Non-invasive Wireless Mobile System for COVID-19 Monitoring in

Nursing Homes

Marta Botella-Campos

, Sandra Viciano-Tudela

, Sandra Sendra

1,2

and Jaime Lloret

Instituto de Investigación Para la Gestión Integrada de Zonas Costeras (IGIC), Universitat Politècnica de València,

Camino de Vera, S/N. 46022, València, Spain

Departamento de Teoría de la Señal, Telemática y Comunicaciones (TSTC), Universidad de Granada,

C/ Periodista Daniel Saucedo Aranda, S/N, 18014, Granada, Spain

Keywords: COVID-19, Android Application, Remote Monitoring, Wireless Sensor Network (WSN), Mobile, Elderly

People.

Abstract: The recent global pandemics are generating serious problems in the elderly population and those who suffer

from previous ailments. When a person is infected, he / she is usually isolated from the rest of persons in his

/ her room to avoid transmitting the virus. In most cases, especially those who live in nursing homes, often

remain in bed with difficulties in moving. So, their monitoring and control of evolution is sometimes difficult.

To solve this problem, this paper presents a non-invasive wireless mobile system to monitor elderly people in

nursing homes. The system is composed by an electronic device with several sensors to monitor vital signs

such temperature, cough, blood pressure, heart rate, oxygen saturation and, difficulty breathing of patients

and an Android application to manage the medical data. Additionally, the system uses a local server to store

the data and provide it to the nurses and physicians. Both the application and the process of collecting data

have been tested together to check the correct generation of alerts and patients’ labelling of degree of urgency.

1 INTRODUCTION

In late 2019, a new virus belonging to the

Coronaviridae family SARS-CoV2 (severe acute

respiratory syndrome coronavirus 2) was detected in

Wuhan. Prior to the presence of this new outbreak,

SARS-CoV (Severe Acute Respiratory Syndrome

Coronavirus) emerged in November 2002 in the

Chinese province of Guangzhou, causing severe

respiratory syndromes among the population, and the

MERS-COV (Middle East Respiratory Syndrome-

related Coronavirus) gave rise to the acute respiratory

syndrome in the Middle East.

Recent studies show that the new SARS-CoV2

shares 94.6% of aa (amino acids) with the previous

SARS-CoV in the seven replicase domains conserved

in ORF1ab, used for the classification of CoV

species. For this reason, the new virus has been

classified as SARS-CoV2, thus indicating that both

belong to the same species (Zhou, 2020a).

https://orcid.org/0000-0002-1317-286X

https://orcid.org/0000-0001-9556-9088

https://orcid.org/0000-0002-0862-0533

Although the origin of this virus is not yet clear, it

seems to have a zoonotic origin. That is, it is believed

to have been caused by an animal infecting a human.

A wide range of species have been considered to be

precursors of this infection, though the hypothesis

that has become more relevant is that this virus

originates from a species of bat. Despite several

studies show that there is a high identity relationship

between the short region of RNA-dependent RNA

polymerase (RdRp) of a bat coronavirus (BatCoV

RaTG13) for 2019-nCoV, there is a discrepancy

between different authors (Zhou, 2020b), and some of

them point out that the origin is in the pangolin

species.

Whichever the origin of the virus may be, the

damage it can cause is becoming more relevant over

time. Since the entry of the virus in multiple

countries, the pandemic is causing a health crisis to

try and stop the number of infections and deaths. The

high number of cases worldwide is due to the fact that

Botella-Campos, M., Viciano-Tudela, S., Sendra, S. and Lloret, J.

Non-invasive Wireless Mobile System for COVID-19 Monitoring in Nursing Homes.

DOI: 10.5220/0010023700070016

In Proceedings of the 17th International Joint Conference on e-Business and Telecommunications (ICETE 2020) - SECRYPT, pages 7-16

ISBN: 978-989-758-446-6

this virus has a high contagion capacity, while SARS-

CoV and MERS-CoV are caused by nosocomial

infections (that is, within the hospital environment)

(Guo, 2020).

As the studies progress, one of the most important

aspects is to avoid further harm to the patient and even

death. One of the most prominent symptoms that it

produces is a severe pneumonia. However, other

indicative symptoms of the disease may appear.

