DESC:FIELD OF THE INVENTION
Embodiment of the present invention relates to a system, apparatus and method for measuring pulse signals to determine imbalances of human body and more particularly for measuring pulse signals at very detailed and subtle level and applying machine intelligence to analyse and interpret the measured detailed signals with utmost precision.
BACKGROUND OF THE INVENTION
Pulse taking and palpation is the most unique, non-invasive and key diagnostic method that is known for correct diagnosis and treatment. Pulse refers to the beating of the arteries caused by the cardiac output when the heart contracts. The pulse condition involves determination of pulse speed, intensity, quantity, pulse strength, pulse energy and depth of the pulse. Pulse detection is painless and has been appreciated and welcomed by people at home and abroad.
Pulse or Nadi (arterial pulse) based diagnosis that works on the principle of blood flow circulation and modulation in the blood vessels is an effective way for quick diagnosis of underlying disease. Usually a pulse is formed by pressing a finger on artery and applying varying pressure to sense pulse condition and blood pressure. Such measurement of pulse signals requires exerting a constant pressure on radial artery to obtain maximum amplitude, which is not the ideal way of diagnosing pulse signals as application of pressure in this manner affects blood circulation and measurement of pulse waveform which may be erred with some noisy data.
However, correct diagnosis of any medical condition from pulse signals mandates the presence of seasoned medical professional with a long term practice and accumulated experience, who may not be available round the clock for obvious, understandable reasons. Further, as there is no quantitative index standard for accurate detection, the judgments are prone to subjectivity errors, which may not be an effective way of providing customized and individual specific recommendation post diagnosis of disease.
Even the professionals of today are unable to measure, analyse and interpret subtle pulse signals which have been known only to practitioners who have been immersed in mastering this skill for almost 40-50 years. It is difficult and nearly impossible having access to such individuals at our beck and call. Beyond the understanding of 3 basic nadis, there has been a very limited and unexplored understanding of various combination of pulse signals and their distinct implications on human body at subtle levels, which rather has an accumulated profound impact on human health and well-being, generally not understood and unequivocally ignored by commoners.
Another existing problem in prior endeavours with respect to measurement of pulse signals via wrist wearables has been non-availability of universal wearables that can be worn around wrist of any size without requiring any kind of customization. Typically, for correct measurement of pulse signals, primary pressure points are located around the radial artery which may require designing the wearable in a manner that defines pressure points along the three primary locations on user wrist. However, since the wrist size can vary across the individuals, there is no such universally wearable device that can aptly sense the pulse vibrations without requiring any customization as per the position coordinates of radial artery.
The above circumstances sets the stage for devising a ready, handy, automated, non-invasive, self-adapting and highly effective universally wearable apparatus that can blend traditional expertise with modern technology and help an individual to understand his physiological state from modulating blood flow and subtle level pulse sensations. This can assist in quickly and correctly diagnosing the underlying medical condition with monitored pulse signals and their varied combinations, and obtain highly specific plan of action and corrective remedy therefor.
In the background of foregoing limitations, the present disclosure sets forth system and method for measuring pulse modulations and signals in a manner such that a very detailed and comprehensive understanding of underlying imbalances in human body can be sensed, analyzed and reported. This disclosure embodies advantageous alternatives and improvements to existing pulse signal measuring systems and methods, and that may address one or more of the challenges or needs mentioned herein, as well as provide other benefits and advantages.
OBJECT OF THE INVENTION
An object of the present invention is to provide a system, apparatus and method for measuring subtle pulse signals and providing vital physiological and pathological information to determine human body imbalances to in real time.
Another object of the present invention is to provide an automated, adaptive and universal sensor based wearable apparatus that can be worn by any individual without requiring any customization for accurate sensing of underlying pulse modulations.
Yet another object of the present invention is to provide a system and method including a self-adaptive wrist wearable that measures pulse signals and assess various pulse combinations to identify imbalance(s) dominating human body condition in both static and dynamic user state.
Yet another object of the present invention is to provide a flexible system, apparatus and method for high precision reproduction of pulse conditions for determining body state and condition at any time without necessitating assistance of any medical practitioner.
Yet another object of the present invention is to provide a non-invasive system, apparatus and method that provides instant, clear and unambiguous feedback to user regarding his real time body condition such that he can take corrective action.
In yet another object of the present invention, a universally wearable wrist apparatus is proposed that can fit all varying wrist sizes without requiring any customization as per coordinates of radial artery, and yet recording subtle pulse movements precisely.
In yet another object of the present invention, the low power requiring system, apparatus and method provide early diagnostics to user or wearer of his health condition which may be impacted with external environmental factors, food intake or even subliminal thoughts.
In one last object of the present invention, the low complexity wrist wearable apparatus helps in obtaining a more complete, continuous and accurate pulse condition figure that enables improving diagnosis efficiency and accuracy.
SUMMARY
This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Furthermore, the claimed subject matter is not limited to implementations that solve any or all disadvantages noted in any part of this disclosure.
