Description:FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
The Patent Rules, 2003
COMPLETE SPECIFICATION
(See sections 10 & rule 13)
1. TITLE OF THE INVENTION
A WEARABLE IMU DRIVEN ON-BOARD GAIT ANALYZER FOR CHILDREN SUFFERING FROM CEREBRAL PALSY (CP)
2. APPLICANT (S)
NAME NATIONALITY ADDRESS
DIVYASAMPARK IHUB ROORKEE FOR DEVICES MATERIALS AND TECHNOLOGY FOUNDATION IN Indian Institute of Technology Roorkee, Roorkee-247667, Uttarakhand, India.
3. PREAMBLE TO THE DESCRIPTION
COMPLETE SPECIFICATION

The following specification particularly describes the invention and the manner in which it is to be performed.

FIELD OF INVENTION:
[001] The present invention relates to the field of gait analysis. The present invention in particular relates to a light-weight, portable, and wearable device for gait analysis of children suffering from cerebral palsy (CP).
DESCRIPTION OF THE RELATED ART:
[002] Pathological gait is clinically characterized using physician observation and camera-based motion-capture systems. Camera-based gait analysis provides a quantitative picture of gait disorders. However, these systems are expensive and are not available at many clinics. Auditory and tactile cueing (e.g., metronome beats and tapping of different parts of the body) are often used by physiotherapists to regulate patients' gait and posture. However, this approach requires the practitioner to closely follow the patient, and does not allow patients to exercise on their own, outside the laboratory setting.
[003] Reference may be made to the following:
[004] Publication No. US2020000373 relates to a quantitative gait training and/or analysis system employs instrumented footwear and an independent processing module. The instrumented footwear may have sensors that permit the extraction of gait kinematics in real time and provide feedback from it. Embodiments employing calibration-based estimation of kinematic gait parameters are described. An artificial neural network identifies gait stance phases in real-time. The proposed onboard gait analyzer is exclusively designed for children suffering from cerebral palsy (CP) whereas the above system is used for general gait analysis. The above device uses artificial neural network while the proposed device uses synchro squeezing transform based algorithm for gait analysis. The device mentioned above is a footwear-based device, whereas the proposed device is specifically attached to the L5 vertebra. The proposed onboard gait analyzer features more advanced hardware configuration and incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for efficient and secure communication. In the above referenced device, more than one sensor are used whereas the proposed onboard gait analyzer uses only one sensor.
[005] Publication No. WO2019175899 relates to a wearable device for gait analysis. The wearable device is portable, affordable and accessible for screening gait and analysis of lower limb joint kinematics and kinetics including ankle, calf, knee, thigh, hip, pelvic, foot plantar pressure, clearance parameters and all spatial temporal parameters. The above device is used for calculating spatiotemporal parameters in healthy individuals, while the proposed onboard gait analyzer device is exclusively designed for children suffering from cerebral palsy (CP). The proposed device is attached to the L5 vertebra and features onboard processing capabilities, incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) methodologies.
[006] Publication No. CN118452903 relates to a passive and active integrated tiltable animal gait behavior analyzer, which adopts a mode that a transparent conveyor belt rotates around three fixed shafts, and solves the problem that the gait behavior of some diseased experimental animals cannot be analyzed due to the fact that the experimental animals are unwilling to walk through the rotary motion of the transparent conveyor belt. The above referenced device is used for analyzing animal gait behavior, while the proposed onboard gait analyzer is specifically designed for children suffering from cerebral palsy (CP). The above system uses a transparent conveyor belt with fixed shafts to analyze animal gait whereas, proposed onboard gait analyzer is a light-weight, wearable device, directly attached to the L5 vertebra, and does not require any external movement system. The above referenced system needs a fixed setup, requiring a controlled laboratory environment. But the proposed onboard gait analyzer is compact, lightweight, and portable device, allowing continuous monitoring of children suffering from cerebral palsy (CP). In the above referenced device, the gait analysis is based on camera images. In the proposed onboard gait analyzer, the gait analysis is carried out using inertial measurement unit (IMU) and onboard processor.
[007] Publication No. TW202402231 relates to an intelligent gait analyzer which includes a chair, a first camera and an electronic device. The chair provides a user to sit. The first camera shoots a first film in which the user walks from the start point to the chair and shoots a second film in which the user stands up from the chair. The electronic device is electrically connected to the first camera to receive the first film and the second film. The electronic device includes a graphics processor and a memory. The above referenced system requires a complete setup and is limited to use within a laboratory environment, and requires high cost. Whereas the proposed onboard gait analyzer is a portable, lightweight, and low-cost standalone device featuring onboard processing capability. The proposed device is specifically designed for children suffering from cerebral palsy (CP) and uses message queuing telemetry transport (MQTT) protocol where clients publish gait data as predefined topics via a broker. The proposed device is attached to the L5 vertebra. The above referenced system requires a high-performance graphics processor and large memory, whereas the proposed onboard gait analyzer requires only minimal storage to save inertial measurement unit (IMU) data.
[008] Publication No. CN115644858 relates to a wearable intelligent gait analyzer based on multi-sensor data fusion technology. The wearable intelligent gait analyzer comprises a double-guide surface electromyography sensor, a wireless communication module and a wireless communication module, wherein the double-guide surface electromyography sensor is used for collecting electric signals generated by muscle contraction; the inertial measurement unit is used for collecting angle, angular velocity and angular acceleration information of leg joints when the lower limbs of the human body move; the plantar thin film pressure sensor is used for collecting plantar pressure information; the main control board is used for carrying out fusion processing on the collected data information through a multi-sensor data fusion technology and a D-S evidence theory fusion algorithm; and the CS architecture network server is used for carrying out gait recognition through a deep neural network intelligent algorithm.. The proposed onboard gait analyzer integrates an inertial measurement unit (IMU), processor, and SD card into a single compact PCB, which is conveniently attached to a velcro belt, whereas the above referenced device requires two sensors i.e. one is electromyography sensor and other is inertial measurement unit to calculate gait parameters. The above gait analyzer employs a client-server (CS) architecture with deep neural networks for gait recognition. In contrast, the proposed onboard gait analyzer is a standalone device with onboard processing capability specifically designed for children suffering from cerebral palsy (CP). The proposed device does not depend on external computational resources or cloud-based processing. The above referenced device uses fusion algorithm and deep neural network intelligent algorithm, whereas the proposed onboard gait analyzer device uses synchro squeezing transform based algorithm.
