Article Search
닫기

Original Article

Split Viewer

International Journal of Fuzzy Logic and Intelligent Systems 2024; 24(3): 295-305

Published online September 25, 2024

https://doi.org/10.5391/IJFIS.2024.24.3.295

© The Korean Institute of Intelligent Systems

E-Healthcare System Using IoT-Based Wearable Device

Marvy Badr Monir Mansour, Amr Ayman, and Marwan Yehia

Department of Electrical Engineering, The British University in Egypt, Cairo, Egypt

Correspondence to :
Marvy Badr Monir Mansour (marvy.badr@bue.edu.eg)

Received: May 15, 2023; Revised: May 30, 2024; Accepted: August 24, 2024

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

E-healthcare services allow patients to receive the healthcare they need while becoming familiar with their local surroundings. In this study, an e-healthcare matching service system was developed to meet these standards, ensuring patients feel confident that the system is accountable for their healthcare needs while also accommodating healthcare travel schedules, practitioners’ licenses, and legal requirements. This system takes a comprehensive approach by focusing on the needs of patients rather than solely on the needs of healthcare practitioners or professionals. Specifically, it prioritizes individual patient needs and, rather than overlooking these needs when scheduling conflicts arise, aims to accommodate them as carefully as possible. Finally, we implemented and tested the system, and the results indicate that the model used in this study can enhance medical sustainability and significantly reduce medical costs.

Keywords: E-healthcare services, Embedded systems and sensors, Internet of Medical Things, Mobile telemedicine services, Telemonitoring systems

Embedded systems have emerged as one of the most important technologies due to their various applications. These systems perform specialized computational tasks and are used across many industries, including consumer, commercial, automotive, manufacturing, and healthcare. In healthcare, embedded systems that handle medical data on multiple body statuses are at the core of electronic systems. An in-circuit emulator between the built-in unit and an external computer can be installed temporarily for debugging or program upgrading. Because embedded systems have limited computational capacity and strict processing power requirements, developing software for embedded applications requires thorough expertise in both software and hardware components. The physical design of the device includes an OLED display, a Bluetooth module, and sensors for heartbeat and temperature. An advanced software algorithm collects temperature, heartbeat, and pressure data, processes it for calibration, and displays the results.

Readings from healthcare devices are routinely collected and analyzed to determine which healthcare services patients need. To provide such services, the necessary functionalities are matched with healthcare providers willing to offer the required care. The purpose of the proposed system is to determine whether daily telemonitoring activities of elderly people can improve their healthcare and quality of life. In our research, we examined different daily activities to calculate certain outcomes, such as predicting key events needing intervention and evaluating the experiences of seniors with telemonitoring systems. Telehealth programs were created to help seniors manage their conditions without unnecessary hospital admissions, allowing them to live comfortably at home. The device helps monitor patient data easily and enables timely interventions if needed, thereby reducing hospital admissions and freeing up space for critical cases. Several mobile telemedicine services are available in app stores. The aim of using mobile apps in healthcare is to eliminate conventional treatment constraints, providing patients with easy and reliable access to services.

Furthermore, mobile medical systems provide hospitals with various on-demand services via the cloud, rather than relying on independent software on local servers. Comprehensive and accurate devices and sensors enable seamless communication systems to track patients in real time. A smart emergency response system can quickly schedule emergency interventions in critical situations and coordinate with a network of emergency vehicles. Mobile health sensors monitor heartbeat, blood pressure, and temperature to alert networks during emergencies. They also provide access to current and past medical records for patients and healthcare professionals. Wireless cloud storage connections allow users to capture, modify, and share web-based medical data. Through the device interface, a patient health record management system displays patient status information and image content. The entire mobile medical infrastructure, using a biosensor network, offers potential benefits, such as discovering the most effective mechanisms to ensure stability in biosensors while considering extreme storage and memory constraints. It also focuses on representing collected data in a detailed manner with limited storage and user interaction, utilizing data modeling so the system does not need to display all data. Rapid advancements in sensor technology may soon enable appropriate actions and precautions to be taken in biosensors.

Intelligent sensors facilitate significant medical advancements. The connectivity of multiple intelligent sensors to application-specific disease responses is a promising approach to addressing various new challenges. Since wireless sensor networks are designed for biomedical applications, this information can help develop sensors for modern innovations. The accelerated production of embedded intelligent sensors to tackle medical challenges offers clear advantages for both patients and society. Biomedical cancer-monitoring implants, for example, help patients heal while enhancing their health, success, and social engagement. Once perfected, these technologies can reduce treatment costs and improve disease management. With a growing global population, the demand for such devices will only increase. Remote telemedicine was introduced to support individuals and communities. Our goal can be achieved when a telemedicine device tracks a person and provides early warnings of potential illnesses, enabling timely interventions [1]. Wearables require major upgrades in precision and accuracy, particularly in the sensitivity of fall detection and the prediction of key outcomes [2]. E-healthcare is highly effective and cost-efficient for treating patients with chronic diseases and is well-received by both patients and medical professionals [3]. Widespread adoption has a significant impact on redefining the place of treatment and care to be more home-based.

Understanding the factors affecting the viability of home healthcare systems involves both practical and theoretical considerations. Our studies have shown that effective planning is crucial for enhancing patient comfort and efficiently reducing the risks and costs associated with upgrading and rebuilding emergency service facilities in hospitals. This contributes to health and environmental sustainability. As a modern service model, home medical care is essential for the advancement of public health, supporting health maintenance and disease prevention through personal health record systems, health records provision, and promotion of healthy lifestyles. Additionally, in major cities experiencing a shortage of medical facilities, telehealth can address the issue of limited medical resources. Telehealth services, in particular, offer the elderly convenient healthcare access and reduced capital costs. We examined structural issues in telehealth, including challenges related to administrative and technical capabilities, needs, aspirations, and patient satisfaction standards. Proper design of telehealth centers not only reduces maintenance costs and eliminates unnecessary facilities but also enhances patient satisfaction by allowing individuals to receive medical treatment at home [4].

The contributions of this study are as follows: First, we present an e-healthcare matching service system designed to address these issues, allowing patients to navigate healthcare travel schedules, practitioner licenses, and legal requirements. The proposed system enables patients to prioritize their specific needs, even when scheduling conflicts arise, and adapts as much as possible to meet their personal requirements. We implemented and tested the system, and the results indicate that the model will improve medical sustainability and significantly reduce medical costs.

