An RFID Based Localization and Mental Stress Recognition System

Using Wearable Sensors

Mhd. Wasim Raed

, Semih Y

, Ali G

unes¸

, Igor Kotenko

2 a

, Elena Fedorchenko

2 b

and Anna Polubaryeva

Department of Computer Engineering, Istanbul Aydin University, Istanbul, Turkey

St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia

ITMO University, St. Petersburg, Russia

anna.polubaryeva@gmail.com

Keywords:

RFID, Mental Stress, Mental Health, Wearable Sensors, Recognition System, Monitoring System, Arduino,

Heart Rate Variability, Electro Dermal Activity, Bitalino Development System.

Abstract:

A vast increase in the percentage of elderly people over the past few decades has induced a serious concern

among the research fraternity worldwide. Consequently, the large increase in the number of elderly needing

assistance because of chronic diseases is expected to take place. Dementia, depression and mental stress are

among the most disabling diseases with dangerous consequences such as wandering into hazardous or insecure

areas. This wandering, particularly in urban areas can be life threatening. Recently, with the rapid emergence

of disruptive technologies like Internet of Things (IoT), Radio Frequency Identiﬁcation (RFID) and wireless

bio sensors, it has become feasible to build systems that combine IoT and the cloud for monitoring the elderly

suffering from dementia or depression. Furthermore, mental chronic diseases, such as stress and depression,

are becoming a major concern for governments around the globe. The American Psychological Association

(APA) categorizes stress, anxiety and depression as main factors for diverse mental health problems. The

cost for treating work-related stress, anxiety and depression, is estimated to be around 617 billion euros per

year in Europe alone. Wearable devices for monitoring chronic diseases such as mental stress and depression

have been considered as game-changers to the way diseases are managed, by measuring vital signs like skin

conductance and changes in the levels of biological stress, and sending warnings remotely to an online server.

This paper proposes a work in progress Arduino based real-time stress recognition and localization system

using wearable RFID and vital sign sensors for elderly suffering from Dementia and mental stress. The

current work utilizes the heart rate variability and Electro Dermal Activity wearable sensors based on the

Bitalino development system for measuring mental stress and anxiety in a smart home setting for elderly

living alone by exposing a number of subjects to stress and anxiety stimulating horror videos. The system was

tested successfully in the university lab.

1 INTRODUCTION

Stress is a common human physiological and physical

body reaction. However, prolonged stress may lead to

adverse effects on human health. One of the victims

of prolonged stress are employees at the workplace

ofﬁce. Stressed employees are often unproductive,

and companies must bear their healthcare costs. Emo-

tionally stressful and traumatic events damage the hu-

man psyche. According to new research, stress may

https://orcid.org/0000-0001-6859-7120

https://orcid.org/0000-0001-6707-9153

damage the heart as well. In the most relevant study

so far on this topic, scientists estimate that a stress-

related psychiatric disorder may increase the rate of

heart attacks by 34%, strokes by 75%, and high blood

pressure by over 100%. A stressful encounter or event

increases the risk of heart attack by a factor of 1.34,

stroke by a factor of 1.75 and high blood pressure by

a factor of 2.15. Even though stress-related disorders

are treatable, it is important to diagnose the symptoms

of stress early through regular monitoring of the hu-

man body. The goal of this project is to develop an ef-

fective stress monitoring system for ofﬁce employees

and thereby prevent the onset of stress-related health

Raed, M., Yön, S., Güne¸s, A., Kotenko, I., Fedorchenko, E. and Polubaryeva, A.

An RFID Based Localization and Mental Stress Recognition System Using Wearable Sensors.

DOI: 10.5220/0011796000003414

In Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 4: BIOSIGNALS, pages 325-331

ISBN: 978-989-758-631-6; ISSN: 2184-4305

 2023 by SCITEPRESS – Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

325

disorders (Bacon, 2019).

Stress is considered as the health epidemic of the

21st century according to World Health Organization

(WHO). The WHO deﬁned the stress as a response

of a mismatch between the pressures and demands in

life with their abilities and knowledge. In fact, the

stress has the impact in not only the emotional and

physical health of human but also businesses (Fink,

2016). In 1999, stress costs European Union 20 bil-

lion euros where 50% to 60% of all sick days and

42 billion dollars for USA in 2002 (Brun, ). Fur-

thermore, according to Richmond Hypnosis Center,

110 million people die every year due to stress. That

means, every 2 seconds, 7 people die. According to

WebMD, intense and long-term anger causes mental

health problems including anxiety, depression, self-

harm, high blood pressure, coronary heart disease,

stroke, and cancer. Heart rate variability (HRV), re-

ferring to the tiny variation of the interval between

successive sinus heartbeats, contains abundant infor-

mation of autonomic nervous response (Malik et al.,

1996; Kim et al., 2006).

