SN Computer Science (2020) 1:185

https://doi.org/10.1007/s42979-020-00195-y

ORIGINAL RESEARCH

Development of Smart Healthcare Monitoring System in IoT

Environment
Md. Milon Islam1   · Ashikur Rahaman1 · Md. Rashedul Islam1

Received: 13 May 2020 / Accepted: 14 May 2020

© Springer Nature Singapore Pte Ltd 2020

Abstract
Healthcare monitoring system in hospitals and many other health centers has experienced significant growth, and portable
healthcare monitoring systems with emerging technologies are becoming of great concern to many countries worldwide nowa-
days. The advent of Internet of Things (IoT) technologies facilitates the progress of healthcare from face-to-face consulting
to telemedicine. This paper proposes a smart healthcare system in IoT environment that can monitor a patient’s basic health
signs as well as the room condition where the patients are now in real-time. In this system, five sensors are used to capture
the data from hospital environment named heart beat sensor, body temperature sensor, room temperature sensor, CO sensor,
and ­CO2 sensor. The error percentage of the developed scheme is within a certain limit (< 5%) for each case. The condi-
tion of the patients is conveyed via a portal to medical staff, where they can process and analyze the current situation of the
patients. The developed prototype is well suited for healthcare monitoring that is proved by the effectiveness of the system.

Keywords  Healthcare monitoring system · Internet of things · Sensors · ESP32

Introduction IoT is making any objects internally connected in the

recent decade and it has been considered as the next techno-
Health is characterized as a full state of physical, men- logical revolution. Smart health monitoring mechanism [1,
tal, and social well-being and not merely a lack of illness. 2], smart parking [3], smart home [4], smart city [5], smart
Health is a fundamental element of people’s need for a better climate [6], industrial sites [7], and agricultural fields [8] are
life. Unfortunately, the global health problem has created some of the applications of IoT. The most tremendous use
a dilemma because of certain factors, such as poor health of IoT is in healthcare management which provides health
services, the presence of large gaps between rural and urban and environment condition tracking facilities. IoT is nothing
areas, physicians, and nurses unavailability during the hard- but linking computers to the internet utilizing sensors and
est time. networks [9, 10]. These connected components can be used
on devices for health monitoring. The used sensors then for-
ward the information to distant locations like M2M, which
are machinery for computers, machines for people, handheld
This article is part of the topical collection “Advances in
Computational Approaches for Artificial Intelligence, Image devices, or smartphones [11]. It is a simple, energy-efficient,
Processing, IoT and Cloud Applications” guest edited by Bhanu much smarter, scalable, and interoperable way of tracking
Prakash K N and M. Shivakumar. and optimizing care to any health problem. Nowadays, mod-
ern systems are providing a flexible interface [12], assistant
* Md. Milon Islam
[email protected] devices [13], and mental health management [14] to lead a
smart life for the human being.
Ashikur Rahaman
[email protected] Heart rate and body temperature are the two most signifi-
cant indicators for human health. Heart rate is the per-minute
Md. Rashedul Islam
[email protected] amount of heartbeats, commonly known as the pulse rate. To
measure the pulse rate, an increase in the blood flow volume
1
Department of Computer Science and Engineering, Khulna can be used by calculating the pulses. Normal heart rate ranges
University of Engineering & Technology, Khulna 9203, between 60 and 100 beats per minute for healthy people. The
Bangladesh

SN Computer Science
Vol.:(0123456789)
 185   Page 2 of 11 SN Computer Science (2020) 1:185

