The Dynamics of the Ubiquitous Internet of Things (IoT) and Trailblazing Data Mining (DM)

International Journal of Wireless & Mobile Networks (IJWMN), Vol.14, No.3, June 2022
DOI:10.5121/ijwmn.2022.14302 21
THE DYNAMICS OF THE UBIQUITOUS
INTERNET OF THINGS (IOT) AND
TRAILBLAZING DATA MINING (DM)
Bongs Lainjo
Cybermatic International, Canada
ABSTRACT
The research study intends to understand the thematic dynamics of the internet of things (IoT), thereby
aiming to address the general objective i.e. “To explore and streamline the IoT thematic dynamics with a
focus on cross-cutting data mining, and IoT apps evidence-based publication trends”. To meet this
objective, secondary research has been compiled as part of the analytic process. It was found from the
research that IoT continues to evolve with significant degrees of proliferation. Complementary and
trailblazing data mining (DM) with more access to cloud computing platforms has catalyzed accelerating
the achievement of planned technological innovations. The outcome has been myriads of apps currently
used in different thematic landscapes. Based on available data on app searches by users, and between
2016 and 2019, themes like sports, supply chain, and agriculture maintained positive trends over the four
years. The emerging Internet of Nano-Things was found to be beneficial in many sectors. Wireless Sensor
Networks (WSNs) were also found to be emerging with more accurate and effective results in gathering
information along with processing data and communication technologies.
In summary, available data indicate that IoT is happening and has a significant implication on data
mining. All indications suggest that it will continue to grow and increasingly affect how we interact with
“things”. A backdrop of concerns exists ranging from developing standard protocols to protecting
individual privacy.
KEYWORDS
IoT, Data Mining (DM), Trail Blaze, Ubiquitous, Evolution
1. INTRODUCTION
Over time, information technology has evolved and transformed our daily way of living. The past
three decades have witnessed an unprecedented evolution of high technology and its associated
themes. Everyone can attest that their life quality has improved thanks to the incorporation of
technology in various sectors such as business and it has increased people’s motivation towards
getting the best results possible. In general, there is very little doubt that technological
innovations have served as an impetus behind these dynamics. The Internet of Things (IoT) has
served and continues to demonstrate the usefulness of human-machine integration through
sensors, and the transformation and manipulation of data through different data mining platforms.
It was the increase in communication protocol development, network creations, and increased
focus on Artificial Intelligence that birthed the IoT. According to Kong [1], the IoT involves the
information of physical objects, including sensors, machines, cars, buildings, and other items,
that allow interaction and cooperation of these objects for achieving specific goals. Others, such
as Welbourne et al. [2], provided more detailed descriptions. That is, IoT was presented as a
structure of computing that facilitates data transfer between digital and mechanical appliances

22
without involving human interaction. This makes it capable of data mining. For example,
Hancock and Hancock [3] mentioned that IoT has three important ramifications including data
collection, remote control capability, and communication between objects. Data cannot be useful
when it stands alone since it is vital to have ways for transforming the data into useful
information. In this regard, a literature review conducted by Chen et al. [4] observed that
algorithms could be applied to IoT for extracting meaningful data. Consequently, the practice of
identifying data patterns that are useful from huge datasets and utilizing for patterns or hidden
information extraction is referred to as data mining (DM). DM can also be perceived as the
exploration and transformation of data that ultimately generates information, which reveals
historically undiscovered trends and patterns. These dynamics are useful in making informed
decisions or predictions in significant cases.
In this paper, DM is specifically highlighted as an indication of its importance and cross-cutting
role in data analytics. Its invaluable contribution in propagating the transformations involved with
different IoT themes cannot be adequately emphasized. The logical layout of the article includes
background, settings, thematic proliferation, thematic implications, prognoses, and more.
2. BACKGROUND
IoT and data mining are complementary platforms. These two technologies have also had a
longstanding effect on various thematic areas including the development of IoT-enabled
technologies such as sensors for data collection, IoT-based systems of communication and data
transfer, and similar kinds of technologies [5]. The IoT and its impact on data mining have rich
backgrounds beginning with the onset of the internet. This has been highlighted in the studies of
Xia et al. [6] and WuHe et al. [5]. Some concerns associated with these platforms include
security, future developments : future architectures, regulations, and standardizations.
The IoT refers to a variety of things that are typically connected to the Internet to enhance the
sharing of data with other things. IoT-connected machines and devices can improve how human
beings work and live. An article by Kim et al. [7] suggested that IoT and its applicable
technologies can integrate classical networks. Consequently, IoT has been serving a vital purpose
ever since it appeared, contributing to innovative applications ranging from traditional equipment
to general house hold devices. It has been attracting the researchers' attention from industry,
government, and academia in the past years. The recent introduction of various transformative
technology into IoT such as data mining have helped it to become more effective [8].
An article by Bin et al. [9] suggested that data mining entails discovering novel, potentially
exciting patterns, particularly from large relevant data sets : data dredging and data archeology.
The main aim of any data mining is to build an efficient descriptive or predictive model using a
vast amount of the most appropriate and relevant data. There are various implications of IoT in
data mining. Some are explained in the following paragraphs.
Firstly, an article by Dachyar et al. [10] mentioned that the term IoT first emerged in a published
paper in the year 2006, showing the paradigm of the evolving concept of internet technology. The
concept of IoT is very crucial in con temporary circumstances [11]. They further added that the
technologies that both shape and support IoT have been in evolution for several years. In the
study conducted by Chen et al. [4], data-center architectures are significantly growing and are
found to be more distributed to accommodate the data that IoT is generating. The distributed
strategy to edge computing is mainly designed to meet the real-time processing requirements
needed for new IoT applications in the field [12]. Most business operations have extended their
data centers to the public cloud to process, assess, and store vast volumes of IoT data.