According to one study, the manifestations of

COVID-19 are fever (90% or more), cough (about

75%), and dyspnoea (up to 50%). A small but

significant number of patients have gastrointestinal

symptoms, and approximately 2% of the patients

have acute Respiratory Distress Syndrome (ARDS),

acute kidney injury (AKI) and myocardial injury

(Jiang, 2020).

It should be noted that different risk groups have

been established against COVID-19 taking into

account the age of the population and the patient's

clinical history. Among these risk groups, we find

adults over 65 years of age, including those living in

nursing homes, and people of any age with serious

underlying conditions, such as: diabetes, asthma, and

immunosuppressed people, among others. In

addition, the number of asymptomatic patients who

have the virus but do not show any symptoms must

be taken into account. These individuals are carriers

of the virus, causing new cases of contagion. The only

way to detect the presence of the virus is by using

rapid tests, in which many research groups are

currently working on. Other valid tests are the

reverse-transcription polymerase chain reaction (RT-

PCR) tests, which is not only expensive but slow.

However, it is also the most reliable. For this reason,

some research groups are developing new detection

methods such as Chest CT (Chest computed

tomography) which is based on images that detect the

presence of the virus. (Ai, 2020).

With the increasing availability of mobile phones,

many research groups are developing massive data

storage systems at a health level, intended to develop

new technologies and communications networks to

allow remote monitoring of patients. An example of

this is the study carried out by Sendra et al. in 2018,

where children with chronic diseases where

monitored through an intelligent system. In this case,

parents or caregivers receive an alert whenever there

is an alteration of the parameters (Sendra, 2018a).

Furthermore, Sendra et al. developed in 2018 an

intelligent system based on LoRa, to observe babies’

progress inside the incubators, by monitoring

parameters such as humidity, temperature and weight

(Sendra, 2018b).

Lloret et al. presented in 2017 an architecture for

intelligent continuous monitoring of chronic patients

using 5G. To do this, they used an automatic learning

system with Big Data that used collected data from

different hospitals, to compare it with the data

received by the patient itself, and thus, be able to

diagnose and generate alarms (Lloret, 2017).

Because of the severity of this disease, it is highly

relevant to be able to anticipate disorders as soon as

possible. In this paper, we aim to monitor patients

infected with COVID-19 in nursing homes, as it is

one of the most vulnerable risk groups. By developing

an application that monitors different parameters such

as: heart rate, oxygen saturation, temperature, blood

pressure, dry cough, dyspnoea, chills and blood in

urine, we intend to create a system able to alert

doctors whenever necessary, in order to improve the

quality of service given in care rooms. Moreover, the

proposed solution will allow doctors to follow-up

other subjective parameters such as: muscle pain,

dizziness, expectoration of blood, etc. Furthermore,

caregiver and doctors will be informed in real-time of

the emergency level of the patient, by means of an

alarm sent to their mobile phones.

The rest of this paper is structured as follows.

Section 2 presents some previous works related on the

proposal where similar existing systems and

applications are presented. The proposed system is

presented in Section 3. Section 4 presents results and

the operation of our system. Finally, the conclusion

and future work are presented in Section 5.

2 RELATED WORK

In this section, different applications developed to

monitor, and control certain diseases are analysed.

Lopes et al. (Lopes, 2011) showed SapoFitness,

an Android application that allows dietary monitoring

and evaluation. To do this, the application records the

user's health status daily, in addition to their food

intake and physical exercise. To offer a greater

experience, an alarm system was installed to inform

the user of the best diet to follow according to their

physical activity. Furthermore, it allows the user to

share their achievements on social networks such as

Facebook and Twitter.

In 2012, Årsand et al. (Årsand, 2012) developed a

mobile health application to assist patients with

diabetes. This application consists of a diary that

allows patients with diabetes to receive personalized

information to achieve objectives related to their

health issues, with data being collected manually and

through automatic wireless data transfer.

ICETE 2020 - 17th International Joint Conference on e-Business and Telecommunications

Park et al. (Park, 2016) developed a mobile

application to predict the most relevant factors that

produced migraines. To do this, a study of people who

suffered from this disease was carried out.