HRV can reﬂect the balance between sympathetic

and parasympathetic branches of the individual auto-

nomic nervous system by its spectral analysis. Time-

domain, frequency-domain and nonlinear indices of

HRV have been widely used as the marked features

for emotion recognition.

Kim et al. used time-domain and frequency-

domain HRV indices to achieve an accuracy of 61.8%

for classifying sadness, stress, surprise and anger

emotions (Kim et al., 2006). Mikuckas et al. de-

veloped a human-computer system for stressful state

recognition by analyzing multiple HRV indices from

time-domain, frequency-domain and nonlinear and

reported that most HRV indices were sensitive to

stress state (Mikuckas et al., 2014).

Furthermore, Dementia is considered to be a

chronic disease, where the elderly suffers from a dete-

rioration in cognitive functions (i.e. the ability to pro-

cess thought) beyond what might be expected from

normal younger people. This disease affects memory,

orientation, thinking, comprehension, learning capac-

ity, judgement, and consciousness. The impairment

of the cognitive function is usually accompanied, and

occasionally preceded, by deterioration in emotional

control, social behavior, or motivation. The impact

of dementia on family, caregivers and society at large

can be multi-dimensional: physical, social, psycho-

logical, and economic (Raad et al., 2021).

Lately, researchers have focused on the impor-

tance of quality of life in a healthcare setting. The

quality of life (QoL) is deﬁned as the need to be

able to carry activities of daily living (ADL) indepen-

dently, enjoy time, and feel empowered (EDA, 2021).

The World Health Organization (WHO) deﬁnes QoL

as “the individual’s recognition of their position in

life in the context of the culture and value systems

in which they live and related to their goals and con-

cerns”. Providing the elderly with smart-home ser-

vices like localization is in the right direction for

boosting their QoL (Raad et al., 2021).

These related studies gave us a good basis for fur-

ther exploring the changes in HRV indices between

different emotional states. This research aims at de-

veloping a comprehensive system based on disrup-

tive technologies like RFID & wearable biosensors

for real time monitoring of mental stress, depression

and wandering detection of elderly. The relevance of

proposed research is particularly in the valuable con-

tribution to the research area of Internet of things,

battery less RFID and wireless biosensor for moni-

toring mental stress and localization of elderly suffer-

ing from Dementia in a smart home setting. Here, we

propose an affordable prototype of a novel real time

stress recognition system using wearable vital sign

sensors. The proposed system constitutes an excellent

work in progress test bed for establishing an optimal

telehealth biosensor network for stress level identiﬁ-

cation, acquisition of vital signs data using biosensors

with wireless capabilities.

The paper is organized as follows. Section 2 de-

scribes the research methodology including the phys-

iological and physical basis of the research as well as

technological basis of the research. Section 3 intro-

duces the proposed RFID based tracking system. The

paper ends with discussion on the future research and

the privacy and security related issues.

2 RESEARCH METHODOLOGY

This section describes the research methodology in-

cluding the physiological and physical basis of the re-

search as well as technological basis of the research.

2.1 Electro Dermal Activity (EDA) and

Stress

The human heart provides vast insight into our hu-

man body. One such term is HRV which measures

the variation in time between two consecutive heart-

beats. HRV is affected by a variety of physiologi-

cal phenomena such as breathing, hormonal reactions,

metabolism, movement of the human body and one

of the factors are stress reactions and emotional reac-

tions. In an ideal scenario, HRV of a person increases

during relaxing activities such as meditation, when a

BIOSIGNALS 2023 - 16th International Conference on Bio-inspired Systems and Signal Processing

326

person is in a good mood, etc., while during a stress-

ful encounter, HRV decreases which point to an in-

verse correlation between HRV and stress (Hoffman,

). Fig.1 illustrates the HRV characteristics under high

stress and low-stress conditions measured using vol-

unteering students subjects during exam period.

Figure 1: NN interval in a low and high stress situation.