typical restful heart for adult males is roughly 70 bpm and for Related Works
adult females 75 bpm [15]. Female with 12 years of age and
above, typically have higher rates of heart in contrast with Some important works have been done in the field of medi-
males. The temperature of human body is simply the heat of cal science using IoT to monitor patient’s health. The works
body and the sum of heat radiated by the body is scientifically associated in this field are outlined as follows.
determined. The average person’s body temperature relies on Tamilselvi et al. [26] developed a health monitoring sys-
different factors such as ambient temperature, the person’s tem that can monitor basic symptoms of a patient like heart
gender, and his eating habits. In healthy adults, it is likely to rate, percentage of oxygen saturation, body temperature, and
range between 97.8 °F (36.5 °C) and 99 °F (37.2 °C). Different eye movement in IoT network. For this purpose, the system
factors such as flu, low-temperature hypothermia, or any other used Heartbeat, ­SpO2, Temperature, and Eye blink sensors
illness may lead to a change in body temperature. In almost as capturing elements and Arduino-UNO as a processing
all illnesses, fever is a typical indicator [16]. Various methods device. The developed system was implemented but no spe-
exist to invasively and noninvasively assess the heart rate and cific performance measures are described for any patient.
body temperature. For the consumer, noninvasive approaches Acharya et al. [27] introduced a healthcare monitoring kit
over a while have proven accurate and convenient [17]. It is in IoT environment. The developed system monitored some
suggested that a healthcare should provide good room condi- basic parameters of human health like Heartbeat, ECG,
tions to facilitate the patients [18]. Some measures like room body temperature, and Respiration. The major hardware
humidity, level of all gases like CO, and ­CO2 can determine components which are used here are pulse sensor, tempera-
the quality of room environment. The toxic gases and certain ture sensor, BP sensor, ECG sensor, and raspberry pi. The
levels of humidity are very harmful to patients. For optimum data were collected from sensors and sent it to raspberry pi
comfort, the room humidity should be between 30 and 65%. for processing and again transmitted it to IoT network. The
Some studies [19, 20] are done only for a smart home, not for major drawback of the system is that no interfaces for data
dedicated healthcare. visualization are developed.
There are several fatal diseases like heart disease [21], Banerjee et al. [28] proposed a pulse rate detection system
diabetes [22], breast cancer [23, 24], liver disorder [25], etc. based on a noninvasive technique. The proposed system used
in medical sector but the main concern of our developed plethysmography process and correspondingly displayed the
system is to monitor the fundamental signs of all types of output digitally that made it a real-time monitoring device.
patients and the patient’s room environment. This paper The method has proved as reliable for the patient compared
proposes a customized healthcare system that monitors to other invasive techniques. Gregoski et al. [29] introduced
the pulse and body temperature of patients as well as room a smartphone-based heart rate monitoring system. The sys-
humidity, CO, and ­CO2 gas level of patient’s room via sen- tem used a mobile light and camera to track finger blood
sors and transmits the data through Wi-Fi that enables the flow and calculated blood flow-based cardiac output. The
medical staffs to get data from the server. The developed sys- developed system described an integrated device that wire-
tem also provides a solution for the problem of maintaining lessly transmitted a person’s pulse to a computer, empower-
a single database of patients in hospitals using a web server, ing people to test their heart rate by merely looking at their
apart from the personalization of critical health-related cri- phones instead of using hands each time. This is an excellent
teria. In this system, the gas sensor is used to identify an design but it is not feasible if continuous heart monitoring is
unexpected occurrence that contrasts the performance with needed. Oresko et al. [30] mentioned a fully functional car-
the threshold and produces a PPM signal if the output value diovascular disease sensing system for smartphones, identi-
crosses the threshold. fying a tool that is developed to be the same given sufficient
The rest of the work is organized as follows. “Related time and monetary resources. The developed prototype only
Works” section describes the recent development of health tracked coronary rhythm in real-time, did not track heart rate
monitoring system in IoT environment. The major hardware over time, and could not detect any cardiovascular disease.
components which are used to develop the prototype are Trivedi et al. [31] suggested a mobile device regulated
illustrated in “Major Hardware Components” section. “Sys- Arduino-based health parameter surveillance framework.
tem Design” section demonstrates the design methodology The collected sensor data are analog and sent it to the board
of the proposed system. The implementation details with of Arduino Uno. By the integrated analog to digital con-
user prototype are depicted in “Implementation Details” verter, the recorded analog values are converted into digi-
section. The experimental results are described in “Experi- tal data. Bluetooth transmitted the physical qualities to the
mental Results Analysis” section. “Conclusion” section con- developed device. The Bluetooth device used a module not
cludes the paper with some future work. covering a wide area. Kumar et al. [32] developed an adap-
tive IoT safety monitoring device. The configuration of the

