UNIT 2

IOT WITH CLOUD COMPUTING

PRUDHVI KIRAN P
Assistant Professor, CSE - IOT Dept.
R. V. R. & J. C. College of Engineering
UNIT - 2 [ 13 Periods ]
IoT Cloud Platforms
Microsoft Azure IoT, Amazon Webs Services IoT, IBM WATSON IoT, Google’s cloud
IoT.
Principles and foundation of Artificial intelligence for IoT
Machine Learning Paradigms for IoT - Supervised learning for IoT (Linear regression, Logistic
regression, SVM-Decision Tree, Naive’s bayes), Deep Learning for IoT, Neural Networks for
IoT.

SUBJECT CODE - CO 314 (EL01)

CLASS DETAILS - IOT V SEM - AUGUST 2023
FACULTY DETAILS - PRUDHVI KIRAN P, Asst. Prof., CSE (IOT), RVR&JC College of Engineering
QUESTION BANK - UNIT 2 [Assignment Questions - 2, 4, 10]
1. Discuss about Microsoft Azure IoT. Mention and explain various services offered by Microsoft
Azure IoT.
2. Discuss about Amazon Webservices IoT. Mention and explain various services offered by
Amazon Webservices IoT.
3. Explain in detail about IBM Watson IoT platform, with concerned functional block diagram.
Write few details about retirement of IBM Watson IoT platform.
4. Explain in detail about Google Cloud IoT Core, with concerned functional block diagram. Write
few details about retirement of Google Cloud IoT Core.
5. Explain briefly about machine learning. Discuss the role of ML in IoT, mentioning 5 real-time
examples.
6. Explain Linear Regression, Logistic Regression and Decision Trees, with neat diagram/graph
representation.
7. Discuss SVM and Navie Bayes, with possible diagram/graph representation.
8. Explain briefly about Supervised Learning. Discuss the role of Supervised Learning in IoT,
mentioning 5 real-time examples.
9. Explain briefly about Neural Networks. Discuss the role of Neural Networks in IoT, mentioning 5
real-time examples.
10. Explain briefly about Deep Learning. Discuss the role of Deep Learning in IoT, mentioning 5 real-
time examples.
END
2.1. IoT Cloud Platforms
IoT cloud platforms bring together capabilities of IoT devices and cloud computing delivered as a
end-to-end (edge-to-cloud) service. They are also referred by other terms such as Cloud Service
IoT Platform. In this age, where billions of IoT devices (IoT devices are devices with multiple sensors
connected to the cloud, typically via gateways.) are connected to the Internet, with this, there is
rapid growth in applications such as Smart Cities, Agriculture, Wearable Tech, Vehicle Tracking,
Retail Shops, and many more. These IoT devices generate very large amounts of data, which is
transported to the cloud to be analyzed/monitored.

IaaS
SENSORS APPLICATIONS
PaaS SaaS

IOT CLOUD PLATFORMS

Role of Cloud Platforms in IoT space:

1. Cloud platforms receive data at scale from your devices, and determine how to process and
store that data.
2. Cloud platforms analyse the data to provide insights, either in real time or after the fact.
3. Cloud platforms, enable us to send commands from the cloud to specific devices.
4. Cloud platforms provision devices and control which devices can connect to your infrastructure.
5. Cloud platforms control the state of your devices and monitor their activities.
6. Cloud platforms manage the firmware installed on your devices.
For example, in a remote monitoring solution for an oil pumping station, the services use data
telemetry from the pumps to identify anomalous behaviour. When a cloud service identifies an
anomaly, it can automatically send a command to the device to take a corrective action. This process
implements an automated feedback loop between the device and the cloud that greatly increases
the solution efficiency.
There are several IoT Cloud Platforms in the market today provided by different cloud service
providers (CSP) that host wide ranging applications. These can also be extended to services that use
advanced Artificial Intelligence (AI) algorithms. Below are some notable IoT cloud platforms in
market;
1. Microsoft Azure IoT Hub
2. Amazon Web Services IoT
3. IBM Watson IoT Platform
4. Google Cloud IoT
5. Oracle Integrated Cloud for IoT
6. SAP Cloud Platform for the Internet of Things
7. Cisco Jasper Control Center
8. PTC ThingWorx Industrial IoT (IIoT) Platform
9. Salesforce IoT
10. Xively
11. Carriots

Choosing across different platforms depends on both business and technical factors like, Scalability,
Reliability, Customization, Operations, Protocols, Hardware, User Cloud Knowledge, Support,
Architecture and Technology Stack, Security and Cost. Of course, Security and privacy is also the main
concern during the adoption of IoT Cloud Platforms.
 Above mentioned are the various functional areas, that play important role in IoT space, which are
managed effectively, only with the IoT Cloud Platform. I.e. these are the things offered by cloud platforms.
 CLOUD PLATFORMS IN OUR SYLLABUS

Launched in 2010 Launched in 2004

23% Market Share 33% Market Share
IOT Services Launched in 2016 IOT Services Launched in 2015

Launched in 2010 Launched in 2008

04% Market Share 10% Market Share
IOT Services Launched in 2014 & IOT Services Launched in 2017 &
Will be Retired in Dec 2023 Retired in Aug 2023
*JUNE 2022 STATS
2.1.1 Azure IoT
 The Azure Internet of Things (IoT) is a collection of Microsoft-managed IoT specific cloud
services, edge components, and SDKs that let you connect, monitor, and control your IoT assets
at scale.
 In simpler terms, it is an IoT solution for IoT devices that communicate with cloud for utilizing
cloud services. Azure IoT offers edge-to-cloud technologies that come with security, privacy and
compliance built-in. Azure IoT is playing prominent role in Manufacturing, Energy, healthcare,
Retail, Transportation & Logistics.
Azure IoT products
1. Azure IoT Hub
2. Azure IoT Central
3. Azure Digital Twins
4. Azure IoT Edge
5. Azure Sphere
6. Windows for IoT
7. Azure RTOS
8. Azure Time Series Insights
1. Azure IoT Hub
 Smart devices connect through Wi-Fi to Azure IoT Hub, which acts as a command center that can
processes messages, triggers actions, and collects information about the device and sends this
information further to the appropriate system or application. This is PaaS (Platform as a Service).
 IoT Hub enables two-way communication between the cloud and connected objects. It supports
the Advanced Message Queuing Protocol (AMQP), Message Queuing Telemetry Transport (MQTT)
(over Transmission Control Protocol (TCP)), and Hypertext Transfer Protocol Secure (HTTPS)
communication protocols.
 IoT Hub enables highly secure and reliable
communication between your IoT application and
the devices it manages.
 IoT Hub keeps an identity register of all devices
connected to the platform. It stores information
about the devices, their authentication details,
and access rights.
 It got full integration with Azure Event Grid (is a platform that provides reliable message delivery
at massive scale and can be used as a fully managed service on Azure Cloud), simplifying IoT
application development and it also had compatibility with Azure IoT Edge for building hybrid IoT
applications.
 Device Update for IoT Hub is a comprehensive platform that customers can use to publish,
distribute, and manage over-the-air updates for everything from tiny sensors to gateway-level
devices and this also includes being able to rapidly responding to security threats.
 Azure IoT hub, uses Microsoft’s IoT connector, for generating a unique access key for every single
device. This ensures that devices are properly authenticated and are under full control and can
only do what they are supposed to, and this also allows you to disable single devices when they get
corrupted.