[009] Publication No. CN114176578 relates to the gait analyzer comprises flat cushion blocks, pressure detection plates and a controller, the top surfaces of the flat cushion blocks are planes, a plurality of flat cushion blocks are sequentially placed front and back to form a platform or a step, a plurality of pressure detection plates are respectively fixed on the top surfaces of the flat cushion blocks and are uniformly provided with a plurality of pressure sensors, and the controller is connected with the flat cushion blocks. And the controller is electrically connected with each pressure detection plate. The flat cushion blocks with the top faces being planes are sequentially arranged front and back to form various platforms or steps for a testee to walk, modular arrangement is achieved, the structure is flexible to adjust, infinite extension can be achieved, and then whether the testee can walk normally or climb stairs or not is judged; the pressure detection plate is mounted on the flat cushion block, so that the treading force of each point of the foot of the testee can be detected in real time, and whether the gait of the testee is normal or not can be judged in an auxiliary manner. The above referenced system relies on a modular pressure-sensing platform composed of cushion blocks and pressure detection plates to analyze gait by measuring foot pressure distribution and it requires a controlled environment where the subject walks on the structured platform to assess gait abnormalities, stair-climbing ability, and weight distribution. In contrast, the proposed onboard gait analyzer is a portable wearable single-device gait analyzer for children suffering from cerebral palsy that uses inertial measurement unit (IMU) data. The above referenced system uses pressure detection plates that are fixed within a specific environment whereas, the proposed onboard gait analyzer device is a lightweight, standalone system that does not require an external platform. It is a wearable and portable device that is attached to the L5 vertebra. Additionally, the proposed device features advanced hardware configurations and incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for efficient and secure communication.
[010] Publication No. CN211022692 relates to a gait analyzer suitable for the rehabilitation of children. Included are soft insoles, a connecting belt is fixedly mounted at the left end of the upper end of the soft insole; a wrist binding belt is fixedly mounted at the upper end of the connecting belt; a hook-and-loop fastener A is fixedly installed on the outer side of the wrist binding belt, a hook-and-loop fastener B is fixedly installed on the inner side of the wrist binding belt, a connecting base is fixedly installed at the right end of the upper end of the soft insole, an elastic binding belt is fixedly installed at the upper end of the connecting base, and a first installing base is fixedly installed at the position, located at the left front end of the connecting belt, of the upper end of the soft insole. The proposed onboard gait analyzer is a inertial measurement unit (IMU)-based wearable system attached to the L5 vertebra, capturing spatiotemporal gait parameters through motion kinematics. In contrast, the above referenced device relies on soft insoles with various binding belts, suggesting a foot-mounted system primarily focused on pressure-based gait assessment. The proposed onboard gait analyzer is suitable for indoor as well as outdoor scenarios without environmental constraints. In contrast, the above referenced device appears to be more rehabilitation-focused, requiring specific attachment mechanisms, which may limit its applicability to controlled environment. The proposed onboard gait analyzer integrates an IMU, processor, and SD card into a single compact PCB containing onboard processing capability whereas the above referenced device does not have onboard processing capability. The proposed device uses machine learning model for activity recognition whereas the above gait analyzer uses camera for detecting walking posture. The onboard gait analyzer device is specifically designed for children suffering from cerebral palsy (CP), and uses message queuing telemetry transport (MQTT) protocol where clients publish gait data as predefined topics via a broker.
[011] Publication No. CN109730686 relates to a gait detection analyzer based on a sensor array. The gait detection analyzer comprises a pressure sensor array, an inertial sensor unit, a processing device and a wireless communication module. The pressure sensor array is used for measuring pressure data of a foot sole of a user during movement; the inertial sensor unit is used for monitoring trajectory data of a foot in space during movement of the user; the processing device is used for processing the pressure data and the trajectory data to obtain gait data of the user; the wireless communication module is used for transmitting gait data to a server to enable the server to analyze and evaluate the gait data by means of preset algorithms. The above referenced device is designed solely for gait analysis and is not specifically tailored to address conditions like cerebral palsy (CP). The proposed onboard gait analyzer is a single device that relies on an inertial measurement unit (IMU) data, and calculates spatiotemporal gait parameters through motion kinematics. In contrast, the above referenced device employs a sensor array, integrating both pressure sensors for foot pressure mapping and inertial sensors for foot trajectory tracking, which adds complexity to the system. The proposed onboard gait analyzer is simpler, having low cost, and easier to deploy, whereas the above referenced system requires a pressure sensor array, foot trajectory tracking, and server-based processing, resulting in higher hardware complexity and cost. Additionally, the proposed device features onboard processing with machine learning for activity recognition, enabling real-time gait analysis without external dependency. In contrast, the referenced gait analyzer transmits gait data wirelessly to a server for cloud-based processing using preset algorithms. The proposed onboard gait analyzer eliminates the need for external computational resources or cloud-based processing, ensuring greater portability and independence. Furthermore, the proposed device is specifically designed for children with cerebral palsy (CP) and uses a single unit positioned at the L5 vertebra.
[012] Publication No. JP2018026018 relates to a gait analyzer capable of reducing an affection of a person who is made a background and a background which is made a person, and capable of accurately analyzing gait of a person. There is provided a gait analyzer for analyzing a gait of a person. The gait analyzer comprises: a GEI generation part; a derivation image generation part; a movement amount calculation part; and a feature amount calculation part. The GEI generation part overlaps plural first frames included in a first moving image in which a gait is captured, so that areas corresponding to a person are overlapped, for generating a first GEI (gait energy image). The proposed onboard gait analyzer performs onboard processing and uses a gait analysis module, distinct from the above system. The above referenced device relies on gait energy images (GEI) derived from video-based motion capture, requiring multiple frames from a recorded gait sequence to generate an overlapped representation of movement patterns. In contrast, the proposed onboard gait analyzer is a single-device solution that uses inertial measurement unit (IMU) data to calculate spatiotemporal gait parameters in real time, eliminating the need for external imaging systems. Another difference is that the above referenced device requires a camera-based setup, making it sensitive to environmental conditions such as lighting, occlusions, and background noise, which may impact accuracy. Whereas, the proposed onboard gait analyzer is wearable, lightweight, and suitable for both indoor and outdoor environment, so as to perform continuous gait monitoring. The above referenced system involves complex image processing techniques, including feature extraction from GEIs and movement amount calculations, requiring high computational power for accurate gait analysis. In contrast, the proposed onboard gait analyzer has onboard processing with machine learning-based activity recognition mdoule, ensuring efficient real-time gait assessment. The proposed device is specifically designed for children suffering from cerebral palsy (CP). The proposed device is positioned at the L5 vertebra of the children, offering a more direct measurement of body motion and gait characteristics compared to a camera-based system that analyses external movement projections. The proposed onboard gait analyzer is more cost-effective, compact, and portable, whereas the above referenced system requires specialized camera setups, controlled environment, and significant computational resources.
[013] Publication No. CN106955109 relates to a gait behavior recording analyzer, a method and a system. The gait behavior recording analyzer comprises two hardware boxes and a support accessory, wherein each hardware box comprises a main control panel as well as a three-dimensional accelerometer and a three-dimensional gyroscope which are connected with the main control panel; the support accessory is worn at waist of a human body; the two hardware boxes are mounted on two sides of the support accessory respectively. The proposed onboard gait analyzer is specifically designed for children suffering from cerebral palsy (CP). Unlike the above referenced device, which involves two hardware boxes, the proposed onboard gait analyzer uses a single unit positioned at the L5 vertebra. The above referenced device uses external resources to analyze gait whereas the proposed onboard gait analyzer provides onboard processing capability to compute gait parameters. The strategic placement at L5 vertebra allows for efficient monitoring of gait dynamics without adding any noise while minimizing hardware complexity. The quantum key distribution (QKD) methodology is also used in the proposed onboard gait analyzer to generate and exchange encryption keys, ensuring secure transmission.
