IoT-Enabled Smart Glove for Enhanced Elderly Care: A Health Monitoring Solution

doi:10.21203/rs.3.rs-4956656/v1

With the growing elderly population, ensuring consistent and reliable healthcare monitoring has become increasingly important. This research introduces an innovative solution in the form of a smart glove designed specifically for elderly care. The glove is equipped with advanced features such as fall detection, emergency messaging via hand gestures, and vital signs monitoring, including oxygen saturation (SpO2) and heart rate.The smart glove integrates the MPU6050 and MAX30100 sensors with Arduino and ESP8266 modules to achieve these functionalities. Fall detection is accurately identified by the MPU6050 sensor, while the MAX30100 sensor monitors SpO2 and heart rate. Hand gestures are recognized and interpreted for sending emergency messages. Data from these sensors are transmitted through IFTTT, enabling alerts and notifications via SMS, email, and a secured website, thus facilitating real-time remote monitoring and communication.This setup provides a comprehensive and reliable method for monitoring the health and safety of elderly individuals, ensuring prompt response and care in emergencies. The proposed system demonstrates significant potential in enhancing the quality of life for elderly individuals by offering a smart, integrated, and user-friendly healthcare solution.

Internet of things

Elderly care

Fall detection

Smart glove

SpO2

Heart Rate

The rapid advancement of technology is driving the shift towards a modern civilization, with the Internet of Things (IoT) being one of the latest innovations. IoT facilitates the efficient exchange of large volumes of data, enabling remote monitoring and control of various objects. Its applications are especially prevalent in the medical field. This study presents a smart glove powered by IoT, specifically designed for the elderly. The glove addresses key eldercare challenges by detecting falls, monitoring vital signs like heart rate and SpO2, and sending emergency alerts through hand gestures.

According to the World Health Organization (WHO), falls are the second leading cause of accidental or unintentional fatalities worldwide [1]. Approximately 6 million people are affected by fatal falls, with a significant 80% of these incidents occurring in low and middle-income countries. Among the elderly population, an alarming 37.3 million cases involve falls severe enough to require medical intervention. The lack of comprehensive healthcare infrastructure and specialized medical professionals in remote and rural regions underscores the urgent need for affordable, rapid, and effective strategies to detect falls promptly. These strategies could include both resource-efficient infrastructure improvements and autonomous, expert-driven systems. Focusing on the fall detection feature, when an elderly individual experiences a fall, the sensor integrated within the smart glove immediately identifies the incident. This data is then sent to a microcontroller, which employs a Wi-Fi module to transmit an alert message and email to a mobile device via a web-based service.

A major concern is the rising aging population, a trend observed over the past decade and anticipated to continue for the next twenty years due to increased life expectancy and decreasing fertility rates [2][3]. As individuals grow older, their bodies become more vulnerable to various age-related conditions such as hypertension, heart failure, coronary artery disease, high blood pressure, and diabetes [4]. Monitoring key vital signs—heart rate, blood pressure, respiration rate, temperature, and peripheral capillary oxygen saturation (SpO2)—is crucial, with SpO2 being particularly significant as inadequate oxygen levels can lead to irreversible damage to vital organs [5]. Low SpO2 readings are associated with higher risks of morbidity and mortality. To address this issue, a wearable device has been proposed to monitor SpO2 and heart rate in real-time for the elderly, thereby enhancing emergency readiness related to oxygen and heart rate. Specifically, a smart glove has been developed to track these vital health parameters using sensors and a microcontroller. The collected data is wirelessly transmitted and displayed in real-time on websites, Google Sheets, and an LCD screen, thereby improving emergency preparedness and response.

Effective communication is crucial to our daily lives, especially in a world where a significant portion of the population includes elderly and disabled individuals who may face difficulties with speaking and mobility. In recent decades, innovations such as electric wheelchairs and hand signals have significantly enhanced the quality of life for those with physical impairments [6][7][8]. These technologies offer valuable mobility solutions for individuals with both upper and lower body disabilities. Research indicates that 466 million people worldwide experience profound deafness and limited abilities, constituting 6% of the global population [9]. Of these, 75 million individuals require wheelchairs, which equates to about 1% of the world's population. To address the communication challenges faced by these individuals, a practical solution has been developed: a handglove equipped with a specialized emergency alert sensor. This sensor enables users to send messages through directional hand gestures—forward, backward, right, and left—similar to traditional hand signals. These gestures activate the transmission of messages via email and mobile devices, and also display the messages on an LCD screen, thus facilitating effective communication and emergency alerting.