The remainder of this paper is organized as follows. Section 2 provides background information on our study. Section 3 reviews the state-of-the-art literature. Section 4 explains the proposed system. Section 5 discusses the simulation results. Finally, Section 6 presents the summary, conclusions, and proposed future work.

The Internet of Things (IoT) is being utilized in various domains, including healthcare, retail, finance, agriculture, and transportation. It plays a significant role in applications ranging from smart homes to healthcare. The IoT is crucial for smart cities, smart homes, wearable devices, retail, transportation, and health, among others. For instance, if patients experience difficulties moving from one place to another and sensors are properly fitted on or inside their bodies, tracking and assisting them as needed would become significantly easier.

2.1 IOT in Healthcare Systems

The IoT is renowned for connecting distinct physical devices. Various devices equipped with IoT technology can share data through different types of sensors. This data can be accessed from anywhere in the world via cloud computing. This capability enables the creation of digital environments, intelligent homes, healthcare services, and real-time data exchanges, such as smart financial services. Some healthcare facilities have begun using sensors in beds to monitor patient mobility and other behaviors. The IoT has significantly advanced e-healthcare by allowing patients and physicians to access health information without visiting healthcare facilities. Wireless body area sensor systems are advanced technologies used in the development of e-health services. These systems consist of multiple sensors that read and interpret medical information when attached to a patient’s body.

Monitoring, tracking, and assessing patient health are among the most challenging aspects of health research. To address these challenges, an intensive care unit (ICU) smart healthmonitoring architecture has been proposed. This system is designed to take precautionary measures while patients are moving significantly and is beneficial for notifying doctors of any changes in environmental factors. Constant monitoring of medical information during home automation is based on customized medical services for future treatment. IoT architectural features are provided to users through RESTful web services. The actual equipment is connected to wearable devices, integrating diverse sensor data to monitor health.

Body temperature and heartbeat rate readings are essential checks at any clinic or hospital. It is important to record and store these health data to monitor patient information effectively when changes occur. Having this information available online would be advantageous, as physicians may need to examine the patient at any time. Patients with Alzheimer’s disease often face additional issues such as nausea, hypertension, diabetes, and other conditions that can be monitored cost-effectively using various sensors. Biometric sensors can be utilized by visitors, nurses, doctors, and other hospital staff, considering the security factors involved in protecting a patient’s life [5].

2.2 IOMT

The Internet of Medical Things (IoMT) offers clinicians and patients new ways to easily obtain, utilize, and enhance the quality, safety, and efficiency of healthcare information. The IoMT helps healthcare providers store, collect, retrieve, and transmit information online. In home healthcare, software that monitors health status and transmits findings remotely to a clinician can improve the ability to address issues before they escalate into acute conditions.

Advancements in wireless detectors and the miniaturization of equipment have numerous potential applications in healthcare systems. The advantages of using a wireless sensor network in medical systems include mobility, easy deployment and scalability, real-time monitoring, sustainability, restructuring, and self-organization. However, wireless devices that rely on existing communication methods have some limitations. For example, some are costly and power-inefficient, while others, like Bluetooth, limit the number of nodes and reduce transmission speed.

The IoT connects physical objects through multifunctional sensors. When implementing an IoT system, selecting the appropriate sensors is crucial. This involves assigning predefined IoT services to various sensors to optimize multiple goals while considering power and distance limitations. Sensor selection, which aims to enhance the utility function, is known to be NP-hard, especially given the vast number of IoT services involved. Evolutionary algorithms (EAs) are needed to address large-scale problems with multiple objectives. Recently, the field has progressed from multi-objective EAs, which typically focus on two or three objectives, to many-objective EAs, which aim to handle four or more often conflicting goals. This study addresses several objectives in sensor selection for an IoT system, including optimizing connection power consumption, balancing power across devices, power harvesting, green concerns, and QoS. To enhance computational efficiency and solution consistency, the problem is approached using a multi-objective EA based on decomposition. Simulations indicate that the proposed EA shows promise, as evidenced by scatter plots and parallel coordinates [6, 7].

Sensor-based ambient assisted living (AAL) technologies are crucial for supporting the aging population. However, many current methods lack a truly comprehensive environment that can accommodate individuals with various medical conditions and learn about healthier and more advanced medical habitats. Recognizing activities of daily living (ADL) is essential for providing adequate and effective care. In multi-population settings, identifying ADLs is particularly challenging, especially with single-mode solutions that offer limited capabilities. To address these limitations, we propose a multimedia monitoring system architecture for AAL in-home healthcare telemetry that integrates data from diverse sensor sources.

Many systems in the field of AAL focus on specific medical issues and can only identify and respond to particular behaviors. For instance, applications such as medication management, fall detection, and activity tracking are often handled separately. SPHERE aims to address the healthcare challenges posed by an aging population by creating a robust interactive framework that uses complementary sensing technologies to provide a more comprehensive view of ADL. The goal is to connect physicians, caregivers, and family members through electronic health records and AAL programs, enabling individuals with various medical conditions to live comfortably at home according to their preferences. Additionally, this approach significantly reduces healthcare costs. In this paper, we present an overview of the SPHERE architecture and discuss improvements made using off-the-shelf sensor technologies and prototyping in various technological areas. By combining these innovations, the device is expected to be available to average families at an affordable cost. SPHERE addresses critical issues such as cost, energy usage, scalability, interoperability, and privacy to ensure its widespread application in healthcare research and AAL applications. We believe that sharing research findings will accelerate development and application for public benefit. Therefore, we plan to make data collected from studies conducted in the live SPHERE laboratory publicly available (subject to appropriate safeguards), along with detailed metadata and contextual information to facilitate data mining and activity recognition algorithms [8].

The advent of the Internet has greatly expanded access to healthcare services. Consequently, various online platforms, such as healthcare facility portals and browsers, have been developed to cater to customer preferences. However, there is a need for more sophisticated mechanisms to provide health recommendations to ensure better healthcare for inexperienced users. In this study, we use a healthcare service recommendation system (HSRF) that considers each user’s unique health statuses and contexts. The HSRF ranks healthcare environments based on user/service similarity. We integrate this system and evaluate its purpose and feasibility.

We propose a personal HSRF that assesses consumer health status to identify appropriate services. Our system collects information on the health status of service consumers and automatically evaluates the medical similarities among healthcare practitioners. It then organizes and recommends suitable health services for each user based on these similarities. We implemented and assessed the usefulness and feasibility of the HSRF. While the reviewer had reservations about some methods used in this study, we found that our system was effective in providing improved health services [9].