In first aspect of present disclosure, a wrist wearable apparatus (200) for pulse detection and classification is disclosed. The wrist wearable apparatus comprising a gel based fluid enclosed within a flexible membrane to form a channelled pathway around wrist of a user. The sensor array is configured to be optimally placed on the flexible membrane, wherein the sensor array comprises of an ultrasonic sensor configured to sense pulse signals based on ultrasound wave transmitted towards and received from underlying blood vessels and a microelectromechanical (MEMS) based inertial measurement unit (IMU) configured to generate user spatial movement data. The computing module is further configured to process and condition the pulse signals received from the ultrasonic sensor and the user spatial movement data received from the MEMS based IMU. The processed pulse signal is analyzed to infer 3D imaging pattern and the analyzed 3D imaging pattern is classified to dynamically determine user physiological state.
In second aspect of present disclosure, a method for detecting and classifying pulse signals sensed from a wrist wearable apparatus is disclosed. The method comprises of sensing pulse signals from a sensor array of the wrist wearable apparatus configured to be optimally placed on a flexible membrane. Here, the pulse signals are sensed based on ultrasound wave transmitted towards and received from underlying blood vessels by an ultrasonic sensor. Thereafter, a user spatial movement data generated from a microelectromechanical (MEMS) based inertial measurement unit (IMU) (20) is received. The pulse signals received from the ultrasonic sensor (10) and the user spatial movement data received from the MEMS based IMU (20) are processed and conditioned and 3D imaging pattern is analyzed and inferred from the processed pulse signals. Finally, the analyzed 3D imaging pattern is classified to dynamically determine user physiological state.
BRIEF DESCRIPTION OF THE DRAWINGS
So that the manner in which the above recited features of the present invention can be understood in detail, a more particular to the description of the invention, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, the invention may admit to other equally effective embodiments. These and other features, benefits and advantages of the present invention will become apparent by reference to the following text figure, with like reference numbers referring to like structures across the views, wherein:
Fig. 1 illustrates a system comprising of wrist apparatus, computing module and a head mounted device, in accordance with an embodiment of the present invention;
Fig. 2 illustrates an exemplary environment of sensor array comprising of a smart combination of sensors positioned on wrist wearable apparatus, in accordance with an embodiment of the present invention; and
Fig. 3 illustrates the pulse waveform to derive observable parameters therefrom, in accordance with an embodiment of the present invention.
DETAILED DESCRIPTION
While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claims. As used throughout this description, the word "may" be used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense, (i.e., meaning must). Further, the words "a" or "an" mean "at least one” and the word “plurality” means “one or more” unless otherwise mentioned. Furthermore, the terminology and phraseology used herein is solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all of these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention. In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase “comprising”, it is understood that we also contemplate the same composition, element or group of elements with transitional phrases “consisting of”, “consisting”, “selected from the group of consisting of, “including”, or “is” preceding the recitation of the composition, element or group of elements and vice versa.
The present invention is described hereinafter by various embodiments with reference to the accompanying drawings, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, a number of materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
In accordance with one general embodiment of present disclosure, the system 1000 of present disclosure, as shown in Fig. 1, comprises of a wrist wearable apparatus 200 and a computing module 300, which may be housed inside or external to the wrist wearable apparatus, and optionally a head mounted device 400 that may be adapted to house the computing module 300 and display messages in response to sensed and classified pulse signals. The wrist wearable apparatus 200 comprises of a smart combination of non-invasive sensors studded on a flexible membrane 15 and adapted to sense one or more vital parameters in real time.
Precisely, the wrist wearable apparatus 200 is configured to dynamically measure physiological signals such as pulse signals of the user for preventive healthcare. As largely understood, the pulse is a rhythmical dilation of blood vessels that is produced by an increased volume of blood being forced into the vessel by the contraction of the heart. It is a weak quasi-periodic signal and can be felt at different points in the body, such as wrist, where the radial artery is located, and the neck where the carotid artery is located.
While the pulse rate is measurement of how many times the heart beats per minute and provides rich information of blood flow, the heart rate is a measurement of how many times the pulse can be felt in a minute. This slight different between the pulse rate and the heart rate is important to note as it can help to determine abnormalities in heart rhythm or blood flow as the pulse is valuable source of information on waveform, wave velocity, amplitude and cycle that reflects pathological condition of user. The real time here refers to measurement of pulse rate over a span of one minute averaged over 30 seconds as instantaneous pulse rate may not be of much added value to the user.
To capture pulse rate and other vital parameters in real time, in accordance with one working embodiment, a wrist wearable apparatus is proposed as wrist has proven to be the most potential solution to the problem for reasons of being convenient and providing ease of access to radial artery for continuous detection of pulse rate. Radial artery being a rich information source of pulse wave and also being not being at great depths beneath the epidermis can be easily accessed when compared to carotid artery in neck.
Accordingly, as shown in Fig. 2, the wrist wearable apparatus 200 comprises of the smart combination of non-invasive sensors along with an entire electronic circuitry (signal processor, power source, communication module, transmitter/receiver and the like) that is capable of measuring one or more vital parameters including pulsation in real time irrespective of whether the user is in static or dynamic state, as will be explained in later sections.
In accordance with first embodiment, the one or more vital parameters of the user may include, but not limited to, the one or more pulse signals, pressing force applied to the skin, arterial pulse palpation rate to derive plurality of physiological parameters, oxygen concentration, blood pressure, body temperature and the like. In accordance with one example embodiment, the non-invasive sensors that may be optionally included in wrist wearable apparatus includes: a) a temperature sensor to sense body temperature, b) optical sensor to measure the change of blood flow in the artery, c) an accelerometer to sense body movements, d) a photoplethysmography (PPG) sensor to monitor pulse rate based on intensity variation of transmitted or reflected light from inner tissues, e) an air pressure sensor to measure pulse, a force sensor or a combination thereof.