23
In an article by Cai et al. [13], the researchers reveal that IoT devices, sensors, and machines
generate a vast amount of data every second. It has further been found that cloud computing
assists in both the storage and analysis of the data. This enables the enterprise to get the
maximum gains of an IoT infrastructure [14]. Hence, the IoT solution connects people, things,
and processes, while cloud computing plays a crucial role in this collaboration to enhance high
visibility.
In a study conducted by Shi et al. [15], with the assistance of edge computing, intelligence in data
mining moves to the edge. There are various scenarios where high-speed data is the key
component of analytics, which assists in processing data with edge computing [16]. The critical
cases of IoT for edge computing include security concerns and the evolution of cloud computing.
According to Ren et al. [17], trail blazers ranked trust issues as one of the significant concerns,
ahead of technology issues. Besides, there are frequently two or three times the likelihood of
more laggards to address privacy issues, data integrity, and cyber security, including other
dimensions of trusted technology. For instance, trail blazers are probably more likely to think of
matters concerning security at the start of the IoT initiatives or choose private networks that play
a crucial role by limiting threat pressure [18].
IoT results in a massive amount of data. Literature reveals that this might possess some prognosis
in the field of e-commerce [19]. First, making information and data available to people enhances
government transparency. Transparency helps in ensuring proper insight and also reduces
government waste. A good way that the enormous data gathered by IoT helps consumers and
businesses is through empowering them towards better decision-making [20]. The IoT further
gives users knowledgeable advice.
Firms are significantly turning to IoT as their sources of data because these are typically derived
from regular monitoring of a vast range of things with in different situations, which become
available. In a study conducted by Misuraca [21], the IoT brings with it new business ventures.
The risks such as the lack of well-coordinated policies and regulations about IoT can significantly
impede its application and implementation [22]. As a result, organizations should, therefore,
develop policies and regulations and also consider their role in enabling the development of IoT
very carefully. Any IoT corporation should demonstrate an inevitable out break growth to
enhance developments [23].
In a study conducted by Saidu et al. [24], the authors indicate that the advent of the Internet has
played a crucial role in information technology and has resulted in more effective modes of
communication. Handheld devices, such as mobile phones, have made access to ambiguous
information processing more feasible [25]. IoT has made it easier for most commercial operations
as they can keep in touch with their clients.
The scope of IoT remains quite wide. If the number of peer-reviewed publications is any
indication, the challenges and degree of IoT technological innovations continue to expand
unabated at an alarming rate. As the adage goes, necessity is the mother of invention. IoT is no
exception as confirmed by the abundant and growing number of related themes associated with
IoT. An extensive and analytic perspective is presented else where in the paper.
Lastly, IoT is changing the gravitational constant in our technological world. As it matures, the
black holes of data gravity in which clouds have been placed will eventually be ripped part from
the millions of smaller data planets [25]. The smaller planets will be situated in houses, factories,
buildings, or any where else where the IoT runs to make the data actionable. Thus, we have to