SN Computer Science
SN Computer Science (2020) 1:185 Page 3 of 11  185

framework is separated into 3 layers such as the control ESP32 Processor

layer, the device layer, and the transport layer. A DS18B20
sensor was used for the measurement of body temperature ESP32 is one of the main IoT learning tools. This offers a
in the control segment and a pulse sensor is used for the full Linux system on a small platform at a very low price.
pulse measurement. The data were loaded from Arduino into ESP32 connects device sensors and actuators through GPIO
the cloud through the Wi-Fi module and Ethernet shield on pins. ESP32 and IoT merge to be a new technology for crea-
the transport layer. The framework layer finally collected tivity in the healthcare system. ESP32 is designed extremely
the server details. However, Arduino Uno was used here, with integrated antenna switches, RF-balun, control amplifi-
and hence, many sensors cannot be treated properly. Desai cation, low-noise amplifier, and filters as well as power man-
et al. [33] developed a wireless sensor network (WSN) to agement modules. It can function as a complete stand-alone
track smart homes and heartbeat. Here, Spartan3 is used in scheme or as a slave to a host MCU, decreasing overhead
parallel data processing with FPGA architecture. The MCU interaction within the main application processor. EPS32 can
results are shown by an LCD, and all sensors are connected communicate with other Wi-Fi and Bluetooth devices via its
with a microcontroller. Nevertheless, all machine elements SPI/SDIO, or I2C/UART interfaces. The ESP32 microcon-
are not integrated in one unit. troller is shown in Fig. 1a.

Heart Beat Sensor

Major Hardware Components
The heartbeat sensor is developed based on the plethys-
Some sort of hardware components is being used in the pro- mography theory. It measures the change in blood volume
posed system. The components which are used to develop through anybody’s organ that causes the light intensity to
the system are outlined as follows. move through that organ. The timing of the pulses is more
critical in systems where the heart pulse rate is to be tracked.
The rate of heartbeats determines the distribution of blood
volume, and the signal pulses are equal to the pulses of

Fig. 1  The hardware components for the healthcare monitoring system. a ESP32 b heart beat sensor c body temperature sensor d room tempera-
ture sensor e CO sensor f ­CO2 sensor

SN Computer Science
 185   Page 4 of 11 SN Computer Science (2020) 1:185

heartbeat when light is consumed by the blood. The heart physiological signs. The collected data are then processed
beat sensor is depicted in Fig. 1b. via an ESP32 module and send to the gateway server. For
the web user interface, ThingSpeak is used for the graphi-
Body Temperature Sensor (LM35) cal interpretation, and display of collected results. Thing-
Speak shows the current status and process of transactions.
The LM35 series are accurate optimized temperature cir- The HTTP protocol provides easy connectivity for the cor-
cuits with output voltage, which is linearly relative to the respondence between a Wi-Fi module and the web server.
temperature in centigrade. The LM35 has a vantage point The HTML user interface is updated every 15 s, allowing
over Kelvin’s linear temperature sensors, as a realistic cen- patients to be tracked in real-time.
tigrade scaling does not allow the consumer to delete the The overall system architecture of the developed system
huge constant voltage from the display. LM35 is shown in is illustrated in Fig. 2. From Fig. 2, it can be seen that all
Fig. 1c. the sensors are used to collect data from hospital environ-
ment. The sensors all are connected to a processing unit
Room Temperature Sensor (DHT11) called ESP32. Upon attaching these (temperature, heart-
beat, gas) sensors, ESP32 works as a heart of the system.
DHT11 is a sensor for temperature and humidity which is ESP32 collects sensor data and then wirelessly transfers
commonly used. The sensor comes with a dedicated tem- them to IoT websites. The board uses its Wi-Fi and its
perature measurement NTC and an 8-bit microcontroller for own processing unit, which is Xtensa dual-core 32-bit LX6
the processing of temperature and humidity values in series. microprocessor. The sensor output is then linked to the
The sensor is also calibrated by the factory, making it easy website of IoT.
to interface with other microcontrollers. The DHT11 sensor The data are accessed through any network supported
is depicted in Fig. 1d. device. There, the data are graphically shown and it is a
channel-based system, and every time while accessing it
CO Sensor (MQ‑9) needs password.

MQ-9 is appropriate for LPG, CO, and ­CH4 detection.