On Premise

FUNCTIONAL REPRESENTATION OF AZURE IOT HUB

VISUAL REPRESENTATION OF AZURE IOT HUB WEB INTERFACE
2. Azure IoT Central
 IoT Central is a SaaS (Software as a Service) that acts as a hub to centralize all of our IoT device
data. In IoT central, we can use the web dashboard to monitor and visualize our device data,
create custom alerts, and set up data-driven workflows using the workflow engine.
Data-driven workflows are processes that use data as the main input and output. They automate or
optimize tasks based on data analysis. Data-driven workflows can help improve efficiency, quality,
and decision-making in projects, teams, and organizations.
 Azure IoT Central is a ready-made UX (User experience) and API (Application Programming
Interface) space for connecting and managing devices, delivering reliable data for business
insights.
 Azure IoT Central provides; Quick connectivity between IoT devices and the cloud,
Centralized management to easily reconfigure and update devices, Visualizations and
analysis to make sense of IoT data, from the big picture to small details, Extensibility to
bridge business applications and IoT data, turning insights into action.
 Azure Central is a SaaS, meaning Microsoft will keep adding new capabilities and/or update and
manage all bundled services like, storage, device registration, data visualization, rule creation
capability against data, for us. Where as IoT hub is a PaaS, meaning Microsoft will support and
update this service, but we have to manage all the bundling with above-mentioned services.
 Microsoft Azure IoT Central allows users to connect IoT devices to the cloud and offers
centralized management (fully managed by service provider, as it is a SaaS) to configure and
updated connected devices. Microsoft's Azure IoT Hub is a managed service (fully managed by
user, as it is a PaaS) for bidirectional communication between IoT devices and Azure. Azure IoT Hub
provides a cloud-hosted solution back end to connect virtually any device. Users can extend their
solutions from the cloud to the edge with per-device authentication, built-in device management,
and scaled provisioning.

FUNCTIONAL REPRESENTATION OF AZURE IOT CENTRAL

VISUAL REPRESENTATION OF AZURE IOT CENTRAL WEB INTERFACE
3. Azure Digital Twins
 Azure Digital Twins is an Internet of Things (IoT) platform that enables you to create a digital
representation of real-world things, places, business processes, and people.
 This platform is designed to simulate and analyze the behavior of connected devices and systems,
as well as to control and automate them.
 Azure Digital Twins gain insights that help you drive better products, optimize operations and
costs, and create breakthrough customer experiences.
 With Azure Digital Twins, developers can create accurate models of the physical world, allowing
them to gain a deeper understanding of their environment and make more informed decisions.
 APIs and tools are included for creating, managing, and analyzing digital twin models. It also
contains a set of pre-built templates and sample models to help developers get started quickly.
 Azure Digital Twins is built on top of the Azure IoT platform, which means it has native integration
with other Azure services like Azure IoT Hub; this can make it easier to connect digital twin models
to physical devices and systems, and to analyze and visualize data from those devices and systems.
 Azure Digital Twins allows for multiuser access and collaboration, this allows for different teams
to work on different parts of the model and also allows for different stakeholders to access the
same model with different level of permissions.
 Azure Digital Twin supports spatial intelligence, which allows for more accurate representation of
the real world, and allows for more detailed analysis of the data collected from IoT devices.
Use Cases - Azure Digital Twins
Smart Buildings & Smart Cities
• Digital Twins can be used to create digital twin models of buildings and other physical structures,
and to analyze and visualize data from sensors and other devices in those buildings. This can be
used to optimize building performance, improve energy efficiency, and enhance the occupant
experience. Azure Digital Twins can be used to create digital twin models of entire cities and to
analyze and visualize data from a wide range of sensors.
Industrial IoT
• Azure Digital Twins can be used to create digital twin models of industrial environments, and to
analyze and visualize data from sensors and other devices that are distributed throughout those
environments. This can be used to optimize production, improve equipment performance,
enhancing the overall efficiency of the facility.
Supply Chain Optimization
• Azure Digital Twins can be used to create digital twin models of supply chain networks, and to
analyze and visualize data from sensors and other devices that are distributed throughout the
supply chain. This can be used to optimize logistics, improve inventory management.
VISUAL REPRESENTATION OF AZURE DIGITAL TWINS WEB INTERFACE
VISUAL REPRESENTATION OF AZURE DIGITAL TWIN OF A FACTORY
4. Azure IoT Edge
 Analytics drives business value in IoT solutions, but not all analytics need to be in the cloud. Azure
IoT Edge helps you bring the analytical power of the cloud closer to your devices to drive better
business insights and enable offline decision making.
 Azure IoT Edge is an Internet of Things (IoT) service that builds on top of the IoT Hub and enables
users to carry out edge computing.
 This service is ideal for solutions that need to analyze data on edge nodes or devices, instead of in
the cloud. By moving parts of the workload to the edge, devices can spend less time sending
messages to the cloud and react more quickly to events.
 Azure IoT Edge allows you to remotely and securely deploy and manage cloud-native workloads
such as AI logic , other Azure services, or your own business logic - to run directly on your IoT
devices. This Optimizes cloud spend and enable your devices to react faster to local changes and
operate reliably even in extended offline periods.
 Azure IoT Edge deploy models built and trained in the cloud and run them on-premises. For
example, using IoT Edge you can deploy a predictive model to a factory camera to test for quality
control and alert you when an issue is detected; along with edge processing, Azure IoT Edge can
also sends it to the cloud for further analysis. Azure IoT Edge is a feature of Azure IoT Hub and
enables you to scale out and manage an IoT solution from the cloud.
FUNCTIONAL REPRESENTATION OF AZURE IOT EDGE
5. Azure Sphere
 Azure Sphere is a secured IoT platform for building solutions that start in silicon and extend
through the OS and the cloud. I.e. Azure Sphere protects your device, data, and infrastructure on
all fronts; hardware, software, and in the cloud.
 It comprises a secured, connected, crossover microcontroller unit (MCU), a custom high-level
Linux-based operating system (OS), and a cloud-based security service that provides continuous,
renewable security.
 An Azure Sphere MCU, along with its operating system and application platform, enables the
creation of secured, internet-connected devices that can be updated, controlled, monitored, and
maintained remotely. A connected device that includes an Azure Sphere MCU, either alongside or
in place of an existing MCUs, provides enhanced security, productivity, and opportunity.
 The software updates can be automatically deployed from the cloud to any connected device to
fix problems, provide new functionality, or counter emerging methods of attack.
 The Azure Sphere Security Service is an integral aspect of Azure Sphere. Using this service, Azure
Sphere MCUs safely and securely connect to the cloud and web. The service ensures that the
device boots only with an authorized version of genuine, approved software. In addition, it
provides a secured channel through which Microsoft can automatically download and install OS
updates to deployed devices in the field to mitigate security problems. Neither manufacturer nor
end-user intervention is required, thus closing a common security hole.
FUNCTIONAL REPRESENTATION OF AZURE SPHERE
AZURE SPHERE MCU
DEVELOPMENT KIT FROM SEED (company name) ENABLED WITH AZURE SPHERE MT3620 (AZURE MCU)
6. Windows for IoT
 Windows IoT (Windows for IoT) is from the family of operating systems from Microsoft, which is
specially designed for use in embedded systems. Windows IoT uses Microsoft Windows
ecosystem, and cloud connectivity to bring enterprise-class power, security, and manageability to
the Internet of Things devices.
 Windows 10 IoT (Internet of Things) is a special edition of the Windows 10 operating
system optimized for use on embedded systems and IoT devices. It is the successor to the
Windows Embedded operating system.
Windows for IoT comes in three editions;
1. Windows IoT Enterprise
 A full version of Windows Enterprise with specialized features to create dedicated devices locked
down to a specific set of applications and peripherals.
2. Windows Server IoT 2022
 A full version of Windows Server 2022 that delivers enterprise manageability and security to IoT
solutions.
3. Windows 10 IoT Core
 The smallest member of the Windows 10 operating system family. While only running a single
app, it still has the manageability and security expected from Windows 10.
7. Azure RTOS
 Azure RTOS, formerly known as ThreadX, is a real-time operating system (RTOS) developed by
Express Logic, which was acquired by Microsoft in April 2019. Azure RTOS is designed primarily for
use in embedded and real-time systems, making it a valuable component for Internet of Things
(IoT) and edge computing applications.
 Now, Azure RTOS is part of the broader Azure IoT ecosystem, which includes various services and
tools to enable IoT solutions. It is s easy-to-use and market-proven and having been deployed on
more than 10 billion devices worldwide.
 Azure RTOS ThreadX is a highly deterministic, embedded real-time operating system (RTOS)
programmed mostly in the language C.
 The Azure RTOS platform is the collection of run-time solutions including Azure RTOS ThreadX (A
high-performance real-time operating system for IoT environment), Azure RTOS NetX and NetX
Duo (A TCP/IP/IPV4/IPV6 embedded network stacks that included cloud connectivity and IP
security protocols for IoT environment), Azure RTOS FileX (An embedded FAT file system for IoT
environment. File Allocation Table (FAT) is a file system that was developed by Microsoft to support
small disks and simple folder structures.), Azure RTOS GUIX (A complete design environment and
run-time to create and maintain 2D graphical user interfaces for IoT environment), Azure RTOS
USBX (A USB stick that provides host, device and on-the-go support) and Azure RTOS LevelX (offers
low-level APIs to read, write, and erase sectors in Flash memories).
8. Azure Time Series Insights
 Azure Time Series Insights (TSI) is a cloud-based service that allows you to explore, analyze, and
visualize IoT data. Azure TSI can collect, process, store, query, and visualize IoT data. It
provides a global view of your data, which can help you:
• Validate your IoT solution
• Discover hidden trends & Avoid downtime to mission-critical devices
• Spot anomalies
• Perform root-cause analysis
Azure TSI provides the following four service modules which can integrated into your custom
applications.
1. Integration
TSI provides an easy integration from data generated using IoT devices by allowing connection
between the cloud data gateways such as Azure IoT Hub. Data from these sources can be easily
consumed in JSON structures.
2. Storage
Azure TSI also takes care of the data that is to be retained in the system for querying and visualizing
the data. By default, data is stored on SSDs for fast retrieval and has a data retention policy of 400
days. This supports querying historic data for up to a period of 400 days.
3. Data Visualization
Once the data is fetched from the data sources and stored in the columnar stores, it can be visualized
in the form of line charts or heat maps. The visuals are provided out of the box by Azure TSI and can be
leveraged for easy visual analysis.
4. Query Service
Although, visualizing the data will answer many questions, however, TSI also provides a query service
which enables you to issue a query for data.