24
keep all our applications blazing fast by running them at a hundred percent. In addition, we can
not leave all our applications vulnerable to the so-called nature of the Internet.
3. SETTINGS
Jacob Morgan supposed that anything that can be connected would be connected [3]. Morgan
referred to the future concerning IoT as an assertion based on an informed observation of the
trend in the IoT space. For instance, according to Kong et al. [1], various countries have adopted
strategies based on the rapid development of IoT technologies with good examples being China
with its Made-in-China 2025 strategy, the US through its American Advanced Manufacturing
Partnership Program, and Germany’s German Industry 4.0 strategy. In light of these strategies
accordingly, the IoT will continue to influence significant paradigm shifts, especially in data
management and applications. Notably, Liu et al. [26] underlined that IoT devices collect high
quality data that is utilized in new technological developments (see Figure 1). Some of these
areas include IoT data mining and analytics, development of Sensors for data collection and
management, e-health, and Big Data analytics.
Figure 1. IoT Ecosystem Platform (Source: Author)a
4. THEMATIC PROLIFERATION OF IOT
During the period July 21 and 24, 2020, a four-year retrospective (2016 -2019) database was
compiled through searches using the Goggle Scholar framework. The selection of the four years
was influenced by accessibility to recent datasets. Besides, having a minimum number of points
was also vital for facilitating possible trends’ identification (see Figures 2 and 3).
In general, there were 103 themes. Among these and based on four-year means, the theme with
the highest number of publications was the “resource management and access control” theme
with 374000 publications. At the bottom, the theme with the least number of publications was
“new human-device interaction with two publications”.
The annual median publications for all the themes over four years were 5415, 8930, 11400, and
11700 for 2016, 2017, 2018, and 2019 respectively. The averages are not reported here because
of their insensitivity to extreme values, which were quite prevalent in the data set. The annual

25
trends were as follows: Between 2016 and 2017, most (88 percent) of the themes had an increase
in the number of publications. Between 2017 and 2018, 81 percent of themes had a positive
change in the number of publications. And finally, from 2018 to 2019, the increase rate was 79
percent.
4.1. Select Themes
The reason for including the select themes in the detailed analysis was that the general population
readership could resonate and recognize them. They include healthcare, education, engineering,
household, transportation agriculture research, law enforcement, security and Trust, business,
manufacturing, supply chains, resource management, location, smart cities, and social media.
The four-year average (Figure 1) position “Resource Management” at the top with 374250
publications, followed by “Social Models “with 251000 publications. The bottom two themes
were “household” and “supply chain” with 2420 and 1398 publications respectively.
Highlights of the selected themes are also included to explore further a more complementary
perspective of these themes. Among these 18 themes (Figure 2), the number of publications in 22
percent had an annual decline in four years; seventeen percent declined on the fourth year only
with “smart city” the only theme with two consecutive declines during the last two years. The rest
had an increasing number of publications over that time frame. Concerning inching trends,
“supply chains” increased the most (102 percent) between 2016 and 2017; 50 percent between
2017 and 2018, and 56 percent between 2018 and 2019. On the other side of the spectrum,
“localization technologies” had a downward trend of 26 percent between 2016 and 2017, 41
percent and 18 percent fall in the number of publications between 2018 and 2019 with the
“resource management” dropping 41 percent in its number of publications between 2017 and
2018. There was not a single theme with the trend change of annual publications higher than the
preceding year.
In summary, these dynamics suggest the extent to which IoT technological innovations can serve
as a proxy to the number of IoT thematic publications. There is also the likelihood that these
innovations can be used to predict ongoing research themes. The implications range from
thematic knowledge sharing to exponential research challenges.
Figure 2. 4-year Averages of Select IoT Themes (Data Source: Google Scholar, Author)

26
Figure 3. Select IoT Thematic Trends - 2016-2019 (Data Source: Google Scholar, Author)
4.2. The Matic Implications
Concerning the research topic i.e. IoT and DM, several implications have been identified in the
existing literature. Deloitte [27], in its report, underlined information system platforms’ influence
in the development of a huge scope for future improvements through its effects on the current
dynamics. For instance, IoT cloud platforms are becoming increasingly important in the global
market. Hence, the IoT cloud platform market was worth 6.4 billion USD in the year 2020. With
this, the IoT solution segment has been significantly dominated by the IoT monetization market.
Hence, due to this reason, it has been estimated that the cloud platform market has an immense
scope in its future growth, thereby generating about 11.5 billion USD by the year 2025. This
further infers that the trend will continue in the future because more organizations have started to
adopt these solutions [27].
Considering the potential of IoT to avail intelligent platforms, Hassan [28] stated that it has a
significant scope of providing intelligent platforms to facilitate the collaboration of distributed
objects through wired networks or local-area wireless networks. Furthermore, information system
platforms have been specifically integrated by healthcare organizations through IoT health
monitoring systems. These platforms offer an effective environment of intelligence for assisting
and monitoring patients in remote areas. Specifically, these devices are used by IoT systems for
ensuring that they can be controlled and queried by other platforms, applications, and controllers.
This further coordinates with multiple objects without the human users’ interference. Even in the
aquarium environment, such kinds of platforms have been used, such as in the case of Libelium.
This platform used sensors that monitored several aspects of water and utilized actuators along
with pump devices that regulated and administered medicines. Most importantly, it was