Owing to its high sensitivity and fast response time, meas- Implementation Details
urements can be taken fastly. Using the potentiometer, the
sensor’s sensitivity can be modified. The MQ-9 sensor is The system is implemented using the combination of hard-
shown in Fig. 1e. ware components. All the hardware components are assem-
bled in the implementation phase. The circuit diagram of the
CO2 Sensor (MQ‑135) developed system is demonstrated in Fig. 3a. All the sensors
are connected with ESP32 using physical pins. ESP32 is
For air quality control systems, the MQ-135 gas sensors are used as a processing device as it has a built-in Wi-Fi module.
used for N
­ H3, Nicotine, Benzene, Smoke, and C ­ O2 detection For all sensors, the Vcc and GND are connected with the Vcc
as well as measurement. The MQ-135 sensor module comes and GND pin of ESP32. In the case of heart beat sensor, the
with a digital pin that enables this sensor to work even with- signal pin is connected with D26 pin of ESP32. The data
out a microcontroller and is beneficial for detecting specific pin of LM35 is mapped with D35 pin of microcontroller
gases. The gasses in PPM are calculated using the analog (ESP32). These are the case with a specific patient. For room
pins. The analog pin is powered by TTL and works on 5 V, condition monitoring, the data pin of DHT11 is linked with
and hence it can be used with most modern microcontrollers. ESP32’s D14 pin. In the implementation, DHT11 is only
The MQ-135 sensor is depicted in Fig. 1f. considered for room humidity measurement. The digital out
pin of MQ-9 and MQ-135 are connected with D27 and D34
of ESP32, respectively, for the measurement of toxic gases
System Design in room environment.
The user prototype is depicted in Fig. 3b where the sys-
Continuous online patient and patient’s room condition mon- tem is tested with one user. From Fig. 3b, it can be shown
itoring is the main idea of the proposed system. Therefore, that the hand of one user is attached with body temperature
the healthcare monitoring system utilizes the three-stage sensor (LM35) and the data are displayed in the web server.
architectural features, namely (1) Sensor Module (2) Data
Processing Module (3) Web User Interface.
The sensors are wired which are used to collect data
from the patient’s body and the environment by gathering

SN Computer Science
SN Computer Science (2020) 1:185 Page 5 of 11  185

Fig. 2  The overall system architecture of the healthcare monitoring system

Experimental Results Analysis in Fig. 4c that is happened due to weather (sunny or rainy)
of that day.
The developed system was tested with various subjects of The error rate of the developed system for heart rate, body
different ages in different conditions. In the test cases, for temperature, and room humidity measurement is demon-
heartbeat, body temperature, and room temperature sensors, strated in Fig. 5a–c, respectively. The highest error rate for
we manually calculated the actual value and observed value the three cases is 4.28%, 0.81%, and 3.07% individually and
from the developed system. Here, the room temperature sen- the lowest cases are 1.49%, 0.41%, and 1.47%, respectively.
sor is used to measure the humidity only. From the data, we It is notable that for all every case, the error rate is not more
measured error rate to show the effectiveness of the sys- than 5% which is acceptable.
tem. As there is no alternative way to measure the toxic gas A snapshot of the continuously collected data in web
level, we just show the data of MQ-9 and MQ-135 in the server (ThingSpeak) is illustrated in Fig. 6. The level toxic
web server. The actual and observed data with error rate for gases (CO and ­CO2) are measured in ppm unit. Any medi-
heartbeat, body temperature, and room temperature sensors cal staff can easily monitor the specific patient as well as
are demonstrated in Tables 1, 2 and 3, respectively. the room condition where the patient is now through any
To analyze the deviation of data obtained by the devel- type of device which has internet access. The patient data
oped system from actual data, Fig. 4 is depicted here. From here is secure because for accessing data, one needs to pass
Fig. 4, it is shown that there is some deviation between the through a password protected system, i.e., only the authentic
actual and observed data. Figure 4a represents the data for staff can monitor the system. By analyzing data, a doctor can
heart rate which are collected using six different subjects easily decide on from a remote location. For a smart health
of different ages in hospital environment. The deviation is environment, there is some specific level of the threshold
occurred due to motion artifact which is caused by the move- for these measurements. When the data crosses the level,
ment of patients during treatment. Sometimes, the sensor is then the medical staff can easily take necessary steps for
displaced that leads to inaccurate data. Moreover, scattering healthcare.
of light from other sources causes deviation. The deviation
of body temperature is found due to the miss-positioning of
the system and environmental effect that is shown in Fig. 4b.
The discrepancy in the case of room humidity is illustrated

