AU2021102703A4

AU2021102703A4 - IoT-BASED SYSTEM AND METHOD FOR FALL DETECTION IN ELDERLY OR PD PEOPLE BY THE MEANS OF SMARTPHONE

Info

Publication number: AU2021102703A4
Application number: AU2021102703A
Authority: AU
Inventors: Pratik Bhattacharjee; Suparna Biswas; Rajesh Bose; Samiran Chattopadhyay; Chandreyee Chowdhury; Sandip Roy
Original assignee: Biswas Dr Suparna; Bose Dr Rajesh; Chattopadhyay Dr Samiran; Chowdhury Dr Chandreyee; Roy Dr Sandip
Current assignee: Biswas Dr Suparna; Bose Dr Rajesh; Chattopadhyay Dr Samiran; Chowdhury Dr Chandreyee; Roy Dr Sandip
Priority date: 2021-05-20
Filing date: 2021-05-20
Publication date: 2021-11-04
Anticipated expiration: 2029-05-20

Abstract

The present disclosure relates to an IoT based system and method for fall detection in elderly or PD people by the means of Smartphone. In the present disclosure an onboard 3 axis accelerometer (BMI160) of a Smartphone device is used. The accelerometer collects the real time data from various movements. The values from sensor are then analyzed by the live fall detection module. When a fall is detected, an immediate alert is generated, the alert is sent to the monitoring screen along with long beep and the same alert is sent to the relative as a text message using a SMS gateway service. The SMS includes the date, time and the location of the fall. The proposed system showed the overall accuracy of 94.45% and after the 4th week of experimentation, 93% of the patients showed improvement in their confidence level as well. 13 100 102 sending the data from a mobile device to a monitoring module sending a GPS coor inate from the Smartphone to a raspberry-pi server 104 pre-processing andanalyzing the data by a fall detection module extracting theaddress ofthe subject using a Google location service 108 integrating a warning message, date, timeandfall location by a integration module inside a monitoring station 4, 112 sending a warning on the screenalong with long beep. 1 1 Figure1 200 Data acquisition module 202 Livefallig detection module 204 GPS module 206 Integ ration module 208 Figure 2

Description

102 sending the data from a mobile device to a monitoring module

sending a GPS coor inate from the Smartphone to a raspberry-pi server 104

pre-processing andanalyzing the data by a fall detection module

extracting theaddress ofthe subject using a Google location service 108

integrating a warning message, date, timeandfall location by aintegration module inside a monitoring station

4, sending a warning on the screenalong with long beep. 1 112 1

Figure1

200

Data acquisition module 202 Livefallig detection module 204

GPS module 206 Integ ration module 208

Figure 2

IoT-BASED SYSTEM AND METHOD FOR FALL DETECTION IN ELDERLY OR PD PEOPLE BY THE MEANS OF SMARTPHONE

FIELD OF THE INVENTION

The present disclosure relates to an IoT based system and method for fall detection in elderly or PD people by the means of Smartphone.

BACKGROUND OF THE INVENTION

One of the vital healthcare aspects for senior adults and person with movement problems is fall. In a report it was found that the fall is one of the major causes of unintentional or accidental injury leading to death worldwide. Fall can be cause of injury and on the top of that late medical help may further worsen the situation.

MEMS (Micro Electromechanical systems) sensors are used in wearable devices for the simplification of design of sensor-based systems. Location based system can be used to locate the person during the health issue, to give the medical help as soon as possible.

It was found that about 38% to 87% PD patients have falls and due to that they have faced serious injuries such as fractures, loss of consciousness, and sometimes death. The fall may induce a fear of fall into their mind as well, which can lead to, increase in dependency, depression and social isolation. This shows the importance of fall prevention, which turned out to be one of the primary requirement in PD.

There are two type of fall detection system, one is image based and the other is sensor based. The sensor based system is gaining more popularity because of its benefits such as, providing privacy aware, Cost-effective, light weight, and fast solutions. In some cases Finite state machine (FSM) may be used for fall and ADL classification based on a KNN classifier.

The image based fall detection devices gives good accuracy due to various types of capturing devices but they usually suffer from delay due to the transmission of images through network for the analysis of a fall and these kind of devices also compromised the privacy of the subject.

In one existing solution, a device was developed using a non-ambulatory method. The device uses five pressure sensor at five points mounted on the shoe of the subject. The device provides a good accuracy and can also be implemented in IoT platform

In another existing solution, a small sized, low cost detection method was proposed that used the single vector magnitude (SVM) and Google API (to identify the outdoor location) and this method showed accuracy of 82%.

