Monitoring system for a feeding bottle

Abstract

A monitoring system for a feeding bottle, in particular for feeding a baby with milk, is provided. During feeding, the motion of the feeding bottle is sensed and from the motion characteristics a sucking performance is determined, in particular it is identified whether the feeding is based on latching or on sucking.

Description

Technical Field

[0001] This invention relates to feeding bottles, and more particularly to a system for monitoring an infant's drinking performance when drinking from a feeding bottle. Background Technology

[0002] When bottle-feeding an infant, it's desirable to know how well the baby is drinking. Monitoring drinking performance and providing feedback to parents is known. A known example is a sleeve for the feeding bottle that includes a load element for measuring the weight of milk contained in the bottle before and after feeding, thus calculating the amount of milk consumed by the infant. The sleeve also includes an accelerometer to give feedback to parents about the correct bottle angle, and for monitoring the child's drinking behavior by observing bottle movement (e.g., to identify drinking bursts and pauses). The system also allows data to be sent to an accompanying application for analysis and visualization.

[0003] This sucking ability changes over time. In particular, two different modes of sucking action occur during infant development. These two different modes are called "suckling" and "sucking".

[0004] Sucking is the primary mode of development, gradually progressing during the second and third months of pregnancy. It involves forward and backward movements of the tongue, with the backward movements being more pronounced. Up and down movements of the palate are also present. The tongue does not protrude beyond the lips. Liquid is drawn from the breast or bottle through rhythmic tongue movements combined with significant opening and closing of the palate. The seal of the lips around the nipple or pacifier may be loose. Breastfeeding is highly automatic and reflexive. It activates a large number of muscles and is therefore important for the infant's facial development.

[0005] By 4 months of age, the reflexive sucking gradually disappears, and drinking becomes more voluntary. The sucking reflex can last until 6 months of age, after which a more mature sucking pattern emerges.

[0006] During sucking, the main body of the tongue rises and falls with the strong activity of its internal muscles, resulting in minor up-and-down movements of the palate. A more secure seal is also maintained by the lips. The strength of the lip closure is a major factor in the tongue's pattern moving from inward to outward and upward to downward.

[0007] Therefore, the differences between sucking and licking involve, for example, the direction of tongue movement (in-out during sucking and up-down during licking), the range of tongue movement, the difference in jaw movement, and the intensity of lip closure.

[0008] The goal is to monitor an infant's drinking characteristics or performance, particularly assessing the maturity of their sucking ability, rather than simply evaluating the total amount or flow rate during drinking. Summary of the Invention

[0009] This invention is defined by the claims.

[0010] According to an example of one aspect of the present invention, a monitoring system for a feeding bottle is provided, comprising:

[0011] Motion sensors are used to sense the movement of the feeding bottle during feeding; and

[0012] A processor adapted to identify sucking performance from the motion sensor signals, wherein the sucking performance identifies whether the feeding is based on eating or sucking; and

[0013] Output interface, used to provide suction performance information.

[0014] Therefore, this invention provides a system for determining sucking performance during feeding. Monitoring the presence (or absence) of sucking and nibbling patterns provides relevant information for parents and professionals. In particular, it enables parents to follow the transition from nibbling to sucking and detect potential problems at an early stage that require special attention, such as those related to nipple and sippy cup use.

[0015] If the transition from sucking to chewing is not handled properly, problems may arise related to feeding (managing thicker liquids and soft foods) and speech. Therefore, it is also very helpful for parents to receive objective data about their baby's oral development, as it is difficult for parents to visually distinguish between sucking and chewing.

[0016] Sucking performance information can identify the progression stages between eating and sucking. In the simplest implementation, there is a simple binary distinction between eating and sucking. In a more refined implementation, the progression stages can be determined. For example, simulated values ​​can be provided, such as those in the range of 0 to 1, where one extreme value represents eating and the other extreme value represents sucking.

[0017] Motion sensors, such as triaxial motion sensors, allow for the consideration of all movements of the bottle.

[0018] Motion sensors include, for example, triaxial accelerometers and / or triaxial gyroscopes. Linear and rotational motion may be of interest, and a variety of sensor types can be used to capture all relevant motion information.