SN Computer Science
 185   Page 6 of 11 SN Computer Science (2020) 1:185

Fig. 3  Implementation details of
the proposed system. a Circuit
diagram b user prototype

SN Computer Science
SN Computer Science (2020) 1:185 Page 7 of 11  185

Table 1  Heart rate data collected by analog machine (actual) and 85

developed system (observed)
Subjects Actual data Observed data Error (%) 80
(bpm) (bpm)

Heart Rate (bpm)

75
S1 67 68 1.49
S2 70 73 4.28
70
S3 74 77 4.05
S4 75 73 2.66
65
S5 73 72 1.36
Actual Data Observed Data
S6 80 83 3.75
60
1 2 3 4 5 6
No. of Subjects
(a)
Table 2  Body temperature data collected by analog machine (actual)
100
and developed system (observed)
Subjects Actual data (°F) Observed data Error (%) 98
(°F)

Body Temperature (F)

S1 97.3 97.8 0.51 96
S2 98.4 97.7 0.71
S3 98.1 98.6 0.50 94
S4 96.9 97.5 0.62
S5 97.5 97.1 0.41 92
Actual Data Observed Data
S6 98.2 97.0 0.81
90
1 2 3 4 5 6
No. of Subjects
(b)
75
Table 3  Room humidity data collected by analog machine (actual)
and developed system (observed)
70
Room Humidity (%)

Experiments Actual data (%) Observed data Error (%)

(%)

1 65 63 3.07 65
2 68 69 1.47
3 63 62 1.58 60
4 70 72 2.85
Actual Data Observed Data
5 66 64 3.03
6 61 60 1.63 55
1 2 3 4 5 6
No. of Experiments
(c)

Fig. 4  Test results of the actual and calculated value. a Heart rate b

body temperature c room humidity

SN Computer Science
 185   Page 8 of 11 SN Computer Science (2020) 1:185

5 Conclusion
4 The system introduced smart healthcare to monitor the basic
important signs of patients like heart rate, body temperature,
Error Rate (%)

3 and some measures of hospital room’s condition such as

room humidity, the level of CO and ­CO2 gases. The rate
2 of success between the observed data and actual data is
approximately greater than 95% for all cases of the devel-
1 oped healthcare system. Authentic medical staff can view
and track the data in real-time even though the patients per-
0 form the tests outside of the hospital. The system can also
1 2 3 4 5 6
No. of Subjects
benefit nurses and doctors in situations of epidemics or cri-
(a) ses as raw medical data can be analyzed in a short time. The
developed prototype is very simple to design and use. The
1 system is very useful in the case of infectious disease like
a novel coronavirus (COVID-19) treatment. The developed
0.8 system will improve the current healthcare system that may
protect lots of lives from death.
Although the system looks somewhat bulky, it will be
Error Rate (%)

0.6
a tiny device by proper manufacturing in the near future.
0.4 The video feature can be added for face to face consulta-
tion between the doctors and patients. Some more meas-
0.2 ures which are very significant to determine a patient’s
condition like the level of diabetes, respiration monitoring,
0 etc. can be addressed as future work.
1 2 3 4 5 6
No. of Subjects
(b)
5

4
Error Rate (%)

0
1 2 3 4 5 6
No. of Experiments
(c)

Fig. 5  The error rate of the developed system for each case. a Heart
rate b body temperature c room humidity

SN Computer Science
SN Computer Science (2020) 1:185 Page 9 of 11  185

Fig. 6  A snapshot of web server

for data visualization. a Heart
rate b body temperature c room
humidity d level of CO e level
of ­CO2