The above alliance of auxiliary sensors has been effective as non-invasive monitoring device of individual heart and health condition, as known in art. However, some major inaccuracies and deficiencies of unclear signals, motion artefacts (such as muscle motion) and low signal to noise ratio in these sensors (especially when used alone) because of being influenced by ambient external lightning conditions makes adoption of these sensors individually unpromising. Also, the burden of combining several sensors makes the overall architecture complex and cumbersome, especially when designed for a small form factor.
The above challenge has led way for devising a combination of smart sensors that can overcome such deficiencies and aptly measures even small, slight modulations in pulsatile signals. For the same, the present disclosure leverages the power of acoustics in contrast to optics for sensing information of underlying pulse movements and alignments, articulating surfaces, and soft tissue characteristics. Accordingly, a sensor array 100 comprising of a smart combination of ultrasonic sensor 10 along with micro-electromechanical system (MEMS) based inertial measurement unit (IMU) 20 has been proposed for precise measurement of pulsatile movement that overcomes deficiencies of prior stand-alone sensors used in art, as shown in Fig. 2.
Apropos, in one exemplary embodiment, the present wrist wearable apparatus 200 provides for a read to integrate multimodal sensor array 100 that includes a combination of miniature ultrasonic sensors 10 and a MEMS based inertial measurement units (IMUs) 20 to propagate the ultrasound through the sub surface of dermis and collect information at various depths below the dermis with minimal noise. The combination of miniaturized sensors over the sensor array 100 is positioned optimally over a flexible membrane 15 that forms a channelled pathway 18 around the user wrist.
In accordance with one working embodiment, the flexible membrane 15 is made up of a suitable material for encapsulating a gel based fluid that flows within the membrane along the channelled pathway in a sinusoidal fashion. The flexible membrane 15 forming a channelled pathway 18 can be easily worn around user’s wrist with the aforementioned sensor array 100 without necessitating exact knowledge of radial artery position coordinates, as will be discussed in upcoming paragraphs. Specifically, the sensor array 100 comprises of a) thin-film based piezoelectric ultrasonic sensors (precisely transducer) 10 operating in ultrasonic band with sensing higher frequency audio signals, and b) MEMS based inertial measurement unit (IMUs) 20 to capture the vibrational energy from the blood flowing within the vessels and corresponding pulsatile movement travelling to the skin surface with minimum interference.
The channelled pathway 18 formed of flexible membrane 15 can be wrapped around the user wrist in a spiral fashion just like any bracelet or hand jewellery. The channelled pathway 18 encloses therewithin a gel based fluid 22 over which an array of sensors 100 is overlaid and placed in contact with, wherein the array of sensors 100 comprising of an ultrasonic transducer 10 along with MEMS based inertial measurement unit (IMUs) 20 transmits ultrasound waves via gel based fluid 22 and measures pressure variations in sub-surface layers and blood vessels corresponding to three major pulse forms, namely Vatta, Pitta and Kapha (discussed in later sections).
The ultrasonic transducer 10 is configured to transmit an acoustic signal from the surface of user wrist and receive an echo or signal propagating back towards the transducer 10 from underlying blood vessels and tissues. This in turn generates an ultrasound wave or ultrasound energy that propagates through the gel based fluid 22 to reach the ultrasonic transducer 10. When the blood flows through the vessels of our body, it generates a pressure wave on the vessel walls. This wave is a result of the force exerted by the heart as it pumps blood throughout the body. This pressure wave travels through the thick tissues of our body and cause vibration of the skin, which gets recorded by the specialized sensors.
These pressure waves may be, for example, acoustic pressure waves (e.g., sound waves) or the like. In response to these interactions, a reflected ultrasound wave, or other ultrasound energy is generated and propagates through the gel based fluid 22 back towards the ultrasound transducer 10. These reflected ultrasound waves are measured or otherwise detected by the ultrasound transducer 10 and converted to ultrasound data. As one example, the ultrasound data may be Doppler ultrasound data that is acquired using a pulsed-wave Doppler technique. Thus, the ultrasound data is acquired from flowing blood within the vessels for further processing by the computing module of the system 1000.
In accordance with one exemplary embodiment, the gel based fluid 22 functions as ultrasound conducting medium to amplify the sensed signals, and may be selected from a group comprising of dibutyl phthalate, dioctyl phthalate, mineral oils, naphthenic oils, paraffinic oils, polybutenes, silicon fluids, vegetable oils and the like. In other preferable embodiment, the flexible membrane 15 may be formed of silicon that has properties similar to skin or any subcutaneous tissue and presents easier fixing option for the given combination of sensor array 100.
In another exemplary embodiment, ultrasonic transducers 10 of small element size, low power consumption, improved bandwidth, and increased integration capability is selected using the thin-film piezoelectric material of high sensitivity. For example, aluminium nitride based film may be used for miniaturization and an array of piezoelectric based ultrasonic transducer 10 may be arranged in a manner to achieve high fill factor to generate acoustic wave and sense acoustic pressure.
In another significant aspect of present disclosure, the sensor array 100 includes microelectromechanical (MEMS) based IMUs 20 that are low cost with much higher sensing capabilities along with a small form factor, which makes them an ideal and realistic choice of sleek wearable devices, such as one proposed in present disclosure. In addition to the ultrasound data acquired by the ultrasonic transducer 10, MEMS data is used for monitoring the spatial movement of wrist accommodating ultrasonic sensors 10 and evaluating signal-to-noise and interference ratio therefrom such that noisy data originating from undue wrist movement or other motion artefacts is discarded. Further, the three-axis MEMS based accelerometer (IMU) can record wrist and other muscle movements for high/low frequency noise elimination from final data. The data obtained from MEMS based IMU 20 can also be used for inferring user state-resting or moving for any kind of motion compensation.