Electro dermal Activity also known as galvanic

skin reﬂects the activity of the sympathetic nervous

system. The state of the sweat glands reﬂects the

measure of skin resistance. When the sympathetic

nervous system is activated, the sweating of the skin

increases the conductance of the skin. During activa-

tion of the sympathetic nervous system due to stress-

ful encounters, the brain sends a signal to the skin to

increase the sweat levels. When the sweat level in-

creases, the corresponding increase in skin conduc-

tance can be measured to study the stress levels. Skin

conductance can be characterized into two types:

1. Tonic skin conductance response which measures

smooth and slow-changing conductance levels

and

2. Phasic skin conductance response which mea-

sures the rapid changing peaks.

The skin conductance level using tonic skin con-

ductance and phasic skin conductance response tests,

conducted in Yi Yang and Bingkun Yang’s work in

Human Computer Interaction Lab (EDA, 2021).

2.2 The System Hardware

The proposed system is implemented in the form of

a prototype of Arduino microcontroller interfaced to

a multitude of bio sensors from Bitalino kit using

the bio signal platform. The Arduino is an open-

source platform for microcontrollers that are used by

communities and non-engineering people to help in

building innovative thinking and encourage commu-

nities to develop new electronic products that help in

many ways such as manufacturing and other sectors.

The Arduino UNO utilized in the proposed stress-

monitoring system is interfaced to Gravity heart rate

sensor (a thumb-sized heart rate monitor designed for

Arduino microcontrollers). It has a Gravity interface,

for easy plug-and-play connectivity. It is a pulse sen-

sor that is developed based on PPG (Photo Plethys-

mography) techniques. It is a simple and low-cost

optical technique that can be used to detect blood vol-

ume changes in the microvascular bed of tissues (see

Fig.2).

Figure 2: Interfacing Gravity heart rate sensor with Arduino

Uno.

BITtalino is a hardware and software toolkit that is

designed to measure body signals. It could be used for

biomedical proposes or industrial applications for the

welfare of workers who work in a harsh environment

and it can help in designing new wearable products

for everyday use. The BITalino hardware has a mi-

croprocessor with an external battery and has 32kB

ﬂash program memory; 1kB EEPROM; 2kB inter-

nal SRAM, operating voltage 3.3V-5V, it can be con-

nected via Bluetooth or USB port. The BiTalino was

utilized using the Biosignal platform to lay the ground

for developing an IoT based wearable stress monitor-

ing system.

The testing took place utilizing volunteering stu-

dents in the ﬁnal year project examination period,

where the students suffer from a lot of mental stress.

The measurement of mental stress took place using

wearable heart rate, EDA & ECG wearable sensors

from Bitalino kit using the Biosignal platform. We

have performed extensive experiments using student

volunteers in the university RF

ID lab due difﬁculties

we encountered to access elderly patients in hospitals.

2.3 The Heart Rate Measurement

The four graphs below illustrate the Heart rate mea-

surement and HRV before and during stressful situa-

tions, graphically depicted in Figures 3-6.

Figures 3 and 4 display the heart rate and the cor-

An RFID Based Localization and Mental Stress Recognition System Using Wearable Sensors

327

responding HRV readings of the student when he is at

rest.

Figures 5 and 6 display the heart rate and HRV at

the time of the stressful encounter. When the subject

experiences a stressful moment his heart rate spikes

and HRV remains low with little to no variation be-

tween successive heartbeats.

Figure 3: Heart rate before the moment of stress.

Figure 4: Heart rate variability before moment of stress.

Figure 5: Heart rate measured at the moment of stress.

Figure 6: HRV measured at the moment of stress.

2.4 Stress Measurement Using EDA

Figures 7 and 8 illustrate the tonic skin conductance

level from BITalino software before and after the

stressful encounter invoked by a horror video. The

skin conductance displayed constant low skin conduc-

tance level in Fig.7 and then displayed a huge spike in

Fig.8 indicating a moment of stress.

Figure 7: Tonic skin conductance in a relaxation scenario.

Figure 8: Tonic skin conductance at the moment of stress.