27
responsible for sending wireless information, which is gathered by the sensors. Additionally,
actions are initiated by the actuators to the mobile interface or web interface accordingly [28].
Gubbi et al. [29] affirmed that cloud computing provided an appropriate platform, which acts as a
receiver of data from ubiquitous sensors. It also played the role of a computer that interpreted, as
well as analyzed the data along with availing the users with web-based visualization, which
becomes easy to understand. Besides, to develop ubiquitous healthcare, IoT has been providing
proper platforms so that body area sensors can be used for uploading the data to the servers [29].
However, Elkhodr et al. [30] argued that IoT incorporation needs proper standards for enabling
horizontal platforms, which are programmable, communicable, and operable across devices
irrespective of their model or industry applications. It was also observed that several studies
reported privacy issues while using mobile applications on relevant phone platforms. Therefore,
it has been suggested “it is most likely that privacy incidents will grow rapidly with the increase
in penetration of the IoT in our daily life. Thus, privacy remains a major problem as IoT
develops. When it comes to IoT, anonymity does not count as privacy. IoTs are designed to
automatically collect data, store them, and easily share and analyse personal data, which can have
potential adverse effects on individuals.”[30].
Another prominent platform, which that has been taken into consideration in Figure 1 is the data
mining algorithm. In this context, Sunhare et al. [31] asserted that if a proper data mining
algorithm is processed with different types of data, then valuable knowledge can be gathered.
Nevertheless, a challenging aspect evident in such instances is that it is difficult to synthesize or
select the most feasible data mining algorithm. Chen et al. ([4] further stated that these kinds of
algorithms can be efficiently used to gather private or hidden information from the available data.
It has also highlighted that more devices are being connected to IoT and hence, a large amount of
data must be analyzed. Furthermore, the latest algorithms must be modified for applying them to
big data. It also estimates that big data-related mining systems will be most appropriate to be
developed in the future for obtaining better results. Specifically, it has been noted in this study
that data mining involves the application of algorithms to the gathered data for finding patterns
and evaluating the same related to discovered knowledge [4]. Data compilation is another
important platform associated with IoT, which is essential in the concerned environment, wherein
the issue of data compression, storage, analysis, and visualization were duly addressed with the
help of data curation of IoT sensor data in the cloud platform. It has also been found that for
edge-based machine learning, as well as energy-efficient data, a compression approach was
suggested in terms of IoT [32]. Besides, Brous et al. [33] found out that informed system rollout
and informed decision-making are also involved in the IoT ecosystem platform. This is because
the IoT has been adopted for reconfiguring the processes of decision-making, especially in asset
management. Furthermore, there is the future scope of better utilization as well. Hence, it has
been suggested that it is important to gather the right information for attaining the best outcomes
[33].
4.3. Prognoses
In a statement by Hancock and Hancock [3], authors indicate that it is hard to know the size or
state of the IoT because it is evolving so rapidly. A similar opinion is observed by Kong, et al. [1]
where an increase in data mining and consequent demand for data storage is predicted. It has
been understood that in the future, the IoT technologies will better integrate with the internet for
developing accurate solutions to interchange and communicate information through sensing
devices. It has been estimated that in the future, wider technological trends will be evidenced
through the enablers such as manufacturing, energy, communication, standards, integration,
intelligence, and interoperability. Additionally, RFID technology will be considered mainstream