In one noteworthy embodiment, with the positioning of an array of sensors 100 over a flexible membrane 15 containing therewithin the gel based fluid 22, the sensed pulse signals are amplified and much of interference that is generally caused by the sensor coming in the contact with skin is minimized. The above combination of sensors are packaged with the process circuit on a flexible printed circuit board (PCB) and positioned with utmost accuracy along the channelled pathway 18 to measure the pulse waveform all along the user wrist. Here, it is pertinent to note that since the sensor array 100 is studded all along the channelled pathway 18, the dominant pulse movement corresponding to primary pulse locations will be automatically picked by the given arrangement of sensors to convey valuable pulse information.
The precise and rigid position and placement of sensors within the sensor array 100 achieves minimization of drifting errors, wrist position, interference, fluctuations and other motion artefacts, which needs to be corrected for accurate analysis. Usually the high frequency noise is perpetuated by external environmental factors (electromagnetic noise or thermal noise and the like), while the low frequency noise may be instigated from user movements. Collectively, these high/low frequency noise can adversely impact accuracy of pulse signal detection.
Hence, the noise infiltrated spurious signals obtained from the smart sensor array 100 are first processed by an amplifier, low pass filter and converter to convert analog signals to digital signals. These digitized signals are then transmitted to the computing module 300 where the digitized signals are fused and bandpass filtered for elimination of errors and high/low frequency noise and minimization of the negative effects of motion artefacts on the signals. The noise treated pulse signals after being transformed to digital signals are processed by the computing module 300 for quantifying or otherwise parameterizing the pressure within the vibrating blood vessels.
In one significant embodiment, the pulse signal is monitored and sampled for processing for a period of time to obtain both time and frequency domain features and/or magnitude thereof to obtain time-frequency representation of data by wavelet transformation approach. In general, a time-series can be obtained by digitizing the analog signals from the sensor array at desired sampling rate and desired time using analog to digital converter (ADC digitizer). This is useful for identification of dynamic physiological patterns and may also help in sifting noise data from such representation. For example, while the repeating patterns can be indicative of some pathological/physiological condition, the non-repetitive or distinct patterns may be characteristic of noise and other motion artefacts.
In one significant approach, the processed ultrasound and MEMS based data can be used to reconstruct a 3D imagery that helps in correct diagnosis with better viewing of 3D anatomy of sub surface tissues and vessels. More importantly, since the pulse signals are captured from sensors that sweep all over the wrist, a more detailed 3D reconstruction can be achieved using either of feature based or voxel based representation. In one preferable embodiment, the voxel based representation created in 3 dimensions is selected for purposes of preserving all vital information from sensed signals.
In general, the vibrations in the skin can be felt by placing a finger on pulse point which provides a valuable information about our overall health and well-being. In present disclosure, the need for sensing the pulse by way of placing the finger is replaced with a much more accurate pulse sensing wearable apparatus 100 that can even measure subtle and light pulse modulations using a smart combination and optimal placement of an array of sensors 100 over a channelled pathway 18.
As can be seen in Fig. 2, the sensor array 100 comprising of ultrasonic transducer 10 and the MEMS based IMU 20 are positioned intermittently or continually all over the channelled pathway containing the gel based fluid 22. As the pulse vibrates and the pulse echo signal gets recorded, the gel based fluid 22 moves and the sensor array segment positioned over the vibrating pulse and moving fluid 22 gets activated, which enables capturing of dominant pulse waveform imaging pattern for further analysis. Thus, irrespective of unavailability of exact position coordinates of the radial artery and associated pressure points for pulse signal mapping, the activated sensor array segment over the channelled pathway 18 provides a direct, clear and unambiguous information on pulsatile signals.
Usually, conventional wearable devices demand too rigid attachment of device with user skin for accurate measurement of underlying body signals. However, too tightly tied wearable stifles user activity, making the device unacceptable to be worn for too long. However, the smart placement of selective sensors over a sensor array 100 all along the channelled pathway 18 makes it usable and wearable by anyone without having to alter the size or getting customized. Irrespective of the wrist size, the wrist wearable apparatus 100 can coil around the user wrist and the blinking or activation or stimulation of gel based fluid 22 along with array of sensors 100 can directly provide coordinates of primary pressure points and dominant pulse waveform for further analysis.
Thus, even the subtle acoustic waves or vibrational signals generated by moving fluid and activated sensors are captured that helps drawing a 3d image pattern of said pulse movement. In one exemplary embodiment, the characteristic points of pulse waveforms, such as percussion waves (P-waves), tidal waves (T-waves), valley and diastolic waves (D-waves), can be detected due to their high sensitivities.
The above explained wrist wearable apparatus 200 will enable healthcare professionals and even the user to infer the pulse type, whether it is a regular or irregular rhythm without having to physically touch the patient/user or even without the user mandated to have an in-depth understanding of pulse signal analysis. This has a potential to revolutionize the way pulse is monitored and diagnosed which is much prone to subjective errors based on experience and subtle capabilities of diagnosing professional’s perception.
The generated 3D imagery pattern is analyzed for the position coordinates of sensed signals and other important observable parameters such as pulse width, pulse depth, pulse rate, pulse rush/relax, pulse intensity, amplitude, frequency, speed, rhythm, type, quantity and texture. It is to be understood that while performing the analysis of sensed signals while the user is in static or resting position, the position coordinates of sensed signals or their origination may be optionally considered. However, while the user is in dynamic motion, using the position coordinates enhance the overall effectiveness of analysis.