3 THE PROPOSED RFID BASED

TRACKING SYSTEM

Elderly suffering from dementia and other chronic

diseases who are living alone at home, are usually too

frail and not able to carry basics activities of daily

living (ADL). Also, elderly suffering from dementia

often show psychotic behavior and instance of com-

plete unawareness, which requires continuous assis-

tance and support. Living in smart homes eases the

situation of these people by providing necessary fa-

cilities and services to make their lives more enjoy-

able. One important aspect of smart homes is the

availability of a seamless localization system. The

main feature of such systems is to be able to track

remotely the movement of the elderly at the room

level. Currently, this is done using surveillance track-

ing systems such as cameras. Although these systems

BIOSIGNALS 2023 - 16th International Conference on Bio-inspired Systems and Signal Processing

328

have been successful, they are privacy invasive. In

this work, we are proposing to use a Sirit RFID ro-

bust reader, commonly used in industrial applications

to track the movement of the elderly. For our design,

the reader is conﬁgured to read and identify tags in

the range of the deployed antennas. The reader is con-

nected to linearly polarized antennas with RF power

of 30 dbm. We used antennas with coverage range of

7 to 15 meters.

3.1 RFID Sensor Platform

The passive RFID tags are used to ﬁnd the location

of the elderly. Therefore, each elderly is to wear a

personal tag all the time. The tag can be attached in

different places on the body as illustrated by Fig.9.

The localization principal is based on three possible

zones: within bedroom, outside bedroom, while exit-

ing the house. The methodology of the proposed solu-

tion is based on distributing four antennas: three in the

house (one antenna in each room) and one at the exit.

To detect that the elderly person is inside their room,

he needs to be detected by the room antenna. The role

of the exit antenna is to trigger that the elderly is tend-

ing to wander outside the house. Time represents the

last timestamp at which the readings took place, they

refresh in real-time (see Table1 for the timestamp of

the elderly localization indoors). See Fig.10 for the

localization algorithm of the elderly roaming inside

and outside the house (Raad et al., 2021).

Figure 9: Tonic skin conductance at the moment of stress.

Table 1: Localization of elderly with timestamp (Raad et al.,

2021).

Id Location Time

0X00A1 In House 11:44:29

0X00A2 Roaming outside House 11:44:01

0X00A3 Inside Room 11:44:38

Figure 10: Higher level Localization of the Elderly (Raad

et al., 2021).

4 DISCUSSION AND

CONCLUSION

We carried several tests to determine the best perfor-

mance of the antennas to detect the wearable RFID

tags. The testing in the lab started by adjusting the

antennas based on their polarization to maximize the

reading probability of the tags inside and outside the

lab environment.

The proposed RFID localization system was

tested successfully using three volunteers. The RFID

part of the research contributes an added value for

boosting the quality of life by mitigating the number

of falls for elderly suffering from Dementia, and by

constituting a robust telehealth smart system for send-

ing warnings in the onset of elderly wandering outside

their home.

In addition to that, in the context of elderly suffer-

ing from depression and mental stress, Physiological

and bio signals such as galvanic skin response, elec-

trocardiogram (ECG), photo plethysmography (PPG),

electromyography (EMG) and electrical impedance

spectroscopy (EIS) can provide reliable information

regarding the intensity of stress level.

The relevant stress data collected constitutes the

ﬁrst phase of this research to investigate the feasibility

of implanting such a system in a non-invasive form.

In this direction, the intended research in the near fu-

ture aims to investigate sensors’ placement within the

human body, which will help to develop an optimiza-

tion conﬁguration of vital sign sensors network for

stress level detection. In order to generate stress, a

set of different audios and videos will be used by re-

ferring to the World Health Organization (WHO) and

specialists in the psychotherapist ﬁelds. The videos

and audios will be selected to speciﬁcally generate

several types of mental stress including neutral, mild,

moderate and severe stress levels. A study on existing

An RFID Based Localization and Mental Stress Recognition System Using Wearable Sensors

329

affective frameworks used for a similar purpose will

be deeply carried out. In addition, to mimic reality

and improve the efﬁciency of the generated stress, a

full virtual reality system with all accessories will be

used with the selected contents. Data collection and

preprocessing will be carried out and various machine

learning algorithms will be investigated through ex-

tensive simulation for stress level classiﬁcation. See

Fig.11 depicting the scenario of investigating the opti-

mum placement of the various wearable mental stress

monitoring sensors on the human body. The future

work will be centered around an IOT telehealth sys-

tem for monitoring the human mental stress to miti-

gate the drastic effect of stress on the quality of life,

and utilizing RFID for immediate localization of el-

derly once the warnings are received by a caregiver.