[0019] The output interface may include, for example, a wireless transmitter for sending suction performance information to a remote device for presentation to the user. The remote device may be, for example, a mobile phone or tablet computer with a suitable app pre-loaded on it.

[0020] The processor may be adapted to:

[0021] Convert the time-domain motion sensor signal to the frequency domain;

[0022] Perform spectral density analysis;

[0023] Determine the signal power within the frequency range corresponding to the sucking frequency; and

[0024] Analyze signal power to identify sucking performance.

[0025] This is one possible processing method using frequency domain analysis.

[0026] In another example, the processor is adapted to:

[0027] Detection of peak values ​​in time-domain motion sensor signals;

[0028] Derive the characteristics of the detected peaks; and

[0029] Analyze features to identify sucking performance.

[0030] This is another possible processing method using time-domain analysis.

[0031] The monitoring system can be configured to be mounted on a sleeve around the feeding bottle. The user can then simply insert the bottle into the sleeve to monitor feeding performance during feeding.

[0032] The present invention also provides a feeding bottle system, comprising:

[0033] Feeding bottles; and

[0034] The monitoring system defined above is used to monitor sucking performance during feeding.

[0035] The present invention also provides a method for monitoring sucking performance during bottle feeding, comprising:

[0036] The movement of the feeding bottle during feeding is sensed to generate a motion sensing signal;

[0037] Sucking performance is identified from the motion sensing signal, wherein the sucking performance identifies whether the feeding is based on eating or sucking; and

[0038] Output suction performance information.

[0039] Sucking performance, for example, represents the progression between sucking and eating. Motion sensing preferably includes triaxial motion sensing.

[0040] In one example, the method includes:

[0041] Convert the time-domain motion sensor signal to the frequency domain;

[0042] Perform spectral density analysis;

[0043] Determine the signal power within the frequency range corresponding to the pump frequency; and

[0044] Analyze signal power to identify sucking performance.

[0045] In another example, the method includes:

[0046] Detect the peak value of the time-domain motion sensor signal;

[0047] Derive the characteristics of the detected peaks; and

[0048] Analyze features to identify sucking performance.

[0049] The present invention also provides a computer program including computer program code components, wherein when the program is run on a computer, the computer program code components are adapted to implement the above-described method.

[0050] These and other aspects of the invention will become apparent from the embodiments described below. Attached Figure Description

[0051] To better understand the invention and to more clearly illustrate how to implement it, reference will now be made to the accompanying drawings by way of example only, wherein:

[0052] Figure 1 A feeding bottle is shown, which is installed in a sleeve that serves as a monitoring system;

[0053] Figure 2 A set of possible signals from a combination of a three-axis accelerometer and a three-axis gyroscope is shown;

[0054] Figure 3 A first example of a processing algorithm executed by a processor is shown;

[0055] Figure 4 A second example of a processing algorithm executed by a processor is shown;

[0056] Figure 5 The data shows that as babies grow from 2 months to 8 months, during the 6-month period, the percentage of babies with the highest blood sugar levels from... Figure 2 The signals from the six sensors were used as a moving average of the spectral density during bottle feeding; and

[0057] Figure 6 A method for monitoring sucking performance during feeding from a feeding bottle is shown. Detailed Implementation

[0058] The invention will be described with reference to the accompanying drawings.

[0059] It should be understood that while the detailed description and specific examples indicate exemplary embodiments of the apparatus, system, and method, they are for illustrative purposes only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the apparatus, system, and method of the present invention will become more readily understood from the following description, the appended claims, and the accompanying drawings. It should be understood that the drawings are merely schematic and not drawn to scale. It should also be understood that the same reference numerals are used in all the drawings to denote the same or similar parts.

[0060] This invention provides a monitoring system for feeding bottles, particularly for feeding bottles used to feed infants. During feeding, the system senses the movement of the feeding bottle and determines the sucking performance based on the movement characteristics, specifically identifying whether the feeding is based on nibbling or sucking.

[0061] Figure 1 A feeding bottle 10 is shown mounted in a sleeve 12, which serves as a monitoring system. The sleeve 12 surrounds the feeding bottle 10.

[0062] In this example, the monitoring unit 16 is disposed in the base of the sleeve 12 and includes a motion sensor 18 and an output interface 20. The monitoring unit 16 can be integrated into or onto the sleeve from any location.