The computing module 300 is configured with a specialized machine learning algorithm that takes the position coordinates of the sensed signal and observable parameters as an input to calculate a score indicative of Ayurvedic body type of user. Thereafter, the aforementioned observable parameters and (optionally) position coordinates of sensed signals (if user is in dynamic state) are taken as input for assigning different scores and weights to each of these input streams for better classification.
In accordance with one significant embodiment, the position from which the pulse signal is sensed results in better approximation of pulse waveform when the user is non-static. Since the wrist wearable apparatus is worn around the wrist to make it suitable for wearing by users of varying wrist sizes, there may not be clear indicators of dominant pulse signals. Now, as can be seen in Fig. 3, major characteristics are inferred from extreme points and inflection points of the waveform (with pulse pressure P mapped against sampling time T) depicting from the aortic opening point (point b), the main wave peak (point c), the tidal wave (point e), and the trough valley (point f). The position information of each point and pulse signal characteristic features can be easily extracted by any of first order and second order differential threshold methods or using features in time frequency domain using wavelet transform or a combination thereof.
In next working embodiment, the pulse signal characteristic features based on position information of pulse points and the observable parameters such as pulse width, pulse depth, pulse rate, pulse rush/relax, pulse intensity, amplitude, frequency, speed, rhythm, type, quantity and texture are fed as input to a deep learning based computing module 300. In one exemplary embodiment, the deep learning module is a convolutional neural network (CNN) comprising of a convolutional layer with an additional pooling layer to avoid overfitting of model and a connecting layer that uses softmax function to output the Ayurvedic body type of user along with predominant pulse waveform determinant of the said Ayurvedic body type.
In other alternate embodiment any of supervised techniques including Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Naïve Bayes Classifiers or unsupervised techniques including self-organizing maps, adaptive resonance and clustering techniques (K-Means) may also be utilized. The trained machine learning algorithm can include or otherwise implement a support vector machine (“SVM”), a random forest, a conditional random field, a hidden Markov model, a neural network, and other deep learning models or algorithms.
In one exemplary embodiment, all the sensors, electronics and the software may be housed in the wrist wearable apparatus 200 or as an external circuitry existing independently or even housed within a head mounted device 400 of the system 1000 (as can be seen in fig. 1). The aim is to assess mental, physical and spiritual health using classified pulse signals, which is known to dictate all the salient features of a human body. In one example embodiment, the array of non-invasive sensors is incorporated into a wearable apparatus 200 and may be arranged in form of grid, lattice, matrix bends, stretches to dynamically measure pulse signals and other associated vital parameters. In one preferred aspect of present disclosure, a wearable patch embodied with an array of sensors is proposed that is capable of sensing various pulse signals and combinations thereof in a manner not explored till date.
In one example, the sensor array can be formed as a mesh, lattice, grid, or matrix having interlocking and/or repeating elements which are all the same size and shape. In order to correctly measure pulse pressure and pulse waveform, it is important to select right set of sensors along with their right placement, overall mechanical structure, and signal acquisition circuit design. In an example, gaps or elements in a mesh, lattice, grid, or matrix can have square, rhomboid, diamond, trapezoidal, or parallelogram shapes.
In an example, gaps or elements in a mesh, lattice, grid, or matrix can have hexagonal shapes. In an example, gaps or elements in a mesh, lattice, grid, or matrix can have triangular shapes. In an example, gaps or elements in a mesh, lattice, grid, or matrix can have circular or elliptical shapes. In an example, gaps or elements in a mesh, lattice, grid, or matrix can have conic section shapes. In an example, gaps or elements in a mesh, lattice, grid, or matrix can have helical or spiral shapes.
In one working embodiment, the wrist wearable apparatus 200 may comprise of a wrist band, patch, strap, bracelet, textile material or a combination thereof. In an example, a non-conductive or less-conductive fiber, trace, yarn, strand, or textile can be selected from the group consisting of: acetate, acrylic, cotton, denim, elastane, Kevlar™, latex, linen, Lycra™, neoprene, nylon, nylon, polyester, wool, silicon rubber, silk, spandex, Danconn or rayon.
The apparatus 200 may be worn on individual wrist or ankle or any other part of the body that is sensing human body vitals. The pulse signal and associated vital information measured by the array of sensors 100 is collected and sent to computing module 300 to detect pulse pressure and pulse waveform for diagnosis and treatment. The pulse pressure is exerted by radial artery at three primary pressure points that provides equivalent electrical output.
The pulse condition is captured as a time series and frequency and advanced machine learning algorithm is applied to identify the pulse patterns and extract dynamic features of underlying physiology. The different and unique combinations of pulse signals helps one understand status quo of imbalances prevailing in human body. For example, the pulse pattern relating to irregular variations signifies pulses alternans that is found in setting of severe ventricular dysfunction and other forms of cardiac pathology or it may be an indication of atrial fibrillation. In another example, the pulse signals read as elephant kind modulation may be indicative of lymphatic obstruction, solid edema, lymphosarcoma, or elephantitis.
It is pertinent to note that reading such modulations is not a craft of any individual who has been shortly trained on reading pulse signals. These are utmost subtle and faintly noticeable pulse signals that may be detected and comprehended only with life time of practice. To understand, the present disclosure proposes a wrist wearable apparatus 200 embodied with a smart sensor array 100, with sensors cautiously and ingeniously selected and positioned in a manner to detect various pulse modulation combinations for anyone wearing the apparatus 200 with a precision as if done with a finger like touch.
As prevalent and known for centuries, human body humor or imbalances may be triggered from external environmental factors, food intake – type of food, time of food, manner in which the food is consumed, and even subliminal thoughts that the wearer is not aware of. For example, with changes in external temperatures, or wrong consumption of food, or repressed negative thoughts the user may feel stressed, anxious, depressed or even prone to other body ailments. These factors are usually unobserved in ordinary life unless one encounters some serious sickness issues or chronic disease associated with human imbalances.
