user when imminent tooth damage is determined to be highly probable.

[0109] In an example implementation, the DaSAB headband 100 may be configured to automatically detect an interruption of a sleep state of the user 105 as a result of application of a first trigger signal and may automatically adapt the trigger signal to avoid waking the user 105 the next time the trigger signal is applied to the user 105. Traditional anti-bruxing systems may typically necessitate a user performing a manual action (rotating a knob, pressing one or more buttons, operating a control element, etc.) to adjust a trigger signal. More particularly, in an example implementation, a method to suppress bruxism may include actions such as automatically determining that the user 105 is in a first sleeping state; detecting a first bruxism action performed by the user 105 in the first sleeping state (for example, detecting a muscle movement in the user 105 that indicates bruxing); applying a first trigger signal to a body part of the user 105 (skin on forehead, for example) in response to detecting the first bruxism action. The first trigger signal may be selected to stimulate the user 105 to suppress the first bruxism action. The method may further include detecting a first transitioning of the user 105 from the first sleeping state to a first waking state in response to applying the first trigger signal; selecting or generating a second trigger signal based at least in part on detecting the first transitioning of the user 105 from the first sleeping state to the first waking state, and applying the second trigger signal to the body part of the user 105 in response to detecting a subsequent bruxism action performed by the user 105.

[0110] In an example scenario, the subsequent bruxism action is performed by the user 105 when in a second sleeping state. The second sleeping state may be lighter or heavier than the first sleeping state and the second trigger signal may be unsuitable to prevent disturbing the user 105 when in the second sleeping state (signal may be too strong, for example). In this case, a third trigger signal may be generated based at least in part on detecting the transitioning of the user 105 from the second sleeping state to the second waking state in response to application of the second trigger signal. The DaSAB headband 100 may automatically apply the third trigger signal to subsequently avoid awakening the user 105 when the user 105 is in the second sleeping state. The process of generating the third trigger based on the second sleeping state, may be repeated multiple times to accommodate multiple sleeping states. In an example implementation, a trigger signal may be generated after repeating the process multiple times (over several nights, for example) and determining a statistical parameter (average, mean, maximum, etc.) based on evaluating the characteristics of the multiple trigger signals (for example, frequency, pulse width, repetition rate,amplitude, etc). This example method allows the DaSAB headband 100 to adapt over time to various levels of sleep and / or various levels of bruxism of the user 105.

[0111] The example method described above may further include determining that the user 105 is in a sleeping state based at least in part on evaluating a first signal received from the electrode(s) 115; detecting the first transitioning of the user 105 from the first sleeping state to the first waking state based at least in part on evaluating a second signal received from a motion sensor (sensor 150, for example) that is placed on another body part of the user 105 or on an object located within a threshold distance of the user 105 (inside / on a pillow, on a headpost of a bed, etc.).

[0112] FIG. 9 shows an example implementation of a bruxing suppression apparatus that includes an example set of sensors 905 incorporated into a pillow 910. In the illustrated example, the set of sensors are arranged in the form of an array spread out over an entirety of the pillow 910. In other implementations, the set of sensors may be arranged in any of various other patterns. In an example implementation, at least some of the set of sensors may be located on a top external surface of the pillow 910. In an example implementation, at least some of the set of sensors may be located in an internal surface of the pillow 905 (below pillow cover, pillow case, etc.). In an example implementation, at least some of the set of sensors may be located on the top external surface of the pillow 910 and some others may be located in an internal surface of the pillow 905.

[0113] The sensors may be of various types including, for example, EMG sensors for detecting muscle activations indicating a bruxing event similar to the headband described above, one or more motion detectors, one or more accelerometers, and / or one or more pressure transducers. Various types of information may be obtained by the sensors. At least some of the sensors are arranged to make contact with the skin on the head of the user 105 (cheek, temple, etc.). These sensors are illustrated in a dashed line circle format such as, for example, illustrated by a sensor 905b. Sensors located elsewhere, such as, for example, the sensor 905a, may provide information such as, for example, the nature of sleep of the user 105. For example, no movement may be detected by the sensors when the user 105 is in deep sleep. The sensors may detect characteristic head movements performed by the user 105 during a sleepless state, a lightly sleeping state, a restless state, when lifting the head from the pillow 910, and / or placing the head on the pillow 910.