[0063] The base of the sleeve may include, for example, a battery, and optionally, a device for providing visual feedback to the user via an LED. The output interface 20 may include such an LED device. However, a preferred implementation alternatively (or additionally) has an output interface that wirelessly transmits the results to the illustrated smartphone 24 or tablet computer.

[0064] The processor 22 determines the sucking performance of the feeding baby based on the sensed motion.

[0065] In the example shown, processor 22 is the processor of mobile phone 24 that wirelessly communicates with monitoring unit 16. Therefore, the sleeve locally detects movement, and the remote processor analyzes this movement to derive sucking performance information. Thus, parents feeding their baby can monitor how their baby's sucking performance is developing on their mobile phone. This is, of course, just one example. The processor 22, which analyzes the motion data, could also be located on the sleeve and integrated with monitoring unit 16. In this case, only the output (sucking performance) needs to be sent to the mobile phone. In this case, it is not necessary to send the raw motion data to the phone, saving time and battery life.

[0066] The motion sensor 18 preferably includes a 3-axis accelerometer and / or a 3-axis gyroscope.

[0067] Figure 2A set of possible signals from a combination of a 3-axis accelerometer and a 3-axis gyroscope is shown. An image of bottle 10 is shown to illustrate the 3-axis orientation.

[0068] This arrangement provides three linear acceleration signals Xacc, Yacc, and Zacc, and three angular velocity signals Xgyro, Ygyro, and Zgyro. The motion sensor is typically an inertial measurement unit and / or a force or acceleration measurement unit.

[0069] The processor 22 is programmed to determine the presence of sucking and / or sucking during feeding. It can also monitor drinking patterns over time to provide objective feedback on the baby's sucking and sucking status and indicate whether problems may be occurring and whether special attention is needed, such as issues related to nipple and sippy cup use.

[0070] As mentioned above, sucking involves the forward and backward movements of the tongue, with the backward movement being more significant. This results in motion along the longitudinal axis of the bottle, i.e., the z-component of the accelerometer. Figure 2 (Zacc in the positive Zacc direction). Therefore, a higher magnitude of acceleration is expected in this direction compared to other directions Xacc and Yacc. In cases where backward motion is more pronounced, the magnitude of acceleration in the negative Zacc direction will be higher than in the positive Zacc direction. Furthermore, the acceleration will follow a cyclic pattern associated with the sucking frequency that is typically between 1 Hz and 2 Hz.

[0071] During sucking, the seal of the lips around the nipple loosens, and there is significant opening and closing of the jaws. Because parents typically hold the bottle at the bottom, the bottom position is relatively fixed. The opening and closing of the jaws can therefore cause angular cyclic motion of the bottle, which can be measured using a gyroscope, specifically the Xgyro and Ygyro signals.

[0072] During sucking, the jaw movement is less noticeable, and the internal muscles are highly active, making the angular movement of the bottle less noticeable.

[0073] Therefore, the main difference between sucking and nibbling is the amount of linear motion along the z-axis and the amount of swaying around the x or y-axis. These types of motion occur less frequently during sucking compared to nibbling.

[0074] Figure 3 A first example of a processing algorithm executed by processor 22 to detect these differences and based on a frequency domain method is shown.

[0075] During feeding, accelerometer 30 generates an accelerometer signal acc(t) and gyroscope 32 generates a gyroscope signal gyro(t). Typically, the sensors perform measurements in three directions. Therefore, the signals are three-dimensional.

[0076] In the next step, processing units 34 and 36 process acc(t) and gyro(t) to remove gravity-induced offset and noise. Depending on the sensor's orientation on the bottle, the three-dimensional signal also needs to be adjusted, for example, using a rotation matrix. Subsequently, the motion in the desired direction can be extracted, represented by accp(t) and gyrop(t).

[0077] Next, the spectrum analysis units 38 and 40 perform spectral density analysis on accp(t) and gyrop(t) to obtain the power spectrum SDacc(f) and SDgyro(f) which describe the signal power as a function of frequency f.