Home healthcare involves licensed practitioners who provide medical treatment or recovery care to patients in their own homes. This setup, which occurs in a familiar and comfortable environment with friends and family, helps patients maintain a good quality of life and alleviates the strain on overcrowded health facilities. However, healthcare workers face challenges in monitoring patients’ health directly because patients are at home rather than in healthcare facilities. The advent of the IoT has addressed this gap. IoT-enabled healthcare systems transmit data directly to information systems via communication networks, minimizing the need for frequent hospital visits by healthcare practitioners. Many offsite systems are available to receive and process data from healthcare devices. However, these systems often operate at one of two extremes. On one hand, some systems provide a graphical overview of health data and recommend that patients seek treatment if necessary. Patients must then find suitable healthcare services on their own, which can be challenging, especially for those with reduced mental capacity. On the other hand, some systems relay health data directly to healthcare providers, who can contact patients and provide guidance. This approach bypasses the patient and transfers control to the healthcare providers. This work introduces a system that includes a tracking component for reading data from patient IoT devices. It recommends home healthcare services based on predefined rule-based logic, allowing patients to prioritize their healthcare needs. The system schedules healthcare professionals who best meet the needs and priorities of the patient through a two-stage procedure, considering the limitations of physical guidance to healthcare professionals.

The Personal Care Matching Program demonstrates the feasibility of IoT in home settings, offering effective control for home healthcare facilities. It also addresses various challenges associated with providing active services in patients’ homes. Beyond logistical restrictions, such as planning for home visits, licensing laws limit the activities that professionals can perform, as well as their working hours and days. The program’s ability to address these logistical issues enhances its service for home healthcare clients [10].

In our project milestones, we conducted research on the hardware components and various sensors according to the system design. We then tested these components and the system design on a test bench. Following this, the design was printed onto a printed circuit board (PCB) and integrated with a battery.

4.1 Methodology

In our system, the desktop application collects biological data from patients using biosensors that measure heart rate, oxygen saturation, and temperature. This data is then transmitted to the network system, with a summary sent to the patient’s desktop computer or mobile phone. Feedback is provided through a website accessible on these devices. Additionally, the system allows a personal doctor to monitor the live status of the data. Figure 1 illustrates a flow diagram of the proposed system, while Figure 2 provides an abstract view of user interaction with our system.

On the software side, a Python script automates the interaction between the hardware components and the user’s personal computer. We also developed a front-end GUI to facilitate ease of use, creating a desktop application for system operation. Additionally, a local database was built using SQLite to demonstrate our working concept, which could be expanded in the future to enhance telehealthcare systems and improve quality of life.

A patient simply wears and connects our device with his/her.

The PC then executes the files necessary to create the database and the website used to collect the required data. Users can view their own data in real time or for a specific period, and doctors can also access this information if abnormalities are detected. Our system supports multiple devices and patients connected to a server, enabling quick access to patient data. This feature is particularly beneficial for elderly patients who may have difficulty traveling to a hospital, allowing them to be monitored by a doctor in real time.

4.2 Proposed System Architecture

The user powers on the device and pairs it with Bluetooth on their personal computer. The first screen displayed on the device is a welcome message reading, “Hello world!” If the sensor does not detect heart rate and oxygen level, the screen will show “Not Detected.” If readings are available, the user’s heart rate, oxygen level, and temperature will be displayed on the OLED screen, as shown in Figure 3. Next, the user moves to their personal computer, where they should have two BAT files, as depicted in Figure 4. These files are necessary to complete the following steps; the user starts by running the BAT files required to operate the website and database.

Subsequently, the user opens a web browser and enters the local host address provided in the WEBRUN.bat terminal, shown in Figure 5. This action directs the user to the web application homepage, as displayed in Figure 6. If the user does not have an account, they navigate to the setup tab, which directs them to a sign-up form to complete, as shown in Figure 7. The software will then take the user’s readings and allow them to view the data, as shown in Figure 8. If the user already has an existing account, they can click on one of the two buttons on the homepage labeled “Live Readings” or “Dashboard” which directs user on either pages to view live readings displayed in a table or in a graph form as in Figure 9.

5.1 Experimental Work

First, we tested our system, as shown in Figure 10, and conducted experiments on a breadboard, as shown in Figure 11.

A schematic of the system is shown in Figure 12, and the PCB layout is displayed in Figure 13. Figures 14 and 15 illustrate the exterior and interior views of the final PCB. The database tables present in the system are shown in Figure 16, with the tables for tbl devices and tbl users detailed in Figure 17.

5.2 Main Results

In this section, we present the results obtained from running the proposed system. Figure 18 shows the readings obtained and stored in the tbl readings table. Figure 19 displays the terminal output, while Figure 20 presents the device data readings.

6.1 Summary

Process reengineering is crucial for developing the clinical, educational, commercial, logistical, and operational structures required for large-scale home healthcare. This system does not replace nursing requirements but helps delay patients’ illnesses and assists with self-management. Home healthcare services are suitable for adults with stable conditions who have the resources and means to live comfortably at home. The computerized home healthcare approach provides a framework for managing the growing number of patients with chronic care needs in both urban and rural areas. Telehealth facilities can better address shortages in medical resources.

Telehealth facilities offer elderly individuals convenient healthcare services and reduce capital costs. Key benefits include lowering capital expenses and eliminating the need for extensive hospital infrastructure. Properly designed telehealth centers not only minimize maintenance costs and avoid unnecessary facilities but also enhance patient satisfaction by allowing individuals to receive treatment while remaining in their homes.

Home healthcare services enable patients to stay in familiar surroundings while receiving the necessary care. Health readings from devices are routinely collected and analyzed to determine which services patients require. These needs are then matched with healthcare providers who are available to deliver the required services. Home medical equivalency services demonstrate how IoT healthcare equipment can be effectively used at home to monitor patients and provide care recommendations. Additionally, this approach addresses the challenge of delivering direct treatment within the client’s home.

6.2 Conclusion

In this paper, we present a healthcare matching system that utilizes IoT technology to recommend home care facility controls for patients. Our system effectively addresses the challenges associated with providing active services in patients’ homes. We also examine structural issues in telehealth and challenges related to administrative and technical capabilities, as well as patient needs, aspirations, and fulfillment standards.