FUNCTIONAL REPRESENTATION OF AZURE TIME SERIES INSIGHTS

2.1.2 Amazon Web Services IoT
 AWS offers Internet of Things (IoT) services and solutions to connect and manage billions of
devices, through AWS IoT. It enables collection, storage, and analysing of IoT data for
industrial, consumer, commercial, and automotive workloads. From secure device connectivity
to management, storage, and analytics, AWS IoT has the broad and deep services which enable
us to build complete Internet of Things solutions.
AWS IoT services are divided into three categories;
1. Device Software
A. FreeRTOS
B. AWS IoT Greengrass
C. AWS IoT ExpressLink
2. Connectivity and Control Services
D. AWS IoT Core
E. AWS IoT Device Defender
F. AWS IoT Device Management
G. AWS IoT FleetWise
3. Analytics services
A. AWS IoT SiteWise
B. AWS IoT Events
C. AWS IoT Analytics
D. AWS IoT TwinMaker
1.A. FreeRTOS
 AWS FreeRTOS is a real-time operating system that provides connectivity and security features
for Internet of Things (IoT) devices. It is designed to run on microcontrollers and allows
developers to easily add devices to the cloud and build IoT applications.
 FreeRTOS is an open-source & cloud-neutral (cloud-neutral software can run in any cloud, across
multiple cloud vendors) real-time operating system. It can also support multiple data storage
formats and industry standards, replicate data across environments, and offer its own
independent security. AWS FreeRTOS integrates with other AWS services such as AWS
Greengrass and AWS IoT Core, providing a secure and scalable environment for IoT applications.
1.B. AWS IoT Greengrass
 AWS IoT Greengrass is a technology feature that links localized equipment to cloud functions.
Even if they are not linked to the cloud, it enables equipment in data gathering and analyses
closer to their source (devices on the Internet of Things) which results in speedier reaction times.
AWS Greengrass also provides encrypted communications across local stations.
1.C. AWS IoT ExpressLink
 AWS IoT ExpressLink powers a range of hardware modules developed and offered by AWS
Partners.
 AWS IoT ExpressLink helps quickly transform products into IoT devices so you can collect, store,
and analyze device data across your applications. Each AWS Partner module includes software
implementing AWS-mandated security requirements, enabling a secure and direct connection to
the cloud without the need for specialized knowledge in networking or cryptography.
 Devices with AWS IoT ExpressLink establish a two-way connection with AWS IoT Core through
native support of the MQTT (publish/subscribe) communication mechanism.
 Partner modules with AWS IoT ExpressLink can connect to the AWS IoT Device Defender service
to report device metrics that can help detect anomalies and generate alerts.
 With AWS IoT ExpressLink, it is easy to remotely deploy security updates, bug fixes, and new
firmware updates to add features and keep your device fleet always up to date.
2.A. AWS IoT Core
 AWS IoT Core is a managed cloud service provided by Amazon Web Services (AWS) that enables
the secure and scalable connection of Internet of Things (IoT) devices to the cloud. It serves as the
core infrastructure for building IoT applications, allowing you to connect, manage, and interact with
a wide range of IoT devices and applications.
 AWS IoT Core provides secure, bi-directional communication for Internet-connected devices (such
as sensors, actuators, embedded devices, wireless devices, and smart appliances) to connect to
the AWS Cloud over MQTT, HTTPS, and LoRaWAN. Key features and components of AWS IoT Core
include;
1. Device Registry
• AWS IoT Core provides a device registry where you can register and manage information about
your IoT devices. Each device is assigned a unique identifier and can have associated metadata and
security credentials.
2. MQTT and HTTP Communication
• IoT devices can communicate with AWS IoT Core using popular IoT protocols such as MQTT and HTTP.
3. Security
• AWS IoT Core offers robust security features, including device authentication and authorization,
message encryption using TLS (Transport Layer Security). You can also create policies to define the
permissions and actions that devices are allowed to perform.
4. Rules Engine
• AWS IoT Core includes a Rules Engine that allows you to define rules for processing incoming data
from devices. You can use these rules to trigger actions, such as storing data in a database, sending
notifications to other AWS services.
5. Device Shadow
• Device Shadow is a feature that enables you to create a virtual representation of your IoT devices
in the cloud. This virtual device state can be used to synchronize and query the state of physical
devices, even when they are offline.
6. IoT Thing Groups
• You can organize your IoT devices into groups using Thing Groups, making it easier to manage and
apply policies to sets of devices.
7. Scalability
• AWS IoT Core is designed to handle a massive number of IoT devices and can automatically scale to
accommodate varying workloads.
2.B. AWS IoT Device Defender
 AWS IoT Device Defender is a security service that allows you to audit the configuration of your
devices, monitor connected devices via rule-based and ML-based detect capabilities, i.e. detecting
abnormal behavior, and mitigate security risks. It gives you the ability to enforce consistent security
policies across your AWS IoT device fleet and respond quickly when devices are compromised.
2.C. AWS IoT Device Management
 AWS IoT Device Management is a cloud-based device management service that makes it easy for
customers to securely manage IoT devices throughout their lifecycle.
 Customers can use AWS IoT Device Management to onboard device information and
configuration, organize their device inventory, monitor their fleet of devices, and remotely
manage devices deployed across many locations and over-the-air (OTA) updates to device
software.
 It can integrate with AWS IoT Core to easily connect and manage devices in the cloud and with
AWS IoT Device Defender to audit and monitor your fleet’s security posture.
2.D. AWS IoT FleetWise
 AWS IoT FleetWise makes it easier for you to collect, transform, and transfer vehicle data to the
cloud in near real time and use that data to improve vehicle quality, safety, and autonomy. AWS
IoT Fleet is not a standalone AWS service, but rather a feature within AWS IoT Core.
FleetWise Usecase 1
Monitoring electric vehicle’s battery health and charge levels and provide the running range estimates
for drivers.
FleetWise Usecase 2
Use insights from commercial vehicle data, like speed and other vehicle related factors to analyze
driver safety, and maintenance schedules.
3.A. AWS IoT SiteWise
 AWS IoT SiteWise is a managed service that lets you collect, model, analyze, and visualize data
from Industrial IoT (IIOT) equipment at scale to optimize operations, and make data-driven
decisions.
 With AWS IoT SiteWise Monitor, you can quickly create web applications/dash boards for non-
technical users to view and analyze your industrial data in real time.
 IoT SiteWise allows you to collect data from a variety of industrial equipment, sensors, and devices
in industrial environment. It supports data ingestion through MQTT, and HTTPS.
 You can perform data transformations within SiteWise to clean, aggregate, and compute values
from raw data. This enables you to derive meaningful insights from your industrial data.
 SiteWise supports the configuration of alarms for industrial equipment, based on defined
thresholds, enabling you to receive notifications when specific conditions are met or exceeded.
 You can easily integrate AWS IoT SiteWise with other AWS services such as AWS IoT Core more to
build comprehensive industrial IoT solutions and perform advanced analytics.
3.B. AWS IoT Events
 AWS IoT Events enables you to monitor your equipment or device fleets for failures or changes in
operation, and to trigger actions when such events occur. AWS IoT Events continuously watches
IoT sensor data from devices, processes, applications, and other AWS services to identify significant
events so you can take action.
 AWS IoT Events includes a prebuilt library of actions you can take, and also enables you to define
your own.
 AWS IoT Events is designed to handle large volumes of data and can automatically scale to
accommodate varying workloads. It also incorporates security features such as encryption and
access control to ensure that your IoT data and event processing are secure.
 AWS IoT Events is particularly useful for applications where you need to respond to specific
conditions or events generated by IoT devices, such as equipment failures, threshold breaches, or
security breaches. By defining event patterns and automating responses, you can improve the
efficiency of your operations and reduce the need for manual intervention.
3.C. AWS IoT Analytics
 AWS IoT Analytics was a service provided by Amazon Web Services (AWS) that allowed you to
process, analyze, and visualize IoT (Internet of Things) data generated by your IoT devices.
 It was designed to help you derive insights from large volumes of IoT data and make data-driven
decisions.
 AWS IoT Analytics also enables us to clean, enrich, and transform our IoT data. It provided tools
for filtering, enriching, and transforming data to make it more suitable for analysis.
 AWS IoT Analytics can integrate with Amazon QuickSight, which is AWS's business intelligence
tool, to create dashboards and visualizations. You could use QuickSight to gain insights from your
IoT data through interactive dashboards.
3.D. AWS IoT TwinMaker
 AWS IoT TwinMaker is a AWS IoT service that helps developers create digital twins of real-world
systems. Digital twins are IoT-enabled digital representations of physical environments, factories,
and industrial equipment. They can be used to optimize industrial operations, increase
production output, Improve equipment performance. End users interact with digital twin by using
a user interface application/web browser.
 TwinMaker creates digital visualizations using measurements and analysis from a variety of real-
world sensors, cameras, and enterprise applications to help you keep track of your physical