[014] Publication No. US2014155786 relates to a canine gait analyzer is used in connection with a treadmill. A sensor assembly includes a plurality of overlapping sensor panels, each having a pressure transducer array connected to a circuit board with conductive traces. An elastomer sheet with carbon-graphite dampens the dog's pawsteps, and is electrically grounded for static electric charge. The sensor assembly is held fast between the belt inner surface and the treadmill bed with a J bracket. The sensor panel edge extends downward on the side of the frame. A C-shaped side cover is attached to the frame and covers the sensor panel edge having the circuit boards. A motor speed controller is connected to the motor, the circuit boards, and to a computer. The above referenced system is designed for usage within a laboratory environment, whereas the proposed onboard gait analyzer is specifically designed for the gait analysis of children suffering from cerebral palsy (CP) in any environment. The proposed device is attached to the L5 vertebra. It calculates spatiotemporal gait parameters using inertial measurement unit data. This proposed device features onboard processing capabilities, and incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) methodologies. The above referenced device incorporates a motor speed controller and computer-based processing, which relies on external hardware for analyzing gait data whereas the proposed onboard gait analyzer is a wearable device with onboard processing and machine learning-based activity recognition, allowing real-time analysis without requiring additional external computing resources. The above referenced device relies on a pressure transducer array embedded in a treadmill, which captures paw pressure and movement, whereas the proposed onboard gait analyzer uses data received from inertial measurement unit (IMU) to compute spatiotemporal gait parameters.
[015] Publication No. JP2013022188 relates to an accurate analysis of the gait of a user. A gait analyzer includes: an acceleration information reception part for time-sequentially receiving first acceleration data measured when a user walks; a smoothing processing part for performing smoothing processing to the first acceleration data; a walking cycle calculation part for performing frequency analysis to each of second acceleration data after the smoothing processing and the first acceleration data, extracting the candidate of a peak frequency from the power spectrum of the second acceleration data, detecting the peak frequency near the candidate from the power spectrum of the first acceleration data, and calculating the walking cycle T of the user by the peak frequency; an autocorrelation calculation part for calculating the autocorrelation function of the first acceleration data; and a peak detection part for detecting a peak in the autocorrelation function on the basis of the walking cycle T. The above device calculates gait information only during walking, while the onboard gait analyzer detects various activities, filters out non-walking activities, and then computes gait parameters. The above referenced device focuses on analysing walking cycles by using acceleration data, whereas the proposed onboard gait analyzer uses an inertial measurement unit (IMU)-based system to capture spatiotemporal gait parameters. Attached to the L5 vertebra, the proposed device performs onboard processing and uses a gait analysis module distinct from the above referenced system. The proposed device uses synchro-squeezing transform based algorithm which provides higher detection accuracy than the algorithm in the above referenced system.
[016] Publication No. US2010262046 relates to an apparatus for analyzing gait and balance to determine visual spatial distortion including a treadmill having a movable tread, at least a weight bearing sensor for measuring weight bearing pressure in right, left, front and rear directions provided under said tread and an analyzer for analyzing lean coupled to output of said weight bearing sensor. The above method describes an equipment for analyzing gait and balance using a treadmill with a movable tread and a weight-bearing sensor that measures pressure in different directions (right, left, front, and rear). In comparison, the proposed onboard gait analyzer is a single device for children suffering from cerebral palsy (CP) is designed for spatiotemporal gait parameters using an inertial measurement unit (IMU) data. The above referenced method relies on a treadmill setup with sensors integrated into the ground, making it suitable for controlled environment. In contrast, the proposed onboard gait analyzer device is portable and wearable, enabling continuous monitoring of gait without requiring specialized equipment or controlled environment. Moreover, the above referenced method focuses on balance assessment and lean analysis using pressure data, while the proposed onboard gait analyzer device uses an inertial measurement unit (IMU) and machine learning model to perform dynamic activity recognition and analyze spatiotemporal gait parameters such as velocity, stride time, and cadence. The proposed onboard gait analyzer features message queuing telemetry transport (MQTT) protocol and quantum key distribution (QKD) methodology for reliable and secure communication.
[017] Publication No. US7172563 relates to a walking gait detection apparatus includes a microphone for picking up low-frequency-band sounds that are transmitted through the body of a pedestrian while walking and an analyzer for performing analysis. Accordingly, the gait of the pedestrian is detected. It is also possible to distinguish the gait pattern on the basis of the stance-phase time of a foot sole and the signal intensity, for example. The gait detection apparatus can accurately estimate the stride length on the basis of a detected gait cycle, the height of the pedestrian, and signals detected during walking. The above referenced device analyzes the gait of pedestrians by capturing low-frequency band sounds, whereas the proposed onboard gait analyzer calculates spatiotemporal gait parameters using an inertial measurement unit. The proposed onboard gait analyzer is specifically designed for children suffering from cerebral palsy (CP). It provides a wearable solution that differs significantly in terms of both algorithm and design, emphasizing portability and real-time monitoring. It incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) methodologies for reliable and secure communication.
[018] Publication No. KR100546447 relates to a gait analyzer and a gait analysis method using the same to reduce the maintenance cost and the management cost by using a joint set and a computer device without installing an additional gait analysis room. A joint momentum measurement part includes a first joint sensor adhered to a hip joint, a second joint sensor adhered to a knee joint, and a third joint sensor adhered to an ankle joint. The first to the third joint sensors include a first rotary shaft, a second rotary shaft, a third rotary shaft, and a potentiometer in order to output analog data according to rotation angles and rotation directions of the hip joint, the knee joint, and the ankle joint. The proposed onboard gait analyzer is attached to the L5 vertebra of children, whereas the above referenced device is mounted on hip, knee, and ankle joint of the subject, requiring three devices, limiting its scalability and requiring more hardware. In contrast, the onboard gait analyzer operates with a single device, focusing on motion kinematics rather than joint-specific movements. The above referenced system uses a mechanical joint sensor setup with analog data output whereas, the proposed onboard gait analyzer uses data collected using inertial measurement unit (IMU). The proposed device is specifically developed for children suffering from cerebral palsy (CP).
[019] Publication No. JP2008161228 relates to a gait analysis system for three-dimensionally measuring the movement of the legs of a walker and measuring and analyzing the spatial movement of a swinging leg without putting loads on the walker undergoing rehabilitation. The gait analysis system is equipped with: a gait sensor mounted on one leg or both legs of the walker undergoing gait training rehabilitation for radio-outputting the detection data of at least one of an acceleration and an angular velocity; radio communication equipment for receiving the detection data; and a gait analyzer for calculating analysis items for the rehabilitation relating to the legs on the basis of the detection data acquired through the radio communication equipment. The above referenced system differs from proposed onboard gait analyzer device as it is designed specifically for rehabilitation. In contrast, the proposed onboard gait analyzer is primarily developed to calculate gait parameters of children suffering from cerebral palsy (CP) using a single device with onboard processing capabilities, making it distinct from the above referenced system. The above referenced system uses a gait sensor mounted on one or both legs of the user to measure acceleration and angular velocity during gait training rehabilitation. In contrast, the proposed onboard gait analyzer is a wearable device that uses an inertial measurement unit (IMU)-based system that computes spatiotemporal gait parameters without the need for multiple sensors on each leg. The above referenced system uses a radio communication system to send data to an external gait analyzer, which could introduce dependency on external hardware for processing. In comparison, the proposed onboard gait analyzer device offers onboard processing capability with the message queuing telemetry transport (MQTT) protocol to reduce packet loss and uses quantum key distribution (QKD) methodology for secure communication.