[0078] The power of the signal in the sucking frequency range (1Hz to 2Hz) is derived from the power spectrum. If sucking behavior is present, relatively high power is expected in this frequency range. Multiple features that may provide information about sucking behavior can be derived from the power spectrum (e.g., absolute power, relative power, and morphological measures) in feature analysis units 42 and 44. The set of features is represented by Facc and Fgyro.

[0079] These features are used to determine whether sucking behavior is present during feeding.

[0080] One option is to use a logistic regression model46, which produces values ​​between 0 and 1 indicating the probability of sucking (Psuckling) or the relative presence of sucking behavior. Other modeling techniques can also be used. For example, decision graphs can be developed to determine whether sucking behavior exists.

[0081] Spectral density analysis is therefore used to assess the power of the relevant acceleration signal within the frequency range of interest. The expected increase in spectral density within this frequency range will decrease over time when sucking is used instead of eating.

[0082] Figure 4 Another time-domain method is shown, also used for real-time detection of sucking behavior. Initial processing steps 34, 36 and... Figure 3 The same. Instead of performing spectral analysis, peak detection units 50 and 52 apply a peak detection method in the time domain to identify peaks related to sucking / eating.

[0083] Subsequently, peak analysis units 54 and 56 are used to calculate multiple features from the identified peaks, such as peak amplitude, peak slope, peak duration, and peak minimum.

[0084] These features can be used in Model 58 to determine the presence of sucking behavior.

[0085] In an alternative approach, a template can be defined for the expected acceleration and gyroscope profile during sucking, and then template matching techniques can be used to determine whether sucking is present.

[0086] In the method described above, there are accelerometer and gyroscope branches, which ultimately serve together as inputs to models 46 and 58 to identify the presence of sucking behavior. In principle, a single branch could also be used (e.g., based solely on the accelerometer or gyroscope). However, by combining information from both sensor types, the final output achieves higher accuracy.

[0087] Figure 5 The data shows that as babies grow from 2 months to 8 months, during the 6-month period, the percentage of babies with the highest blood sugar levels from... Figure 2 The signals from the six sensors were used as a moving average of the spectral density during bottle feeding.

[0088] Regular sucking behavior was expected at 2 months of age. By the end of the study, sucking behavior was expected to be introduced at 8 months of age. For each feeding, the spectral density of the accelerometer and gyroscope signals was calculated.

[0089] Figure 5 Each row in the graph represents a different age from 2 months to 8 months. The arrows indicate the progress of the graph from 2 months to 8 months.

[0090] In the initial stages of the study, a spectral power peak around 1.2 Hz (corresponding to the sucking frequency) was observed in the z-component of the accelerometer and the x and y-components of the gyroscope. As the infant grew, the total power across all frequencies increased, indicating that the motion intensified over time. However, the clear peak near the sucking / sucking frequency gradually disappeared.

[0091] This demonstrates that spectral density information can distinguish between sucking and nibbling. Spectral information can be used as input to a classifier to estimate the probability that bottle movement is due to sucking or nibbling. Examples of techniques include clustering, logistic regression, and neural networks.

[0092] In the example above, some processing is performed on a remote device via an application. Of course, alternatively, the system could be fully integrated into the sleeve. Alternatively, some processing can be performed even more remotely; for example, a mobile phone could send data to an external host for processing and then return the result.

[0093] The example above is based on using a sleeve surrounding the bottle. Alternative implementations exist, such as sensors integrated into the nipple or a ring beneath it.

[0094] Figure 6 A method for monitoring sucking performance during feeding from a feeding bottle is shown.

[0095] In step 60, the movement of the feeding bottle during feeding is sensed to generate a motion sensing signal.

[0096] In step 62, sucking performance is identified from the motion sensing signals. The feeding is determined to be based on either eating or sucking.

[0097] In step 64, suction performance information is output.

[0098] As described above, this system utilizes a processor to perform data processing. The processor can be implemented in various ways, using software and / or hardware, to perform a variety of required functions. A processor typically employs one or more microprocessors that can be programmed using software (e.g., microcode) to perform the desired functions. A processor can be implemented as a combination of dedicated hardware for performing certain functions and one or more programmable microprocessors and associated circuitry for performing other functions.

[0099] Examples of circuits that may be used in various embodiments of the present invention include (but are not limited to) conventional microprocessors, application-specific integrated circuits (ASICs), and field-programmable gate arrays (FPGAs).