The proposed method enhances patient satisfaction by improving the quality of healthcare services. An increasing number of health services are being delivered at home rather than in healthcare facilities, reducing the need for patients and their families to travel. By aligning patients’ cultural and gender preferences with their medical experts, the system facilitates more effective and convenient communication of health issues. This, in turn, enables healthcare providers to deliver the appropriate treatment more effectively.

6.3 Future Work

The identification of the most cost-effective option among specialists who meet all the criteria is an area where the proposed service could be improved. Healthcare professionals often have specific authorizations, with some holding licenses from multiple organizations. When assigning patients to specialists, it would be advantageous to select those with fewer additional licenses, reserving those with extra credentials for potential home applications. This approach could reduce the risk of encountering issues with meeting home care needs in the near future.

Moreover, smart devices have shown significant improvements in validity and consistency, particularly regarding sensor responsiveness and event modeling. Future research should focus on developing tools that facilitate decision-making based on a combination of activity data, physiological data, and self-reported symptoms. While these new techniques are being developed, initial stages may experience trust issues due to their novelty.

Logistical constraints and licensing regulations could pose challenges, potentially limiting the scope of duties that professionals can perform. Additionally, labor regulations govern work hours and days for professionals. Therefore, it is crucial for such services to be designed in a way that navigates logistical constraints and adheres to legal requirements. Finally, we plan to incorporate the Google Coral Development Board in our future work.


Figure A.1. Arduino code for reading output.


Figure A.2. Python code for inserting readings to the database.


Figure A.3. Terminal output code.

Fig. 1.

Flow-diagram of the proposed system.


Fig. 2.

Abstract user interaction flowchart.


Fig. 3.

OLED readings.


Fig. 4.

File run.


Fig. 5.

WEBRUN.bat terminal.


Fig. 6.

Website homepage.


Fig. 7.

Setup page.


Fig. 8.

Live readings.


Fig. 9.

User’s dashboard.


Fig. 10.

Test phase for the system.


Fig. 11.

Early experiments on breadboard.


Fig. 12.

Schematic layout of system.


Fig. 13.

PCB layout.


Fig. 14.

Exterior view of final PCB.


Fig. 15.

Interior view of final PCB.


Fig. 16.

Database tables present in system.


Fig. 17.

Tables of (a) tbl_devices and (b) tbl_users.


Fig. 18.

Readings obtained and stored in table of tbl_readings.


Fig. 19.

Terminal output.


Fig. 20.

Device data readings.


Fig. 21.

Figure A.1. Arduino code for reading output.


Fig. 22.

Figure A.2. Python code for inserting readings to the database.


Fig. 23.

Figure A.3. Terminal output code.


  1. Fouad, H, and Farouk, H (2016). Performance optimization of healthcare mobile applications using embedded system design and implementation. International Journal of Robotics and Mechatronics. 2, 116-121. https://doi.org/10.21535/ijrm.v2i4.889
    CrossRef
  2. Gokalp, H, and Clarke, M (2013). Monitoring activities of daily living of the elderly and the potential for its use in telecare and telehealth: a review. Telemedicine and e-Health. 19, 910-923. https://doi.org/10.1089/tmj.2013.0109
    Pubmed CrossRef
  3. Darkins, A, Ryan, P, Kobb, R, Foster, L, Edmonson, E, Wakefield, B, and Lancaster, AE (2008). Care coordination/home telehealth: the systematic implementation of health informatics, home telehealth, and disease management to support the care of veteran patients with chronic conditions. Telemedicine and e-Health. 14, 1118-112. https://doi.org/10.1089/tmj.2008.0021
    CrossRef
  4. Du, G, and Sun, C (2015). Location planning problem of service centers for sustainable home healthcare: evidence from the empirical analysis of Shanghai. Sustainability. 7, 15812-15832. https://doi.org/10.3390/su71215787
    CrossRef
  5. Jayapradha, S, and Vincent, PDR . An IOT based Human healthcare system using Arduino Uno board., Proceedings of 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), Kerala, India, 2017, pp.880-885. https://doi.org/10.1109/ICICICT1.2017.8342681
    CrossRef
  6. Lin, CC, Deng, DJ, and Lu, LY (2017). Many-objective sensor selection in IoT systems. IEEE Wireless Communications. 24, 40-47. https://doi.org/10.1109/MWC.2017.1600409
    CrossRef
  7. Younas, I, and Naeem, A (2022). Optimization of sensor selection problem in IoT systems using opposition-based learning in many-objective evolutionary algorithms. Computers & Electrical Engineering. 97. article no 107625. https://doi.org/10.1016/j.compeleceng.2021.107625
    CrossRef
  8. Woznowski, P, Fafoutis, X, Song, T, Hannuna, S, Camplani, M, and Tao, L . A multi-modal sensor infrastructure for healthcare in a residential environment., Proceedings of 2015 IEEE International Conference on Communication Workshop (ICCW), London, UK, 2015, pp.271-277. https://doi.org/10.1109/ICCW.2015.7247190
    CrossRef
  9. Lee, CO, Lee, M, Han, D, Jung, S, and Cho, J . A framework for personalized healthcare service recommendation., Proceedings of the 10th International Conference on e-health Networking, Applications and Services (HealthCom), Singapore, 2008, pp.90-95. https://doi.org/10.1109/HEALTH.2008.4600117
    CrossRef
  10. Lin, TS, Liu, PY, and Lin, CC (2019). Home healthcare matching service system using the Internet of Things. Mobile Networks and Applications. 24, 736-747. https://doi.org/10.1007/s11036-018-1087-y
    CrossRef

Marvy Badr Monir Mansour is currently working as an assistant professor of Computer Engineering in the Electrical Engineering Department at the Faculty of Engineering, The British University in Egypt (BUE), Egypt. Dr. Mansour earned her Ph.D. in 2018 from the Computer and Systems Engineering Department at Ain Shams University, Egypt. She received her M.Sc. in 2013 and B.Sc. (IEng) in 2007 with honors from the Computer Engineering Department at the Arab Academy for Science, Technology, and Maritime Transport (AASTMT), Egypt. Since 2019, Dr. Mansour has served as an advisory board member and reviewer for various prestigious journals and conferences. She has numerous notable publications in esteemed venues. Her research interests include, but are not limited to, cryptography, cybersecurity, AI, blockchain, vehicular networks, cloud computing, and edge technologies.