[0114] In some implementations, the pillow 910 may include a biofeedback module. For example, the pillow 910 may be configured as an entire AB AU in some embodiments.

[0115] In some implementations, the pillow 910 may, for example, communicate (e.g., by a communication module, not shown in this figure) with a controller, biofeedback module, and / or other ABAU components. For example, an ABAU and / or components of an ABAU (e.g., biofeedback module, other sensors) may be disposed on the user (e.g., on the user’s head). In someimplementations, for example, the pillow 910 may, for example, be communicably coupled to a remote controller(s).

[0116] In various embodiments, some of the components described herein may include analog or digital components, which may be discrete, integrated, or a combination of each. Some embodiments may include programmed, programmable devices, or some combination thereof (e.g., PLAs, PLDs, ASICs, microcontroller, microprocessor), and may include one or more data stores (e.g., cell, register, block, page) that provide single or multi-level digital data storage capability, and which may be volatile, non-volatile, or some combination thereof. Some control functions may be implemented in hardware, software, firmware, or a combination of any of them.

[0117] Computer program products may contain a set of instructions that, when executed by a processor device, cause the processor to perform prescribed functions. These functions may be performed in conjunction with controlled devices in operable communication with the processor. Computer program products, which may include software, may be stored in a data store tangibly embedded on a storage medium, such as an electronic, magnetic, or rotating storage device, and may be fixed or removable (e.g., hard disk, floppy disk, thumb drive, CD, DVD).

[0118] Although an example of a system, which may be portable, has been described with reference to the above figures, other implementations may be deployed in other processing applications, such as desktop and networked environments.

[0119] Temporary auxiliary energy inputs may be received, for example, from chargeable or single use batteries, which may enable use in portable or remote applications. Some embodiments may operate with other DC voltage sources, such as (nominal) batteries, for example. Alternating current (AC) inputs, which may be provided, for example from a 50 / 60 Hz power port, or from a portable electric generator, may be received via a rectifier and appropriate scaling. Provision for AC (e.g., sine wave, square wave, triangular wave) inputs may include a line frequency transformer to provide voltage step-up, voltage step-down, and / or isolation.

[0120] Although particular features of an architecture have been described, other features may be incorporated to improve performance. For example, caching (e.g., LI, L2, . . .) techniques may be used. Random access memory may be included, for example, to provide scratch pad memory and or to load executable code or parameter information stored for use during runtime operations. Other hardware and software may be provided to perform operations, such as network or other communications using one or more protocols, wireless (e.g., infrared) communications, stored operational energy and power supplies (e.g., batteries), switching and / or linear power supply circuits, software maintenance (e.g., self-test, upgrades), and the like. One or more communication interfaces may be provided in support of data storage and related operations.10121 1 Some systems may be implemented as a computer system that can be used with various implementations. For example, various implementations may include digital circuitry, analog circuitry, computer hardware, firmware, software, or combinations thereof. Apparatus can be implemented in a computer program product tangibly embodied in an information carrier, e.g., in a machine-readable storage device, for execution by a programmable processor; and methods can be performed by a programmable processor executing a program of instructions to perform functions of various embodiments by operating on input data and generating an output. Various embodiments can be implemented advantageously in one or more computer programs that are executable on a programmable system including at least one programmable processor coupled to receive data and instructions from, and to transmit data and instructions to, a data storage system, at least one input device, and / or at least one output device. A computer program is a set of instructions that can be used, directly or indirectly, in a computer to perform a certain activity or bring about a certain result. A computer program can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0122] Suitable processors for the execution of a program of instructions include, by way of example, both general and special purpose microprocessors, which may include a single processor or one of multiple processors of any kind of computer. Generally, a processor will receive instructions and data from a read-only memory or a random-access memory or both. The essential elements of a computer are a processor for executing instructions and one or more memories for storing instructions and data. Generally, a computer will also include, or be operatively coupled to communicate with, one or more mass storage devices for storing data files; such devices include magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and optical disks. Storage devices suitable for tangibly embodying computer program instructions and data include all forms of non-volatile memory, including, by way of example, semiconductor memory devices, such as EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, ASICs (applicationspecific integrated circuits).

[0123] In some implementations, each system may be programmed with the same or similar information and / or initialized with substantially identical information stored in volatile and / or nonvolatile memory. For example, one data interface may be configured to perform autoconfiguration, auto download, and / or auto update functions when coupled to an appropriate host device, such as a desktop computer or a server.