factory, building, or industrial plant.
 A digital twin is a live digital representation of a system and all of its physical and digital
components. It is dynamically updated with real time data to mimic the true structure, state, and
behavior of the system. You can use it to drive business outcomes.
AWS IoT TwinMaker provide the following capabilities;
Entity component system knowledge graph
• AWS IoT TwinMaker provides tools for modeling devices, equipment, spaces, and processes in a
knowledge graph. This knowledge graph contains metadata about the system and can connect to
data in different locations. AWS IoT TwinMaker provides built-in connectors for data stored in AWS
IoT SiteWise.
Scene composer
• The AWS IoT TwinMaker console provides a scene composition tool for creating scenes in 3D. You
upload your previously built 3D/CAD models, optimized for web display and converted to .gltf
or .glb format. You then use the scene composer to place multiple models in a single scene,
creating visual representations of their operations.
• You can also overlay data in the scene. For example, you can create a tag in a scene location that
connects to temperature data from a sensor. This associates the data with the location.
2.1.3 IBM Watson IoT
 The IBM Watson IoT Platform is a cloud-hosted service that connects devices, gateways, and
applications for IoT solutions. It provides a set of services to connect, capture, register, analyze,
and archive IoT devices and data. The platform supports MQTT and REST protocols for
administrative functions, applications, event processing, device communication, and gateway
creation.
 The IBM Watson IoT platform helps you to manage connected devices so users can have access
to historical and live data. There are several features offered by the IBM Watson Platform. These
features include:
1. Dashboard
• When you gain access to this platform, you will see the user-friendly dash board. The dashboard
of the IBM Watson IoT platform comprises a number of cards and boards that offer different
visualization options for IoT solution.
2. Devices, gateways, and applications
• The device management control system is another feature the IBM IoT platform offers. With this
feature, users can develop and remove devices, gateways, and applications. Also, this feature
helps users to check and enable actions in the device, like a reset or a firmware upgrade request.
3. Security
• IBM IoT platform can help in managing the security aspects of a solution. This may likely include
checking the rules of a country, designing policies for device connections, and providing white and
black lists for the IP address of a device. Also, you can have control over users allowed or
prevented from managing the IoT organization.
4. Management and connection of devices
• You can easily connect to the IBM IoT platform and then connect and manage your IoT devices.
Also, users can create their own mobile IoT apps and visualization dashboards.
5. Enables team development
• The IBM IoT platform enables team development of IoT. This is because IBM IoT enables the
development of AI technologies in addition to the facilities provided by this platform.
6. Data Lifecycle Management
• IBM IoT platform offers data lifecycle management. This means that users can access real-time
data from their devices. They can as well choose to store data for a desired period. This allows
users to gain access to historical data.
7. AI & Visualization
• Empowers businesses with AI-driven analytics and visualizations to enable them to make
data-driven decisions.
• This software provides an extensive analytical functions catalog to allow companies to augment,
enrich, and gather data insights quickly. The Blockchain add-on enables businesses to track, trust,
and trace information across their business network.
FUNCTIONAL REPRESENTATION OF AZURE IBM Watson IoT
 IBM Watson IoT Platform - RETIREMENT
 IBM informed customers to move to another IoT management platform, as the December 1, 2023
is last date for IBM Watson IoT Platform. This information is sent to costumers over email on
November 2022, stating that;
“Please note, devices will be unable to connect to the MQTT and HTTP endpoints and existing
connections will be shut down. All remaining customers using this service should plan to move to
alternative services before December 1, 2023,”
 The platform was activated in 2014 offering customers one place to manage their IoT devices,
monitor usage and collect as well as process the generated data. In 2018, IBM announced Watson
IoT Platform is the next evolution would be delivering a future-proof Industrial IoT solution.
However, after selling Watson Health in 2022, it announced the sunset the Watson IoT Platform
service too. It looks like, IBM kept scrutinizing its unprofitable business lines. However, right-now,
IBM Watson IoT platform is no longer accepting new signups for the platform.
 For companies currently using Google IoT Core, it’s important to start thinking about migrating to
a different platform in order to ensure the continuity of their business operations. One of those
options is Azure IoT. Azure IoT allows businesses to easily connect, monitor, and control Internet
of Things (IoT) devices. It provides a wide range of features and capabilities, like device
management and provisioning, data processing, and analytics.
2.1.4 Google’s “Cloud IoT Core”
 The best part of using Google Cloud Platform is that it provides unique offerings for Big Data,
Artificial Intelligence and IoT services.
 Google’s Cloud Internet of Things (IoT) Core is a fully managed service for securely connecting
and managing IoT devices, from a few to millions. It allows users to easily and securely connect,
manage, and ingest data using various types of sensors and devices. It provides a way to collect,
process, analyze, and visualize IoT data in real time in a secured manner.
Google’s Cloud Internet of Things (IoT) Core Work Architecture
Google's IoT Core architecture is categorized into four stages: Data Gathering, Data Ingestion, Data
Processing, and Data Analysis.
1. Data Gathering
• The first stage, data gathering, occurs at the sensors and devices. Sensors gather data from
outside and send it to the cloud, either directly or through an intermediary device using a
gateway.
• A device is usually responsible to prepare the data for transmission to the cloud. Depending on
the network, preparation can include cleaning, preprocessing, analysis, and even machine
learning inference.
3. & 4. Data Ingestion and Processing
• This is a fully managed solution for ingesting and processing IoT data. Usually, Cloud IoT Core
devices are securely connected to the cloud. Cloud Pub/Sub receives messages from devices and
publishes them for subscribers to read.
D. Data Analysis
• Data analysis can be done on the Edge or on the cloud. Google's Cloud IoT Core is fully
integrated with IoT data. It includes visualizing and predicting results to generate actionable
outcomes.
Google’s Cloud Internet of Things (IoT) Core Features
1. Single Global System
• It can connect all devices and gateways to Google Cloud using protocols like MQTT and HTTP and
these are managed as a single global system. Provides connection endpoints for protocols with
automatic load balancing for all device connections.
2. Out-of-box Data Insights
• Downstream analytics integrate with Big data analytics and ML services such as Cloud Dataflow,
BigQuery, Cloud Bigtable for real-time analytics during the dataflow through a custom pipeline.
3. Fully Managed and Scalable
• The service is fully serverless and doesn’t require software installation. It scales instantly without
limits.
4. Role-level Access Control
• IAM (Identity and Access Management protocols) protocols can be applied to device registries to
control user access to devices and data.
5. End-to-end Security
• Cloud IoT Core uses asymmetric key authentication. Security is an important aspect while deploying
and managing an IoT network. Cloud IoT Core has several security features to protect the network
of IoT Core which are all connected through sensors and devices.
• All Devices are authenticated individually. So if there is an attack it will not affect the whole system.
FUNCTIONAL REPRESENTATION OF Google’s “Cloud IoT Core”
 Google’s Cloud IoT Core - RETIREMENT
 IBM is not alone in deciding one IoT platform is one too many. Google Cloud turned off its IoT
services as of August 2023, leaving customers with less than a year to find alternatives. In a
missive to customers, Google Cloud said;
"We're writing to let you know that Google Cloud IoT Core Service will be discontinued on August
15 2023 at which point, your access to the IoT Core Device Manager API will no longer be available.
IoT devices using IoT core service will be unable to connect to MQTT and HTTP bridges after that
date.”
 Google introduced Cloud IoT Core as a fully managed service for securely connecting and
managing devices, at the Google I/O conference in May 2017. According to the company, the
decision to discontinue the Google Cloud IoT platform was made in order to “focus their efforts on
a limited number of products that will have the biggest impact.”
 For companies currently using Google IoT Core, it’s important to start thinking about migrating to
a different platform in order to ensure the continuity of their business operations.One of those
options is Azure IoT. Azure IoT allows businesses to easily connect, monitor, and control Internet
of Things (IoT) devices. It provides a wide range of features and capabilities, like device
management and provisioning, data processing, and analytics. That all includes the full benefits
the Microsoft Cloud brings like security, scalability, and flexibility, making it a great choice for IoT
solutions of all sizes.
UNIT - 2 [ 10 Periods ]
IoT Cloud Platforms
Microsoft Azure IoT, Amazon Webs Services IoT, IBM WATSON IoT, Google’s cloud
IoT.
Principles and foundation of Artificial intelligence for IoT
Machine Learning Paradigms for IoT - Supervised learning for IoT (Linear regression, Logistic
regression, SVM-Decision Tree, Naive’s bayes), Deep Learning for IoT, Neural Networks for
IoT.