SN Computer Science
 185   Page 10 of 11 SN Computer Science (2020) 1:185

Acknowledgements  The authors would like to thank the Department 15. Reddy GK, Achari KL. A non invasive method for calculating
of Computer Science and Engineering (CSE), Khulna University of calories burned during exercise using heartbeat. In: 2015 IEEE
Engineering & Technology (KUET) to facilitate the work. 9th international conference on intelligent systems and control
(ISCO). IEEE; 2015. p. 1–5.
16. Santoso D, Dalu Setiaji F. Non-contact portable infrared ther-
Compliance with Ethical Standards  mometer for rapid influenza screening. In: 2015 International con-
ference on automation, cognitive science, optics, micro electro-
Conflict of interest  On behalf of all authors, the corresponding author mechanical system, and information technology (ICACOMIT).
states that there is no conflict of interest. IEEE; 2015. p. 18–23.
17. Teichmann D, Brüser C, Eilebrecht B, Abbas A, Blanik N, Leon-
hardt S. Non-contact monitoring techniques—principles and
applications. In: Conference proceedings of the IEEE engineer-
References ing in medicine and biological society; 2012.
18. Yang C-T, Chen S-T, Den W, Wang Y-T, Kristiani E. Imple-
1. Rahaman A, Islam M, Islam M, Sadi M, Nooruddin S. Developing mentation of an intelligent indoor environmental monitoring
IoT based smart health monitoring systems: a review. Rev Intell and management system in cloud. Futur Gener Comput Syst.
Artif. 2019;33:435–40. https​://doi.org/10.18280​/ria.33060​5. 2019;96:731–49. https​://doi.org/10.1016/j.futur​e.2018.02.041.
2. Riazul Islam SM, Kwak Daehan, Humaun Kabir M, Hossain M, 19. Patil K, Laad M, Kamble A, Laad S. A consumer-based smart
Kwak Kyung-Sup. The Internet of Things for health care: a com- home with indoor air quality monitoring system. IETE J Res.
prehensive survey. IEEE Access. 2015;3:678–708. https​://doi. 2019;65:758–70. https​://doi.org/10.1080/03772​063.2018.14621​
org/10.1109/ACCES​S.2015.24379​51. 08.
3. Lin T, Rivano H, Le Mouel F. A survey of smart parking solu- 20. Marques G, Pitarma R. An indoor monitoring system for ambient
tions. IEEE Trans Intell Transp Syst. 2017;18:3229–53. https​:// assisted living based on Internet of Things architecture. Int J Envi-
doi.org/10.1109/TITS.2017.26851​43. ron Res Public Health. 2016;13:1152. https​://doi.org/10.3390/
4. Al-Ali AR, Zualkernan IA, Rashid M, Gupta R, Alikarar M. A ijerp​h1311​1152.
smart home energy management system using IoT and big data 21. Ayon SI, Islam MM, Hossain MR. Coronary artery heart disease
analytics approach. IEEE Trans Consum Electron. 2017. https​:// prediction: a comparative study of computational intelligence
doi.org/10.1109/TCE.2017.01501​4. techniques. IETE J Res. 2020. https​://doi.org/10.1080/03772​
5. Zanella A, Bui N, Castellani A, Vangelista L, Zorzi M. Internet 063.2020.17139​16.
of Things for smart cities. IEEE Internet Things J. 2014;1:22–32. 22. Islam Ayon S, Milon Islam M. Diabetes prediction: a deep learn-
https​://doi.org/10.1109/JIOT.2014.23063​28. ing approach. Int J Inf Eng Electron Bus. 2019;11:21–7. https​://
6. Mois G, Folea S, Sanislav T. Analysis of three IoT-based wireless doi.org/10.5815/ijiee​b.2019.02.03.
sensors for environmental monitoring. IEEE Trans Instrum Meas. 23. Islam MM, Iqbal H, Haque MR, Hasan MK. Prediction of breast
2017;66:2056–64. https​://doi.org/10.1109/TIM.2017.26776​19. cancer using support vector machine and K-nearest neighbors.
7. Chen B, Wan J, Shu L, Li P, Mukherjee M, Yin B. Smart fac- In: 2017 IEEE Region 10 humanitarian technology conference
tory of Industry 4.0: key technologies, application case, and chal- (R10-HTC). IEEE, 2017. p. 226–9.
lenges. IEEE Access. 2018;6:6505–19. https​://doi.org/10.1109/ 24. Hasan MK, Islam MM, Hashem MMA. Mathematical model
ACCES​S.2017.27836​82. development to detect breast cancer using multigene genetic pro-
