Dr. Neeraj Dahiya et al. International Journal of Recent Research Aspects ISSN: 2349-7688, Vol. 8,
Issue 1 March 2021, pp. 4-13
© 2021 IJRAA All Rights Reserved page - 4-
Artificial Intelligence of Things:
Purpose, Techniques and Practical
Implications
Dr. Neeraj Dahiya
1
, Dr. Uma Rani
2
1
Department of CSE, SRM University, Delhi-NCR, Sonipat, Haryana.
2
Department of CSE, DPG Institute of Technology & Management, Haryana.
Abstract: The Artificial Intelligence of Things (AIoT) is the combination of artificial intelligence
(AI) technologies with the Internet of Things (IoT) infrastructure to achieve more efficient IoT
operations, improve human-machine interactions and enhance data management and analytics.
AI can be used to transform IoT data into useful information for improved decision making
processes, thus creating a foundation for newer technology such as IoT Data as a Service (IoTDaaS).
AIoT is transformational and mutually beneficial for both types of technology as AI adds value to
IoT through machine learning capabilities and IoT adds value to AI through connectivity, signaling
and data exchange. As IoT networks spread throughout major industries, there will be an
increasingly large amount of human-oriented and machine-generated unstructured data. AIoT can
provide support for data analytics solutions that can create value out of this IoT-generated data.
With AIoT, AI is embedded into infrastructure components, such as programs, chipsets and edge
computing, all interconnected with IoT networks. APIs are then used to extend interoperability
between components at the device level, software level and platform level. These units will focus
primarily on optimizing system and network operations as well as extracting value from data..
Keywords: Data Mining, Big Data, Distributed computing, Hadoop
I. INTRODUCTION
Mining of Data includes successful information assortment
and warehousing just as PC handling. Information digging is
utilized for analyzing crude information, including deals
numbers, costs, and clients, to grow better showcasing
techniques, improve the presentation or decline the expenses
of maintaining the business. Additionally, Data mining
serves to find new examples of conduct among purchasers
[1].
Fig. 1 Data mining techniques
Comprehensively, there are seven primary Data Mining
methods.
1. Statistics: It is a part of science which identifies
with the assortment and portrayal of information. A
measurable strategy isn't considered as a Data
Mining procedure by numerous investigators.
Notwithstanding, it assists with finding the
examples and construct prescient models [2].
2. Clustering: Grouping is probably the most
seasoned strategy utilized in Data Mining. It is the
way toward recognizing comparable information
that are like one another.
3. Visualization: Perception is utilized toward the
start of the Data Mining measure [3].
4. Decision Tree: This method can be utilized for
investigation examination, information pre-
preparing and expectation work [4].
5. Association Rules: Affiliation Rules help to
discover the relationship between at least two
things. It assists with knowing the relations between
the various factors in information bases. Affiliation
rules find the shrouded designs in the informational
collections [5].
6. Neural Networks: Neural Network is another
significant procedure utilized by individuals
nowadays. This method is frequently utilized in the
beginning phases of the Data Mining innovation.
Neural systems are anything but difficult to use as
they are robotized to a specific degree and in light
of this the client isn't relied upon to have a lot of
information about the work or information base [6].
7. Classification: This strategy helps in inferring