The present disclosure can apprise user of such pathological condition or a lurking illness much earlier than the disease witnesses itself and takes much more worse and dreadful form. The present wrist wearable apparatus 200 continuously monitor user body situations and timely inform user if his body is under any kind of adverse influence from any above existing factors. Thus, the apparatus takes care of overall well-being of the user based on correct and accurate diagnosis of variations and modulations of pulse signals so that timely and corrective action can be taken before sickness prevails.
The optimal layout of non-invasive sensor(s) on the wrist wearable apparatus 200 is capable of continuously measuring three basic pulse signal modulations and combinations thereof, which as per the Ayurvedic literature governs functioning of entire human physiology. These three pulse modulations namely Vata Pulse, Pitta Pulse, and Kapha Pulse are collectively referred as Tridosha and any kind of disturbance in their equilibrium may cause a disorder which is reflected in the modulation of blood vessels carrying blood, called as Nadi. Measuring the modulation in blood flow can serve as a vital diagnostic tool for individuals equipped with right kind of wrist wearable apparatus 200.
As research posits, the Vata Pulse is characterised by fast, feeble, cold, light, thin condition of human body which disappears on applying pressure. These pulse sensations are read as they move in small and undulating snake like fashion. Next, the Pitta Pulse is understood from prominent, strong, high amplitude, hot body temperature that lifts up the palpating fingers. These pulse sensations are read as they move in sharp undulating frog like fashion. Lastly, the Kapha Pulse is understood from deep, slow, broad, wavy, thick, cool, warm, or regular body conditions. These pulse sensations are read as they move in smooth and moderate swimming swam like fashion. In addition, by measuring the pulse modulations around the arteries of the left and right wrists, the health condition of the human internal organs, especially five organs (heart, liver, spleen, lung, condition of the kidney) can be accurately inferred.
These pulse modulations and their subtle combinations when read and interpreted in a detailed manner are expressive of various imbalances and body humors. For example, the parameters such as rate of modulation such as ranging 80-90 is symbolic of Vata imbalance; 70-80 signifies Pitta imbalance and 50-60 shows Kapha imbalance in human body. Even the rhythm of pulse movement, whether regular or irregular is read by these specialized sensors along with the force (low, high, moderate) to have clear insight of human body fluctuations and imbalances.
In another significant aspect of present disclosure, a method for detecting and classifying pulse signals from a wrist wearable apparatus 200 is disclosed, wherein the method comprises of measuring pulse signals via a sensor array 100 optimally positioned within the wrist wearable apparatus 200. Here, the sensor array is placed on a flexible membrane enclosing therewithin a gel based fluid to form a channelled pathway around wrist of user. The pulse signals are measured via ultrasonic sensors based on ultrasound wave transmitted towards and received from underlying blood vessels. Further, the user spatial movement data is captured by microelectromechanical (MEMS) based inertial measurement unit (IMU). In next step, the sensed pulse signals received from the ultrasonic sensor and the user spatial movement data received from the MEMS based IMU is processed and conditioned by a computing module 300. A 3D imaging pattern is derived from processed signal data and analyzed to classify it for determining user physiological state.
In accordance with an embodiment, the machine-readable instructions may be loaded into the memory unit from a non-transitory machine-readable medium, such as, but not limited to, CD-ROMs, DVD-ROMs and Flash Drives. Alternately, the machine-readable instructions may be loaded in a form of a computer software program into the memory unit. The memory unit in that manner may be selected from a group comprising EPROM, EEPROM and Flash memory. Further, the micro controller is operably connected with the memory unit. In various embodiments, the micro controller is one of, but not limited to, a general-purpose processor, an application specific integrated circuit (ASIC) and a field-programmable gate array (FPGA).
In general, the word “module,” as used herein, refers to logic embodied in hardware or firmware, or to a collection of software instructions, written in a programming language, such as, for example, Java, C, or assembly. One or more software instructions in the modules may be embedded in firmware, such as an EPROM. It will be appreciated that modules may comprised connected logic units, such as gates and flip-flops, and may comprise programmable units, such as programmable gate arrays or processors. The modules described herein may be implemented as either software and/or hardware modules and may be stored in any type of computer-readable medium or other computer storage device.
Further, while one or more operations have been described as being performed by or otherwise related to certain modules, devices or entities, the operations may be performed by or otherwise related to any module, device or entity. As such, any function or operation that has been described as being performed by a module could alternatively be performed by a different server, by the cloud computing platform, or a combination thereof. It should be understood that the techniques of the present disclosure might be implemented using a variety of technologies. For example, the methods described herein may be implemented by a series of computer executable instructions residing on a suitable computer readable medium. Suitable computer readable media may include volatile (e.g., RAM) and/or non-volatile (e.g., ROM, disk) memory, carrier waves and transmission media. Exemplary carrier waves may take the form of electrical, electromagnetic or optical signals conveying digital data steams along a local network or a publicly accessible network such as the Internet.
It should also be understood that, unless specifically stated otherwise as apparent from the following discussion, it is appreciated that throughout the description, discussions utilizing terms such as "controlling" or "obtaining" or "computing" or "storing" or "receiving" or "determining" or the like, refer to the action and processes of a computer system, or similar electronic computing device, that processes and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices. Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the embodiments shown along with the accompanying drawings but is to be providing broadest scope of consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the invention is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present invention.
,CLAIMS:We Claim:

1) A wrist wearable apparatus (200) for pulse detection and classification, wherein the wrist wearable apparatus (200) comprises:
a gel based fluid (22) enclosed within a flexible membrane (15) to form a channelled pathway (18) around wrist of a user;
a sensor array (100) configured to be optimally placed on the flexible membrane (15), wherein the sensor array (100) comprises of:
an ultrasonic sensor (10) configured to sense pulse signals based on ultrasound wave transmitted towards and received from underlying blood vessels;
a microelectromechanical (MEMS) based inertial measurement unit (IMU) (20) configured to generate user spatial movement data; and
a computing module (300) configured to:
process and condition the pulse signals received from the ultrasonic sensor (10) and the user spatial movement data received from the MEMS based IMU (20);
analyze 3D imaging pattern inferred from the processed pulse signals; and
classify the analyzed 3D imaging pattern to dynamically determine user physiological state.

2) The wrist wearable apparatus (200), as claimed in claim 1, wherein the sensor array (100) is continually or intermittently spaced over the flexible membrane (15).

3) The wrist wearable apparatus (200), as claimed in claim 1, wherein the ultrasonic sensor (10) is an ultrasonic transducer comprising of a thin film based piezoelectric sensors operable in ultrasonic range.

4) The wrist wearable apparatus (200), as claimed in claim 3, wherein the thin film is formed of aluminium nitride.