In another existing solution, a system was proposed in which fine grained fall detection is possible. The fast fall detection system was based on accelerometer and gyroscope using the TEMPO 3.0 system. However in this system the subject has to carry an additional device which elderly people may forgot to carry. These types of systems with accelerometer and gyroscope can detect the fall in any direction with up to 98% accuracy, but the Smartphone is kept in the chest pocket of the subject during the test which may not be appropriate because subject can be a heart patient with pacemakers or device can fall when the subject may lean forward.

In another existing solution, a hidden markov chain is used that can detect and predict the fall using MEMS tri-axis accelerometer MMA7260Q. But the location information along with the fall detection warning and distinguishes between the falls like activities were not considered in this solution. The UHF-RFID tag based device independent architecture is a good option for indoor environment where chances of fall are higher. One such model was proposed in another existing solution, in this model several tags has been put in different positions of the room to record the movement of the subject. The model uses a threshold based method for fall detection in indoor using RSSI. The model showed an accuracy of 91.5%. In another existing solution a prototype is used to monitor the ADL of senior adults. Sometimes the near fall event can indicate the future expected fall and a wearable sensor may be used to record such events To classify between the real fall and fall alike event appropriate filter should be used to remove the noise from the initial data, and the data should be classified with proper care. The PD patient usually suffers from freezing of gait (FoG), MEMS like MPU6050 having an integrated 3 axis accelerometer and 3 axis gyroscope may be used to analyze and detect a gait and alert to prevent the possible fall by using the standard deviation method. In another existing solution a Smartphone based detection techniques has been implemented using built in accelerometer and gyroscope.

In one prior art solution (US20200170548A), a method of gait data collection has been proposed, the method comprising collecting movement data, determining from the data a movement parameter that includes a third order derivative of position, comparing the movement parameter with a threshold value, and counting at least a near fall if the movement parameter exceeds the threshold value.

In another prior art solution (US10531817B2), the invention relates to a fall detection method and system. The fall detection method comprises: receiving Wi-Fi signal stream propagating through an environment; determining a physical CSI stream; determining a CSI phase difference; and determining according to the CSI streams and the CSI phase difference stream, a fall event.

In another prior art solution (US9058736B2), an apparatus for detection of human falls comprises: an acceleration detector for detecting vibration events; a microphone for detection of corresponding sound events; and a classification unit to classify concurrent events from the microphone and accelerometer detector. If the event appears to be a human fall, then a alarm is raised.

However, some of the recent relevant works fail to address the issue such as: unresponsiveness of the device after a fall; only the warning of critical non self recovery fall is sent to the relative/s and the event of self recovery fall stored in the system for future reference. The stored information can be used by the clinical experts; text based complete address specification within the warning SMS so that the receivers phone does not require internet connectivity to track the location on map; remote storage of data and processing for reliability and post analysis even without the internet. Therefore there is a need for an IoT based system and method for fall detection in elderly or PD people by the means of Smartphone.

SUMMARY OF THE INVENTION

The present disclosure relates to an IoT based system and method for fall detection in elderly or PD people by the means of Smartphone. The present disclosure proposes a smart threshold based FDS using a smart phone on board 3-axis accelerometer (BMI106) having a nominal computational overhead. The accelerometer helps in real time data collection from various moments of elder people and the sensor values are captured and analyzed by a threshold based model that runs on a smart IoT gateway. The developed system can distinguish among the normal motion, fell but recovered, and fell but not recovered states. Whenever a non self recovery fall is detected the system will generate a warning message and sends appropriate notification to the relative or caregiver of the elder person. The processing part is done by Raspberry Pi 4 which is a portable device and capable of implementing post processing algorithm and supports built in Wi-Fi and Bluetooth connectivity. The fall data is stored to make it available in future for clinical purposes. The proposed system is capable of detecting fall based on the last received data from broken device, without waiting further. The system sends complete address of the fallen subject along with the warning message instead of the link which requires the internet connectivity to point out the location of the Google map. The experimentation was performed over 4 weeks, taking feedbacks after every 7 th day, on 30 PD patients with different level of severity of the disease. The 75 trail are performed in the outdoor and 75 indoor. The proposed disclosure showed the overall accuracy of 9 4 .4 5 % and after the 4th week 93%of the patients showed improvement in their confidence level.

The present disclosure seeks to provide an IoT based method for fall detection in elderly or PD people by the means of a Smartphone. The method comprises: sending the data from a mobile device to a monitoring module; sending a GPS coordinate from the Smartphone to a raspberry-pi server; pre-processing and analyzing the received data by a fall detection module; extracting the address of the subject using a Google location service; integrating a warning message, date, time and fall location by a integration module inside a monitoring station; and sending a warning on the screen along with long beep.