A considerable amount of research has focused on detecting and preventing falls among the elderly, as seen in studies [10] and [11]. Various approaches have been explored to detect falls, involving a range of sensors and methods [12][13][14]. However, the use of multiple sensors can increase costs and add complexity for elderly users. Much of the research in this area has concentrated on platforms such as Arduino and MSP430 [11][12][15][16]. Relevant literature includes studies on processing SpO2 and heart rate data [17–18], the advancement of IoT wearable health devices [19–20], and the use of the MAX30100 sensor [21–22]. Additionally, the application of IoT in healthcare, including Electrocardiogram (ECG) monitoring [23] and blood pressure measurement [24], has been extensively discussed. Some reports have also explored integrating multiple health parameters into a single system [25]. Recent research efforts have increasingly focused on aiding individuals with disabilities. For example, Hossain et al. [26] developed an AI-based intelligent robot to assist autistic children with communication and mobility. Gomez-Donoso et al. introduced a multi-sensor wheelchair designed for people with disabilities, while Shayban et al. [27] proposed a head gesture device for wirelessly controlling wheelchairs, addressing the limitations of traditional joystick controls. Current research [28][29][30] on robotic wheelchairs highlights various challenges [31][32][33]. Mahbuba Alam et al. [34] presented a wearable gesture-controlled robot that uses motion sensors and machine learning for accurate gesture recognition. An intelligent wheelchair [35] designed for quadriplegic patients incorporates sensors for self-navigation and obstacle detection. Prannah et al. [36] proposed a smart wheelchair with navigation capabilities that utilizes head gestures and an accelerometer sensor for controlled movement.

This study introduces an IoT-based smart handglove, which acts as a multifunctional solution to three key challenges encountered by the elderly. Rigorous testing was conducted to guarantee its reliable functionality, utilizing diverse platforms to exhibit results and address problems. In situations where the elderly fall or require assistance with tasks like going to the bathroom or getting water, the handglove sends instant email notifications for aid, functioning seamlessly even without an internet connection, and dispatching alerts to mobile devices. Furthermore, a purpose-built website has been established to showcase essential health metrics like heart rate and oxygen saturation, complemented by the availability of this data on a Google Sheet. This inventive solution particularly advantages individuals residing in rural areas by negating the necessity to travel for checkups and diminishing the reliance on full-time caregiving services. This innovative system significantly reduces the financial burden associated with frequent checkups, transportation costs to attend appointments, and the hiring of a caretaker. The ultimate aim is to furnish an uncomplicated, financially viable remedy to the three pivotal hurdles confronted by the elderly, thereby guaranteeing outcomes of commendable quality. The main objective of this work is to offer a straightforward and cost-effective solution to three significant challenges faced by the elderly, ensuring high-quality outcomes.

The remainder of the paper is structured as follows: Section 2 details the materials and method used for developing the smart glove, including the integration of sensors and communication modules. Section 3 presents the results and analysis, focusing on the system's performance in fall detection and vital signs monitoring. Finally, Section 4 concludes the paper and suggests potential future work to enhance the system's functionality.

The purpose of this system is to design a smart handglove through which various crucial health factors of elderly people can be measured. It also detects falls and sends emergency messages through hand gestures. In this section, an elaborate explanation of the methodologies and materials utilized in this study is presented. The first subsection introduces the block diagram of the proposed system.

2.1. Block Diagram

The block diagram of the proposed system is depicted in Fig. 1. The identification of falls among senior citizens is executed through the utilization of the mpu6050 sensor. Then, the microcontroller and wifi module collaborate to disseminate this vital information to a predetermined recipient's mobile device, thereby facilitating timely SMS and email notifications. Furthermore, an integrated buzzer system has been ingeniously integrated, primed to trigger in the regrettable scenario of the falling of the elderly individual.For initiating an emergency message, the patient will perform a specific hand gesture in the desired direction. This action will then be detected by the mpu6050 sensor, triggering the transmission of notifications to a designated person's mobile device through SMS and email. Utilizing the Max30100 sensor enables the monitoring of heart rate and oxygen saturation (spo2) in the elderly. This sensor collects the essential data, which is then transmitted to both a dedicated website and a Google Sheet through the microcontroller. Subsequently, this data is forwarded via the wifi module for transmission. Furthermore, the data can conveniently visualized on the LCD screen, which offers a user-friendly interface for clear information.

