Data Science Research Methods Project: IoMT and Emotions

This data science project delves into two primary areas: Ambient Assistive Living (AAL) and the Internet of Medical Things (IoMT). The first part of the project explores the application of IoMT in healthcare, particularly in the context of elderly care and mental health, discussing the benefits of personalized care, cost reduction, and real-time data analysis. It highlights technologies such as smart homes and telemonitoring networks, while also addressing challenges related to the human factor and the importance of social connections. The second part investigates the connection between emotions and social media content, examining how males and females respond differently to humorous and negative videos. The project uses quantitative data, including normalized emotional scores and anxiety scales, and analyzes the data using histograms and boxplots to understand the distribution and spread of emotional responses, identifying trends and variations between genders. The project concludes with a discussion of findings and implications for future research, drawing from existing literature and providing insights into the evolving landscape of data science applications in healthcare and social media analysis.

Running head: Data Science Research Methods
Data Science Research Methods
Name of the Student
Name of the University

2Data Science Research Methods
Table of Contents
Task 1.........................................................................................................................................3
Task 2:........................................................................................................................................7
References:...............................................................................................................................13

3Data Science Research Methods
Task 1
Ambient Assistive living using internet of Medical Things:
To understand ambient assistive living it is perhaps useful to first get an idea of a new
revolutionary technology known as IoT. IoT is a network of interconnected computing
machines or devices with unique identifiers that have the ability to transmit data over a
network without needing human intervention (Farooq et al 2015) . IoT finds application in all
fields and the medical field is no exception. As technology advances the life expectancy of
people also increases and with it comes the challenge of care giving for a large elderly
population (Blackman et al 2016). The proper application of internet of medical things can
cut costs for healthcare to a large extent and simplify this ever complicated process of taking
care of a diverse demographic. With more accurate diagnosis, lower costs, personalized care
IoMT has been dubbed by some as the future of healthcare. The IoMT can not only help
inform, monitor and notify caregivers it can also provide healthcare providers with actual real
time data to identify issues before they become cause for concern. Allied Market research
predicts that the IoT healthcare market will hit $136.8 billion by the year 2021 (Koleva et al
2015).
In this report it will be explored how IoT and the health industry interact and helps in
assistive living for people. As there are many subtopics which is impacted by IoT and AAL;

4Data Science Research Methods
here mainly the impact of the technology on care of elderly people ,mental health patients and
cost effectiveness of the process will be discussed in the existing literature.
Technological advancement has made it possible for people to communicate with
objects and objects to communicate with themselves forming a network of networks.
Ambient assisted living contains ways of supporting elderly people in their daily routine to
allow an independent and safe lifestyle as long as possible. Another technology called Keep
In Touch (KIT) uses smart objects and technologies to form telemonitoring networks( Quiros
et al 2015). The application of IoT and AAL in the health industry show that the process are
successful and accepted by elderly people and is pushing new domains in the healthcare
industry. A combination of KIT and Closed Loop Healthcare, a central AAL paradigm can be
realized through the IoT, where the old people can live in their home with smart objects, thus
building smart homes, and communicating to the outside world in an organized goal oriented
manner.
The IoT developed organically by several fields of technology evolving together such
as
1. Ubiquitous Communication/ Connectivity
2. Pervasive Computing
3. Ambient Intelligence
Ubiquitous computing means the general ability of objects to communicate with each
other; ambient intelligence means the capability of objects to register changes in the physical
world and thus intervene in the process. This is how IoT gets its name, the ability of smart
objects to communicate among each other and build networks of things i.e. the network of
networks.

5Data Science Research Methods
IoT has been of much help in the field of mental health care. The impact of IoT in
health has brought many new innovations in terms of monitoring, welfare interventions and
providing informative and relevant services. In pathologies such as mental health IoT is a
vital factor to improve the patient life quality and effectiveness of the medical service. High
risk depressive patients can have more chances of survival with AAL.
Systems that use Ambient Intelligence are commonly called AAL tools (Calvaresi et
al 2017) . There are a variety of AAL tools depending on the use needed of it. Medication
management tools that comes as cabinet and disperses the correct medicine to be taken at the
right time and has provisions for setting reminders and contacting the patient or their family
if the meds are not taken. For the elderly population AAL tools such as fall detection alarms,
emergency response systems and video surveillance facilities. And most importantly the
digital storage of the health reports and remote access of the same for the health providers has
the potential to make the otherwise bureaucratic process very smooth.