SUBJECT CODE - CO 314 (EL01)

CLASS DETAILS - IOT V SEM - AUGUST 2023
FACULTY DETAILS - PRUDHVI KIRAN P, Asst. Prof., CSE (IOT), RVR&JC College of Engineering
 UNDERSTANDING TECHNOLOGIES

ARTIFICIAL INTELLIGENCE

MACHINE LEARNING

DEEP LEARNING
SUPERVISED LEARNING
NEURAL NETWORKS
 ARTIFICIAL INTELLIGENCE
 Artificial intelligence is a machine’s ability to perform the cognitive functions (such as perceiving,
reasoning, learning, interacting with an environment, problem solving, and even exercising
creativity) like human minds.
 Every day we probably interact with AI even if we don't realize it; by using Facial Detection and
Recognition, Text Editors or Autocorrect, Maps and Navigation, Search and Recommendation
Algorithms and many more.
MACHINE LEARNING
 Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on
the use of data and algorithms to imitate the way that humans learn, gradually improving its
accuracy.
 Through the use of statistical methods, machine learning algorithms are trained to make
CLASSIFICATIONS/PREDICTIONS, and to uncover key insights in data. These insights subsequently
drive decision making within applications and businesses, ideally impacting key growth metrics.
 Example ML Use cases - Image Recognition, Speech Recognition, Predict Traffic Patterns, Self-
Driving Cars, Catching Email Spam, Catching Malware, Virtual Personal Assistant, many more.
 SUPERVISED LEARNING
 Supervised learning is the type of machine learning in which machines are trained using well
"labelled" training data, and on basis of that data, machines predict the output.
 Labelled data is raw data that has been assigned one or more labels to add context or meaning. In
machine learning and artificial intelligence, these labels often serve as a target for the model to
predict.
 While unlabelled data consists of raw inputs with no designated outcome, labelled data is
precisely the opposite. Labelled data is carefully annotated with meaningful tags, or labels, that
classify the data's elements or outcomes.
 In supervised learning, the training data provided to the machines work as the supervisor that
teaches the machines to predict the output correctly. It applies the same concept as a student
learns in the supervision of the teacher.
 For Example; we have a facial recognition task. Unlabeled data would consist of a set of facial
images without any identification information. Conversely, labeled data in this scenario would
include the same facial images with corresponding identification tags, i.e., the name of the person
in each image. Thus, a machine learning model can learn to associate particular facial features with
specific individuals.
FUNCTIONAL REPRESENTATION OF MACHINE LEARNING (SUPERVISED LEARNING)
 NEURAL NETWORKS
 Neural networks, also known as artificial neural networks (ANNs) or simulated neural networks
(SNNs), are a subset of machine learning and are at the heart of deep learning algorithms. Their
name and structure are inspired by the human brain, mimicking the way that biological neurons
signal to one another.
 Artificial neural networks (ANNs) are comprised of a node layers, containing an input layer, one or
more hidden layers, and an output layer. Each node, or artificial neuron, connects to another and
has an associated weight and threshold. If the output of any individual node is above the specified
threshold value, that node is activated, sending data to the next layer of the network. Otherwise,
no data is passed along to the next layer of the network.
 Neural networks rely on training data to learn and improve their accuracy over time. However,
once these learning algorithms are fine-tuned for accuracy, they are powerful tools in computer
science and artificial intelligence, allowing us to classify and cluster data at a high velocity.
 Neural networks can analyze human speech despite varying speech patterns, pitch, tone,
language, and accent (virtual assistants like Amazon Alexa and automatic transcription software),
Neural networks can track user activity to develop personalized recommendations, as they can
also analyze all user behavior and discover new products or services that interest a specific user.
 INPUT ONE HIDDEN
LAYER LAYER

OUTPUT
LAYER

FUNCTIONAL REPRESENTATION OF DEEP LEARNING

 DEEP LEARNING
 Deep learning is a subset of machine learning, which is essentially a neural network with more
hidden layers along with input and output layers. These neural networks attempt to simulate the
behavior of the human brain; shown while “learning” from large amounts of data.
 While a neural network with a single layer can still make approximate predictions, deep learning
with additional hidden layers can help to optimize and refine the accuracy.
 Deep learning drives many machine learning (AI) applications and services that improve
automation, performing analytical and physical tasks without human intervention. Deep learning
technology lies behind everyday products and services (such as digital assistants, voice-enabled TV
remotes, and credit card fraud detection) as well as emerging technologies (such as self-driving
cars).
 Deep learning distinguishes itself from classical machine learning by the type of data that it works
with and the methods in which it learns. Machine learning algorithms leverage structured,
labeled data to make predictions - meaning that specific features are defined from the input data
for the model and organized into tables. This doesn’t necessarily mean that it doesn’t use
unstructured data; it just means that if it does, it generally goes through some pre-processing to
organize it into a structured format.
 Deep learning eliminates some of data pre-processing that is typically involved with machine
learning. Deep learning algorithms can ingest and process unstructured data, like text and images,
and it automates feature extraction, removing some of the dependency on human experts. For
example, let’s say that we had a set of photos of different pets, and we wanted to categorize by
“cat”, “dog”, “hamster”, et cetera. Deep learning algorithms can determine which features (e.g.
ears) are most important to distinguish each animal from another. In machine learning, this
hierarchy of features is established manually by a human expert.
INPUT MULTIPLE HIDDEN LAYERS
LAYER