[0124] In some implementations, one or more user-interface features may be custom configured to perform specific functions. Various embodiments may be implemented in a computer system that includes a graphical user interface and / or an Internet browser. To provide for interaction with a user, some implementations may be implemented on a computer having a display device. The display device may, for example, include an LED (light-emitting diode) display. In some implementations, a display device may, for example, include a CRT (cathode ray tube). In some implementations, a display device may include, for example, an LCD (liquid crystal display). A display device (e.g., monitor) may, for example, be used for displaying information to the user. Some implementations may, for example, include a keyboard and / or pointing device (e.g., mouse, trackpad, trackball, joystick), such as by which the user can provide input to the computer.

[0125] In various implementations, the system may communicate using suitable communication methods, equipment, and techniques. For example, the system may communicate with compatible devices (e.g., devices capable of transferring data to and / or from the system) using point-to-point communication in which a message is transported directly from the source to the receiver over a dedicated physical link (e.g., fiber optic link, point-to-point wiring, daisy-chain). The components of the system may exchange information by any form or medium of analog or digital data communication, including packet-based messages on a communication network. Examples of communication networks include, e.g., a LAN (local area network), a WAN (wide area network), MAN (metropolitan area network), wireless and / or optical networks, the computers and networks forming the Internet, or some combination thereof. Other implementations may transport messages by broadcasting to all or substantially all devices that are coupled together by a communication network, for example, by using omni-directional radio frequency (RF) signals. Still other implementations may transport messages characterized by high directivity, such as RF signals transmitted using directional (i.e., narrow beam) antennas or infrared signals that may optionally be used with focusing optics. Still other implementations are possible using appropriate interfaces and protocols such as, by way of example and not intended to be limiting, USB 2.0, Firewire, ATA / IDE, RS-232, RS-422, RS-485, 802.11 a / b / g, Wi-Fi, Ethernet, IrDA, FDDI (fiber distributed data interface), token-ring networks, multiplexing techniques based on frequency, time, or code division, or some combination thereof. Some implementations may optionally incorporate features such as error checking and correction (ECC) for data integrity, or security measures, such as encryption (e.g., WEP) and password protection.|0126| In various embodiments, the computer system may include Internet of Things (loT) devices. loT devices may include objects embedded with electronics, software, sensors, actuators, and network connectivity which enable these objects to collect and exchange data. loT devices may be in-use with wired or wireless devices by sending data through an interface to another device. loT devices may collect useful data and then autonomously flow the data between other devices.

[0127] Various examples of modules may be implemented using circuitry, including various electronic hardware. By way of example and not limitation, the hardware may include transistors, resistors, capacitors, switches, integrated circuits, other modules, or some combination thereof. In various examples, the modules may include analog logic, digital logic, discrete components, traces and / or memory circuits fabricated on a silicon substrate including various integrated circuits (e.g., FPGAs, ASICs), or some combination thereof. In some embodiments, the module(s) may involve execution of preprogrammed instructions, software executed by a processor, or some combination thereof. For example, various modules may involve both hardware and software.

[0128] In some aspects, the techniques described herein relate to a bruxing suppression apparatus including: an electronic circuit including: a biofeedback module (120); at least one electrode (115); a data store (245) including a program of instructions including a bruxing detection engine (130) and a false positive detection engine (135); and, a processor (205) operably coupled to the data store (245), the biofeedback module (120), and the at least one electrode (115), such that, when the processor (205) executes the program of instructions, the processor (205) performs a run-time operation that automatically detects and mitigates bruxing, the operations including: receive an activation signal to activate bruxing suppression; detect, by the bruxing detection engine (130), a bruxing event in a user (105) in operable contact with the at least one electrode, the detecting based at least in part on evaluating a detection signal received from the at least one electrode; retrieve from the data store, upon detecting the bruxing event, an anti-bruxing actuation pattern model; generate a feedback signal based on the anti-bruxing actuation pattern model, the feedback signal including a first frequency, first pattern, first amplitude, and / or first mode of feedback; operate the biofeedback module (120) to mitigate the bruxing event based on application of the feedback signal to the user (105); detect, by the false positive detection engine (135), a false positive condition; interrupt operation of the biofeedback module (120) in response to detecting the false positive condition; detect an elimination of the false positive condition; and automatically resume operation of the biofeedback module (120) in response to detecting the elimination of the false positive condition.|0129| In some aspects, the techniques described herein relate to a bruxing suppression apparatus, further including: in response to detecting a reduction in efficacy of operation of the biofeedback module in mitigating bruxing in the user (105), update the feedback signal to include at least a second frequency, second pattern, second amplitude, and / or second mode of feedback different than the first frequency, first amplitude, and / or first mode of feedback.