Amr Ayman is a computer engineer. He received his B.Sc. in 2021 from the Electrical Engineering Department at the Faculty of Engineering, The British University in Egypt (BUE). His research interests include E-healthcare, the Internet of Things, routing protocols, and wireless sensor networks.

Marwan Yehia is an IT Service Desk Engineer at Orange Business Services. He received his B.Sc. in 2021 from the Electrical Engineering Department at the Faculty of Engineering, The British University in Egypt (BUE). His research interests include computer networks, E-healthcare, and the Internet of Things.

Article

Original Article

International Journal of Fuzzy Logic and Intelligent Systems 2024; 24(3): 295-305

Published online September 25, 2024 https://doi.org/10.5391/IJFIS.2024.24.3.295

Copyright © The Korean Institute of Intelligent Systems.

E-Healthcare System Using IoT-Based Wearable Device

Marvy Badr Monir Mansour, Amr Ayman, and Marwan Yehia

Department of Electrical Engineering, The British University in Egypt, Cairo, Egypt

Correspondence to:Marvy Badr Monir Mansour (marvy.badr@bue.edu.eg)

Received: May 15, 2023; Revised: May 30, 2024; Accepted: August 24, 2024

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

E-healthcare services allow patients to receive the healthcare they need while becoming familiar with their local surroundings. In this study, an e-healthcare matching service system was developed to meet these standards, ensuring patients feel confident that the system is accountable for their healthcare needs while also accommodating healthcare travel schedules, practitioners’ licenses, and legal requirements. This system takes a comprehensive approach by focusing on the needs of patients rather than solely on the needs of healthcare practitioners or professionals. Specifically, it prioritizes individual patient needs and, rather than overlooking these needs when scheduling conflicts arise, aims to accommodate them as carefully as possible. Finally, we implemented and tested the system, and the results indicate that the model used in this study can enhance medical sustainability and significantly reduce medical costs.

Keywords: E-healthcare services, Embedded systems and sensors, Internet of Medical Things, Mobile telemedicine services, Telemonitoring systems

1. Introduction

Embedded systems have emerged as one of the most important technologies due to their various applications. These systems perform specialized computational tasks and are used across many industries, including consumer, commercial, automotive, manufacturing, and healthcare. In healthcare, embedded systems that handle medical data on multiple body statuses are at the core of electronic systems. An in-circuit emulator between the built-in unit and an external computer can be installed temporarily for debugging or program upgrading. Because embedded systems have limited computational capacity and strict processing power requirements, developing software for embedded applications requires thorough expertise in both software and hardware components. The physical design of the device includes an OLED display, a Bluetooth module, and sensors for heartbeat and temperature. An advanced software algorithm collects temperature, heartbeat, and pressure data, processes it for calibration, and displays the results.

Readings from healthcare devices are routinely collected and analyzed to determine which healthcare services patients need. To provide such services, the necessary functionalities are matched with healthcare providers willing to offer the required care. The purpose of the proposed system is to determine whether daily telemonitoring activities of elderly people can improve their healthcare and quality of life. In our research, we examined different daily activities to calculate certain outcomes, such as predicting key events needing intervention and evaluating the experiences of seniors with telemonitoring systems. Telehealth programs were created to help seniors manage their conditions without unnecessary hospital admissions, allowing them to live comfortably at home. The device helps monitor patient data easily and enables timely interventions if needed, thereby reducing hospital admissions and freeing up space for critical cases. Several mobile telemedicine services are available in app stores. The aim of using mobile apps in healthcare is to eliminate conventional treatment constraints, providing patients with easy and reliable access to services.

Furthermore, mobile medical systems provide hospitals with various on-demand services via the cloud, rather than relying on independent software on local servers. Comprehensive and accurate devices and sensors enable seamless communication systems to track patients in real time. A smart emergency response system can quickly schedule emergency interventions in critical situations and coordinate with a network of emergency vehicles. Mobile health sensors monitor heartbeat, blood pressure, and temperature to alert networks during emergencies. They also provide access to current and past medical records for patients and healthcare professionals. Wireless cloud storage connections allow users to capture, modify, and share web-based medical data. Through the device interface, a patient health record management system displays patient status information and image content. The entire mobile medical infrastructure, using a biosensor network, offers potential benefits, such as discovering the most effective mechanisms to ensure stability in biosensors while considering extreme storage and memory constraints. It also focuses on representing collected data in a detailed manner with limited storage and user interaction, utilizing data modeling so the system does not need to display all data. Rapid advancements in sensor technology may soon enable appropriate actions and precautions to be taken in biosensors.

Intelligent sensors facilitate significant medical advancements. The connectivity of multiple intelligent sensors to application-specific disease responses is a promising approach to addressing various new challenges. Since wireless sensor networks are designed for biomedical applications, this information can help develop sensors for modern innovations. The accelerated production of embedded intelligent sensors to tackle medical challenges offers clear advantages for both patients and society. Biomedical cancer-monitoring implants, for example, help patients heal while enhancing their health, success, and social engagement. Once perfected, these technologies can reduce treatment costs and improve disease management. With a growing global population, the demand for such devices will only increase. Remote telemedicine was introduced to support individuals and communities. Our goal can be achieved when a telemedicine device tracks a person and provides early warnings of potential illnesses, enabling timely interventions [1]. Wearables require major upgrades in precision and accuracy, particularly in the sensitivity of fall detection and the prediction of key outcomes [2]. E-healthcare is highly effective and cost-efficient for treating patients with chronic diseases and is well-received by both patients and medical professionals [3]. Widespread adoption has a significant impact on redefining the place of treatment and care to be more home-based.

Understanding the factors affecting the viability of home healthcare systems involves both practical and theoretical considerations. Our studies have shown that effective planning is crucial for enhancing patient comfort and efficiently reducing the risks and costs associated with upgrading and rebuilding emergency service facilities in hospitals. This contributes to health and environmental sustainability. As a modern service model, home medical care is essential for the advancement of public health, supporting health maintenance and disease prevention through personal health record systems, health records provision, and promotion of healthy lifestyles. Additionally, in major cities experiencing a shortage of medical facilities, telehealth can address the issue of limited medical resources. Telehealth services, in particular, offer the elderly convenient healthcare access and reduced capital costs. We examined structural issues in telehealth, including challenges related to administrative and technical capabilities, needs, aspirations, and patient satisfaction standards. Proper design of telehealth centers not only reduces maintenance costs and eliminates unnecessary facilities but also enhances patient satisfaction by allowing individuals to receive medical treatment at home [4].