The flowchart outlines a system that monitors falls and hand movements. The process begins with the initialization of the MPU6050 sensor, which captures motion data. A Wi-Fi connection is then established to enable data transmission. The system continuously checks for falls and hand movements in a loop. Upon detecting a fall, the system triggers a multi-step response: an audible alert sounds, an LCD displays a visual alert, and notifications are sent to caretakers via the internet. For hand movements, the data is displayed on the LCD and shared online. This system ensures constant monitoring and timely responses to incidents.

Table 1: Description of the components.

Components

Description

Hand glove

Arduino UNO

MPU6050

MAX30100

ESP 8266

LCD Display

Bread Board

Buzzer

Switch

Jumper Wire

A hand glove is used to operate this system.

The Arduino Uno is a microcontroller board that utilizes the Microchip ATmega328P microcontroller (MCU). It offers digital and analog input/output (I/O) pins – 14 digital and 6 analog. This board is programmable using the Arduino IDE and can be powered through a USB cable connection accommodating 7 to 20-volt voltages.

The MPU6050 module functions as a motion tracking device containing a 3-axis accelerometer and 3-axis gyroscope, enabling measurement of acceleration, velocity, displacement, and other motion-related parameters for objects.

The MAX30100 serves as a comprehensive solution for pulse oximetry and heart rate monitoring, integrating optimized optics, a photodetector, dual LEDs, and precise analog signal processing.

The ESP8266 is a microchip that integrates built-in TCP/IP networking software and operates as both a microcontroller and a Wi-Fi-enabled device.

LCDs, extensively used in electronics, visually convey information and status; the LCD16x2 type specifically shows 2 lines with 16 characters.

A breadboard serves as a platform for creating prototypes of electronic circuits.

A buzzer is an auditory device that transforms audio patterns into sound signals

A push button switch is an apparatus utilized for managing an electrical circuit

A jumper wire is an electrical cable utilized to link distant electric circuits in printed circuit boards.

This research project is structured into three key sections: fall detection, hand gesture communication, and monitoring of oxygen saturation (SpO2) and heart rate levels. The system employs an Arduino Uno microcontroller to interface with a WiFi network, processing input data from a specially designed hand glove. The collected data is transmitted to the authorized caregiver via email and SMS. For real-time visualization, the results are also displayed on an LCD screen. The subsequent sections detail the methodology for implementing each of these functions.

2.2 Fall Detection

To accomplish the task, the MPU6050 sensor, which integrates both a gyroscope and an accelerometer, is utilized. This sensor module features a 3-axis accelerometer and a 3-axis gyroscope. The gyroscope determines orientation, while the accelerometer provides data on angular parameters along the X, Y, and Z axes. To detect a fall, the magnitude of acceleration is compared to a predefined threshold. The fall detection signal from the MPU6050 sensor is transmitted to an Arduino UNO microcontroller connected to the sensor. The Arduino UNO then sends a signal to an ESP8266, which processes the information and forwards it to IFTTT.

IFTTT, which stands for "If This Then That," operates over WiFi to send messages through its web service. It utilizes conditional statements, known as applets, to automate tasks. In the event of a fall, IFTTT applets trigger notifications, sending both email and SMS alerts to caregivers. Additionally, the fall detection message is displayed on an LCD screen, and a buzzer sounds to alert when a fall is detected. This system provides a straightforward approach to monitoring elderly individuals.

2.3. Emergency message with hand gesture

The MPU6050 sensor facilitates the transmission of emergency messages through hand gestures. Functioning as both an accelerometer and a gyroscope, it measures rotational movement across three axes, detects gravitational acceleration, and captures various motion parameters. Using the accelerometer capability of the MPU6050, elderly individuals can convey four critical messages by moving their hands in specific directions: forward, backward, right, and left.