8. Ayaz M, Ammad-Uddin M, Sharif Z, Mansour A, Aggoune gramming. In: 2016 5th International conference on informatics,
E-HM. Internet-of-Things (IoT)-based smart agriculture: toward electronics and vision (ICIEV). IEEEl; 2016. p. 574–9.
making the fields talk. IEEE Access. 2019;7:129551–83. https​:// 25. Haque MR, Islam MM, Iqbal H, Reza MS, Hasan MK. Perfor-
doi.org/10.1109/ACCES​S.2019.29326​09. mance evaluation of random forests and artificial neural networks
9. Hasan M, Islam MM, Zarif MII, Hashem MMA. Attack and for the classification of liver disorder. In: 2018 International con-
anomaly detection in IoT sensors in IoT sites using machine ference on computer, communication, chemical, material and
learning approaches. Internet Things. 2019;7:100059. https​://doi. electronic engineering (IC4ME2). IEEE; 2018. p. 1–5.
org/10.1016/j.iot.2019.10005​9. 26. Tamilselvi V, Sribalaji S, Vigneshwaran P, Vinu P, GeethaRamani
10. Nooruddin S, Milon Islam M, Sharna FA. An IoT based J. IoT based health monitoring system. In: 2020 6th International
device-type invariant fall detection system. Internet Things. conference on advanced computing and communication systems
2020;9:100130. https​://doi.org/10.1016/j.iot.2019.10013​0. (ICACCS). IEEE; 2020. p. 386–9.
11. Islam M, Neom N, Imtiaz M, Nooruddin S, Islam M, Islam M. 27. Acharya AD, Patil SN. IoT based health care monitoring kit. In:
A review on fall detection systems using data from smartphone 2020 Fourth international conference on computing methodolo-
sensors. Ingénierie des systèmes d Inf. 2019;24:569–76. https​:// gies and communication (ICCMC). IEEE; 2020. p. 363–8.
doi.org/10.18280​/isi.24060​2. 28. Banerjee S, Roy S. Design of a photo plethysmography based
12. Mahmud S, Lin X, Kim J-H, Iqbal H, Rahat-Uz-Zaman M, Reza pulse rate detector. Int J Rec Trends Eng Res. 2016;2:302–6.
S, Rahman MA. A multi-modal human machine interface for 29. Gregoski MJ, Mueller M, Vertegel A, Shaporev A, Jackson BB,
controlling a smart wheelchair. In: 2019 IEEE 7th conference on Frenzel RM, Sprehn SM, Treiber FA. Development and validation
systems, process and control (ICSPC). IEEE; 2019. p. 10–3. of a smartphone heart rate acquisition application for health pro-
13. Mahmud S, Lin X, Kim J-H. Interface for Human Machine Inter- motion and wellness telehealth applications. Int J Telemed Appl.
action for assistant devices: a review. In: 2020 10th Annual com- 2012;2012:1–7. https​://doi.org/10.1155/2012/69632​4.
puting and communication workshop and conference (CCWC). 30. Oresko JJ, Jin Zhanpeng, Cheng Jun, Huang Shimeng, Sun Yuwen,
IEEE; 2020. p. 768–73. Duschl H, Cheng AC. A wearable smartphone-based platform for
14. Lin X, Mahmud S, Jones E, Shaker A, Miskinis A, Kanan S, Kim real-time cardiovascular disease detection via electrocardiogram
J-H. Virtual reality-based musical therapy for mental health man- processing. IEEE Trans Inf Technol Biomed. 2010;14:734–40.
agement. In: 2020 10th Annual computing and communication https​://doi.org/10.1109/TITB.2010.20478​65.
workshop and conference (CCWC). IEEE; 2020. p. 948–52.

SN Computer Science
SN Computer Science (2020) 1:185 Page 11 of 11  185

31. Trivedi S, Cheeran AN. Android based health parameter monitor- 33. Desai MR, Toravi S. A smart sensor interface for smart homes and
ing. In: 2017 International conference on intelligent computing heart beat monitoring using WSN in IoT environment. In: 2017
and control systems (ICICCS). IEEE; 2017. p. 1145–9. International conference on current trends in computer, electrical,
32. Kumar SP, Samson VRR, Sai UB, Rao PLSDM, Eswar KK. Smart electronics and communication (CTCEEC). IEEE; 2017. p. 74–7.
health monitoring system of patient through IoT. In: 2017 Inter-
national conference on I-SMAC (IoT in social, mobile, analytics Publisher’s Note Springer Nature remains neutral with regard to
and cloud) (I-SMAC). IEEE; 2017. p. 551–6. jurisdictional claims in published maps and institutional affiliations.

SN Computer Science