The contributions of this study are as follows: First, we present an e-healthcare matching service system designed to address these issues, allowing patients to navigate healthcare travel schedules, practitioner licenses, and legal requirements. The proposed system enables patients to prioritize their specific needs, even when scheduling conflicts arise, and adapts as much as possible to meet their personal requirements. We implemented and tested the system, and the results indicate that the model will improve medical sustainability and significantly reduce medical costs.

The remainder of this paper is organized as follows. Section 2 provides background information on our study. Section 3 reviews the state-of-the-art literature. Section 4 explains the proposed system. Section 5 discusses the simulation results. Finally, Section 6 presents the summary, conclusions, and proposed future work.

2. Background

The Internet of Things (IoT) is being utilized in various domains, including healthcare, retail, finance, agriculture, and transportation. It plays a significant role in applications ranging from smart homes to healthcare. The IoT is crucial for smart cities, smart homes, wearable devices, retail, transportation, and health, among others. For instance, if patients experience difficulties moving from one place to another and sensors are properly fitted on or inside their bodies, tracking and assisting them as needed would become significantly easier.

2.1 IOT in Healthcare Systems

The IoT is renowned for connecting distinct physical devices. Various devices equipped with IoT technology can share data through different types of sensors. This data can be accessed from anywhere in the world via cloud computing. This capability enables the creation of digital environments, intelligent homes, healthcare services, and real-time data exchanges, such as smart financial services. Some healthcare facilities have begun using sensors in beds to monitor patient mobility and other behaviors. The IoT has significantly advanced e-healthcare by allowing patients and physicians to access health information without visiting healthcare facilities. Wireless body area sensor systems are advanced technologies used in the development of e-health services. These systems consist of multiple sensors that read and interpret medical information when attached to a patient’s body.

Monitoring, tracking, and assessing patient health are among the most challenging aspects of health research. To address these challenges, an intensive care unit (ICU) smart healthmonitoring architecture has been proposed. This system is designed to take precautionary measures while patients are moving significantly and is beneficial for notifying doctors of any changes in environmental factors. Constant monitoring of medical information during home automation is based on customized medical services for future treatment. IoT architectural features are provided to users through RESTful web services. The actual equipment is connected to wearable devices, integrating diverse sensor data to monitor health.

Body temperature and heartbeat rate readings are essential checks at any clinic or hospital. It is important to record and store these health data to monitor patient information effectively when changes occur. Having this information available online would be advantageous, as physicians may need to examine the patient at any time. Patients with Alzheimer’s disease often face additional issues such as nausea, hypertension, diabetes, and other conditions that can be monitored cost-effectively using various sensors. Biometric sensors can be utilized by visitors, nurses, doctors, and other hospital staff, considering the security factors involved in protecting a patient’s life [5].

2.2 IOMT

The Internet of Medical Things (IoMT) offers clinicians and patients new ways to easily obtain, utilize, and enhance the quality, safety, and efficiency of healthcare information. The IoMT helps healthcare providers store, collect, retrieve, and transmit information online. In home healthcare, software that monitors health status and transmits findings remotely to a clinician can improve the ability to address issues before they escalate into acute conditions.

Advancements in wireless detectors and the miniaturization of equipment have numerous potential applications in healthcare systems. The advantages of using a wireless sensor network in medical systems include mobility, easy deployment and scalability, real-time monitoring, sustainability, restructuring, and self-organization. However, wireless devices that rely on existing communication methods have some limitations. For example, some are costly and power-inefficient, while others, like Bluetooth, limit the number of nodes and reduce transmission speed.

3. Literature Review

The IoT connects physical objects through multifunctional sensors. When implementing an IoT system, selecting the appropriate sensors is crucial. This involves assigning predefined IoT services to various sensors to optimize multiple goals while considering power and distance limitations. Sensor selection, which aims to enhance the utility function, is known to be NP-hard, especially given the vast number of IoT services involved. Evolutionary algorithms (EAs) are needed to address large-scale problems with multiple objectives. Recently, the field has progressed from multi-objective EAs, which typically focus on two or three objectives, to many-objective EAs, which aim to handle four or more often conflicting goals. This study addresses several objectives in sensor selection for an IoT system, including optimizing connection power consumption, balancing power across devices, power harvesting, green concerns, and QoS. To enhance computational efficiency and solution consistency, the problem is approached using a multi-objective EA based on decomposition. Simulations indicate that the proposed EA shows promise, as evidenced by scatter plots and parallel coordinates [6, 7].

Sensor-based ambient assisted living (AAL) technologies are crucial for supporting the aging population. However, many current methods lack a truly comprehensive environment that can accommodate individuals with various medical conditions and learn about healthier and more advanced medical habitats. Recognizing activities of daily living (ADL) is essential for providing adequate and effective care. In multi-population settings, identifying ADLs is particularly challenging, especially with single-mode solutions that offer limited capabilities. To address these limitations, we propose a multimedia monitoring system architecture for AAL in-home healthcare telemetry that integrates data from diverse sensor sources.

Many systems in the field of AAL focus on specific medical issues and can only identify and respond to particular behaviors. For instance, applications such as medication management, fall detection, and activity tracking are often handled separately. SPHERE aims to address the healthcare challenges posed by an aging population by creating a robust interactive framework that uses complementary sensing technologies to provide a more comprehensive view of ADL. The goal is to connect physicians, caregivers, and family members through electronic health records and AAL programs, enabling individuals with various medical conditions to live comfortably at home according to their preferences. Additionally, this approach significantly reduces healthcare costs. In this paper, we present an overview of the SPHERE architecture and discuss improvements made using off-the-shelf sensor technologies and prototyping in various technological areas. By combining these innovations, the device is expected to be available to average families at an affordable cost. SPHERE addresses critical issues such as cost, energy usage, scalability, interoperability, and privacy to ensure its widespread application in healthcare research and AAL applications. We believe that sharing research findings will accelerate development and application for public benefit. Therefore, we plan to make data collected from studies conducted in the live SPHERE laboratory publicly available (subject to appropriate safeguards), along with detailed metadata and contextual information to facilitate data mining and activity recognition algorithms [8].

The advent of the Internet has greatly expanded access to healthcare services. Consequently, various online platforms, such as healthcare facility portals and browsers, have been developed to cater to customer preferences. However, there is a need for more sophisticated mechanisms to provide health recommendations to ensure better healthcare for inexperienced users. In this study, we use a healthcare service recommendation system (HSRF) that considers each user’s unique health statuses and contexts. The HSRF ranks healthcare environments based on user/service similarity. We integrate this system and evaluate its purpose and feasibility.