28
in the retail sector. Besides, ambient intelligence will be mastered alongside interacting virtual
world with that of the physical one [34].
Hussein [35] asserted that “Owing to the fact that IoT has become a vital element as regards the
future of the internet with its increased usage, it necessitates a need to adequately address security
and trust functions” (p. 80). It has been further understood that IoT along with DM has several
future applications and a scope of improvement. In the future, IoT can be applied to develop
smart cities, which would require using sensors and radio frequency identification. The
application of the Internet of Nano-things (IoNT) can also be explored in the field of healthcare,
which will enable organizations to collect new medical data. It will further be responsible for
conducting better diagnoses and discoveries (see Figure 4). Smart agriculture, as well as water
management, can also be done by implementing IoT and DM in the future. The IoT ecosystem
platforms can also be used in the logistics and retail sector, which will contribute to improving
the small living standards of the citizens. Additionally, IoT can also be explored in collaboration
with blockchain technology in the future for enhancing overall security and privacy or security
issues [35]. It has also been understood that IoT will explore all kinds of application areas in near
future. These areas also involve big data analytics, which enables organizations to undertake
accurate decisions for developing enhanced IoT systems [36].
Figure 4. Internet of Nano-Things. (Source: Hussein, 2019)
5. THE FUTURE OF TECHNOLOGY
The preceding literature has presented IoT and its implication on data mining as rapidly growing
[3], [4]. Some have described it as ever-growing, while others have illustrated its future as hard to
quantify due to available possibilities for growth [3]. For instance, when Jacob Morgan mentions
that eventually “anything that can be connected will be connected”, it signifies that the
implication of IoT on data mining will be significant. For instance, even Kong, et al. [1],
mentioned that with the increase in IoT business, the demand for data storage and computing will
put pressure on the ability of cloud computing. In this regard, data mining’s scope in the future
must also be explored. Hence, it was estimated by Venkatadri and Reddy [37] that data mining
also has a vast scope in the upcoming days. This is because soft computing approaches can be
explored, for instance, genetic programming, fuzzy logic, and neural networks. These kinds of
techniques can be incorporated with the help of cloud computing and multi-agent technologies.
The prime areas, wherein these technological advancements can be applied involve medical
diagnosis, business, social networking, research and scientific analysis, and the web [37]. Apart
from these areas, healthcare applications can also be highly estimated. This is because “IoT in

29
healthcare has the potential to make a reality that All staff in hospital areas can benefit from
access to an up-to-date electronic health record detailing the patient’s condition and treatment,
and affording access to their information, medical history, services and diagnostics” (p. 4). The
power of DM has also been identified in this study, wherein it has been found that “Recent AI
technology allows to expand the fields of Data Mining as well as the speed under the new
evolution of storage and processing performances of computing machines” [37].
5.1. Findings
There are considerable implications of IoT on data mining. Some of the already experienced
effects include increased efficiency in data capture and processing, more accurate statistics,
facilitation of collection and transfer of big data, among other implications [5], [26]. The paper
also finds potential challenges including data security and impact on privacy through IoT-enabled
data mining. Additionally, Deloitte [27] asserted that IoT platforms such as IoT orchestration,
which is a single platform, have been offering organizations the ability to integrate the existing
systems and workflows with IoT. This helps in integrating data from future and current connected
systems and devices. Highlighting the effect of these platforms on the current dynamics, the
author indicated that organizations incurred low costs for computing data and storing them on the
cloud platform. Even edge computing has been trending in the present scenario. It has also been
noted that with the help of these platforms, the costs of devices, connectivity, and sensors have
been reduced. These have further enabled the development of mobile application platforms and
smartphone penetration enhancement [27].
Intelligent platforms have also been optimally using interconnected and heterogeneous networks,
including the internet. These advancements have been possible with the successful development
of Radio Frequency Identification (RFID) technology along with wireless communication
technologies [28]. Concerning information system platforms, it has been understood that
“Intelligence may be contained completely within a device, combined with platform intelligence
in the cloud, or reside almost completely within a platform to which the device connects to
perform some functions” [28].
The data mining algorithm is a vital IoT platform, which is responsible for facilitating valuable
analytics, managing services and networks efficiently, and estimate future events precisely
irrespective of all constraints. Herein, it has been highlighted that when new raw data are
processed with the help of traditional data mining algorithms then accurate insights are not
gained. This is the reason why a responsive and intelligent environment is not established by the
system. In this context, it has been stated that “we predicted astronomically huge heterogeneous
network of IoT devices with data mining algorithms to subsist as a seamless fabric, covering and
synthesizing the intelligent environment” [31]. All these depict the importance of developing a
precise ‘data mining algorithm’ so that flexible, open, and dynamic ad-hoc IoT services can be
made possible. These algorithms when applied to input data can enable the extraction of personal,
as well as useful information. However, the fulfillment of all these aspects is highly challenging
concerning IoT [31].
IoT devices have been increasingly used for enhancing the lifestyle of people in society. They are
also useful in conserving energy, enhancing sectors such as health, agriculture, and
transportation, thereby adopting the smart approach. The data retrieved from those devices are
helpful in increasing knowledge on trends and patterns that further increase the efficiency of
companies and improve economies and the global community. Considering the usage of IoT and
its impact on the current dynamics, it has been understood that it enables exploiting data analytics
and big data. This helps in facilitating data preprocessing, combining, gathering, and categorizing
along with decision-making [38]. Besides, focusing on trailblazing DM, it has been found that the