For example, a rightward hand motion sends a "Need Food" message, while a leftward wave communicates "Need Water." Moving the hand forward indicates "Emergency Help Coming," and a backward motion signals "Call Attendee." The MPU6050 sensor transmits these directional signals to the ESP8266 when the hands move in any specified direction. The NodeMCU ESP8266 then connects to WiFi and forwards the messages to the IFTTT web service. Through IFTTT, the elderly person's message is efficiently sent to the caregiver's phone via SMS and email.

2.4. SpO2 and heart rate monitoring

Firstly, a complete circuit is built to monitor both SpO2 and heart rate. The MAX30100 sensor is employed to carry out the measurements. To facilitate this, an open-source customizable microcontroller board called Arduino Uno is linked to the Max30100 sensor. Concurrently, the NodeMCU ESP8266 microcontroller is utilized to establish a connection between the Arduino Uno and to gather data from elderly patients. It's important to note that the NodeMCU ESP8266 operates as a WiFi module, enabling the transmission of data to the online platform.

The information gathered from the sensor can be accessed in two manners: one involves using a website, and the other entails utilizing Google Sheets. Additionally, the collected data will also be visible on an LCD screen. The data will be levelled within a Google Sheet, after which it will be directed to the website. This setup permits authorized individuals like doctors, caregivers, and family members of elderly individuals to view previous records of oxygen saturation (SpO2) and heart rate readings. The website is password protected, limiting entry to those mentioned above. This comprehensive system allows for real-time remote monitoring of the health status of elderly patients by medical caregivers.

2.5. Cost of Materials.

The project’s development and production focused on achieving a cost-effective and affordable price, as detailed in Table 2. By applying innovative design techniques, the total system cost is kept at 22.50 USD, ensuring an economical solution. The costs for acquiring the materials needed for the device construction are thoroughly described in Table 2. The goal was to set a competitive price of 22.50 USD, providing excellent value. Table 2 offers a comprehensive breakdown of the overall expenses.

Table 2

Cost of the components.
Component	Model	Quantity	Price (USD)
Microcontroller	Arduino UNO	1	9
Accelerometer Gyroscope	MPU6050	1	2
Heart Rate and Oximeter Pulse Sensor	Max 30100	1	3
WiFi Module	ESP 8266	1	3
LCD Display	16X2 I2C	1	2.50
Buzzer	AUD-00002	1	1
Switch		1	1
Hand glove		1	1.50
Bread Board		1	1.50
Jumper Wire		10 × 3	1
Total Cost			22.50

This section discusses the system developed for this research and summarizes the results achieved. The setup comprises an MPU6050, a heart rate sensor, and an oximeter pulse sensor, all interfaced with an Arduino Uno microcontroller. The Arduino Uno, powered through a USB connection to a device, receives data from the sensors. This data is then transmitted to the Arduino and displayed on various platforms using a Wi-Fi module. It can be viewed on the Arduino IDE's serial monitor, a website, received via email, sent as text messages to mobile devices, recorded in a Google Sheet, and shown on an LCD screen. Figure 5 illustrates a detailed diagram of the entire system.

In Figure 6, the Arduino IDE's serial monitor displays information related to fall detection, with the data sourced from the MPU6050 sensor. In Figure 7, if an elderly person experiences a fall, the MPU6050 sensor will detect it, and the message "Emergency Help Coming" will be displayed on the LCD screen, controlled by the Arduino Uno microcontroller. Additionally, the LCD shows the output when different hand gestures are made to convey emergency messages. For instance, when an elderly person gestures their hand glove to the left, it signals a need for water; when moved to the right, it indicates a request for food; and when moved forward, it signifies an urgent requirement. The MPU6050 sensor detects these gestures, prompting corresponding messages on the LCD screen.

Figure 8 shows that when an elderly person falls, the MPU6050 sensor detects it, and the fall event is communicated to a designated person's mobile device via the ESP8266 WiFi module. In Figure 9, it is demonstrated that the elderly person can send important messages to specific contacts by making directional hand gestures, with the IFTTT applet being used to send these emails.

In Figure 10, the heart rate and SpO2 data are displayed on the Arduino IDE's serial monitor, with the information gathered from the MAX30100 sensor. Figure 11 presents the heart rate and oxygen saturation (SpO2) readings on the LCD screen.