Figure 11: Optimum placement of the wearable mental

stress sensors.

Finally it should be noticed that the 21st century

has brought with it a higher risk of attacks on medi-

cal devices and medical applications, the emergence

of new types of such attacks and, accordingly, an en-

hanced risk for patients, what use wearable, wireless

or embedded medical devices and may suffer from

the malicious actions of such intruders: medical data

nowadays is more valuable and attractive for attack-

ers than ﬁnancial data (Burky, 2022; Doynikova et al.,

2022).

In regard with the elderly, suffering from dementia

and other diseases mentioned in this article, the risk

blast off even more: using the devices of more vulner-

able patients, attackers can access the data of medical

institutions, relatives of such patients, directly harm

the elders.

Recent studies have shown that there are countless

attack vectors, attack methodologies and vulnerabili-

ties of the medical devices of all types (Yaqoob et al.,

2019). The security and safety of medical devices

are vital for people using any kind of medical device,

including implantable medical devices (IMDs). It is

possible that IMDs will also be subject to complex

cyberattacks – ransomware attacks – over time. At

the moment, the most urgent problem seems to be

breaking such IMDs by simply studying the speciﬁ-

cations and documentation for them, which are freely

available on Google, as well as by breaking the cryp-

tographic protection (Radcliffe, 2011). Lee et al. (Li

et al., 2011) researched insulin pump systems. They

managed not only to get encrypted information from

the device, but also to fake false glucose readings on

the monitor. In addition, they successfully sent their

own commands to the pump due to the lack of authen-

tication. Radcliffe (Radcliffe, 2011) and Takahashi

(Takahashi, 2011) have shown that they can take full

control of some insulin pump systems because these

medical devices receive unauthorized radio signals or

commands. That is why these and other researchers

are not only hacking medical devices, but also work-

ing on security solutions such as passwords for pace-

makers and other embedded medical devices (Storm,

2011).

Another example of a wearable device that may

attract the attention of hackers is Nymi, a small wear-

able device that uses an electrocardiogram (ECG)

to authenticate the user (D’Souza, ). According to

the developers of this device, a person’s own heart-

beat is a unique key that can be used to unlock any

paired device. If the device is hacked, then with the

help of persistent identiﬁcation, one can access any

other devices that belong to a person: a car, pref-

erences, location, and downloaded data. Manipulat-

ing a medical devices of people with mental chronic

diseases may cause severe damage and unpredictable

outcomes. This is why it is so signiﬁcant to take a

security and privacy of the medical devices into con-

sideration within the whole period of medical device

existence (starting from design and till utilization).

The new system developed by the authors of this

article is based on Radio Frequency Identiﬁcation

(RFID) technology, which many authors consider rev-

olutionary and versatile: RFID can be used both in the

provision of direct medical services, the provision of

the services related to medical purposes, and directly

to track patients (Bochem et al., 2022; Abugabah

et al., 2020; Rajak and Shaw, 2021). It should be

noted that despite the increased and ever-increasing

risk for the security and privacy of medical devices,

manufacturers of the latter still pay less attention to

safety issues, giving priority to the efﬁciency and per-

formance of devices (Doynikova et al., 2022). The

RFID-based tracking system proposed in this article,

in addition to efﬁciency, also will take into account

issues of privacy and security.

ACKNOWLEDGEMENTS

The Authors Acknowledge the support of Istanbul

Aydin University.

BIOSIGNALS 2023 - 16th International Conference on Bio-inspired Systems and Signal Processing

330

REFERENCES

(2021). What should i know to use eda

data in my experiment? Available on-

line: https://support.empatica.com/hc/en-

us/articles/203621955-What-should-I-know-to-

use-EDA- data-in-my-experiment-. Accessed on 24

November 2022.

Abugabah, A., Nizamuddin, N., and Abuqabbeh, A. (2020).

A review of challenges and barriers implementing rﬁd

technology in the healthcare sector. Procedia Com-

puter Science, 170:1003–1010. The 11th International

Conference on Ambient Systems, Networks and Tech-

nologies (ANT) / The 3rd International Conference on

Emerging Data and Industry 4.0 (EDI40) / Afﬁliated

Workshops.

Bacon, S. (2019). Stress, psychiatric disorders, and cardio-

vascular disease. BMJ, 365:l1577.

Bochem, A., Abugabah, A., and Smadi, A. A. (2022). Smart

rﬁd application in health care: Using rﬁd technology

for smart inventory and logistic systems in hospitals.