30
data mining framework is highly effective in applying IoT. In this concern, “IoT generates
enormous amount of heterogenous valuable data. To convert this data into knowledge, data
mining systems are developed” [39]. It has also been understood that there are several limitations
for considering IoT data, as it must be analyzed on a real-time basis. Therefore, improving
personal security in the future and enhancing people’s overall quality of life will require
considering effective solutions such as cloud computing and deep learning to derive knowledge
from new situations [40].
Besides, advancements in designing sensors are also found to be an important aspect. This is
because with improved sensors real-time data collection and analysis could be possible, which
further has contributed to the development of IoT dynamics along with that of DM. Specifically,
wireless sensor networks (WSNs) are increasing in importance, as it has contributed in
developing the quality of information, as well as communication technologies. These networks
have also been responsible for integrating and connecting the internet in a wide area of
application, for instance, industries [41]. Even Elkhodr et al. [30] acclaimed that “Todays’
sensors can monitor temperature, ambiance, soil makeup, pollution in the air, noise, presence of
objects or movements among other actuating functionalities triggered based on some sensed
information” [30].
6. THE USEFULNESS OF THE PRESENT RESEARCH
The findings presented have clearly shown that the existing research can benefit people’s
knowledge on the impacts of advancing the IoT dynamics and how it links to the DM aspects.
Besides, it has also been found that various platforms such as sensors are also getting evolved
with IoT, which, in turn, have led to the development of better IoT solutions for addressing all the
issues that have been persisting.
6.1. Added Value to Current Research
Herein, it needs to be mentioned that the information gathered from varied existing literature and
studies carried forth by numerous researchers have significantly added value to the current
research. This is because the general objectives of the research paper have been effectively
addressed. Besides, the exploration of future scope and implications of IoT and DM have
contributed to the existing literature, which makes the present research a significant resource for
future reference.
7. DISCUSSION
The findings and information gathered from the above sections have highlighted that IoT has
become an emerging technology and has an immense scope in enabling better solutions. The
above-made analysis also indicates that the IoT dynamics are ubiquitous and evolving. This has
been particularly understood by examining cross-cutting trailblazing DM [17], [27], [29]. With
these evolutions, several platforms associated with the IoT ecosystems have also been developed
in the current era. This includes devices, data generation, sensors, data compilation, information
system platforms, data mining algorithm, information system rollout, and an informed decision-
making process. Besides, their advancements are expected to be more evident in the future, which
will further enhance the outcomes [4], [28], [29], [30], [32], [33]. Additionally, developments
have also been evident in designing sensors. With the evolution of several technologies and
WSNs, the sensors are gradually becoming more intelligent [41].

31
8. CONCLUSIONS
The preceding discussion has indicated that IoT is happening and has a significant implication on
data mining. All indications suggest that it will continue to grow and increasingly affect how we
interact with “things”. A backdrop of concerns exists. Some of the matters raised by researchers
include the rate of growth of the technology against the ability to regulate implementation,
challenges in standardization, information integrity, and data security [42], [43]. Accordingly, the
implications of IoT on data mining will continue to be felt in what can be described as an
unprecedented manner similar to what was mentioned in the paper, as many “things” continue to
be connected and communicated through IoT, a significant effect will continue to be noticed in
data mining.
9. FUTURE RESEARCH
The present study has effectively addressed the general objective throughout the paper. The study
understood that the IoT dynamics are ubiquitous, as the IoT has been evolving with time.
Particularly, by emphasizing data mining, it has been understood that the IoT ecosystem
platforms also evolved, which made the future implications more promising and effective for
making the life of people better. However, the present study still had some limitations. One of the
limitations was the exclusion of primary data. Hence, future researchers must consider primary
research for obtaining more accurate outcomes. Besides, the present study is found to be
qualitative. However, integrating statistical analysis with the help of quantitative research would
generate better results. Furthermore, the present research paper is found to be wider as it has
covered all the aspects of data mining and IoT ecosystems. However, with a more focused aim,
the research would have generated detailed information. Hence, these aspects need to be
considered in future research so that the study area is explored to the fullest.
REFERENCES
[1] Kong, D., Liu, D., Zhang, L., He, L., Shi, Q., & Ma, X. (2020). Sensor anomaly detection in the
industrial internet of things based on edge computing. Turkish Journal of Electrical Engineering &
Computer Sciences, 28(1), 331–346. doi:10.3906/elk-1906-55
[2] Welbourne, E., Battle, L., Cole, G., Gould, K., Rector, K., & Raymer, S. et al. (2009). Building the
internet of things using RFID: the RFID ecosystem experience. IEEE Internet Computing, 13(3), 48-
55. https://doi.org/10.1109/mic.2009.52
[3] Hancock, B., & Hancock, L. (2016). Somebody's watching: The ever growing internet of things. Phi
Kappa Phi Forum, 96(3), 12-15.
[4] Chen, F., Deng, P., Wan, J., Zhang, D., Vasilakos, A. V., & Rong, X. (2015). Data mining for the
internet of things: literature review and challenges. International Journal of Distributed Sensor
Networks, 1-14.
[5] Wu He, Gongjun Yan, & Li Da Xu. (2014). Developing vehicular data cloud services in the IoT
environment. IEEE Transactions on Industrial Informatics, 10(2), 1587-1595.
https://doi.org/10.1109/tii.2014.2299233
[6] Xia, F., Yang, L., Wang, L., &Vinel, A. (2012). Internet of Things. International Journal Of
Communication Systems, 25(9), 1101-1102. https://doi.org/10.1002/dac.2417
[7] Kim, M., Man, K. L., &Helil, N. (2019). Advanced internet of things and big data technology for
smart human-care services. Journal of Sensors, 2019, 1-3.
[8] Lee, I., & Lee, K. (2015). The Internet of Things (IoT): Applications, investments, and challenges for
enterprises. Business Horizons, 58(4), 431-440.
[9] Bin, S., Yuan, L., & Xiaoyi, W. (2010, April). Research on data mining models for the internet of
things. In 2010 International Conference on Image Analysis and Signal Processing (pp. 127-132).
IEEE.