[020] Publication No. KR20240097196 relates to a smart gait analyzer based on a 9-axis inertial sensor, which comprises: a first sensor unit which is fixed to the waist, thigh, and lower leg of a pedestrian and detects an inertial signal including a 3-axis acceleration signal, a 3-axis gyro signal, and a 3-axis geomagnetic signal according to the movement of the pedestrian; a first support time calculation unit which calculates a left foot support time and a right foot support time of the pedestrian using the inertial signals detected by the first sensor unit; and a first balance determination unit which determines a difference in left and right balance of the body using the difference between the left foot support time and the right foot support time calculated by the first support time calculation unit. The proposed onboard gait analyzer is attached to the L5 vertebra of children and uses a single device, whereas the above referenced device with multiple sensors is mounted on waist, thigh, and lower leg of a pedestrian, requiring three devices. The proposed onboard gait analyzer is specifically used for children suffering from cerebral palsy (CP). The above referenced system focuses on balance and support time analysis, while the proposed device performs activity recognition and thereafter uses synchro squeezing transform-based algorithm to determine the spatiotemporal gait parameters. The proposed device uses message queuing telemetry transport (MQTT) protocol and quantum key distribution (QKD) for reliable data communication.
[021] Patent No. US11484710 relates to an apparatus, systems, and methods for real-time gait modulation. A functional electrical stimulation (FES) device is disclosed comprising one or more elastic wearable articles, a control unit comprising a wireless communication module, one or more processors, one or more memory units, a portable power supply, an electrical muscle stimulation (EMS) generator, and an inertial measurement unit (IMU) comprising at least a gyroscope. The FES device can also comprise one or more electrode arrays configured to be in physical contact with the limb of the user. The FES device involves one or more elastic wearables designed to be worn on the limbs of children, whereas the proposed onboard gait analyzer device is specifically attached to the L5 vertebra of the children. The data obtained from the L5 position is less noisy, and the device attached at this location is more stable. Additionally, the FES device is intended for use in conditions such as stroke, multiple sclerosis, and other similar conditions, while the proposed onboard gait analyzer device is exclusively designed for children suffering from cerebral palsy (CP). The components used for designing the PCB and the synchro-squeezing transform-based algorithm for the proposed onboard gait analyzer are entirely distinct from those used in the FES device. The proposed onboard gait analyzer analyzes gait using data collected with an inertial measurement unit (IMU).
[022] Patent No. US11660024 relates to methods for analyzing gait of a subject. In particular, the present invention relates to a method for analyzing gait of a subject, said method comprising: providing data representing the 3D-movement of a foot of said subject over time; identifying within said data first data segments that each represent of at least one stride; determining one or more stride features for each of said first data segments; and defining one or more clusters on the basis of at least one stride feature of said one or more stride features. Each of the defined clusters represents a class of strides, e.g. a class may represent the typical stride of a subject. The proposed onboard gait analyzer focuses on children suffering from cerebral palsy (CP) and uses a single unit positioned at the L5 vertebra. This strategic placement allows for efficient monitoring of gait dynamics without adding any noise while minimizing hardware complexity. The above referenced method focuses on analyzing gait by identifying stride segments from 3D movement data of the foot, determining stride features, and clustering strides into categories, allowing the identification of patterns in a subject’s walking behaviour. Whereas, the proposed onboard gait analyzer is a portable, wearable device gait analyzer for children suffering from cerebral palsy (CP) that uses inertial measurement unit (IMU) data to calculate spatiotemporal gait parameters. Furthermore, the proposed onboard gait analyzer device integrates message queuing telemetry transport (MQTT) for efficient communication and quantum key distribution (QKD) methodology to generate and exchange encryption keys, ensuring secure transmission.
[023] Publication No. US2021267492 relates to systems and methods for detecting a motor developmental delay and/or neurodevelopmental disorder of an infant are described herein. An example method can include receiving motion data associated with the infant's gross motor activity; analyzing, using a machine learning algorithm, the motion data to detect a kinematic feature; comparing the kinematic feature to an expected relationship between the kinematic feature and infant age; and detecting the neurodevelopmental disorder based on the comparison. The above referenced device calculates kinematic feature whereas the proposed onboard gait analyzer computes spatiotemporal gait parameters. The proposed device integrates IMU, processor, and SD card into a single compact chip. It is designed to be simpler, lightweight, and cost-effective, and has onboard processing capability. Further, it uses message queuing telemetry transport (MQTT) protocol where clients publish gait data as predefined topics via a broker. It is attached to the L5 vertebra of the children whereas the above referenced device is attached to the infant's thigh, shin, or foot.
[024] Publication No. US2024115159 relates to a method comprising: receiving, with respect to each of a plurality of subjects, data comprising at least one of: a data representing center of pressure (COP) of a subject during at least on gait phase; a data representing center of gravity (COG) of the subject during at least on gait phase; and; a data representing posture of the subject during at least on gait phase; processing the data to extract a plurality of features representing the data, at a training stage, training a machine learning model on a training set comprising all of the plurality of features; and at an inference stage, applying the trained machine learning model to a target set of the features obtained for target subject, to classify posture, proprioception and/or kinesthesis of the target subject. The above referenced system analyzes gait using COP and COG, whereas the proposed onboard gait analyzer analyzes gait using inertial measurement unit (IMU) data. The proposed onboard gait analyzer specifically addresses children suffering from cerebral palsy. It focuses on real-time processing on an onboard processor, incorporating message queuing telemetry transport (MQTT) and quantum key distribution (QKD) methodologies.
[025] Publication No. US2024268710 relates to a method for assessing movement of a body portion includes, via one or more machine learning models, analyzing a sensor signal indicative of movement of the body portion to determine a movement of the body portion; determining a sensor confidence level based, at least in part, on a characteristic of the sensor signal; receiving a series of images indicative of movement of the body portion; measuring an angle of movement of the body portion; determining a vision confidence level based, at least in part, on a quality of an identification the body portion; selecting the sensor signal, the measured angle of movement, or a combination thereof as an input into a machine learning model based on the sensor confidence level and the vision confidence level, respectively; analyzing the input to determine a movement pattern of the body portion; and outputting the movement pattern to a user. The above referenced method combines sensor signals and visual data to assess movement patterns whereas the proposed onboard gait analyzer relies solely on inertial measurement unit (IMU) data for gait analysis, eliminating the need for visual data or cameras. The above referenced method requires cameras, making it unsuitable for outdoor environments. In contrast, the proposed onboard gait analyzer is designed to be simpler, lightweight, and cost-effective, with onboard processing capabilities that enable operation in any environment using a single device. The above method focuses on precise movement patterns by leveraging multiple modalities, which involve high cost but the proposed device is a low-cost device, which uses spatiotemporal gait parameters for gait analysis of children suffering from cerebral palsy (CP). The proposed device integrates IMU, processor, and SD card into a single compact chip, which is conveniently attachable to a velcro belt. The proposed device employs onboard processing and a gait analysis module distinct from the above referenced system.