The present disclosure also seeks to provide an IoT-Based system for fall detection in elderly or PD people by the means of Smartphone. The system comprises: a data acquisition module responsible for collection of a raw acceleration data from a Smartphone sensor; a live falling detection module responsible for cleaning and analyzing the data received from the Data acquisition module using a single vector magnitude to detect the fall; a GPS module responsible for mapping the address with the co-ordinates returned by a Smartphone GPS; and an integration module responsible for fetching the location from the GPS module in the case of a true fall response from the live fall detection module and generates the appropriate warning and SMS in addition to record the event locally.

An objective of the present disclosure is to provide an IoT based system and method for fall detection in elderly or PD people by the means of Smartphone.

Another object of the present disclosure is to use Raspberry Pi 4 for processing.

Another object of the present disclosure is to use an onboard 3-axis accelerometer (BMI160) of a Smartphone device to help in real time data collection.

Another object of the present disclosure is to capture and analyze the sensor values using threshold based model which is running on a smart IoT gateway.

Another object of the present disclosure is to immediately alert the relative/caregiver whenever a fall without self recovery is detected.

Another object of the present disclosure is to send appropriate notification to the relative as a text message whenever a fall is detected

Another object of the present disclosure is to store the fall data for making it available to the clinical person for further analysis.

To further clarify advantages and features of the present disclosure, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.

BRIEF DESCRIPTION OF FIGURES

These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

Figure 1 illustrates a flow chart of an IoT based method for fall detection in elderly or PD people by the means of Smartphone in accordance with an embodiment of the present disclosure;

Figure 2 illustrates a block diagram of an IoT based system for fall detection in elderly or PD people by the means of Smartphone in accordance with an embodiment of the present disclosure.

Figure 3 illustrates the system architecture in accordance with an embodiment of the present disclosure;

Figure 4 illustrates End-To-End workflow of the proposed FDS in accordance with an embodiment of the present disclosure;

Figure 5 illustrates a table of overall summary of the output in accordance with an embodiment of the present disclosure;

Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have been necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help to improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having benefit of the description herein.

DETAILED DESCRIPTION

For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the drawings and specific language will be used to describe the same. It will nevertheless be understood that no limitation of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein being contemplated as would normally occur to one skilled in the art to which the invention relates.

It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be restrictive thereof.

Reference throughout this specification to "an aspect", "another aspect" or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such process or method. Similarly, one or more devices or sub-systems or elements or structures or components proceeded by "comprises...a" does not, without more constraints, preclude the existence of other devices or other sub-systems or other elements or other structures or other components or additional devices or additional sub-systems or additional elements or additional structures or additional components.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The system, methods, and examples provided herein are illustrative only and not intended to be limiting.

Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.

Figure 1 illustrates a flow chart of an IoT based method for fall detection in elderly or PD people by the means of Smartphone in accordance with an embodiment of the present disclosure. At step 102 the method 100 includes, sending the data from a mobile device to a monitoring module, the mobile device carries stamped 3-axis values of an accelerometer data to a Raspberry Pi based monitoring station. The data is collected for three scenarios i.e. normal walking, fall but recovered in which no warning is generated but event gets recorded, and fall and not recovered in which audio-visual warning is generated.

At step 104 the method 100 includes, sending a GPS coordinate from the Smartphone to a raspberry-pi server. The Raspberry-Pi based monitoring system acts as both storage and processing unit. The monitoring station clean, process and analyses the acceleration data sent by the Smartphone.

At step 106 the method 100 includes pre-processing and analyzing the data by a fall detection module. The fall detection module analyzes the live stream-based on a 3-phase detection algorithm and generates warning whenever a fall without self recovery is detected.

At step 108 the method 100 includes extracting the address of the subject using a Google location service. The address is extracted with the help of Raspberry-Pi server which receives the GPS coordinates by the Smartphone.

At step 110 the method 100 includes, integrating a warning message, date, time and fall location by a integration module inside a monitoring station.

At step 112 the method 100 includes, sending the warning on the screen along with long beep. The same warning is also sent to the relatives as a text message using the SMS gateway service. The SMS may have multiple recipients.

Figure 2 illustrates a block diagram of an IoT based system for fall detection in elderly or PD people by the means of Smartphone in accordance with an embodiment of the present disclosure. The system 200 includes a data acquisition module 202 responsible for collection of a raw acceleration data from a Smartphone sensor.

In an embodiment, a live falling detection module 204 is responsible for cleaning and analyzing the data received from the Data acquisition module using a single vector magnitude to detect the fall.