32
[10] Dachyar, M., Zagloel, T. Y. M., &Saragih, L. R. (2019). Knowledge growth and development:
internet of things (IoT) research, 2006–2018. Heliyon, 5(8), e02264.
[11] Ibarra-Esquer, J. E., González-Navarro, F. F., Flores-Rios, B. L., Burtseva, L., &Astorga-Vargas, M.
A. (2017). Tracking the evolution of the internet of things concept across different application
domains. Sensors, 17(6), 1379.
[12] Duan, Y., Lu, Z., Zhou, Z., Sun, X., & Wu, J. (2019). Data privacy protection for edge computing of
smart city in DIKW architecture. Engineering Applications of Artificial Intelligence, 81, 323-335.
[13] Cai, H., Xu, B., Jiang, L., &Vasilakos, A. V. (2016). IoT-based big data storage systems in cloud
computing: perspectives and challenges. IEEE Internet of Things Journal, 4(1), 75-87.
[14] Jara, A. J., Genoud, D., &Bocchi, Y. (2014, July). Big data for cyber physical systems: an analysis of
challenges, solutions and opportunities. In 2014 Eighth International Conference on Innovative
Mobile and Internet Services in Ubiquitous Computing (pp. 376-380). IEEE.
[15] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE
Internet of Things Journal, 3(5), 637-646.
[16] Ren, J., Guo, H., Xu, C., & Zhang, Y. (2017). Serving at the edge: A scalable IoT architecture based
on transparent computing. IEEE Network, 31(5), 96-105.
[17] Ren, S., Hui, C. L. P., & Choi, T. M. J. (2018). AI-Based Fashion Sales Forecasting Methods in Big
Data Era. In Artificial Intelligence for Fashion Industry in the Big Data Era (pp. 9-26). Springer,
Singapore.
[18] Rabah, K. (2018). Convergence of AI, IoT, big data and block chain: a review. The Lake Institute
Journal, 1(1), 1-18.
[19] Li, Z., Wang, Y., & Wang, K. S. (2017). Intelligent predictive maintenance for fault diagnosis and
prognosis in machine centers: Industry 4.0 scenario. Advances in Manufacturing, 5(4), 377-387.
[20] Schimek, R. S. (2016). IoT case studies: companies leading the connected economy. American
International Group, 2-26.
[21] Misuraca, G. (2009). Futuring e-Government: Governance and policy implications for designing an
ICT-enabled knowledge society. ACM, 83-90.
[22] Kumar, R., Zhang, X., Khan, R. U., & Sharif, A. (2019). Research on data mining of permission-
induced risk for android IoT devices. Applied Sciences, 9(2), 277.
[23] Qiao, H., & Wang, G. (2012). Ananalys is of the evolution in Internet of Things industry based on
industry life cycle theory. Advanced Materials Research, 785-789.
[24] Saidu, C. I., Usman, A. S., & Ogedebe, P. (2015). Internet of things: impact on economy. Journal of
Advances in Mathematics and Computer Science, 241-251.
[25] Tsai, C. W., Lai, C. F., Chiang, M. C., & Yang, L. T. (2013). Data mining for internet of things: A
survey. IEEE Communications Surveys & Tutorials, 16(1), 77-97.
[26] Liu, C., Nitschke, P., Williams, S. P., &Zowghi, D. (2020). Data quality and the Internet of Things.
Computing, 102(2), 573-599.
[27] Deloitte. (2020). Internet of Things (IoT) The rise of the connected world. Deloitte Touche Tohmatsu
Limited, 3-33.
[28] Hassan, Q.F. (2016). Innovative research and applications in next-generation high performance
computing. IGI Global, 397-427.
[29] Gubbi, J., Buyya, R., Marusic, S., &Palaniswami, M. (2013). Internet of Things (IoT): A vision,
architectural elements, and future directions. Future Generation Computer Systems, 29(7), 1645-
1660. https://doi.org/10.1016/j.future.2013.01.010
[30] Elkhodr, M., Shahrestani, S., & Cheung, H. (2016). The internet of things: new interoperability,
management and security challenges. International Journal of Network Security & Its Applications
(IJNSA), 8(2), 85-102.
[31] Sunhare, P., Chowdhary, R. R., & Chattopadhyay, M. K. (2020). Internet of things and data mining:
An applications oriented survey. Journal of King Saud University-Computer and Information
Sciences, 2-22.
[32] Krishnamurthi, R., Kumar, A., Gopinathan, D., Nayyar, A., & Qureshi, B. (2020). An overview of iot
sensor data processing, fusion, and analysis techniques. Sensors, 20(21), 1-23.
[33] Brous, P., Janssen, M., Herder, P. (2018). Internet of Things adoption for reconfiguring decision-
making processes in asset management. Business Process Management Journal, 1-19.
[34] Perwej, Y., Omer, M. K., Sheta, O. E., Harb, H. A. M., &Adrees, M. S. (2019). The future of Internet
of Things (IoT) and its empowering technology. International Journal of Engineering Science, 20192-
20203.