OUTPUT
LAYER

FUNCTIONAL REPRESENTATION OF DEEP LEARNING

HOW ARTIFICIAL INTELLIGENCE (MACHINE LEARNING) IS CHANGING INTERNET OF THINGS?
 IoT allows devices to communicate with each other
and act on those insights. To be useful for decision-
making, the data provided by devices needs to be
collected, stored, processed, and analysed; As IoT
adoption increases, businesses are struggling to
process the data efficiently and use it for real-world
decision making and insights; because the data
collected by IoT devices is experiencing latency and
congestion during the cloud transport for
processing.
 The AIoT, combination of artificial intelligence (AI)
technologies and the internet of things (IoT)
infrastructure , can bring processing to the IoT
endpoint instead of analyzing it in a separate
environment (cloud); leading to faster analytics.
AIoT's goal is to create more efficient IoT operations, AIoT
improving human-machine interactions and enhance
data management and analytics.
 Smart devices can analyze their own information without sending it to a data center located on
the other side of the world (cloud), enabling much faster speeds and lower latencies. For example,
this low latency could let self-driving vehicles, for instance, recognize obstacles in a fraction of a
second, enabling safe navigation. Regardless of the specifics, faster analytics means faster
decision-making, which is beneficial in any industry.
 AI can also address some of the IoT’s biggest challenges; Conventional IoT systems are infamously
difficult to secure, due to devices’ lack of built-in security measures. Intelligent algorithms can
actively monitor for suspicious activity or unauthorized access on IoT devices. AIoT brings this
process closer to the endpoints.
 Bringing AI to the IoT can make both technologies more accessible and scalable. IoT devices are
only as helpful as your ability to analyse their data, and AI is only useful if you have enough
information for it to study, I.e., Combining the two produces better results than using separately.
 AI algorithms can pick out the most important IoT data and summarize it before sending it to
other devices. That compression lowers network requirements, making large-scale IoT
environments more viable.
 Artificial intelligence unlocks the true potential of IoT by enabling networks and devices to learn
from past decisions, predict future activity, and continuously improve performance and decision-
making capabilities.
 PROGRAM ELEMENTS-STRUCTURE AIoT - REALTIME USE CASES
1. Autonomous vehicles
Autonomous vehicles are capable of driving safely from one point to another without any human
intervention. This is made possible by a range of advanced technologies, at the core of which lies AIoT.
Cars by Tesla are a good example of how a combination of AI and IoT can drastically transform the
automobile industry. These use sensors, gadgets, cameras, and a host of advanced technologies that
work together to ensure safe automated driving. The computers of autonomous vehicles can collect
and analyze information from several sources in real-time to make the most accurate driving decisions.
Accordingly, autonomous vehicles are a prime example of Edge AI.
2. Video Surveillance
The incorporation of AI and IoT makes video surveillance and security smarter. With traditional video
management systems (VMS), human operators are required to watch multiple video feeds. As a result,
manually operated security video systems depend on subjective judgment, limited attentiveness, and
inconsistent reaction times. AIoT combines machine learning algorithms with the video feed of
cameras to analyze data in real-time, detect objects, recognize people and identify events
automatically.
Example; the US supermarket giant Walmart uses image recognition cameras at checkouts to detect
theft. Other applications include weapon detection/intrusion event detection with virtual fences.
3. Traffic Monitoring
Monitoring Traffic AIoT-based sensors and devices are widely popular for real-time traffic analysis in
Smart Cities. Such AI systems include smart drones to assess congestion levels and perform crowd
analysis. In transportation, computer vision based AIoT systems automatically identify accidents,
traffic violations, stopped vehicles, and more.
4. Manufacturing And Production
AIoT systems are very popular in IIoT, the Industrial Internet of Things. In manufacturing, such
intelligent systems are used for real-time monitoring of machinery and to detect defective parts. Deep
neural networks are trained to detect defective parts in real time by analyzing the real-time video
feed of inexpensive cameras with AI models.
5. Smart Buildings/Offices
Companies opt for a network of smart environmental sensors installed within their offices that detect
the presence of people and automatically alter the lighting and temperature to maximize energy
savings. In addition, facial recognition technology enables smart buildings to control access by using
linked cameras and AI to compare live photos with a database to determine who gets access.
6. Healthcare
Medical devices and wearables collect and monitor real-time health data, such as heart rate, and can
detect irregular heartbeats. And can also monitor health of devices (Predictable Maintenance).
7. Collaborative robots (cobots)
AIoT acts as a heart of Cobots, which are intended to assist people in the manufacturing and assembly
of components. They aid humans in various tasks, such as production, assembly, packaging and quality
control of products, by using data from IoT devices and AI tools, including computer vision.
Many more applications of AIoT; Smart cities, Smart retail, Smart homes, Social media and human
resources (HR), Autonomous delivery robots
Inexpensive Cameras - Expensive Functionality
 Supervised Learning Algorithms for IoT
A. Linear regression B. Logistic regression C. SVM D. Decision Tree E. Naive bayes)
Supervised learning is the type of machine learning in which machines are trained using well
"labelled" training data, and on basis of that data, machines predict the output. Labelled data is
raw data that has been assigned one or more labels to add context or meaning. I.e. A supervised
learning algorithm takes a known set of input data (the learning set) and known responses to the
data (the output), and forms a model to generate reasonable predictions for the response to the
new input data. Use supervised learning if you have existing data for the output you are trying to
predict.
Two main categories of supervised learning algorithms, distinguished by the target variable type;
1. Classification
Classification algorithms are used to predict or classify the discrete values such as Male or Female,
True or False, Spam or Not Spam, etc. Example - Predicting whether a customer will default in
paying a loan or not (Yes/No), based on monthly salary, their credit history etc.
2. Regression
Regression algorithms are used to predict the continuous values such as price, salary, age, etc.
Example - Prediction of house prices based on different parameters like house age, distance from
the main road, location, area, etc.
 CLASSIFICATION REGRESSION