Participants were asked to download the application

and introduce their data every time they felt a

headache, by selecting among different factors. Sixty-

two participants kept diary entries until the end of the

study. The results showed that the most relevant

common factors were stress, fatigue, sleep

deprivation, hormonal changes, and weather

conditions. Moreover, the type of factors and the

medication used were proven to give a characteristic

pain in each case.

Meanwhile, Hartzler et al. (Hartzler, 2016)

showed NutriWalking (NW), an application focused

on patients with type 2 diabetes mellitus and

depression that allows them not only to maintain

healthy nutritional habits, but also to provide

personalized daily exercise goals for each user. In the

future, they intend to improve this application to

allow users to establish contact with each other

through the development of a social network.

BENECA (Energy Balance on Cancer) mHealth

is an application developed by Lozano-Lozano et al.

(Lozano-Lozano, 2019). The objective of this

application is to monitor the energy balance of people

who have overcome breast cancer. In this study,

eighty breast cancer survivors participated to obtain

data of feasibility, pre-test and post-test differences

regarding their lifestyles, quality of life, and

motivation to perform physical activities. According

to the results obtained, this study concluded that the

quality of life of these patients can be improved

through monitoring.

Garcia et al. (Garcia, 2019) proposed a mobile

phone application for cerebral stroke detection. This

application allows to establish the index of

demographic incidents of cardiovascular accidents.

Furthermore, according to the results obtained, the

application was able to distinguish which persons

suffered a cardiovascular accident. In this case, three

of the most characteristic factors that occur during

strokes were analysed. Moreover, patients’ smiles

were analysed as well as their capacity to repeat a

sentence and whether they were able to raise their

arms. In addition to contacting emergency services to

reduce wait time, the application alerts a family

member via Short Message Service (SMS).

Although there are currently many applications to

monitor various diseases, it should be noted that none

of them monitor hospitalized patients nor elders in

nursing homes. Furthermore, many applications rely

on user inputs rather than medical supervision.

Moreover, none of these applications deal with the

prevention and medical care of elders suffering from

COVID-19.

For these reasons, in this paper we present an

application developed to track COVID-19 patients

and alert health carers whenever a patient’s urgency

state changes for the worse. By monitoring different

parameters such as heart rate, temperature, blood

pressure, etc., we aim at easing the triage of patients

in order to improve the efficiency and quality of

service given in care rooms, as well as allowing carers

to have real-time access to a patient’s state without

the need of physical presence.

3 PROPOSED SYSTEM

This section presents the proposed system. The

platform is composed by an electronic device with

several sensors, which transmits the data using a

wireless interface card compatible with the IEEE

802.11b/g/n, and a mobile phone with a management

software developed in Android to collect and manage

the data.

3.1 Overall Description

After analysing the most common symptoms

produced by the COVID-19 virus and the difficulty

of having real-time monitoring systems (especially in

nursing homes) due to the high cost of these systems,

we believe it is necessary to develop low-cost system

to allow the control of vital signs in patients as well

as their progress.

As Fig. 1 shows, the proposed system is composed

by a series of sensors that to monitor the most

common parameters of this disease, in a non-invasive

way. These are: temperature, dry cough, blood

pressure, heart rate, oxygen saturation, chills, blood

in urine and dyspnoea. The data is collected in real-

time by a wireless node and sent to the local server to

be saved into the database. This way, the local server

maintains the patients' medical records that will be

access by nurses or physicians through an Android

application in a smartphone or tablet. In this system,

both the server and smartphones will be locally

managed to preserve the patients’ intimacy.

Non-invasive Wireless Mobile System for COVID-19 Monitoring in Nursing Homes

Figure 1: Diagram description of proposal.

3.2 Hardware Used to Develop the

System

To develop the electronic device in charge of

collecting data, we decided to use a NodeMCU

(NodeMCU, 2020) module based on the ESP8266

(ESP-12) processor at 80MHz. This device contains

9 GPIO pins with I2C and SPI, 1 analog input and a

4 MB flash memory. Finally, it includes a wireless

interface compatible with the IEEE 802.11b/g/n

standard. Though it is possible to develop our systems

with other microprocessors, its size (smaller than 3x5

cm) makes it ideal for this type of application. As we

mentioned before, the system is composed by several

sensors to measure fever, cough, blood pressure, heart

rate, oxygen saturation and difficulty breathing,

among others. To measure them, non-invasive

sensors are used.