[0100] In various implementations, a processor may be associated with one or more storage media, such as volatile and non-volatile computer memories (e.g., RAM, PROM, EPROM, and EEPROM). The storage media may be encoded with one or more programs that, when executed on one or more processors and / or controllers, perform the required functions. The various storage media may be fixed within the processor or controller, or they may be transferable, allowing one or more programs stored thereon to be loaded into the processor.

[0101] By studying the accompanying drawings, the disclosure, and the appended claims, those skilled in the art can understand and implement variations of the disclosed embodiments in practicing the claimed invention. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude multiple. A single processor or other unit can implement the functions of several items as described in the claims. The fact that certain measures are recited in mutually different dependent claims does not imply that combinations of these measures cannot be advantageously used. Computer programs can be stored / distributed on suitable media, such as optical storage media or solid-state media provided with or as part of other hardware, but can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems. If the term "suitable" is used in the claims or description, it should be noted that the term "suitable" is intended to be equivalent to the term "configured as." Any reference numerals in the claims should not be construed as limiting the scope.

Claims

1. A monitoring system (12) for a feeding bottle (10), comprising: Motion sensor (18) is used to sense the movement of the feeding bottle during feeding; as well as Processor (22), adapted to identify from motion sensor signals whether the feeding is based on sucking or nibbling; as well as Output interface (20) is used to provide sucking performance information, which identifies whether the feeding is based on eating or sucking.

2. The monitoring system according to claim 1, wherein the sucking performance information identifies the progression stages between sucking and nibbling.

3. The monitoring system according to claim 1, wherein the motion sensor (18) includes a triaxial motion sensor.

4. The monitoring system according to claim 2, wherein the motion sensor (18) includes a triaxial motion sensor.

5. The monitoring system according to claim 3, wherein the motion sensor (18) comprises a triaxial accelerometer and / or a triaxial gyroscope.

6. The monitoring system according to claim 4, wherein the motion sensor (18) comprises a triaxial accelerometer and / or a triaxial gyroscope.

7. The monitoring system according to any one of claims 1 to 6, wherein the output interface (20) includes a wireless transmitter for transmitting the sucking performance information to a remote device (24) for presentation to a user.

8. The monitoring system according to any one of claims 1 to 6, wherein the processor (22) is adapted to: Convert the time-domain motion sensor signal to the frequency domain; Perform spectral density analysis; Determine the signal power within the frequency range corresponding to the sucking frequency; and The signal power is analyzed to identify the sucking performance.

9. The monitoring system according to any one of claims 1 to 6, wherein the processor (22) is adapted to: Detection of peak values ​​in time-domain motion sensor signals; Derive the characteristics of the detected peak; and The characteristics are analyzed to identify the sucking performance.

10. The monitoring system (12) according to any one of claims 1 to 6 is arranged for mounting a sleeve around the feeding bottle.

11. A feeding bottle system, comprising: Feeding bottle (10); as well as The monitoring system (12) according to any one of claims 1 to 10 is used to monitor the sucking performance during feeding.

12. A method for monitoring sucking performance during feeding from a feeding bottle, comprising: The movement of the feeding bottle during feeding is sensed to generate a motion sensing signal; The motion sensing signal is used to identify whether the feeding is based on sucking or licking. as well as Output sucking performance information, which identifies whether the feeding is based on eating or sucking.

13. The method of claim 12, wherein the sucking performance information identifies the progression stage between eating and sucking.

14. The method of claim 12 or 13, wherein sensing motion includes triaxial motion sensing.

15. The method according to claim 12 or 13, comprising: Convert the time-domain motion sensor signal to the frequency domain; Perform spectral density analysis; Determine the signal power within the frequency range corresponding to the sucking frequency; as well as The signal power is analyzed to identify the sucking performance.

16. The method according to claim 12 or 13, comprising: Detection of peak values ​​in time-domain motion sensor signals; Derive the characteristics of the detected peak; as well as The characteristics are analyzed to identify the sucking performance.

17. A computer program product comprising computer program code, wherein when the program code is run on a computer, the program code is adapted to implement the method according to any one of claims 12 to 16.

Images