fundamentally, Classification is about predicting a label (discreet or fixed) and Regression is about
predicting a quantity (continuous or measurable).
Some of the major Supervised Machine Learning Algorithms include;
1. Linear Regression REGRESSION
2. Logistic Regression
3. Decision Tree CLASSIFICATION
4. SVM
5. Naive Bayes
1. Linear Regression
 Linear regression is the simplest and most widely-used model for supervised learning with
continuous targets. Linear regression analysis is used to predict the value of a variable based on
the value of another variable (one or more). The variable you want to predict is called the
dependent variable. The variable you are using to predict the other variable's value is called the
independent variable.
 Linear regression algorithm shows a linear relationship between a dependent (x) and one or more
independent (y) variables, hence called as linear regression. Since linear regression shows the
linear relationship, the value of dependent variable is changing according to the value of the
independent variable(s). For example, the number of hours would be the independent variable
and the money earned would be the dependent variable. The amount of money earned depends on
the number of hours worked.
 Linear regression can be further divided into two types of the algorithms; Simple Linear Regression
(single independent variable is used) and Multiple Linear regression (more than one independent
variable is used).
 The linear regression model provides a sloped straight line representing the relationship between
the variables. Below image/graph is the representation of linear regression;
 For Example, The weight of the person is linearly related to their height. So, this shows a linear
relationship between the height and weight of the person. According to this, as we increase the
height, the weight of the person will also increase.
LINEAR REGRESSION IN IOT
• Predictive Maintenance
Linear regression can be used to predict the remaining useful life of machinery and equipment based
on historical sensor data. It can estimate when a machine is likely to fail.
• Energy Consumption Forecasting
IoT sensors in smart buildings can collect data on energy usage, temperature, and occupancy. Linear
regression models can help forecast future energy consumption, allowing for better energy
management and cost reduction.
• Environmental Monitoring
Linear regression can be applied to analyze IoT sensor data related to environmental factors such as air
quality, temperature, and humidity. This analysis can help predict pollution levels, weather patterns,
and environmental changes.
• Agricultural Yield Prediction
IoT devices in precision agriculture collect data on soil quality, weather conditions, and crop health.
Linear regression models can predict crop yields based on these data.
• Inventory Management
Linear regression can assist in inventory optimization by analyzing historical sales data from IoT-
connected point-of-sale systems. It can help businesses forecast demand and adjust their inventory
levels accordingly.
• Traffic Flow Prediction
IoT sensors in smart cities collect traffic data, such as vehicle speed, volume, and congestion. Linear
regression models can predict traffic flow and congestion patterns, allowing for better traffic
management and route planning.
• Retail Sales Forecasting
Linear regression can analyze IoT data from retail environments, including foot traffic, weather
conditions, and promotional activities, to forecast sales and optimize marketing strategies.
• Supply Chain Optimization
Linear regression can be used to analyze IoT data related to supply chain performance, including
shipping times, order volumes, and supplier performance. This analysis can optimize logistics and
inventory management.
• Quality Control
In manufacturing IoT applications, linear regression can be used to model relationships between
sensor data and product quality. It can help identify factors that contribute to defects and improve
quality control processes.
• Wearable Health Devices
Linear regression can be applied to data from wearable IoT devices, such as fitness trackers and health
monitors, to predict health-related outcomes like heart rate, blood pressure, or calorie expenditure.
Linear regression is well-suited for scenarios where there is a linear relationship between input
variables and the target variable. It provides a straightforward way to model and make predictions
based on historical data collected by IoT devices. However, in situations with nonlinear relationships,
Linear Regression is not suitable.
2. Logistic Regression
 Logistic regression is a statistical method in supervised learning for predicting a binary outcome,
such as yes or no, based on a data set. Logistic regression is often used for classification and
predictive analytics.
 Logistic regression estimates the probability of an event occurring, such as voted or didn’t vote,
based on a given dataset of independent variables. Since the outcome is a binary/probability, the
dependent variable is bounded between 0 and 1. I.e. logistic regression is only used when our
dependent variable is binary and on other hand, in linear regression the dependent variable is
continuous.
 In Logistic regression, instead of fitting a
regression line, we fit an "S" shaped logistic
function, which predicts two maximum values (0
or 1).
 The threshold value inlogistic regression is 0.5.
This means that by default, the model will predict
the class with the highest probability (1) when
the probability is greater than or equal to 0.5.
And it predicts lowest probability (0), when the
probability is less than 0.5.
 Some popular examples of logistic regression include; predicting if an e-mail is spam or not spam
or if a tumor is malignant or not malignant.
LOGISTIC REGRESSION IN IOT
• Anomaly Detection
Logistic regression can be used to classify data from IoT sensors as either normal or anomalous. When
monitoring a system for anomalies, this can help detect unusual behavior or security breaches.
• Predictive Maintenance
In IoT-based predictive maintenance, logistic regression can classify equipment or machinery as either
healthy or in need of maintenance based on sensor data. This helps prioritize maintenance efforts.
• Quality Control
Logistic regression can classify products as either defective or non-defective based on sensor
measurements in manufacturing IoT applications, aiding in quality control processes.
• Fault Detection
In industrial IoT, logistic regression can classify devices or components as either faulty or functioning
correctly based on sensor data. This helps in quickly identifying and addressing issues.
• Healthcare Monitoring
Logistic regression models can classify patient health status as normal or critical based on data from
wearable IoT devices, allowing for early intervention in medical emergencies.
• Security
Logistic regression can be used to classify network traffic patterns as either normal or suspicious in IoT
security applications, aiding in intrusion detection and prevention.
• Environmental Monitoring
In IoT environmental monitoring systems, logistic regression can classify environmental conditions as
safe or potentially hazardous based on sensor data, triggering alerts or actions as needed.
• User Behaviour Analysis
Logistic regression can classify user behavior as legitimate or fraudulent based on patterns observed in
IoT data. This is valuable for applications like fraud detection in online transactions.
• Occupancy Detection
In smart building systems, logistic regression can classify rooms or areas as occupied or vacant based
on data from occupancy sensors, enabling energy-saving strategies.
• Predictive Agriculture
Logistic regression can classify soil conditions as suitable or unsuitable for planting based on sensor
data in precision agriculture, assisting in crop management decisions.
• Traffic Management
Logistic regression can classify traffic conditions as normal or congested based on data from IoT traffic
sensors, helping with real-time traffic management and route planning.
• Waste Management
In smart waste management systems, logistic regression can classify waste bins as full or empty based
on sensor data, optimizing waste collection routes.
Logistic regression is particularly useful when the problem at hand involves making binary decisions
or classifying data into two categories. However, for multi-class classification problems, Logistic
Regression is not suitable and other algorithms like decision trees, random forests, support vector
machines, or deep learning models might be more appropriate.
3. Decision Tree
 Decision Tree is a Supervised learning technique that can be used for both classification and
Regression problems, but mostly it is preferred for solving Classification problems.
 hey are easy to understand, interpret, and implement, making them an ideal choice for beginners
in the field of machine learning.
 In a Decision tree, there are two nodes, which are the Decision Node and Leaf Node. Decision
nodes are used to make any decision and have multiple branches, whereas Leaf nodes are the
output of those decisions and do not contain any further branches. It uses a flowchart like a tree
structure to show the predictions that result from a series of feature-based splits.

It starts with a root node

and ends with a decision
made by leaves.
Decision Tree Terminologies
 Root Node: The initial node at the beginning of a decision tree, where the entire population or
dataset starts dividing based on various features or conditions.
 Decision Nodes: Nodes resulting from the splitting of root nodes are known as decision nodes.
These nodes represent intermediate decisions or conditions within the tree.
 Leaf Nodes: Nodes where further splitting is not possible, often indicating the final classification or
outcome. Leaf nodes are also referred to as terminal nodes.
 Sub-Tree: Similar to a subsection of a graph being called a sub-graph, a sub-section of a decision
tree is referred to as a sub-tree. It represents a specific portion of the decision tree.
 Pruning: The process of removing or cutting down specific nodes in a decision tree to prevent
overfitting and simplify the model.
 Branch / Sub-Tree: A subsection of the entire decision tree is referred to as a branch or sub-tree. It
represents a specific path of decisions and outcomes within the tree.
 Parent and Child Node: In a decision tree, a node that is divided into sub-nodes is known as a
parent node, and the sub-nodes emerging from it are referred to as child nodes.
 The parent node represents a decision or condition, while the child nodes represent the potential
outcomes or further decisions based on that condition.
 Below is the example, decision tree. It starts with root node and ends with leaf nodes, determining
some facts.

DECISION TREE IN IOT

• Anomaly Detection
Decision Trees can be used to detect anomalies in IoT sensor data. By training a decision tree on
historical data, you can create a model that classifies data points as normal or anomalous
• Predictive Maintenance
Decision Trees can help in predicting equipment failures in IoT-based predictive maintenance systems.
By analyzing sensor data, the algorithm can identify conditions that often lead to failures, allowing for
timely maintenance.
• Quality Control
In manufacturing IoT applications, Decision Trees can classify products as either defective or non-
defective based on sensor measurements, aiding in quality control processes.
• Fault Detection
Decision Trees can be used to classify devices or components as faulty or functioning correctly based on
sensor data in industrial IoT, facilitating early detection and intervention.
• Healthcare Monitoring
Decision Trees can classify patient health conditions as normal, at risk, or critical based on data from
wearable IoT devices, helping with medical decision-making.
• Security
Decision Trees can be used for intrusion detection in IoT security systems. By analysing network traffic
patterns, the algorithm can identify suspicious behavior and trigger alerts.
• Environmental Monitoring
Decision Trees can classify environmental conditions as safe or potentially hazardous based on sensor
data in IoT environmental monitoring systems, triggering warnings or taking appropriate actions.
• User Behavior Analysis
Decision Trees can classify user behavior in IoT applications as legitimate or fraudulent based on
patterns observed in data. This is valuable for fraud detection and security.
• Occupancy Detection
In smart building systems, Decision Trees can classify rooms or areas as occupied or vacant based on
data from occupancy sensors, enabling energy-efficient management.
• Predictive Agriculture
Decision Trees can classify soil conditions as suitable or unsuitable for planting based on sensor data in
precision agriculture, aiding in crop management decisions.
• Traffic Management
Decision Trees can classify traffic conditions as normal, congested, or critical based on data from IoT
traffic sensors, helping with real-time traffic management and route planning.
• Waste Management
In smart waste management systems, Decision Trees can classify waste bins as full, partially full, or
empty based on sensor data, optimizing waste collection routes.