[026] Publication No. CN117731275 relates a walking information processing method and wearable equipment, which can be applied to the field of inertial sensing application. The method comprises the following steps: collecting walking information of a target object to obtain a first section of walking information, a second section of walking information and a third section of walking information which are sequentially arranged according to a collection time period; determining a linear included angle between a first straight route corresponding to the first section of walking and a second straight route corresponding to the third section of walking; in response to the fact that the angle value of the linear included angle is larger than or equal to a first preset angle threshold value, a target turning step of the target object is determined from the second section of walking of the target object according to the angular bisector of the linear included angle and the second section of walking information; and determining a turning step set of the target object from the second section of walking step according to the target turning step, the first straight-going route of the target object and the second straight-going route of the target object.
[027] The proposed onboard gait analyzer device is designed specifically for children suffering from cerebral palsy while the above referenced device is not designed for any specific disease. The above referenced device focuses on trajectory or turning steps, whereas onboard gait analyzer device measures spatiotemporal gait parameters, such as step length, cadence, and stride time, etc. It is equipped with onboard processing capability for activity recognition and gait analysis. The proposed device is lightweight, cost-effective, and suitable for both indoor and outdoor environments, unlike the referenced method, which may require more extensive data processing for trajectory-based analysis. The proposed device is attached to the L5 vertebra of the children suffering from cerebral palsy. The quantum key distribution (QKD) methodology is also used in proposed device to ensure secure transmission.
[028] Publication No. CN118557180 relates to a lower limb rehabilitation training monitoring system for a stroke patient and relates to the technical field of rehabilitation training. Real-time lower limb training data of a target user is dynamically monitored through wearable equipment; the data conversion module is used for converting the data to obtain a real-time training signal; reading a predetermined multi-domain fusion analysis scheme; performing feature analysis on the first training signal based on a predetermined multi-domain fusion analysis scheme to obtain first signal feature information; the first signal feature information is compared and evaluated through the signal comparison and evaluation module, a comparison and evaluation result is obtained and dynamically displayed to the rehabilitation feedback display, and the problems that the training efficiency is low, the training effect is poor, and the rehabilitation effect is poor due to the lack of real-time performance and pertinence for lower limb rehabilitation training monitoring of the stroke patient are solved. The above referenced system is designed for stroke patients undergoing rehabilitation while the proposed onboard gait analyzer is designed specifically for children suffering from cerebral palsy (CP). The above referenced system collects data from lower limb whereas the proposed device is attached at L5 vertebra of the children. The proposed device performs onboard data processing to extract gait parameters from the data collected using inertial measurement unit (IMU). The quantum key distribution (QKD) methodology is also used in proposed onboard gait analyzer device to ensure secure transmission.
[029] Publication No. CN112331300 relates to a cerebral palsy child knee-climbing joint collaborative motion analysis system based on an acceleration sensor, and the system comprises a joint motion acceleration collection device and a joint collaborative motion analysis module based on acceleration. The joint motion acceleration collection device comprises a device body and elastic bandages connected with the two sides of the device body and conveniently fixed to limb joints of children with cerebral palsy, and an acceleration acquisition module, a single-chip microcomputer module, a display module, a wireless transmission module and a power module are integrated on the device body. The above referenced device attaches to limb joints, whereas the proposed onboard gait analyzer is attached to the L5 vertebra which ensures device stability and less noise. The above referenced system focuses on joint motion analysis during knee-crawling, while the proposed onboard gait analyzer is specifically designed for gait analysis of children suffering from cerebral palsy (CP). The proposed onboard gait analyzer also incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for secure communication.
[030] Publication No. CN108338790 relates to a human body gait assessment system, which comprises a nine-axis inertial sensor, a signal transmission unit and an assessment unit, wherein the nine-axis inertial sensor is used for measuring linear acceleration data, angular velocity data and object inclination angle data of a three-dimensional space; the plurality of data is acquired by the inertial sensor by conducting measurement at a certain time interval; the signal transmission unit is used for transmitting the plurality of data to the assessment unit; and the assessment unit is in charge of judging pace states of a human body by calculating accumulated values of data in a left-right direction, so as to measure fall risks, and the assessment unit, via a mode of searching the maximum value in the various processed data, can predict the fall direction; therefore, the system is accurate in assessment mode and simple in calculation; and the system is especially applicable to patients with cerebral palsy. This device calculates gait information only during walking, while the proposed onboard gait analyzer detects various activities, filters out non-walking activities, and then computes gait parameters. Attached at the L5 vertebra, the proposed onboard gait analyzer employs onboard processing and a gait analysis module distinct from the above system. The proposed onboard gait analyzer is a lightweight, portable wearable solution using a synchro squeezing transform based algorithm, differing from the algorithm in the above system. While the above reference system focuses on pace states and fall risk, the proposed device focuses on spatiotemporal gait parameters like step length, stride length, etc. for gait analysis. In addition, the proposed onboard gait analyzer also incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for secure communication.
[031] Publication No. IN202441071540 relates to an AI-enhanced wearable walking aid designed to assist individuals with mobility impairments by providing adaptive support, real-time gait analysis, and predictive fall prevention. The device consists of a wearable exoskeleton frame fitted with a sensor suite, including inertial measurement units, pressure sensors, and proximity sensors, that monitor the user's movements and environment in real time. The data is processed by an AI-powered control unit, which analyzes gait, posture, and balance to dynamically adjust mechanical support mechanisms embedded in the device. The invention includes predictive fall prevention technology, capable of identifying potential fall risks and responding with corrective actions, such as activating mechanical stabilizers or providing user alerts. This AI-based sensor suit for assessing fall risk is entirely different from the proposed onboard gait analyzer, which is specifically designed for children with cerebral palsy (CP). The above referenced device requires the person to wear an exoskeleton suite whereas the proposed device is simply attached to the L5 vertebra of children. Further, the above referenced device is more suitable for controlled environment due to usage of pressure sensors whereas the proposed device can be used in indoor as well as free living environment. The proposed gait analyzer also features onboard processing capabilities, incorporating message queuing telemetry transport (MQTT) and quantum key distribution (QKD) methodologies.
[032] Publication No. IN202341026949 relates to a system and method for predicting neurodegenerative diseases using human gait analysis. The system includes wearable sensors for capturing gait data, a data processing unit for extracting gait parameters, and a machine learning module for analysing the gait data. The system further includes a gait scoring module for calculating a gait score based on a reference database of gait parameters associated with neurodegenerative diseases, a prediction module for predicting the likelihood of a subject developing a neurodegenerative disease, and an abnormal gait identification module for identifying specific gait abnormalities indicative of neurodegenerative diseases. The system also includes a longitudinal monitoring module for tracking changes in gait characteristics over time. The proposed onboard gait analyzer is specifically designed for children suffering from cerebral palsy (CP). In comparison to the above referenced device, the proposed device has onboard processing capability to perform gait analysis in real time without any external computational resources. Further, the use of message queuing telemetry transport (MQTT) and quantum key distribution (QKD) ensures reliable data transmission while the device is attached to the L5 vertebra.