5) The wrist wearable apparatus (200), as claimed in claim 1, wherein the gel based fluid (22) contained within the flexible membrane (15) amplifies the sensed pulse signals and is selected from a group comprising of dibutyl phthalate, dioctyl phthalate, mineral oils, naphthenic oils, paraffinic oils, polybutenes, silicon fluids, vegetable oils and the like.

6) The wrist wearable apparatus (200), as claimed in claim 1, wherein the pulse signals are processed, fused and band-pass filtered for minimizing noise, interference drifting errors, and motion artefacts.

7) The wrist wearable apparatus (200), as claimed in claim 1, wherein, in an event the pulse signal is sensed, the gel based fluid (22) flows within the flexible membrane (15) and segment of the sensor array (100) positioned over vibrating pulse and the flowing fluid (22) is activated for direct pulse measurement.

8) The wrist wearable apparatus (200), as claimed in claim 1, wherein the computing module (300) is configured to classify the analyzed 3D imaging pattern using supervised or unsupervised machine learning algorithm operating on observable parameters pulse width, pulse depth, pulse rate, pulse rush/relax, pulse intensity, amplitude, time and frequency domain features, speed, rhythm, type, quantity and texture in an event the user is in static position.

9) The wrist wearable apparatus (200), as claimed in claim 1, wherein the computing module (300) is configured to classify the analyzed 3D imaging pattern using supervised or unsupervised machine learning algorithm based on position coordinates of the sensed signals and/or observable parameters: pulse width, pulse depth, pulse rate, pulse rush/relax, pulse intensity, amplitude, time and frequency domain features, speed, rhythm, type, quantity and texture, in an event the user is in non-static position.

10) The wrist wearable apparatus (200), as claimed in claim 9, wherein the position coordinates of the sensed signals is obtained using differential threshold approach or a wavelet transform approach or a combination thereof based on characteristic features of the sensed pulse signal.

11) The wrist wearable apparatus (200), as claimed in claim 10, wherein the characteristic features of the sensed pulse signal comprises domain features of percussion wave, tidal wave, valley and diastolic wave.

12) The wrist wearable apparatus (200), as claimed in claim 1, further comprising of an analog to digital converter for converting analog pulse signals into equivalent electrical signal for obtaining the 3D imaging pattern of the pulse waveform.

13) The wrist wearable apparatus (200), as claimed in claim 1, wherein the sensed pulse signals are processed to reconstruct 3D imagery pattern using a feature based reconstruction, a voxel based reconstruction or a combination thereof.

14) The wrist wearable apparatus (200), as claimed in claim 1, wherein the wrist wearable apparatus (200) is a wrist band, patch, strap, bracelet, textile material or a combination thereof.

15) The wrist wearable apparatus (200), as claimed in claim 1, wherein the computing module (300) is configured to classify the analyzed 3D imaging pattern into Vata pulse, Pitta pulse and Kapha pulse or a combination thereof to determine the predominant Ayurvedic body type of the user for inferring the user pathological state.

16) A method for detecting and classifying pulse signals sensed from a wrist wearable apparatus (200), the method comprising:
sensing pulse signals from a sensor array (100) of the wrist wearable apparatus (200) configured to be optimally placed on a flexible membrane (15);
wherein the pulse signals are sensed based on ultrasound wave transmitted towards and received from underlying blood vessels by an ultrasonic sensor (10);
receiving a user spatial movement data generated from a microelectromechanical (MEMS) based inertial measurement unit (IMU) (20);
processing and conditioning the pulse signals received from the ultrasonic sensor (10) and the user spatial movement data received from the MEMS based IMU (20);
analysing 3D imaging pattern inferred from the processed pulse signals; and
classifying the analyzed 3D imaging pattern to dynamically determine user physiological state.

17) The method for detecting and classifying pulse signals, as claimed in claim 16, wherein a channelled pathway (18) enclosing therewithin a gel based fluid (22) is formed around wrist of user.

18) The method for detecting and classifying pulse signals, as claimed in claim 16, wherein the ultrasonic sensor (10) is an ultrasonic transducer comprising of a thin film based piezoelectric sensors operable in ultrasonic range.

19) The method for detecting and classifying pulse signals, as claimed in claim 16, wherein the pulse signals are processed, fused and band-pass filtered for minimizing noise, interference drifting errors, and motion artefacts.

20) The method for detecting and classifying pulse signals, as claimed in claim 17, wherein, in an event the pulse signal is sensed, the gel based fluid (22) flows within the flexible membrane (15) and segment of the sensor array (100) positioned over vibrating pulse and the flowing fluid (22) is activated for direct pulse measurement.

21) The method for detecting and classifying pulse signals, as claimed in claim 16, wherein, the analyzed 3D imaging pattern is classified using supervised or unsupervised machine learning algorithm operating on observable parameters: pulse width, pulse depth, pulse rate, pulse rush/relax, pulse intensity, amplitude, time and frequency domain features, speed, rhythm, type, quantity and texture in an event the user is in static position.

22) The method for detecting and classifying pulse signals, as claimed in claim 16, wherein, the analyzed 3D imaging pattern is classified using supervised or unsupervised machine learning algorithm based on position coordinates of the sensed signals and/or observable parameters: pulse width, pulse depth, pulse rate, pulse rush/relax, pulse intensity, amplitude, time and frequency domain features, speed, rhythm, type, quantity and texture, in an event the user is in non-static position.

23) The method for detecting and classifying pulse signals, as claimed in claim 22, wherein, the position coordinates of the sensed signals is obtained using differential threshold approach or a wavelet transform approach or a combination thereof based on characteristic features of the sensed pulse signal.

24) The method for detecting and classifying pulse signals, as claimed in claim 23, wherein the characteristic features of the sensed pulse signal comprises domain features of percussion wave, tidal wave, valley and diastolic wave.

25) The method for detecting and classifying pulse signals, as claimed in claim 16, wherein the sensed pulse signals are processed to reconstruct 3D imagery pattern using a feature based reconstruction, a voxel based reconstruction or a combination thereof.

26) The method for detecting and classifying pulse signals, as claimed in claim 16, wherein the analyzed 3D imaging pattern is classified into Vata pulse, Pitta pulse and Kapha pulse or a combination thereof to determine the predominant Ayurvedic body type of user for inferring the user pathological state.