33
[35] Hussein, W. N. (2019). The Implementation Success Factors for IoT and Big Data Analytics in
Transportation System, IOP Conf. Ser.: Mater. Sci. Eng. 705 012049, 2019.
[36] Kumar, S., Tiwari, P., &Zymbler, M. (2019). Internet of Things is a revolutionary approach for future
technology enhancement: a review. Journal of Big Data, 6(1), 1-21.
[37] Venkatadri, M.,&Reddy, L.C. (2011). A review on data mining from past to the future. International
Journal of Computer Applications (0975 – 8887), 15(7), 19-22.
[38] Mudholkar, P., &Mudholkar, M. (2020). Internet of things (IoT) and big data: a review. International
Journal of Management, Technology and Engineering, 5001-5007.
[39] Gupta, P., & Gupta, R. (2017). Data mining framework for IoT applications. International Journal of
Computer Applications, 174(2), 4-7.
[40] Wlodarczak, P., Ally, M., &Soar, J. (2017). Data mining in IoT. Data Analysis for a New Paradigm
on the Internet, 1100-1103.
[41] Sheng, Z., Mahapatra, C., Zhu, C., & Leung, V. C. (2015). Recent advances in industrial wireless
sensor networks toward efficient management in IoT. IEEE Access, 3, 622-637.
[42] He, Y., Guo, J., & Zheng, X. (2018). From Surveillance to Digital Twin: Challenges and Recent
Advances of Signal Processing for Industrial Internet of Things. IEEE Signal Processing Magazine,
35(5), 120-129. https://doi.org/10.1109/msp.2018.2842228
[43] Tsai, C., Lai, C., &Vasilakos, A. (2014). Future Internet of Things: open issues and challenges.
Wireless Networks, 20(8), 2201-2217. https://doi.org/10.1007/s11276-014-0731-0
AUTHORS
Bongs Lainjo, MASc, Engineering, is an RBM systems consultant with expertise in
program evaluation. Bongs is a former UN Senior Advisor of Program Management,
Reproductive Health Commodity Security (RHCS) and Evaluation. Prior to that, he
worked for USAID as a Logistics and Management Information Systems Advisor
(LISA). He also served as COP/Senior Data Management Advisor for Columbia
University after spending close to a decade teaching as a professor at a number of
Canadian academic institutions. Bongs has worked in several countries in Africa,
Asia, Pacific Island Countries, Canada, and the United States.

The Dynamics of the Ubiquitous Internet of Things (IoT) and Trailblazing Data Mining (DM)

Recommended

More Related Content

Similar to The Dynamics of the Ubiquitous Internet of Things (IoT) and Trailblazing Data Mining (DM) (20)

Recently uploaded (20)

The Dynamics of the Ubiquitous Internet of Things (IoT) and Trailblazing Data Mining (DM)