We propose a personal HSRF that assesses consumer health status to identify appropriate services. Our system collects information on the health status of service consumers and automatically evaluates the medical similarities among healthcare practitioners. It then organizes and recommends suitable health services for each user based on these similarities. We implemented and assessed the usefulness and feasibility of the HSRF. While the reviewer had reservations about some methods used in this study, we found that our system was effective in providing improved health services [9].

Home healthcare involves licensed practitioners who provide medical treatment or recovery care to patients in their own homes. This setup, which occurs in a familiar and comfortable environment with friends and family, helps patients maintain a good quality of life and alleviates the strain on overcrowded health facilities. However, healthcare workers face challenges in monitoring patients’ health directly because patients are at home rather than in healthcare facilities. The advent of the IoT has addressed this gap. IoT-enabled healthcare systems transmit data directly to information systems via communication networks, minimizing the need for frequent hospital visits by healthcare practitioners. Many offsite systems are available to receive and process data from healthcare devices. However, these systems often operate at one of two extremes. On one hand, some systems provide a graphical overview of health data and recommend that patients seek treatment if necessary. Patients must then find suitable healthcare services on their own, which can be challenging, especially for those with reduced mental capacity. On the other hand, some systems relay health data directly to healthcare providers, who can contact patients and provide guidance. This approach bypasses the patient and transfers control to the healthcare providers. This work introduces a system that includes a tracking component for reading data from patient IoT devices. It recommends home healthcare services based on predefined rule-based logic, allowing patients to prioritize their healthcare needs. The system schedules healthcare professionals who best meet the needs and priorities of the patient through a two-stage procedure, considering the limitations of physical guidance to healthcare professionals.

The Personal Care Matching Program demonstrates the feasibility of IoT in home settings, offering effective control for home healthcare facilities. It also addresses various challenges associated with providing active services in patients’ homes. Beyond logistical restrictions, such as planning for home visits, licensing laws limit the activities that professionals can perform, as well as their working hours and days. The program’s ability to address these logistical issues enhances its service for home healthcare clients [10].

4. Proposed System Design

In our project milestones, we conducted research on the hardware components and various sensors according to the system design. We then tested these components and the system design on a test bench. Following this, the design was printed onto a printed circuit board (PCB) and integrated with a battery.

4.1 Methodology

In our system, the desktop application collects biological data from patients using biosensors that measure heart rate, oxygen saturation, and temperature. This data is then transmitted to the network system, with a summary sent to the patient’s desktop computer or mobile phone. Feedback is provided through a website accessible on these devices. Additionally, the system allows a personal doctor to monitor the live status of the data. Figure 1 illustrates a flow diagram of the proposed system, while Figure 2 provides an abstract view of user interaction with our system.

On the software side, a Python script automates the interaction between the hardware components and the user’s personal computer. We also developed a front-end GUI to facilitate ease of use, creating a desktop application for system operation. Additionally, a local database was built using SQLite to demonstrate our working concept, which could be expanded in the future to enhance telehealthcare systems and improve quality of life.

A patient simply wears and connects our device with his/her.

The PC then executes the files necessary to create the database and the website used to collect the required data. Users can view their own data in real time or for a specific period, and doctors can also access this information if abnormalities are detected. Our system supports multiple devices and patients connected to a server, enabling quick access to patient data. This feature is particularly beneficial for elderly patients who may have difficulty traveling to a hospital, allowing them to be monitored by a doctor in real time.

4.2 Proposed System Architecture

The user powers on the device and pairs it with Bluetooth on their personal computer. The first screen displayed on the device is a welcome message reading, “Hello world!” If the sensor does not detect heart rate and oxygen level, the screen will show “Not Detected.” If readings are available, the user’s heart rate, oxygen level, and temperature will be displayed on the OLED screen, as shown in Figure 3. Next, the user moves to their personal computer, where they should have two BAT files, as depicted in Figure 4. These files are necessary to complete the following steps; the user starts by running the BAT files required to operate the website and database.

Subsequently, the user opens a web browser and enters the local host address provided in the WEBRUN.bat terminal, shown in Figure 5. This action directs the user to the web application homepage, as displayed in Figure 6. If the user does not have an account, they navigate to the setup tab, which directs them to a sign-up form to complete, as shown in Figure 7. The software will then take the user’s readings and allow them to view the data, as shown in Figure 8. If the user already has an existing account, they can click on one of the two buttons on the homepage labeled “Live Readings” or “Dashboard” which directs user on either pages to view live readings displayed in a table or in a graph form as in Figure 9.

5. Simulation and Results

5.1 Experimental Work

First, we tested our system, as shown in Figure 10, and conducted experiments on a breadboard, as shown in Figure 11.

A schematic of the system is shown in Figure 12, and the PCB layout is displayed in Figure 13. Figures 14 and 15 illustrate the exterior and interior views of the final PCB. The database tables present in the system are shown in Figure 16, with the tables for tbl devices and tbl users detailed in Figure 17.

5.2 Main Results

In this section, we present the results obtained from running the proposed system. Figure 18 shows the readings obtained and stored in the tbl readings table. Figure 19 displays the terminal output, while Figure 20 presents the device data readings.

6. Summary, Conclusion and Future Work

6.1 Summary

Process reengineering is crucial for developing the clinical, educational, commercial, logistical, and operational structures required for large-scale home healthcare. This system does not replace nursing requirements but helps delay patients’ illnesses and assists with self-management. Home healthcare services are suitable for adults with stable conditions who have the resources and means to live comfortably at home. The computerized home healthcare approach provides a framework for managing the growing number of patients with chronic care needs in both urban and rural areas. Telehealth facilities can better address shortages in medical resources.

Telehealth facilities offer elderly individuals convenient healthcare services and reduce capital costs. Key benefits include lowering capital expenses and eliminating the need for extensive hospital infrastructure. Properly designed telehealth centers not only minimize maintenance costs and avoid unnecessary facilities but also enhance patient satisfaction by allowing individuals to receive treatment while remaining in their homes.

Home healthcare services enable patients to stay in familiar surroundings while receiving the necessary care. Health readings from devices are routinely collected and analyzed to determine which services patients require. These needs are then matched with healthcare providers who are available to deliver the required services. Home medical equivalency services demonstrate how IoT healthcare equipment can be effectively used at home to monitor patients and provide care recommendations. Additionally, this approach addresses the challenge of delivering direct treatment within the client’s home.