[0130] In some aspects, the techniques described herein relate to a bruxing suppression apparatus, wherein the false positive condition is caused by at least one of an improper contact between the at least one electrode and a body portion of the user (105), a doffing of the bruxing suppression apparatus by the user (105), and / or a donning of the bruxing suppression apparatus by the user (105).

[0131] In some aspects, the techniques described herein relate to a bruxing suppression apparatus, wherein the run-time operation is performed upon the user (105) in an awake state.

[0132] In some aspects, the techniques described herein relate to a bruxing suppression apparatus, wherein the electronic circuit further includes a training engine, wherein the processor (205) is further operably coupled to the training engine, and wherein when the processor (205) executes the program of instructions, the processor (205) performs operations further including: generate a baseline profile of the user (105) based on a training procedure (including for example the baseline EMG signal of that individual’s resting, non-activated muscle), the training procedure including: convey, to the user (105), a first request to train the bruxing detection engine (130); and train the bruxing detection engine (130) based at least in part on input received from the user (105) in response to the first request.

[0133] In some aspects, the techniques described herein relate to a bruxing suppression apparatus, wherein the processor (205) performs operations further including: convey to the user (105), a second request to retrain the bruxing detection engine (130); retrain the bruxing detection engine (130) based at least in part on input received from the user (105) over at least a first time period, the retraining including modifying at least one characteristic of the feedback signal; and modify the baseline profile of the user (105) based at least in part on the retrained bruxing suppression apparatus.

[0134] In some aspects, the techniques described herein relate to a bruxing suppression apparatus, wherein the second request is conveyed to the user (105) upon detecting that the user (105) is in an awake state, and wherein the retraining procedure is one of periodically repeated, randomly repeated, or performed over a subsequent time period.

[0135] In some aspects, the techniques described herein relate to a bruxing suppression apparatus, wherein the processor (205) performs operations further including: dynamically remodify theT1baseline profile of the user (105) based on one or more signals received from the at least one electrode (115).

[0136] In some aspects, the techniques described herein relate to a bruxing suppression apparatus, wherein the one or more signals are received from at least one electrode (115) while the user (105) is in a sleeping state.

[0137] In some aspects, the techniques described herein relate to a computer-implemented method performed by at least one processor (205) of a bruxing suppression apparatus to prevent bruxing, the method including: detect, by a bruxing detection engine (130), a bruxing event in a user (105), the detecting based at least in part on evaluating a detection signal received from at least one electrode (115); retrieve from a data store (245), upon detecting the bruxing event, an anti-bruxing actuation pattern model; configure a biofeedback module (120) to generate a feedback signal based on the anti-bruxing actuation pattern model; operate the biofeedback module (120) to mitigate the bruxing event based on application of the feedback signal to the user (105); detect, by a false positive detection engine (135), a false positive condition; in response to the false positive condition, interrupt operation of the biofeedback module (120); detect an elimination of the false positive condition; and resume operation of the biofeedback module (120) in response to the elimination of the false positive condition.

[0138] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the bruxing event occurs while the user (105) is in an awake state.

[0139] In some aspects, the techniques described herein relate to a computer-implemented method, further including: generating a baseline profile of the user (105) based on a training procedure, the training procedure including: conveying to the user (105), a first request to train the bruxing detection engine (130); and training the bruxing detection engine (130) based at least in part on input received from the user (105) in response to the first request.

[0140] In some aspects, the techniques described herein relate to a computer-implemented method, further including: conveying to the user (105), a second request to retrain the bruxing detection engine (130); retraining the bruxing detection engine (130) based at least in part on input received from the user (105) over at least a first time period, the retraining including modifying at least one characteristic of the feedback signal; and modifying the baseline profile of the user (105) based at least in part on the retrained bruxing suppression apparatus.