6Data Science Research Methods
Fig: An example of how IoT can interact with the healthcare industry. A patient with diabetes
can be allotted an Id card which, when scanned, links to a secure cloud which stores their
health record electronically including their medical histories and lab results. Therefore,
patients, physicians or nurses can easily access this information (Lee and Lee 2015).
Another technology that has broadened the scope of AAL is ambient intelligence
which is defined as the ability of a computing system to recognize objects in its presence and
respond accordingly. Information technology has also contributed to fashion AAL into the
advanced tech it is today. For examples, the smartphones that are in use today collect a
wealth of data related to health of an individual. Sensors such as gyroscope, accelerometer,
proximity sensor, and a GPS, that are present in smartphones which can facilitate real time
monitoring of data and help the healthcare providers to make more personalized
recommendations ( Garcia and Rodriguez 2015 ).
Lastly it is important to not lose sight of the future challenges and drawbacks this
emerging new technology might need to address. Most of the current advances in AAL have
not engaged to the human factor in the process. The importance of social activities and social
connections cannot be underplayed as can be seen by the failure of social networking sites
like Facebook which promised a way of connecting people world over but has also brought
along with it heightened alienation in our society. Health Care cannot be simply be delegated
to technology as caregiving is after all a humane process and there has always been a
personalized relation going on in the whole process from doctors to nurses to the patient and
his or her family (Suryadevara and Mukhopadhyay 2014). This is the main argument for the
future challenge of AAL apart from the technological shortcomings. Technology grows at a
fast and shortcomings can generally be overcome without much difficulty but the main
challenge is trying to bring a humane environment in dealing with the situation as sensitive as
caregiving which cannot be merely technically resolved.

7Data Science Research Methods
Task 2:
Introduction:
The task here is an investigation to understand how our emotions are connected to what we
watch in social media. The question also seeks to understand how male and female react
differently to the videos. For the experiment, a funny video and a negative video are shown to
the participants and are asked to answer a questionnaire. The questionnaire contains
quantitative information about the videos watched and rates the emotional score of watching
a funny videos on a scale of 1 to 9 and rating the negative videos watched on an anxiety scale
of 0 to 80.
a)
NMF NFF NMN NFN
-
0.9284767
-
1.08908
-
0.08631
0.15771
1
-
0.9284767
0.75762
2
0.56099
1 -0.8264
0.7427813
5
0.14205
4
0.56099
1
1.96192
1
0.7427813
5
0.14205
4
-
0.21577
-
0.25234

8Data Science Research Methods
-
0.9284767
-
1.70465 0.94937
1.22383
5
-
0.9284767
-
2.32022
0.43153
2
1.46986
3
0.7427813
5
0.75762
2
-
0.47469
0.48574
9
0.7427813
5
0.75762
2
-
0.34523
-
1.07243
0.7427813
5
0.75762
2
-
1.51036
-
1.15444
-
0.9284767
0.14205
4
-
0.21577
-
0.33435
-
0.9284767
0.75762
2 -1.3809
-
0.58038
0.7427813
5
0.75762
2
-
0.86306
-
1.23645
0.7427813
5
0.14205
4
-
0.21577
0.15771
1
-
2.5997347
0.04315
3
0.7427813
5
-
1.89874
0.7427813
5
1.46720
8
0.7427813
5
1.59666
8
0.7427813
5
1.59666
8
Where,
NMF = Normalized emotional score for males watching funny videos.
NFF = Normalized emotional score for females watching funny videos.
NMN = Normalized emotional score for males watching negative videos.
NFN = Normalized emotional score for females watching negative videos.