6.2 Conclusion

In this paper, we present a healthcare matching system that utilizes IoT technology to recommend home care facility controls for patients. Our system effectively addresses the challenges associated with providing active services in patients’ homes. We also examine structural issues in telehealth and challenges related to administrative and technical capabilities, as well as patient needs, aspirations, and fulfillment standards.

The proposed method enhances patient satisfaction by improving the quality of healthcare services. An increasing number of health services are being delivered at home rather than in healthcare facilities, reducing the need for patients and their families to travel. By aligning patients’ cultural and gender preferences with their medical experts, the system facilitates more effective and convenient communication of health issues. This, in turn, enables healthcare providers to deliver the appropriate treatment more effectively.

6.3 Future Work

The identification of the most cost-effective option among specialists who meet all the criteria is an area where the proposed service could be improved. Healthcare professionals often have specific authorizations, with some holding licenses from multiple organizations. When assigning patients to specialists, it would be advantageous to select those with fewer additional licenses, reserving those with extra credentials for potential home applications. This approach could reduce the risk of encountering issues with meeting home care needs in the near future.

Moreover, smart devices have shown significant improvements in validity and consistency, particularly regarding sensor responsiveness and event modeling. Future research should focus on developing tools that facilitate decision-making based on a combination of activity data, physiological data, and self-reported symptoms. While these new techniques are being developed, initial stages may experience trust issues due to their novelty.

Logistical constraints and licensing regulations could pose challenges, potentially limiting the scope of duties that professionals can perform. Additionally, labor regulations govern work hours and days for professionals. Therefore, it is crucial for such services to be designed in a way that navigates logistical constraints and adheres to legal requirements. Finally, we plan to incorporate the Google Coral Development Board in our future work.

Appendix A


Figure A.1. Arduino code for reading output.


Figure A.2. Python code for inserting readings to the database.


Figure A.3. Terminal output code.

Fig 1.

Figure 1.

Flow-diagram of the proposed system.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 2.

Figure 2.

Abstract user interaction flowchart.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 3.

Figure 3.

OLED readings.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 4.

Figure 4.

File run.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 5.

Figure 5.

WEBRUN.bat terminal.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 6.

Figure 6.

Website homepage.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 7.

Figure 7.

Setup page.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 8.

Figure 8.

Live readings.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 9.

Figure 9.

User’s dashboard.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 10.

Figure 10.

Test phase for the system.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 11.

Figure 11.

Early experiments on breadboard.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 12.

Figure 12.

Schematic layout of system.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 13.

Figure 13.

PCB layout.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 14.

Figure 14.

Exterior view of final PCB.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 15.

Figure 15.

Interior view of final PCB.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 16.

Figure 16.

Database tables present in system.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 17.

Figure 17.

Tables of (a) tbl_devices and (b) tbl_users.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 18.

Figure 18.

Readings obtained and stored in table of tbl_readings.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 19.

Figure 19.

Terminal output.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 20.

Figure 20.

Device data readings.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 21.

Figure 21.

Figure A.1. Arduino code for reading output.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 22.

Figure 22.

Figure A.2. Python code for inserting readings to the database.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

Fig 23.

Figure 23.

Figure A.3. Terminal output code.

The International Journal of Fuzzy Logic and Intelligent Systems 2024; 24: 295-305https://doi.org/10.5391/IJFIS.2024.24.3.295

References

  1. Fouad, H, and Farouk, H (2016). Performance optimization of healthcare mobile applications using embedded system design and implementation. International Journal of Robotics and Mechatronics. 2, 116-121. https://doi.org/10.21535/ijrm.v2i4.889
    CrossRef
  2. Gokalp, H, and Clarke, M (2013). Monitoring activities of daily living of the elderly and the potential for its use in telecare and telehealth: a review. Telemedicine and e-Health. 19, 910-923. https://doi.org/10.1089/tmj.2013.0109
    Pubmed CrossRef
  3. Darkins, A, Ryan, P, Kobb, R, Foster, L, Edmonson, E, Wakefield, B, and Lancaster, AE (2008). Care coordination/home telehealth: the systematic implementation of health informatics, home telehealth, and disease management to support the care of veteran patients with chronic conditions. Telemedicine and e-Health. 14, 1118-112. https://doi.org/10.1089/tmj.2008.0021
    CrossRef
  4. Du, G, and Sun, C (2015). Location planning problem of service centers for sustainable home healthcare: evidence from the empirical analysis of Shanghai. Sustainability. 7, 15812-15832. https://doi.org/10.3390/su71215787
    CrossRef
  5. Jayapradha, S, and Vincent, PDR . An IOT based Human healthcare system using Arduino Uno board., Proceedings of 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT), Kerala, India, 2017, pp.880-885. https://doi.org/10.1109/ICICICT1.2017.8342681
    CrossRef
  6. Lin, CC, Deng, DJ, and Lu, LY (2017). Many-objective sensor selection in IoT systems. IEEE Wireless Communications. 24, 40-47. https://doi.org/10.1109/MWC.2017.1600409
    CrossRef
  7. Younas, I, and Naeem, A (2022). Optimization of sensor selection problem in IoT systems using opposition-based learning in many-objective evolutionary algorithms. Computers & Electrical Engineering. 97. article no 107625. https://doi.org/10.1016/j.compeleceng.2021.107625
    CrossRef
  8. Woznowski, P, Fafoutis, X, Song, T, Hannuna, S, Camplani, M, and Tao, L . A multi-modal sensor infrastructure for healthcare in a residential environment., Proceedings of 2015 IEEE International Conference on Communication Workshop (ICCW), London, UK, 2015, pp.271-277. https://doi.org/10.1109/ICCW.2015.7247190
    CrossRef
  9. Lee, CO, Lee, M, Han, D, Jung, S, and Cho, J . A framework for personalized healthcare service recommendation., Proceedings of the 10th International Conference on e-health Networking, Applications and Services (HealthCom), Singapore, 2008, pp.90-95. https://doi.org/10.1109/HEALTH.2008.4600117
    CrossRef
  10. Lin, TS, Liu, PY, and Lin, CC (2019). Home healthcare matching service system using the Internet of Things. Mobile Networks and Applications. 24, 736-747. https://doi.org/10.1007/s11036-018-1087-y
    CrossRef