A website has been established to enable specific individuals to remotely monitor crucial health metrics such as oxygen levels and heart rate, regardless of their physical distance. Figure 12 displays the login page of the website, which is fully secured with a password. Only the designated individual is permitted access, ensuring complete protection from unauthorized users. In figure 13, a different patient dashboard is displayed. Figure 14 shows a patient's health data for a full month. The datasheet for this includes reference ranges for both healthy and unhealthy conditions. Data collection for system validation will involve five groups of subjects: normal, abnormal, mild hypoxemia, moderate hypoxemia, and severe hypoxemia. This data will be used as a reference, in accordance with Health Regulation [5]. In Figure 15, it is demonstrated that a particular individual can observe the patient's health data remotely by utilizing Google Sheets.

Table 3: Comparison with other work.

No	Name	Fall Detection	Message with hand gesturing	Heart rate	SpO2	Data in website	Data in SMS	Data in Email	Data in Google Sheet	Data in LCD
1	This Paper	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes
2	Ref[6]	No	Yes	No	No	No	Yes	Yes	No	No
3	Ref[11]	Yes	No	No	No	No	Yes	No	No	No
4	Ref[13]	Yes	No	No	No	No	Yes	No	No	No
5	Ref[30]	No	No	Yes	Yes	Yes	No	No	No	No
6	Ref[34]	No	No	Yes	No	No	Yes	No	No	Yes

The research focused on the development of a smart glove system aimed at enhancing elderly care through real-time monitoring and emergency response features. This study integrated MPU6050 and MAX30100 sensors with Arduino and ESP8266 modules to achieve fall detection, vital signs monitoring (including SpO2 and heart rate), and emergency communication via hand gestures. Data transmission was facilitated through IFTTT, allowing for alerts and notifications to be sent via SMS, email, and a secured website. The smart glove system addresses critical challenges in elderly care by providing a reliable and comprehensive tool for monitoring and responding to health emergencies. The integration of advanced sensors and real-time communication mechanisms enhances safety and enables timely medical intervention. This system represents a substantial improvement in remote healthcare monitoring, potentially reducing risks and improving the quality of life for elderly individuals. The implementation of this smart glove system marks a significant advancement in elderly care technology. Future research will be essential for further refining the system, expanding its capabilities, and conducting extensive field evaluations to assess its effectiveness in various real-world environments. This ongoing development will contribute to the continued improvement of healthcare solutions for the elderly, addressing their unique needs and enhancing their overall well-being. In future research or developments, it is possible to integrate new algorithms. In upcoming efforts, a variety of additional sensors can be integrated to measure various health metrics, and alternative microcontrollers may also be considered for implementation.

Funding

The authors did not receive support from any organization for the submitted work.

Competing interests

The authors declare that they have no competing interests.

Availability of data and materials

Our prototype and its modules are confidential

Authors’ contributions

All authors read and approved the final manuscript.