[033] The article entitled “An accessible training device for children with cerebral palsy” by Guoqing Wan, Hsieh-Chun Hsieh, Chien-Heng Lin, Hung-Yu Lin, Chien-Yu Lin, and Wen-Hsin Chiu; IEEE Transactions On Neural Systems And Rehabilitation Engineering, Vol. 29, March 8, 2021 talks about the Walking and balance capabilities can be improved upon using repetitive ankle dorsiflexion exercises. Here we developed two types of pedal switches incorporated with training devices to improve their walking and balance performance of children with cerebral palsy. The first type of pedal switch can be used to operate a home appliance, while the second type of pedal switch can connect them to web games. Pedal switches can be used for home rehabilitation. This randomized controlled trial included patients in the intervention (n = 24) and control (n = 24) groups who completed 15 weeks of ankle training. The experimental group performed ankle dorsiflexion using a pressure-activated pedal switch connected to the web games. The control group performed ankle dorsiflexion exercises using a pedal switch that operated a home appliance (a fan). Standing balance and walking performance were estimated using the Zebris FDM system, a pressure force platform, the Pediatric Balance Scale score, and the 1-minute walk test. The pre- and posttest data were analyzed using analysis of variance and analysis of covariance, which revealed that the intervention group had more significant improvements in sway patterns and balance and walking. The developed facility of a modified pedal switch integrated with web games can achieve better exercise adherence to promote balance and walking performance than that with home appliances. Maintaining motivation in children with cerebral palsy plays a very important role in the rehabilitation process. The above referenced system uses two pressure-activated pedal switches for rehabilitation whereas the proposed onboard gait analyzer uses IMU data for calculating the spatiotemporal gait parameters, such as step length, cadence, stride duration, etc. The proposed device is a standalone, light weight, wearable device that performs both activity recognition and gait analysis in real time. This device integrates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for reliable and secure data transfer. The above referenced pedal switch-based training method is intended for controlled home-based rehabilitation, requiring an external platform. Whereas the proposed device can be used in any free-living environment.
[034] The article entitled “A-gas: A probabilistic approach for generating automated gait assessment score for cerebral palsy children” by Rishabh Bajpai; Deepak Joshi; IEEE Transactions On Neural Systems And Rehabilitation Engineering, Vol. 29; August 15, 2021 talks about the gait disorders in children with cerebral palsy (CP) affect their mental, physical, economic, and social lives. Gait assessment is one of the essential steps of gait management. It has been widely used for clinical decision making and evaluation of different treatment outcomes. However, most of the present methods of gait assessment are subjective, less sensitive to small pathological changes, time-taking and need a great effort of an expert. This work proposes an automated, comprehensive gait assessment score (A-GAS) for gait disorders in CP. Kinematic data of 356 CP and 41 typically developing subjects is used to validate the performance of A-GAS. For the computation of A-GAS, instance abnormality index (AII) and abnormality index (AI) are calculated. AII quantifies gait abnormality of a gait cycle instance, while AI quantifies gait abnormality of a joint angle profile during walking. AII is calculated for all gait cycle instances by performing probabilistic and statistical analyses. Abnormality index (AI) is a weighted sum of AII, computed for each joint angle profile. A-GAS is a weighted sum of AI, calculated for a lower limb. Moreover, a graphical representation of the gait assessment report, including AII, AI, and A-GAS is generated for providing a better depiction of the assessment score. Furthermore, the work compares A-GAS with a present rating-based gait assessment scores to understand fundamental differences. Finally, A-GAS’s performance is verified for a high-cost multi-camera set-up using nine joint angle profiles and a low-cost single camera set-up using three joint angle profiles. Results show no significant differences in performance of A-GAS for both the set-ups. Therefore, A-GAS for both the set-ups can be used interchangeably. The above referenced article proposes a method for scoring gait disorder which can be used in any hardware set-up. Whereas this article proposes an algorithm for gait assessment, the proposed invention is a portable wearable gait device focusing on real-time gait monitoring and secure data transmission. The proposed onboard gait analyzer provides immediate feedback, whereas the above referenced method is designed for post-processing and clinical evaluation. The proposed onboard gait analyzer device relies on inertial measurement unit (IMU) data, integrates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for secure wireless transmission of gait data, ensuring privacy and real-time accessibility whereas the above referenced method does not address data security concerns, as it primarily focuses on statistical and probabilistic gait assessment using stored datasets.
[035] The article entitled “Abnormal gait classification in children with cerebral palsy using ConvLSTM hybrid model and GAN” by Yelle Kavya; S. Sofana Reka; IEEE Access (Volume: 12); 07 August 2024 talks about the abnormal gait patterns are a common feature of Cerebral Palsy, a neurodevelopmental disease for which early identification is essential for treatment. In the proposed research, a novel methodology is provided for classifying abnormal gait patterns in children with Cerebral Palsy, using gait analysis as a diagnostic tool. To improve gait classification accuracy and efficiency, a hybrid model of Convolutional Long Short-Term Memory (ConvLSTM) model and Generative Adversarial Network (GAN) is used in the suggested technique. This study concentrated on temporal signal data, using hypothetical planes with minimal regard for anatomical indicators. The reduction technique enables a more efficient and successful gait analysis. Heatmap images were created from the selected temporal data. GAN generated images were added to the dataset in order to overcome the problems caused by class imbalance and guarantee a thorough depiction of abnormal gait patterns. In the work, a ConvLSTM-based model with a batch size of 32, training as well as validation datasets were evaluated over a period of 50 epochs. The effectiveness of the suggested model was compared to other models such as Gated Recurrent Unit, Convolutional Neural Network, and Long Short-Term Memory model that were trained using the same input data. Our suggested ConvLSTM model produced an impressive accuracy of 91.8% and a loss of 0.42. The Convolutional Long Short Term Memory model performed better than the other models when compared based on a number of criteria, including accuracy, precision, recall, and F1-score. The performance measures demonstrate how well our method works to classify the abnormal gait in kids with Cerebral Palsy. In contrast to heat maps used in the above reference, the proposed onboard gait analyzer uses IMU data to compute gait parameters. While the above referenced system requires a 3D motion capture system which compels a fixed setup for operation, the proposed solution is lightweight, wearable, and provides greater flexibility for operation in any free living environment. The above referenced study focuses on the classification task whereas the proposed device provides a complete system integrating activity recognition and gait analysis modules. The proposed onboard gait analyzer enables continuous tracking, while the research paper emphasizes offline classification. The proposed onboard gait analyzer directly collects motion data from the inertial measurement unit (IMU), processes it onboard, and transmits results securely, whereas the above study uses temporal gait signals transformed into heatmap images, which are then processed by deep learning models, making it dependent on pre-collected datasets. Further, the proposed onboard gait analyzer integrates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for secure data transfer, ensuring privacy and real-time accessibility.