9Data Science Research Methods
b)

10Data Science Research Methods
The histogram for normalized score for males watching funny videos shows that the
distribution is left skewed with a standard deviation 1.03, skewness =-1.085 and kurtosis =
0.387.

11Data Science Research Methods
The histogram for normalized score for females watching funny videos shows that the
distribution is left skewed with a standard deviation 1.04, skewness =-1.408 and kurtosis =
0.867.
The histogram for normalized score for females watching negative videos shows that the
distribution is slightly left skewed with a standard deviation 1.02, skewness =-.070 and
kurtosis = -0.536.

12Data Science Research Methods
The histogram for normalized score for females watching negative videos shows that the
distribution is slightly left skewed with a standard deviation 1.04, skewness = -.629 and
kurtosis = -0.536.
c)

13Data Science Research Methods
Fig: The side by side boxplot for male and female’s normalized scores from watching
negative videos are drawn.
The boxplots shows the spread of the data and from the fig it can be seen that the spread is
higher for the males than the females. There does not seem to be any outliers for the
emotional scores of both males and females in watching the negative videos. The mean for
normalized score is zero for both the males and the females. The median value is lies below
the mean for both the genders but is higher in case of males. Similar it can be seen the spread
of the data is higher in case of the male members than the female members.

14Data Science Research Methods
References:
Blackman, S., Matlo, C., Bobrovitskiy, C., Waldoch, A., Fang, M.L., Jackson, P., Mihailidis,
A., Nygård, L., Astell, A. and Sixsmith, A., 2016. Ambient assisted living technologies for
aging well: a scoping review. Journal of Intelligent Systems, 25(1), pp.55-69.
Calvaresi, D., Cesarini, D., Sernani, P., Marinoni, M., Dragoni, A.F. and Sturm, A., 2017.
Exploring the ambient assisted living domain: a systematic review. Journal of Ambient
Intelligence and Humanized Computing, 8(2), pp.239-257.
Farooq, M.U., Waseem, M., Mazhar, S., Khairi, A. and Kamal, T., 2015. A review on
internet of things (IoT). International Journal of Computer Applications, 113(1), pp.1-7.
Garcia, N.M. and Rodrigues, J.J.P.C., 2015. Ambient Assisted Living, From Technology to
Intervention. In Ambient Assisted Living (pp. 22-25). CRC Press.
Koleva, P., Tonchev, K., Balabanov, G., Manolova, A. and Poulkov, V., 2015, October.
Challenges in designing and implementation of an effective Ambient Assisted Living system.
In 2015 12th International Conference on Telecommunication in Modern Satellite, Cable and
Broadcasting Services (TELSIKS) (pp. 305-308). IEEE.
Le Parc, P. (2015). Special Issue on Ambient Assisted Living. Journal Of Intelligent Systems,
24(3). doi: 10.1515/jisys-2015-0012
Lee, I. and Lee, K., 2015. The Internet of Things (IoT): Applications, investments, and
challenges for enterprises. Business Horizons, 58(4), pp.431-440.
Memon, M., Wagner, S. R., Pedersen, C. F., Beevi, F. H. A., & Hansen, F. O. (2014).
Ambient assisted living healthcare frameworks, platforms, standards, and quality attributes.
Sensors, 14(3), 4312-4341.
Queirós, A., Silva, A., Alvarelhão, J., Rocha, N.P. and Teixeira, A., 2015. Usability,
accessibility and ambient-assisted living: a systematic literature review. Universal Access in
the Information Society, 14(1), pp.57-66.

15Data Science Research Methods
Suryadevara, N.K. and Mukhopadhyay, S.C., 2014. Determining wellness through an
ambient assisted living environment. IEEE Intelligent Systems, 29(3), pp.30-37.
Wan, J., Gu, X., Chen, L. and Wang, J., 2017, October. Internet of things for ambient assisted
living: challenges and future opportunities. In 2017 International Conference on Cyber-
Enabled Distributed Computing and Knowledge Discovery (CyberC) (pp. 354-357). IEEE.

16Data Science Research Methods