Vieira, E. R., da Silva, R. A., Clemson, L., & Smith, M. L. (2022). Falls. Encyclopedia of Gerontology and Population Aging (pp. 1766–1775). Springer International Publishing.
Nor, N. N. F. M., & Ghazali, S. (2021). Malaysia towards an ageing country. Geografia, 17(3), 234–245.
Hu, B. D. C., Fahmi, H., Yuhao, L., Kiong, C. C., & Harun, A. (2018, August). Internet of Things (IOT) monitoring system for elderly. In 2018 International Conference on Intelligent and Advanced System (ICIAS) (pp. 1–6). IEEE.
Wang, Z., Yang, Z., & Dong, T. (2017). A review of wearable technologies for elderly care that can accurately track indoor position, recognize physical activities and monitor vital signs in real time. Sensors (Basel, Switzerland), 17(2), 341.
Bagha, S., & Shaw, L. (2011). A real time analysis of PPG signal for measurement of SpO2 and pulse rate. International journal of computer applications, 36(11), 45–50.
Sabuj, B., Islam, M. J., & Rahaman, M. A. (2019, December). Human robot interaction using sensor based hand gestures for assisting disable people. In 2019 International Conference on Sustainable Technologies for Industry 4.0 (STI) (pp. 1–5). IEEE.
Mahmood, M., Rizwan, M. F., Sultana, M., Habib, M., & Imam, M. H. (2020, June). Design of a low-cost hand gesture controlled automated wheelchair. In 2020 IEEE Region 10 Symposium (TENSYMP) (pp. 1379–1382). IEEE.
Jameel, H. F., Mohammed, S. L., & Gharghan, S. K. (2020, February). Wheelchair control system based on gyroscope of wearable tool for the disabled. In IOP Conference Series: Materials Science and Engineering (Vol. 745, No. 1, p. 012091). IOP Publishing.
Wagner, L. (2021). Disabled people in the world in 2019: Facts and figures. Retrieved from Inclusive City Maker website: https://www.inclusivecitymaker.com/disabled-people-in-the-world-in-2019-facts-and-figures
Chaccour, K., Darazi, R., Hassani, E., A. H., & Andres, E. (2016). From fall detection to fall prevention: A generic classification of fall-related systems. IEEE Sensors Journal, 17(3), 812–822.
Yacchirema, D., De Puga, J. S., Palau, C., & Esteve, M. (2018). Fall detection system for elderly people using IoT and big data. Procedia computer science, 130, 603–610.
Aziz, O., Klenk, J., Schwickert, L., Chiari, L., Becker, C., Park, E. J., & Robinovitch, S. N. (2017). Validation of accuracy of SVM-based fall detection system using real-world fall and non-fall datasets. PLoS one, 12(7), e0180318.
Ajerla, D., Mahfuz, S., & Zulkernine, F. (2019). A real-time patient monitoring framework for fall detection. Wireless Communications and Mobile Computing, 2019(1), 9507938.
Sterling, D. A., O’connor, J. A., & Bonadies, J. (2001). Geriatric falls: injury severity is high and disproportionate to mechanism. Journal of Trauma and Acute Care Surgery, 50(1), 116–119.
Bersch, S. D., Chislett, C. M., Azzi, D., Khusainov, R., & Briggs, J. S. (2011, May). Activity detection using frequency analysis and off-the-shelf devices: Fall detection from accelerometer data. In 2011 5th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops (pp. 362–365). IEEE.
Kostopoulos, P., Nunes, T., Salvi, K., Deriaz, M., & Torrent, J. (2015, October). F2D: A fall detection system tested with real data from daily life of elderly people. In 2015 17th International Conference on E-health Networking, Application & Services (HealthCom) (pp. 397–403). IEEE.
Li, Q., Stankovic, J. A., Hanson, M. A., Barth, A. T., Lach, J., & Zhou, G. (2009, June). Accurate, fast fall detection using gyroscopes and accelerometer-derived posture information. In 2009 sixth international workshop on wearable and implantable body sensor networks (pp. 138–143). IEEE.
Jia, N. (2009). Detecting human falls with a 3-axis digital accelerometer. Analog Dialogue, 43(7), 1–7.
Biroš, O., Karchnak, J., Šimšík, D., & Hošovský, A. (2014, January). Implementation of wearable sensors for fall detection into smart household. In 2014 IEEE 12th International Symposium on Applied Machine Intelligence and Informatics (SAMI) (pp. 19–22). IEEE.
Erdogan, S. Z., & Bilgin, T. T. (2012). A data mining approach for fall detection by using k-nearest neighbour algorithm on wireless sensor network data. Iet Communications, 6(18), 3281–3287.
Wu, F., Zhao, H., Zhao, Y., & Zhong, H. (2015). Development of a wearable-sensor‐based fall detection system. International journal of telemedicine and applications, 2015(1), 576364.