3.2.1 Temperature Monitoring

In order to measure the body temperature, a

thermistor in contact with the person's body will be

used. A thermistor is a sensor that modifies its

electrical resistance depending on the temperature. Its

operation is based on the resistance change of a

semiconductor material according to temperature. We

can work with negative temperature coefficient

thermistors (NTC) or positive temperature coefficient

thermistors (PTC). In NTC thermistors, the resistance

decreases as their temperature increases while PTC

thermistors increase their resistance as their

temperature increases. In our case, the use of an NTC

will be chosen because its behaviour is practically

linear throughout its entire working range.

3.2.2 Heart Rate Monitoring

The AD8232 ECG module is a sensor that measures

the heart rate (AD8232, 2020). It is a low-cost data

acquisition card used for biopotential measurement

such as the electrical activity of the heart.

Electrocardiograms can be extremely noisy, so the

AD8232 acts as an operational amplifier for

measuring PR and QT intervals. This module has a

maximum current consumption of 170 μA with a

working temperature range from -40 to 85 degrees. It

is designed to extract, amplify, and filter small

biological signals. Finally, it can be configured to

obtain the ECG waveform or directly the output as an

analog reading.

To measure the cardiac rhythm, a differential

measurement with 3 electrodes is performed. The

electrodes must be connected to the patient according

to the Einthoven triangle (See Fig. 2).

3.2.3 Cough and Dyspnoea Monitoring

The measurement of cough and breathing difficulties

is usually translated into involuntary movements of

the patient's chest. Additionally, dry cough produces

dry short bumps of noise or voice with great

amplitude. Taking advantage of these characteristics

and the measurement properties of the accelerometers

and microphones, it is possible to measure both

events and differentiate them.

The MMA8451 (MMA8451, 2020) is a low-cost

and high-precision 3-axis accelerometer with 14-bit

ADC. This device is capable of detecting movement,

inclination, and basic orientation. Its working range is

Microphones are sensors able to detect how loud

Server + Data base

WiFi

Gateway

Data from patient

Smartphone of

caregivers/nurses/physicians

Updated data of patient

Data provided by phisician

• Cough

• Blood pressure

• Temperature

• Difficulty breathing

• Heart rate

ICETE 2020 - 17th International Joint Conference on e-Business and Telecommunications

Figure 2: Position of electrodes to measure ECG.

from ±2g to ±8g, and it can be easily used with

microcontroller modules such as Arduino. This

sensor can be accessed by using the I2C

communication protocol, so it can share the medium

with other I2C devices.

a sound is. There are several types of

microphones; the most popular ones are the

condenser microphones and piezoelectric

microphones. Condenser microphone are essentially

capacitors formed by a thin diaphragm mounted in

front of a plate. When sound reaches the condenser,

the diaphragm vibrates thereby changing the distance

between the conductors and effectively changes the

capacitance between the diaphragm and the plate. A

LM358 op-amp could be used to amplify the detected

signal. When cough is detected, the microphone will

detect short, high intensity noise bumps that will be

recorded along with the accelerometer data.

The data from both sensors will be combined

according to the following table (see Table 1):

3.2.4 SpO

Monitoring

The optical pulse oximetry (Mannheimer, 1997) is a

non-invasive method to determine the percentage of

oxygen saturation in blood. Its operation is based on

the fact that haemoglobin (Hb) and saturated

haemoglobin (oxyhaemoglobin, HbO2) have

different light absorption coefficients for different

wavelengths. Oxygenated blood absorbs more

infrared light, while poorly oxygenated blood absorbs

more red light. There are parts of the body where the

skin is thin enough and blood vessels are visible. In

these places, it is possible to identify this difference

of light absorption to determine the degree of

saturation. To monitor this parameter, a MAX30102

module will be used.

The MAX30102 (MAX30102, 2020) is a sensor

manufactured by Maxim Integrated that incorporates

the pulse and oximeter functions in a single

integrated. It can de used together with an Arduino-

type processor module using the I2C communication

protocol.

The MAX30102 sensor incorporates two LEDs,

one red spectrum (660 nm) and one infrared (880

nm), as well as photodiodes to measure reflected light

and an 18-bit ADC. The MAX30102 is placed on the

skin, for example on the finger or wrist. The sensor

detects the reflected light and determines the degree

of saturation.