[0141] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the second request is conveyed to the user (105) upon detecting that the user (105) is in an awake state, and wherein the retraining procedure is one of periodically repeated,randomly repeated, or performed over a subsequent time period that is different than the first time period.

[0142] In some aspects, the techniques described herein relate to a computer-implemented method, further including: dynamically remodifying the baseline profile of the user (105) based on one or more signals received from the at least one electrode (115).

[0143] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the one or more signals are received from at least one electrode (115) while the user (105) is in a sleeping state.

[0144] In some aspects, the techniques described herein relate to a computer program product (CPP) including a program of instructions tangibly embodied on a non-transitory computer readable medium wherein, when the instructions are executed on a processor (205), the processor (205) causes operations to be performed to prevent bruxing, the operations including: detect, by a bruxing detection engine (130), a bruxing event in a user (105), the detecting based at least in part on evaluating a detection signal received from at least one electrode (115); retrieve from a data store (245), upon detecting the bruxing event, an anti-bruxing actuation pattern model; configure a biofeedback module (120) to generate a feedback signal based on the anti-bruxing actuation pattern model; operate the biofeedback module (120) to mitigate the bruxing event based on application of the feedback signal to the user (105); detect, by a false positive detection engine (135) a false positive condition; interrupt the biofeedback module (120) in response to detecting the false positive condition; detect an elimination of the false positive condition; and resume operation of the biofeedback module (120) in response to the detecting the elimination of the false positive condition.

[0145] In some aspects, the techniques described herein relate to a CPP, wherein the bruxing event occurs while the user (105) in an awake state.

[0146] In some aspects, the techniques described herein relate to a CPP, wherein the operations further include: generating a baseline profile of the user (105) based on a training procedure, the training procedure including: conveying to the user (105), a first request to train the bruxing detection engine (130); and training the bruxing suppression apparatus based at least in part on input received from the user (105) in response to the first request.

[0147] In some aspects, the techniques described herein relate to a CPP wherein the operations further include: conveying to the user (105), a second request to retrain the bruxing detection engine (130); retraining the bruxing detection engine (130) based at least in part on input received from the user (105) over at least a first time period, the retraining including modifying at least onecharacteristic of the feedback signal; and modifying the baseline profile of the user (105) based at least in part on the retrained bruxing detection engine (130).

[0148] In some aspects, the techniques described herein relate to a CPP, wherein the second request is conveyed to the user (105) upon detecting that the user (105) is in an awake state, and wherein the retraining procedure is one of periodically repeated, randomly repeated, or performed over a subsequent time period that is different than the first time period.

[0149] In some aspects, the techniques described herein relate to an apparatus to suppress bruxing, including: at least one electrode (115); means for generating and applying biofeedback to a user (105) in response to a feedback signal; a processor (205) operably coupled to the means for generating and applying biofeedback, and further operably coupled to a data store (245) including a bruxing detection engine (130) and a false positive detection engine (135), such that, when the processor (205) executes the program of instructions, the processor (205) performs operations that automatically detects and mitigates bruxing, the operations including: detect, by the bruxing detection engine (130), a bruxing event in the user (105) in operable contact with the at least one electrode, the detecting based at least in part on evaluating a detection signal received from the at least one electrode; upon detecting the bruxing event, generate a feedback signal based on an anti- bruxing actuation pattern model selected based on the bruxing event; operate the means for generating and applying biofeedback such that the feedback signal is applied to the user (105); in response to detecting, by the false positive detection engine (135), a false positive condition, interrupt operation of the biofeedback module (120); automatically resume operation of the biofeedback module (120) in response to detecting an elimination of the false positive condition.

[0150] A number of implementations have been described. Nevertheless, it will be understood that various modifications may be made. For example, advantageous results may be achieved if the steps of the disclosed techniques were performed in a different sequence, or if components of the disclosed systems were combined in a different manner, or if the components were supplemented with other components.