In an embodiment, a GPS module 206 is responsible for mapping the address with the co ordinates returned by a Smartphone GPS. The module is invoked only when the fall is detected or there is a break of the device.

In an embodiment, an integration module 208 is responsible for fetching the location from the GPS module in the case of a true fall response from the live fall detection module and generates the appropriate warning and SMS in addition to record the event locally.

Figure 3 illustrates the system architecture in accordance with an embodiment of the present disclosure. The system consists four main modules: Data acquisition module; Live fall detection module; GPS module; The integration module.

Data acquisition module: This module resides in monitoring station, consisting of a local storage and is module is responsible for collection of raw acceleration data through the Smartphone sensor, and stores the data locally to forward it to live fall detection and other modules.

Live fall detection module: this module cleans and analyzes the data received from the data acquisition module using signal vector magnitude to detect a possible fall.

GPS module: This module maps the address with the coordinates returned by the Smartphone GPS. This module is only invoked when a fall or break of the device is detected.

The integration module: This module is responsible for fetching the location from the GPS module when a fall is detected and generates the appropriate warning and SMS and record the event locally.

Figure 4 illustrates End-To-End workflow of the proposed FDS in accordance with an embodiment of the present disclosure. The Smartphone carriers the raw live 3 axis accelerometer data to the Raspberry Pi based monitoring module station, the monitoring station acts as both data storage and processing unit. The connectivity between the monitoring station and Smartphone is established either via cellular data when roaming outdoor or via a Wi-Fi when roaming indoor. The received data is then analyzed by the fall detection module. The Smartphone also sends the location coordinates to the monitoring station and the address is then extracted using the Google location services. The fall detection module analyzes the accelerometer data and generates warning whenever a fall without self recovery is detected. The integration module is then integrates the warning messages, date-time, and fall location. The warning message is then sent on the screen along with the long beep and also sends a text message to the relative.

Figure 5 illustrates a table of overall summary of the output in accordance with an embodiment of the present disclosure. The experimentation was performed over 4 weeks taking the feedback after every 7 th day, on PD patients. The results were averages for each person and each activity to obtain the final results. 75 trial were performed in the outdoor and same for the indoor. The overall results showed the accuracy of 94.45% and the formula used for calculating the accuracy is: Accuracy = (Correct interpretation / Number of trials) * 100

The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.

Claims

WE CLAIM

1. An IoT-Based method for fall detection in elderly or PD people by the means of a Smartphone, the method comprises of:

sending the data from a mobile device to a monitoring module; sending a GPS coordinate from the Smartphone to a raspberry-pi server; pre-processing and analyzing the data by a fall detection module; extracting the address of the subject using a Google location service; integrating a warning message, date, time and fall location by a integration module inside a monitoring station; and sending a warning on the screen along with long beep.

2. The method as claimed in claim 1, wherein the said mobile device carries stamped 3-axis values of an accelerometer data to a Raspberry Pi based monitoring station.

3. The method as claimed in claim 1, wherein the said data is collected for three scenarios i.e. normal walking, fall but recovered in which no warning is generated but event gets recorded, and fall and not recovered in which audio-visual warning is generated.

4. The method as claimed in claim 2, wherein the said raspberry-pi based monitoring station acts as both storage and processing unit. The monitoring station cleans, processes and analyses the acquired acceleration data from Smartphone.

5. The method as claimed in claims 1, wherein the said fall detection module analyze the live stream-based on a 3-phase detection algorithm and generates warning whenever a fall without self-recovery is detected.

6. The method as claimed in claim 1, wherein the said address is extracted by the Raspberry-Pi server after receiving the GPS coordinates by the Smartphone.

7. The method as claimed in claim 1, wherein the said warning has been also sent to the relatives as a text messages using a SMS gateway service.

8. An IoT-Based system for fall detection in elderly or PD people by the means of Smartphone, the system comprises of:

a data acquisition module responsible for collection of a raw acceleration data from a Smartphone sensor; a live falling detection module responsible for cleaning and analyzing the data received from the Data acquisition module using a single vector magnitude to detect the fall; a GPS module responsible for mapping the address with the co-ordinates returned by a Smartphone GPS; and an integration module responsible for fetching the location from the GPS module in the case of a true fall response from the live fall detection module and generates the appropriate warning and SMS in addition to record the event locally.

9. The system as claimed in claim 7, wherein the data acquisition module also stores the raw acceleration data locally in addition to forwarding them live, to other modules.

10. The system as claimed in claim 7, wherein the said GPS module is invoked only when a fall is detected or there is a fall or break of the device.

11. The system as claimed in claim 7, wherein the said integration module also generates the warning and SMS (single or group) if there is a fall and break of the device.