3.2.5 Blood Pressure Monitoring

Blood pressure is measured with a commercial device

equipped with a wireless communication interface.

There are different devices with same characteristics.

In our case, we have used the Beurer BC57 blood

pressure monitor (Beurer BC57, 2020). This device

allows automatic measurements, arrhythmia

detection and contains a wireless Bluetooth interface

that allows us to communicate with our module.

Finally, using the different described sensors the

entire electronic solution would be composed as

follows (see Fig 3). These devices will be placed in a

small box that will be fixed in the chest of patient with

an elastic belt, similar to the ones used by runners.

3.3 Android Application

In this section, the proposed application to monitor

patients infected with COVID-19 virus is presented.

The flowchart of the application is depicted in Fig.

4. Once the application is started, the user must be

connected to the main Local Area Network (LAN) to

access the collected data and medical records of the

patients. Moreover, the user credentials must be

granted by the Information Technology department of

the organization in order to access the database. If the

user is not connected to the main LAN or does not

have credentials to access, a notification message will

be shown to inform the user of the terminal. However,

if the mobile phone is connected to the main LAN and

Table 1: Relation of accelerometer and microphone.

Event

Accelerometer

Microphone

Result

Cough

The patient has cough

Difficulty breathing

The patient has difficult to breath

No event

The patient is OK.

Non-invasive Wireless Mobile System for COVID-19 Monitoring in Nursing Homes

Figure 3: Diagram of hardware solution.

the user has credentials, the application will show the

main activity, in which the user will be able to see the

list of patients being monitored sorted by degree of

urgency, following the Manchester Triage System

(MTS) shown in Table 2.

New patients can be added by clicking the Add

button and filling the registration form. To access

medical information related to a patient, the user must

click on the corresponding row. By doing this, the

application will jump to its second activity where the

monitored parameters are shown by default.

Table 2: Manchester Triage System.

Group

Urgency

Code

Wait time

Life risk

Red

0 min

Very urgent

Orange

10-15 min

Urgent

Yellow

60 min

Semi urgent

Green

2 hours

Non-urgent

Blue

4 hours

However, this view presents two tabs: Monitored

data and Medical records, that the user can click to

navigated through the patient’s profile. As said

before, the first tab shows the parameters being

monitored in real-time, while the second tab shows

additional information, such as the patient’s contact

person and the list of medical visits registered since

the patient was enrolled. These records can be access

by clicking on a row of the grid, while new records

must be added by clicking the New Record button.

When selecting a previous visit, the user will be able

to enter in consultation mode to see the previous

diseases, the doctor’s consultation, and the follow-up

of the symptoms. However, in this mode, the user will

not be able to edit the gathered information. When

creating a new record, the user will enter in Edition

mode, where the information gathered in the last

medical visit will be presented for the user to edit. Fig.

5 shows the different screens of the proposed

application.

Additionally, the application will send a

notification message to the terminal whenever the

level of urgency changes. Fig. 6 shows two examples

of notification messages sent to the terminal.

These notification messages will only be sent

when the urgency level is yellow or higher, meaning

that the doctor will have 60 min or less to visit a

patient. Among the information given in these

messages, the user will be able to see the level of

urgency determined by the colour of the icon, as well

as the name of the patient in need of medical care and

the cause of the alert.

The algorithm used to determine the level of

urgency of a patient is shown in Algorithm 1, where

the values of the urgency level correspond to the

groups of the Manchester Triage System shown in

Table 2.

As the algorithm shows, the absence of one of the

monitored signals will trigger a red flag. However, if

all sensors are working correctly, the system starts

tracking the different parameters starting with the

heart rate. This way, if the heart rate of the patient is

higher than 90 bpm, the system will trigger a red flag.

Nevertheless, a heart rate equal or lower than 90 bpm

will trigger a blue flag.

NodeMCU with

IEEE 802.11 b/g/n interface

Microphone

Thermistor

Accelerometer

Bracelet to measure blood

pressure

AD8232 Module

MAX30102

ICETE 2020 - 17th International Joint Conference on e-Business and Telecommunications

Figure 4: Application flowchart.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)

Figure 5: Screenshots of the proposed application.