Claims

CLAIMSWhat is claimed is:

1. A bruxing suppression apparatus comprising: an electronic circuit comprising: a biofeedback module (120); at least one electrode (115); a data store (245) comprising a program of instructions comprising a bruxing detection engine (130) and a false positive detection engine (135); and, a processor (205) operably coupled to the data store (245), the biofeedback module (120), and the at least one electrode (115), such that, when the processor (205) executes the program of instructions, the processor (205) performs a run-time operation that automatically detects and mitigates bruxing, the operations comprising: detect, by the bruxing detection engine (130), a bruxing event in a user (105) in operable contact with the at least one electrode, the detecting based at least in part on evaluating a detection signal received from the at least one electrode, wherein, upon the bruxing event detected, the false positive detection engine is configured to perform false positive filtering operations upon a false positive is detected, wherein the false positive filtering operations comprise: interrupt operation of the biofeedback module (120) in response to detecting the false positive condition; and in response to a detection of an elimination of the false positive condition, automatically resume operation of the biofeedback module (120) ; retrieve from the data store, upon detecting the bruxing event and without the false positive, an anti-bruxing actuation pattern model; after retrieving the anti-bruxing actuation pattern model, generate a feedback signal based on the anti-bruxing actuation pattern model, the feedback signal comprising a first frequency, first pattern, first amplitude, and / or first mode of feedback; and, operate the biofeedback module (120) to mitigate the bruxing event based on application of the feedback signal to the user (105).

2. The bruxing suppression apparatus of claim 1, further comprising: in response to detecting a lack of efficacy of operation of the biofeedback module in mitigating bruxing in the user (105), update the feedback signal to comprise at least a second frequency, second pattern, second amplitude, and / or second mode of feedback different than the first frequency, second pattern, first amplitude, and / or first mode of feedback.

3. The bruxing suppression apparatus of claim 1, wherein the false positive condition is caused by at least one of an improper contact between the at least one electrode and a body portion of the user (105), a doffing of the bruxing suppression apparatus by the user (105), and / or a donning of the bruxing suppression apparatus by the user (105)4. The bruxing suppression apparatus of claim 1, wherein the false positive condition comprises a user movement while the user (105) is in an awake state.

5. The bruxing suppression apparatus of claim 1, wherein the electronic circuit further includes a training engine, wherein the processor (205) is further operably coupled to the training engine, and wherein when the processor (205) executes the program of instructions, the processor (205) performs operations further comprising: generate a baseline profile of the user (105) based on a training procedure, the training procedure including: convey, to the user (105), a first request to train the bruxing detection engine (130); and train the bruxing detection engine (130) based at least in part on input received from the user (105) in response to the first request.

6. The bruxing suppression apparatus of claim 5, wherein the processor (205) performs operations further comprising: convey to the user (105), a second request to retrain the bruxing detection engine (130); retrain the bruxing detection engine (130) based at least in part on input received from the user (105) over at least a first time period, the retraining comprising modifying at least one characteristic of the feedback signal; and modify the baseline profile of the user (105) based at least in part on the retrained bruxing suppression apparatus.

7. The bruxing suppression apparatus of claim 6, wherein the second request is conveyed to the user (105) upon detecting that the user (105) is in an awake state, and wherein the retraining procedure is one of periodically repeated, randomly repeated, or performed over a subsequenttime period.

8. The bruxing suppression apparatus of claim 6, wherein the processor (205) performs operations further comprising: dynamically remodify the baseline profile of the user (105) based on one or more signals received from the at least one electrode (115).

9. The bruxing suppression apparatus of claim 2, wherein the first and second patterns comprise audio patterns of a buzz, a beep, a click, and a ramp.

10. A computer-implemented method performed by at least one processor (205) of a bruxing suppression apparatus to prevent bruxing, the method comprising: detect, by a bruxing detection engine (130), a bruxing event in a user (105), the detecting based at least in part on evaluating a detection signal received from at least one electrode (115), wherein, upon the bruxing event detected, the false positive detection engine is configured to perform false positive filtering operations upon a false positive is detected, wherein the false positive filtering operations comprise: interrupt operation of the biofeedback module (120) in response to detecting the false positive condition; and, in response to a detection of an elimination of the false positive condition, automatically resume operation of the biofeedback module (120); retrieve from a data store (245), upon detecting the bruxing event and without the false positive, an anti-bruxing actuation pattern model; configure a biofeedback module (120) to generate a feedback signal based on the anti- bruxing actuation pattern model; operate the biofeedback module (120) to mitigate the bruxing event based on application of the feedback signal to the user (105).

11. The computer-implemented method of claim 10, wherein the false positive condition comprises a user movement while the user (105) is in an awake state.