[036] The article entitled “The pediatric smart shoe: wearable sensor system for ambulatory monitoring of physical activity and gait” by Nagaraj Hegde; Ting Zhang; Gitendra Uswatte; Edward Taub; Joydip Barman; Staci McKay; IEEE Transactions on Neural Systems and Rehabilitation Engineering (Volume: 26, Issue: 2); February 2018 talks about the cerebral palsy (CP) is a group of nonprogressive neuro-developmental conditions occurring in early childhood that causes movement disorders and physical disability. Measuring activity levels and gait patterns is an important aspect of CP rehabilitation programs. Traditionally, such programs utilize commercially available laboratory systems, which cannot to be utilized in community living. In this study, a novel, shoe-based, wearable sensor system (pediatric Smart Shoe) was tested on 11 healthy children and 10 children with CP to validate its use for monitoring of physical activity and gait. Novel data processing techniques were developed to remove the effect of orthotics on the sensor signals. Machine learning models were developed to automatically classify the activities of daily living. The temporal gait parameters estimated from the Smart Shoe data were compared against reference measurements on a GAITRite mat. A leave-one-out cross-validation method indicated a 95.3% average accuracy of activity classification (for sitting, standing, and walking) for children with CP and 96.2% for healthy children. Average relative errors in gait parameter estimation (gait cycle, stance, swing, and step time, % single support time on both lower extremities, along with cadence) ranged from 0.2% to 6.4% (standard deviation range = 1.4%-9.9%). These results suggest that the pediatric Smart Shoe can accurately measure physical activity and gait of children with CP and can potentially be used for ambulatory monitoring. The above referenced study uses smart shoe that integrates multiple sensors into footwear whereas, the proposed onboard gait analyzer is attached to the L5 vertebra of children using velcro belt, ensuring more device stability and comfort. The above referenced study uses pressure and accelerometer sensors, whereas the proposed device uses accelerometer and gyroscope sensors for activity recognition. The proposed device has onboard processing capability to perform gait analysis in real time without any dependence on external/cloud based computational resources. Further, it incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for secure wireless data transmission.
[037] In order to overcome the challenges of the above listed prior art, the present invention provides a light-weight, portable, and wearable device for gait analysis of children suffering from cerebral palsy (CP).
OBJECTS OF THE INVENTION:
[038] The principal object of the present invention is to provide a light-weight, portable, and wearable device for gait analysis of children suffering from cerebral palsy.
[039] Another objective is that the device works as a standalone unit featuring an activity recognition model and a gait analysis module, and incorporates the MQTT protocol and QKD methodologies, and is conveniently attached to the L5 vertebra using a velcro belt.
[040] Another object of the present invention is that the device features machine learning based onboard processing capability to remove dependence on external computational resources or cloud-based processing.
SUMMARY OF THE INVENTION:
[041] The present invention relates to designing a light-weight, portable, and wearable device for gait analysis of children suffering from cerebral palsy (CP).
[042] The device includes a processor, an IMU (accelerometer and gyroscope), Bluetooth, an SD card module, a voltage regulator, a boost converter, a USB charging circuit, and a battery. The device has an onboard processor with a machine learning model for activity detection, and a gait analysis module. The device also supports the message queuing telemetry transport (MQTT) protocol.
[043] The wearable device technology for gait analysis provides cost-effective and accurate assessment of gait abnormalities outside traditional lab environment. Its portability and use of wearable sensors make it accessible and scalable for remote healthcare applications, aligning with the increasing demand for telemedicine and personalized rehabilitation solutions. Its integration with IoT systems and advanced analytics make it a competitive product in the growing smart healthcare market, targeting both clinical and consumer segments.
[044] The proposed onboard gait analyzer is designed for continuous real-time tracking and cloud integration, allowing remote accessibility. It is a compact, standalone, and battery-operated wearable device that enables continuous gait monitoring, and is attached to the L5 vertebra of the children.
BREIF DESCRIPTION OF THE INVENTION
[045] It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered for limiting of its scope, for the invention may admit to other equally effective embodiments.
[046] Figure 1 illustrates the functional architecture of proposed onboard gait analyzer.
[047] Figure 2 shows the schematic diagram of the proposed onboard gait analyzer.
[048] Figure 3 shows the flowchart of the gait analysis algorithm used in the proposed onboard gait analyzer.
[049] Figure 4 shows the side view of the 3D assembly box.
[050] Figure 5 shows the top, bottom and inner view of the 3D assembly box.
DETAILED DESCRIPTION OF THE INVENTION:
[051] The present invention provides a light-weight, portable, and wearable device for gait analysis of children suffering from cerebral palsy (CP).
[052] Referring to Figure 1, the device includes a microcontroller (1), an IMU (2) consisting of accelerometer (3), gyroscope (4), Bluetooth (5), an SD card module (6), and a power supply (7) consisting of voltage regulator (8), a boost converter (9), a USB charging circuit (10), and a battery (11). The device has a control unit (12) with a machine learning model for activity detection, and a gait analysis module. The device supports the message queuing telemetry transport (MQTT) protocol.
[053] The device features a microcontroller module supporting bluetooth low energy (BLE) communication for seamless wireless data transfer. It serves as the main controller, managing and coordinating the operation of other components. Equipped with a processor with Flash memory and RAM, it enables efficient computation and processing tasks. Additionally, it can simultaneously handle sensor data processing and wireless communication between the microcontroller and external devices like smartphones or computers.
[054] The device features a sensor module that combines an accelerometer and a gyroscope. The accelerometer measures linear acceleration along the X, Y, and Z axes, making it useful for detecting movement. The gyroscope measures angular velocity, aiding in the tracking of rotational motion. The sensor module is integrated with a microcontroller that performs onboard signal processing on the raw data collected through the sensors.
[055] Voltage regulator is a step-down DC-DC converter module designed to convert high input voltage into a lower, stable output voltage suitable for the microcontroller and other components. It ensures reliable system operation by maintaining consistent power delivery, even during input voltage fluctuations. Additionally, it operates efficiently, minimizing power loss during the voltage conversion process.
[056] The SD card module acts as a storage interface for logging data, enabling the collection of sensor data for backup. It supports large storage capacities, making it suitable for handling extensive datasets generated from continuous gait monitoring. The module integrates seamlessly with the microcontroller, facilitating the recording of spatiotemporal gait parameters and IMU data.
[057] A step-up DC-DC converter module that increases a lower input voltage to a higher output voltage for components requiring elevated power levels. It ensures the battery's output voltage is boosted as needed, enhancing the system's operational flexibility and efficiency.
[058] A single-cell Li-ion/Li-polymer battery charger integrated circuit that provides a safe and efficient method for charging a battery through a universal serial bus (USB) connection. It manages current regulation, voltage regulation, and charge termination to prevent overcharging and ensure battery protection. This compact and power-efficient solution is ideal for effective battery management.
[059] A rechargeable lithium-ion or lithium-polymer battery serves as the primary power source for the entire system. It provides a voltage supply to the microcontroller, sensors, and other components, ensuring reliable operation. The battery enhances the device's portability, enabling it to function independently without requirement of an external power supply.