Non-invasive Wireless Mobile System for COVID-19 Monitoring in Nursing Homes

Figure 6: Notification messages.

4 RESULTS

This section presents the detection of parameters and

the alert generation. The section also includes some

screenshots of the Android application when

notification messages are received.

To evaluate the correct operation of our

application and proposed system, values are

measured in 6 anonymous patients. The measured

values are labelled with a value from 0 to 3

(depending on the type of parameter), following the

values of Table 3. As we can see, some parameters

such as cough or dyspnoea have only 2 possibilities,

that is, the patient has cough, or the patient has not

cough. However, other parameters such as heart rate

are always present in the patient. For this reason, an

additional state has been considered for temperature,

blood pressure, blood oxygen saturation and heart

rate. This additional parameter indicates that the

sensor is not collecting data. For a patient with serious

diseases such as COVID-19 may imply a dangerous

situation and the patient would be labelled as very

urgent to be assisted by a nurse or physician as soon

as possible. Other parameters such as chills or cough

are not symptoms that require urgent attention and

therefore patients with these symptoms would be

labelled in yellow, according to Manchester Triage

System (Table 2), if the patient does not have any

another serious symptom. Fig. 7 shows the data

collected in 6 patients of these 8 symptoms, while Fig.

8 shows the labels they would receive, considering

the measured data and the Manchester Triage System.

Algorithm 1: Triangle algorithm.

Table 3: Measured ranges and its value to make decisions.

ICETE 2020 - 17th International Joint Conference on e-Business and Telecommunications

Figure 7: Data from patients.

Figure 8: Label assigned according to Manchester Triage System.

5 CONCLUSION AND FUTURE

WORK

COVID-19 disease is being especially serious for

elderly people who are in nursing homes. When

persons are infected, they are usually confined in their

rooms and often remain in bed with difficulties in

moving.

In order to facilitate the monitoring and care of

these patients, this paper has presented a system

consisting of an Android application for data

management and a multisensor device to monitor the

vital signs of patients. Through the application, nurses

and doctors can monitor patients and they are also

notified if any patient worsens his condition. The

system is designed to process data locally (inside the

network of the nursing home) in order to preserve the

privacy of patients and their clinical data.

As future work we would like to include other

sensors to automatically collect data and apply

machine learning systems to catalog other diseases

and symptoms. Finally, we would like to extend the

application to use it in hospital environments.

REFERENCES

AD8232 features. Available at:

https://learn.sparkfun.com/tutorials/ad8232-heart-rate-

monitor-hookup-guide/all [Last access: May 22, 2020]

Ai, T., Yang, Z., Hou, H., Zhan, C., Chen, C., Lv, W., Tao,

Q., Sun, Z., Xia, L., 2020. Correlation of chest CT and

RT-PCR testing in coronavirus disease 2019 (COVID-

19) in China: a report of 1014 cases. Radiology,

200642.

Årsand, E., Frøisland, D. H., Skrøvseth, S. O., Chomutare,

T., Tatara, N., Hartvigsen, G., Tufano, J. T., 2012.

Mobile health applications to assist patients with

1 1

0 0

00 0 0 0

1 1 1 1

2 2

1 1

00 0

0 0 0

0 0

Patient 1 Patient 2 Patient 3 Patient 4 Patient 5 Patient 6

Chills Dry Cough Dyspnoea Blood in urine Temperature Blood Pressure Bloos Oxygen Saturation Heart Rate

3 3

Patient 1 Patient 2 Patient 3 Patient 4 Patient 5 Patient 6

Non-invasive Wireless Mobile System for COVID-19 Monitoring in Nursing Homes

diabetes: lessons learned and design

implications. Journal of diabetes science and

technology, 6(5), 1197-1206.

Beurer BC57 features. Available at:

https://www.beurer.com/web/gb/products/medical/blo

od-presure/wrist-blood-pressure-monitors/bc-57.php

García, L., Tomás, J., Parra, L., Lloret, J., 2019. An m-

health application for cerebral stroke detection and

monitoring using cloud services. International Journal

of Information Management, 45(), 319-327.

Guo, Y. R., Cao, Q. D., Hong, Z. S., Tan, Y. Y., Chen, S.

D., Jin, H. J., Tan, K-S., Wang, D-Y., Yan, Y., 2020.