12. The computer-implemented method of claim 10, further comprising: generating a baseline profile of the user (105) based on a training procedure, the training procedure comprising: conveying to the user (105), a first request to train the bruxing detection engine (130); and training the bruxing detection engine (130) based at least in part on input received from the user (105) in response to the first request.

13. The computer-implemented method of claim 12, further comprising: conveying to the user (105), a second request to retrain the bruxing detection engine (130); retraining the bruxing detection engine (130) based at least in part on input received from the user (105) over at least a first time period, the retraining comprising modifying at least one characteristic of the feedback signal; and modifying the baseline profile of the user (105) based at least in part on the retrained bruxing suppression apparatus.

14. The computer-implemented method of claim 13, wherein the second request is conveyed to the user (105) upon detecting that the user (105) is in an awake state, and wherein the retraining procedure is one of periodically repeated, randomly repeated, or performed over a subsequent time period that is different than the first time period.

15. The computer-implemented method of claim 13, further comprising: dynamically remodifying the baseline profile of the user (105) based on one or more signals received from the at least one electrode (115).

16. The computer-implemented method of claim 15, wherein the feedback signal comprising a first frequency, first pattern, first amplitude, and / or first mode of feedback .

17. A computer program product (CPP) comprising a program of instructions tangibly embodied on a non-transitory computer readable medium wherein, when the instructions are executed on a processor (205), the processor (205) causes operations to be performed to prevent bruxing, the operations comprising: detect, by a bruxing detection engine (130), a bruxing event in a user (105), the detecting based at least in part on evaluating a detection signal received from at least one electrode (115), wherein, upon the bruxing event detected, the false positive detection engine is configured to perform false positive filtering operations upon a false positive is detected, wherein the false positive filtering operations comprise: interrupt operation of the biofeedback module (120) in response to detecting the false positive condition; and in response to a detection of an elimination of the false positive condition, automatically resume operation of the biofeedback module (120); retrieve from a data store (245), upon detecting the bruxing event, an anti-bruxing actuation pattern model; configure a biofeedback module (120) to generate a feedback signal based on the anti- bruxing actuation pattern model; operate the biofeedback module (120) to mitigate the bruxing event based on application of the feedback signal to the user (105)18. The CPP of claim 17, wherein the false positive comprises a user movement while user (105) in an awake state.

19. The CPP of claim 17, wherein the operations further comprise: generating a baseline profile of the user (105) based on a training procedure, the training procedure comprising: conveying to the user (105), a first request to train the bruxing detection engine (130); and training the bruxing suppression apparatus based at least in part on input received from the user (105) in response to the first request.

20. The CPP of claim 19 wherein the operations further comprise: conveying to the user (105), a second request to retrain the bruxing detection engine (130);retraining the bruxing detection engine ( 130) based at least in part on input received from the user (105) over at least a first time period, the retraining comprising modifying at least one characteristic of the feedback signal; and modifying the baseline profile of the user (105) based at least in part on the retrained bruxing detection engine (130).

21. The CPP of claim 20, wherein the second request is conveyed to the user (105) upon detecting that the user (105) is in an awake state, and wherein the retraining procedure is one of periodically repeated, randomly repeated, or performed over a subsequent time period that is different than the first time period.

22. An apparatus to suppress bruxing, comprising: at least one electrode (115); means for generating and applying biofeedback to a user (105) in response to a feedback signal; a processor (205) operably coupled to the means for generating and applying biofeedback, and further operably coupled to a data store (245) comprising a bruxing detection engine (1 0) and a false positive detection engine (135), such that, when the processor (205) executes the program of instructions, the processor (205) performs operations that automatically detects and mitigates bruxing, the operations comprising: detect, by the bruxing detection engine (130), a bruxing event in the user (105) in operable contact with the at least one electrode, the detecting based at least in part on evaluating a detection signal received from the at least one electrode, wherein, upon the bruxing event detected, the false positive detection engine is configured to perform false positive filtering operations upon a false positive is detected, wherein the false positive filtering operations comprise: interrupt operation of the biofeedback module (120) in response to detecting the false positive condition; and, in response to a detection of an elimination of the false positive condition, automatically resume operation of the biofeedback module (120); upon detecting the bruxing event and without the false positive, generate a feedback signal based on an anti-bruxing actuation pattern model selected based on the bruxing event; operate the means for generating and applying biofeedback such that the feedback signal is applied to the user (105).

Images