In 2022 45th Jubilee International Convention on In-

formation, Communication and Electronic Technol-

ogy (MIPRO), pages 18–23.

Brun, J. P. Stress: The health epidemic of the 21st century.

Available online: https://www.who.int/occupational\

health/topics/brunpres0307.pdf?ua=1.

Burky, A. (2022). Medical devices are a weak

link in hospital cyber defenses, putting pa-

tients in the crossﬁre: study. Available on-

line: https://www.ﬁercehealthcare.com/health-

tech/cyberattack-revolving-doors-medical-devices-

put-patients-crossﬁre. Accessed on 24 November

2022.

Doynikova, E., Novikova, E., Murenin, I., Kolomeets, M.,

Levshun, D., Tushkanova, O., Levshun, D., Meleshko,

A., and Kotenko, I. (2022). Security Measuring Sys-

tem for IoT Devices, pages 256–275.

D’Souza, A. Your heartbeat may soon be your only

password. Available online: https://www.wired.com/

insights/2014/06/heartbeat-may-soon-password/. Ac-

cessed on 24 November 2022.

Fink, G. (2016). Stress: The health epidemic of the 21st

century. Available online: https://scitechconnect.

elsevier.com/stress-health-epidemic-21st-century/.

Accessed on 24 November 2022.

Hoffman, T. What is heart rate variability (hrv) &

why does it matter?: Firstbeat blog. Avail-

able online: https://www.ﬁrstbeat.com/en/blog/

what-is-heart-rate-variability-hrv/. Accessed on 24

November 2022.

Kim, K. H., Bang, S. W., and Kim, S. R. (2006). Emo-

tion recognition system using short-term monitoring

of physiological signals. Medical and Biological En-

gineering and Computing, 42:419–427.

Li, C., Raghunathan, A., and Jha, N. (2011). Hijacking

an insulin pump: Security attacks and defenses for a

diabetes therapy system. In 2011 IEEE 13th Interna-

tional Conference on e-Health Networking, Applica-

tions and Services, HEALTHCOM 2011, 2011 IEEE

13th International Conference on e-Health Network-

ing, Applications and Services, HEALTHCOM 2011,

pages 150–156. 2011 IEEE 13th International Confer-

ence on e-Health Networking, Applications and Ser-

vices, HEALTHCOM 2011 ; Conference date: 13-06-

2011 Through 15-06-2011.

Malik, M., Bigger, J. T., Camm, A. J., E., K. R., Malliani,

A., and Moss, A. J. (1996). Heart rate variability:

standards of measurement, physiological interpreta-

tion, and clinical use. Circulation, 93(5):1043–1065.

Mikuckas, A., Mikuckiene, I., Venckauskas, A., Kazanavi-

cius, E., Lukas, R., and Plauska, I. (2014). Emotion

recognition in human computer interaction systems.

Elektronika ir Elektrotechnika, 20(10):51–56.

Raad, M. W., Deriche, M., and Kanoun, O. (2021). An

rﬁd-based monitoring and localization system for de-

mentia patients. In 2021 18th International Multi-

Conference on Systems, Signals & Devices (SSD),

pages 1–7.

Radcliffe, J. (2011). Hacking medical devices for fun and

insulin breaking the human scada system. Accessed

on 24 November 2022.

Rajak, M. and Shaw, K. (2021). An extension of technology

acceptance model for mhealth user adoption. Technol-

ogy in Society, 67:101800.

Storm, D. (2011). Black hat: Lethal hack and wireless at-

tack on insulin pumps to kill people. Available online:

https://www.computerworld.com/article/2470689/black-

hat–lethal-hack-and-wireless-attack-on-insulin-

pumps-to-kill-people.html. Accessed on 24 Novem-

ber 2022.

Takahashi, D. (2011). Excuse me while i

turn off your insulin pump. Available

online: https://venturebeat.com/mobile/

excuse-me-while-i-turn-off-your-insulin-pump/.

Accessed on 24 November 2022.

Yaqoob, T., Abbas, H., and Atiquzzaman, M. (2019). Se-

curity vulnerabilities, attacks, countermeasures, and

regulations of networked medical devices—a review.

IEEE Communications Surveys & Tutorials, 21:3723–

3768.

An RFID Based Localization and Mental Stress Recognition System Using Wearable Sensors

331