The origin, transmission and clinical therapies on

coronavirus disease 2019 (COVID-19) outbreak–an

update on the status. Military Medical Research, 7(1),

1-10.

Hartzler, A. L., Venkatakrishnan, A., Mohan, S., Silva, M.,

Lozano, P., Ralston, J. D., Ludman, E., Rosenberg, D.,

Newton, K.M., Nelson, L. Pirolli, P., 2016.

Acceptability of a team-based mobile health (mHealth)

application for lifestyle self-management in individuals

with chronic illnesses. In 2016 38th Annual

International Conference of the IEEE Engineering in

Medicine and Biology Society (EMBC’16), Aug. 16-22,

2016, Orlando, FL, USA. (pp. 3277-3281).

Jiang, F., Deng, L., Zhang, L., Cai, Y., Cheung, C. W., Xia,

Z., 2020. Review of the clinical characteristics of

coronavirus disease 2019 (COVID-19). Journal of

General Internal Medicine, 35(), 1545–1549.

Lloret, J., Parra, L., Taha, M., Tomás, J., 2017. An

architecture and protocol for smart continuous eHealth

monitoring using 5G. Computer Networks, 129(), 340-

351.

Lopes, I. M., Silva, B. M., Rodrigues, J. J., Lloret, J.,

Proença, M. L., 2011, A mobile health monitoring

solution for weight control. In 2011 International

Conference on Wireless Communications and Signal

Processing (WCSP’11), Nov. 9-11, 2011, Nanjing,

China (pp. 1-5).

Lozano-Lozano, M., Cantarero-Villanueva, I., Martin-

Martin, L., Galiano-Castillo, N., Sanchez, M. J.,

Fernández-Lao, C., Postigo-Mrtin, P., Arroyo-Morales,

M., 2019, A Mobile System to Improve Quality of Life

Via Energy Balance in Breast Cancer Survivors

(BENECA mHealth): Prospective Test-Retest

Quasiexperimental Feasibility Study. JMIR mHealth

and uHealth, 7(6), e14136.

Mannheimer, P. D., Cascini, J. R., Fein, M. E., & Nierlich,

S. L. (1997). Wavelength selection for low-saturation

pulse oximetry. IEEE transactions on biomedical

engineering, 44(3), 148-158.

MAX30102 features. Available at:

https://datasheets.maximintegrated.com/en/ds/MAX30

102.pdf [Last access: May 22, 2020]

MMA8451 3AXIS Accelerometer deatures. Available at:

https://www.nxp.com/docs/en/data-

sheet/MMA8451Q.pdf [Last access: May 22, 2020]

NodeMCU features. Available at:

https://components101.com/development-

boards/nodemcu-esp8266-pinout-features-and-

datasheet [Last access: May 22, 2020]

Park, J. W., Chu, M. K., Kim, J. M., Park, S. G., Cho, S. J.,

2016, Analysis of trigger factors in episodic

migraineurs using a smartphone headache diary

applications. PLoS One, 11(2), e0149577.

Sendra, S., Parra, L., Lloret, J., Tomás, J., 2018, Smart

system for children's chronic illness

monitoring. Information Fusion, 40 (), 76-86

Sendra, S., Romero-Díaz, P., Navarro-Ortiz, J., Lloret, J.

(2018, October). Smart infant incubator based on LoRa

networks. In 2018 IEEE/ACS 15th International

Conference on Computer Systems and Applications

(AICCSA). Oct. 28

– Nov. 1

, 2018. Aqaba (Jordan).

(pp. 1-6).

Zhou, P., Yang, X. L., Wang, X. G., Hu, B., Zhang, L., et

al., 2020. A pneumonia outbreak associated with a new

coronavirus of probable bat origin. Nature, 579(7798),

270-273.

Zhou, P., Yang, X. L., Wang, X. G., Hu, B., Zhang, L.,

Zhang, et al., 2020. Discovery of a novel coronavirus

associated with the recent pneumonia outbreak in

humans and its potential bat origin. BioRxiv. Available

at:

https://www.biorxiv.org/content/10.1101/2020.01.22.9

14952v2.full.pdf+html [Last access: May 22, 2020]

ICETE 2020 - 17th International Joint Conference on e-Business and Telecommunications