[060] The battery acts as the primary power source, providing energy to the system while ensuring portability. It supplies power to the charging module, which manages the safe recharging of the battery by regulating the voltage and current, preventing overcharging or damage. The battery also powers the step-up converter, which boosts its voltage to 5V, suitable for components requiring higher operational power. The voltage regulator then steps down this 5V to a stable 3.3V, which is essential for the reliable operation of the IMU, processor, and memory.
[061] The sensor module, combining accelerometer and gyroscope, collects data such as acceleration and angular velocity. This data is transmitted to the processor via I2C communication, which ensures efficient and seamless data transfer and thereafter the data is saved in the SD card. The processor, equipped with onboard memory, retrieves pre-stored algorithms to process this raw data and generate spatiotemporal gait parameters. The memory is also used to temporarily store intermediate and processed data, enabling efficient computations.
[062] Once the gait parameters are computed, the processor wirelessly transmits the results to an Android application using Bluetooth Low Energy (BLE), an energy-efficient feature integrated into the processor. The Android app displays the processed gait data in real time, offering insights into parameters like stride length and gait speed. Additionally, the app facilitates uploading of the data to the cloud when connected to the internet, ensuring remote accessibility and secure long-term storage. It incorporates message queuing telemetry transport (MQTT) and quantum key distribution (QKD) for efficient and secure communication.
[063] Firstly, the raw accelerometer and gyroscope data captured by the accelerometer and gyroscope undergoes pre-processing using a 4th-order low-pass Butterworth filter with a sampling frequency of 33 Hz and a cutoff frequency of 15 Hz. This filter removes all frequencies greater than 15 Hz, effectively eliminating high-frequency noise. A convolutional neural network (CNN)-based model is then employed for activity recognition and classification. The model is a sequential convolutional neural network that processes 132 samples of accelerometer data from the x, y, and z axes at the specified 33 Hz sampling rate. The input layer of the model has a shape of 80 × 3 × 1, where the three dimensions correspond to the three axes of accelerometer data.
[064] The activity recognition model identifies and classifies the activity while filtering out any data unrelated to walking. Once the walking activity data is isolated, it undergoes a coordinate transformation from the body frame to the earth frame to align the data with a global reference. The filtered accelerometer data is then integrated to calculate the velocity. However, during integration, small error biases inherent in accelerometer readings can accumulate, leading to drift, a phenomenon where the calculated velocity deviates significantly from the true value over time. Drift correction is therefore essential to maintain the accuracy of the velocity data.
[065] To analyze gait events, the synchro-squeezing transform (SST) is applied to the velocity data for detecting minima points, also known as Initial Contacts (ICs). After detecting ICs, the velocity is integrated again to compute position data. As with velocity, position data is prone to drift due to accumulated errors during integration, necessitating drift correction to ensure accurate position estimation. Subsequently, the SST is applied once more to detect maxima points in the gait cycle, referred to as Final Contacts (FCs). Using both IC and FC points, an inverted pendulum model is employed to calculate step length, stride length, and other spatiotemporal gait parameters. These parameters provide valuable insights into gait patterns, enabling detailed gait analysis of children suffering from cerebral palsy.
[066] In the inverse pendulum model, the body is approximated as an inverted pendulum pivoting about the stance foot during the single-support phase of walking. It effectively describes how the center of mass (CoM) moves in an arc-like trajectory. To reduce noise, the device is positioned close to the CoM, providing stability and ensuring precise measurements. This stability enables accurate calculation of gait parameters such as step length and stride length.The system balances local processing for immediate results and cloud-based data storage for extended functionality. This ensures usability in both connected and offline environments.
[067] Methods:
[068] The Synchro-Squeezing Transform (SST) is a powerful time-frequency analysis tool used in gait analysis to extract precise features from non-stationary signals. By enhancing the resolution of time-frequency representation, the SST provides detailed insights into the variability and dynamics of gait. It is particularly effective in identifying subtle changes in walking patterns. Using the SST, the initial and final contact points are identified from velocity and position data, respectively.
[069] Drift correction is a crucial step in gait analysis to address error caused by sensor drift, which accumulates over time due to noise or integration error. By applying drift correction techniques, such as zero-velocity updates or filtering, the accuracy of position and velocity data is significantly improved. This ensures that gait parameters like step length, stride length, and walking speed are computed reliably. Proper drift correction enhances the precision of spatial-temporal measurements, making it essential for accurate gait analysis.
[070] Message queuing telemetry transport (MQTT) is a lightweight communication protocol used for the devices with limited power resources. It uses publish/subscribe architecture for data communication. The proposed device acts as a publisher, transmitting messages to a broker, while android application functions as a subscriber, receiving and processing relevant data. This architecture facilitates efficient two-way communication for device management, control, and seamless data exchange.
[071] In gait analysis, Quantum Key Distribution (QKD) enhances the security of sensor data transmission by using quantum physics principles, such as the no-cloning theorem and uncertainty principle, to securely exchange encryption keys. The QKD ensures the detection of potential intrusions by identifying changes in quantum states, safeguarding sensitive gait data. Additionally, ASCON-128, a lightweight cipher, is used for encrypting and decrypting gait data in resource-constrained wearable devices. It provides data confidentiality and integrity with minimal computational complexity and memory overhead while offering strong resilience against cryptographic attacks. Together, QKD and ASCON-128 establish a secure and efficient framework for transmitting gait data.
[072] Numerous modifications and adaptations of the system of the present invention will be apparent to those skilled in the art, and thus it is intended by the appended claims to cover all such modifications and adaptations which fall within the true spirit and scope of this invention.
, C , Claims:WE CLAIM:
1. A wearable device for gait analysis of children suffering from cerebral palsy (CP) comprising of-
a. Low-energy Bluetooth (5) and microcontroller (1) equipped with onboard processor and memory to store the sensor data, algorithms and spatiotemporal gait features.
b. Sensing module (2) consisting of accelerometer (3) and gyroscope (4) to capture the linear acceleration and orientation inputs, respectively.
c. Micro SD card module to store data (6).
d. Direct current (DC) boost converter (9) to increase the voltage.
e. Voltage regulator (8) for consistent power supply.
f. Switch and light emitting diode (LED).
g. Battery (11) with micro-USB port (10) to charge the battery.
2. The wearable device, as claimed in claim 1, wherein the device is attached to the L5 vertebra of the children using a velcro belt.
3. The wearable device, as claimed in claim 1, wherein the system is powered by lithium-ion battery, boosted to 5V via a converter and regulated to 3.7V for sensor module which integrates accelerometer and gyroscope, connects to the microcontroller for data acquisition.
4. A wearable device, as claimed in claim 1, comprising of activity recognition module and gait analysis module.
5. A wearable device, as claimed in claim 1, is a standalone gait analyzer with onboard machine learning based processing capability for activity recognition.
6. A wearable device, as claimed in claim 1, transmits the data and spatiotemporal parameters to the cloud through an Android application.
7. A wearable device, as claimed in claim 1, wherein the device acts as a message queuing telemetry transport (MQTT) client to publish gait data as predefined topics via a broker, and an Android application subscribes to receive the data, enabling publish-subscribe based communication.
8. A wearable device, as claimed in claim 1, wherein quantum key distribution (QKD) is used to generate encryption keys, ensuring secure and tamper-evident data transmission between the device and an Android application.