Li, Y., Chen, G., Shen, Y., Zhu, Y., & Cheng, Z. (2012, October). Accelerometer-based fall detection sensor system for the elderly. In 2012 IEEE 2nd international conference on cloud computing and intelligence systems (Vol. 3, pp. 1216–1220). IEEE.
Shuo, C. (2015, May). Fall detection system using arduino fio. In Proceedings of the IRC Conference on Science, Engineering and Technology, Singapore (Vol. 13).
He, Y., Li, G. F., Zhao, Y. P., Sun, Y., & Jiang, G. Z. (2018). Numerical simulation-based optimization of contact stress distribution and lubrication conditions in the straight worm drive. Strength of Materials, 50, 157–165.
Jadooki, S., Mohamad, D., Saba, T., Almazyad, A. S., & Rehman, A. (2017). Fused features mining for depth-based hand gesture recognition to classify blind human communication. Neural Computing and Applications, 28, 3285–3294.
Li, G., Tang, H., Sun, Y., Kong, J., Jiang, G., Jiang, D., & Liu, H. (2019). Hand gesture recognition based on convolution neural network. Cluster Computing, 22, 2719–2729.
Li, B., Sun, Y., Li, G., Kong, J., Jiang, G., Jiang, D., & Liu, H. (2019). Gesture recognition based on modified adaptive orthogonal matching pursuit algorithm. Cluster Computing, 22, 503–512.
Fang, Y., Liu, H., Li, G., & Zhu, X. (2015). A multichannel surface EMG system for hand motion recognition. International Journal of Humanoid Robotics, 12(02), 1550011.
Rahaman, A., Islam, M. M., Islam, M. R., Sadi, M. S., & Nooruddin, S. (2019). Developing iot based smart health monitoring systems: A review. Rev d'Intelligence Artif, 33(6), 435–440.
Tham, O. Y., Markom, M. A., Bakar, A. A., Tan, E. M. M., & Markom, A. M. (2020, October). IoT health monitoring device of oxygen saturation (SpO2) and heart rate level. In 2020 1st International conference on information technology, advanced mechanical and electrical engineering (ICITAMEE) (pp. 128–133). IEEE.
Sharma, N., Mangla, M., Mohanty, S. N., Gupta, D., Tiwari, P., Shorfuzzaman, M., & Rawashdeh, M. (2021). A smart ontology-based IoT framework for remote patient monitoring. Biomedical Signal Processing and Control, 68, 102717.
Hong-Tan, L. I., Cui-Hua, K., Muthu, B., & Sivaparthipan, C. B. (2021). WITHDRAWN: Big data and ambient intelligence in IoT-based wireless student health monitoring system.
Paganelli, A. I., Velmovitsky, P. E., Miranda, P., Branco, A., Alencar, P., Cowan, D., & Morita, P. P. (2022). A conceptual IoT-based early-warning architecture for remote monitoring of COVID-19 patients in wards and at home. Internet of Things, 18, 100399.
Wan, J., Al-awlaqi, A. A. H., Li, M., O’Grady, M., Gu, M., Wang, X., J., & Cao, N. (2018). Wearable IoT enabled real-time health monitoring system. EURASIP Journal on Wireless Communications and Networking, 2018(1), 1–10.
Otoom, M., Otoum, N., Alzubaidi, M. A., Etoom, Y., & Banihani, R. (2020). An IoT-based framework for early identification and monitoring of COVID-19 cases. Biomedical signal processing and control, 62, 102149.
Sheares, G. (2020). Internet of Things-enabled smart devices, biomedical big data, and real-time clinical monitoring in COVID-19 patient health prediction. American Journal of Medical Research, 7(2), 64–70.
Kumar, K., Kumar, N., & Shah, R. (2020). Role of IoT to avoid spreading of COVID-19. International Journal of Intelligent Networks, 1, 32–35.
Wickramasinghe, A., Torres, R. L. S., & Ranasinghe, D. C. (2017). Recognition of falls using dense sensing in an ambient assisted living environment. Pervasive and mobile computing, 34, 14–24.
Hussain, A., Wenbi, R., Da Silva, A. L., Nadher, M., & Mudhish, M. (2015). Health and emergency-care platform for the elderly and disabled people in the Smart City. Journal of Systems and Software, 110, 253–263.
Sebbak, F., & Benhammadi, F. (2017). Majority-consensus fusion approach for elderly IoT-based healthcare applications. Annals of Telecommunications, 72(3), 157–171.

No competing interests reported.

IoT-Enabled Smart Glove for Enhanced Elderly Care: A Health Monitoring Solution

Status:

Version 1

Abstract

Figures

1. Introduction

2. Materials and Method

2.1. Block Diagram

2.2 Fall Detection

2.3. Emergency message with hand gesture

2.4. SpO2 and heart rate monitoring

2.5. Cost of Materials.

3. Result and Analysis

4. Conclusion and Future Work

Declarations

References

Additional Declarations

Status:

Version 1