Decision Trees are advantageous in IoT applications because they are relatively easy to interpret,
which can be important for making informed decisions. They can also handle both categorical and
numerical data, making them versatile for various IoT data types. However, for very complex and large
datasets, decision trees may not be used.
4. Support Vector Machine (SVM)
 SVM is a powerful supervised algorithm that works best on smaller datasets but on complex ones.
Support Vector Machine, abbreviated as SVM can be used for both regression and classification
tasks, but generally, they work best in classification problems.
 The goal of the SVM algorithm is to create the best line or decision boundary that can segregate n-
dimensional space into classes so that we can easily put the new data point in the correct category
in the future. This best decision boundary is called a hyperplane.
 SVM chooses the extreme points/vectors that help in creating the hyperplane. These extreme cases
are called as support vectors, and hence algorithm is termed as Support Vector Machine. Consider
the below diagram in which there are two different categories that are classified using a decision
boundary or hyperplane. In this diagram, positive hyper plane and negative hyper plane are called
as support vectors.
 Examples of the SVM include; Data classification, Facial detection & expression classification, Text
categorization & handwriting recognition and speech recognition.
SVM IN IOT
• Anomaly Detection
SVM can be used to detect anomalies in IoT sensor data. By training a SVM on historical data, you can
create a model that classifies data points as normal or anomalous.
• Predictive Maintenance
SVM can help in predicting equipment failures in IoT-based predictive maintenance systems. By
analyzing sensor data, the algorithm can identify conditions that often lead to failures, allowing for
timely maintenance.
• Quality Control
In manufacturing IoT applications, SVM can classify products as either defective or non-defective based
on sensor measurements, aiding in quality control processes.
• Fault Detection
SVM can be used to classify devices or components as faulty or functioning correctly based on sensor
data in industrial IoT, facilitating early detection and intervention.
• Healthcare Monitoring
SVM can classify patient health conditions as normal, at risk, or critical based on data from wearable
IoT devices, helping with medical decision-making.
• Security
SVM can be used for intrusion detection in IoT security systems. By analysing network traffic patterns,
the algorithm can identify suspicious behavior and trigger alerts.
• Environmental Monitoring
SVM can classify environmental conditions as safe or potentially hazardous based on sensor data in IoT
environmental monitoring systems, triggering warnings or taking appropriate actions.
• User Behavior Analysis
SVM can classify user behaviour in IoT applications as legitimate or fraudulent based on patterns
observed in data. This is valuable for fraud detection and security.
• Occupancy Detection
In smart building systems, SVM can classify rooms or areas as occupied or vacant based on data from
occupancy sensors, enabling energy-efficient management.
• Predictive Agriculture
SVM can classify soil conditions as suitable or unsuitable for planting based on sensor data in precision
agriculture, aiding in crop management decisions.
• Traffic Management
SVM can classify traffic conditions as normal, congested, or critical based on data from IoT traffic
sensors, helping with real-time traffic management and route planning.
• Waste Management
In smart waste management systems, SVM can classify waste bins as full, partially full, or empty based
on sensor data, optimizing waste collection routes.
SVM is a versatile algorithm and can be particularly effective when dealing with high-dimensional
data or when a clear margin of separation exists between classes. However, it may require careful
preprocessing of data and parameter tuning to achieve optimal results in specific IoT applications.
5. Naive Bayes
 Naive Bayes algorithm is a supervised learning algorithm, which is based on Bayes theorem and
used for solving classification problems.
 Naive Bayes is a probabilistic machine learning algorithm that is commonly used for classification
tasks. The simplest solutions are usually the most powerful ones, and Naïve Bayes is a good
example of that. It has been successfully used for many purposes, but it works particularly well
with natural language processing (NLP) problems (Text Classification).
Bayes’ Theorem is named after English statistician, Thomas Bayes. It is a very important theorem in
mathematics that is used to find the probability of an event, based on prior knowledge of conditions
that might be related to that event. Below is the Bayes formula;
probability of B occurring probability of A occurring
given evidence A has
already occurred

probability of A occurring
given evidence B has probability of B occurring
already occurred
Which tells us: how often A happens given that B happens, written P(A|B) also called posterior
probability, When we know: how often B happens given that A happens, written P(B|A) and how likely
A is on its own, written P(A) and how likely B is on its own, written P(B). In simpler terms, Bayes’
Theorem is a way of finding a probability when we know certain other probabilities.
 Naive Bayes is a simple supervised machine learning algorithm that uses the Bayes’ theorem with
strong independence assumptions between the features to procure results. That means that the
algorithm just assumes that each input variable is independent. For example, if you use Naive
Bayes for sentiment analysis, given the sentence ‘I like Harry Potter’, the algorithm will look at the
individual words and not the full sentence.
 In fact, in a sentence, words that stand next to each other influence the meaning of each other, and
the position of words in a sentence is also important. However, for the Naive Bayes algorithm,
phrases like ‘I like Harry Potter’, Harry Potter like I’, and ‘Potter I like Harry’ are the same.
Here are some of the common applications of Naive Bayes for real-life tasks;
 Document classification; This algorithm can help you to determine to which category a given
document belongs. It can be used to classify texts into different languages, genres, or topics
(through the presence of keywords).
 Spam filtering; Naive Bayes easily sorts out spam using keywords. For example, in spam, you can
see the word ‘gambling’ much more often than in regular mail. The algorithm must be trained to
recognize such probabilities and, then, it can efficiently apply them for spam filtering.
 Sentiment analysis; Based on what emotions the words in a text express, Naive Bayes can calculate
the probability of it being positive or negative. For example, in customer reviews, ‘good’ or
‘inexpensive’ usually mean that the customer is satisfied.
 Image classification; For personal and research purposes, it is easy to build a Naive Bayesian
classifier. It can be trained to recognize hand-written digits or put images into categories through
supervised machine learning.
NAIVE BAYES IN IOT
• Anomaly Detection
Naive Bayes can be used for anomaly detection in IoT sensor data. By modeling the normal behavior of
IoT devices, it can identify deviations from the expected patterns, indicating anomalies or security
breaches.
• Environmental Monitoring
In IoT environmental monitoring systems, Naive Bayes can classify environmental conditions as safe or
potentially hazardous based on sensor data, enabling timely responses to environmental changes or
pollution events.
• Quality Control
In manufacturing IoT applications, Naive Bayes can classify products as defective or non-defective
based on sensor measurements, assisting in quality control processes.
• Predictive Agriculture
Naive Bayes can classify soil conditions as suitable or unsuitable for planting based on sensor data in
precision agriculture, assisting in crop management decisions.
• Occupancy Detection
In smart buildings, Naive Bayes can classify rooms or areas as occupied or vacant based on data from
occupancy sensors, enabling energy-efficient management of lighting and HVAC systems.
• Healthcare Monitoring
Naive Bayes models can classify patient health conditions, such as normal, at risk, or critical, based on
data from wearable IoT devices, aiding in medical decision-making.
• User Behavior Analysis
Naive Bayes can classify user behavior in IoT applications as legitimate or fraudulent based on patterns
observed in data. This is essential for fraud detection and security.
• Waste Management
In smart waste management systems, Naive Bayes can classify waste bins as full, partially full, or empty
based on sensor data, optimizing waste collection routes.
• Predictive Maintenance
While not typically used for predictive maintenance, Naive Bayes can be applied to classify
maintenance-related decisions, such as whether a piece of equipment needs maintenance or not
based on historical data.
It's important to note that Naive Bayes has its limitations, particularly its assumption of feature
independence, which may not hold in all real-world scenarios. In situations where feature
independence doesn't hold, other machine learning algorithms like decision trees, random forests,
support vector machines, or deep learning models may be more appropriate. The choice of algorithm
should depend on the nature of the data and the specific requirements of the IoT application.
TECHNOLOGY WISE APPLICATIONS
 ARTIFICIALELEMENTS-STRUCTURE
PROGRAM INTELLIGENCE (MACHINE LEARNING/SUPERVISED LEARNING) - IOT APPLICATIONS
• Predictive Maintenance
ML algorithms can analyze sensor data from IoT devices to predict when equipment or machinery is
likely to fail. This enables proactive maintenance, reducing downtime and saving costs for businesses.
• Anomaly Detection
ML models can identify unusual patterns or anomalies in sensor data, which can be indicative of
security breaches, equipment malfunctions, or other abnormal events in IoT networks.
• Energy Management
ML can optimize energy consumption in IoT systems by analyzing historical data and making real-time
adjustments to control heating, cooling, lighting, and other energy-consuming devices in a smart
building or industrial setting.
• Healthcare Monitoring
IoT devices like wearables and medical sensors can collect a vast amount of data. ML algorithms can
analyze this data to monitor patients' health conditions, detect anomalies, and alert healthcare
providers in case of emergencies.
• Smart Agriculture
ML helps optimize farming operations by analyzing data from IoT sensors on soil moisture, weather
conditions, and crop health to make decisions on irrigation, fertilization, and pest control.
• Traffic Management
ML can analyze data from traffic cameras, sensors, and GPS devices to optimize traffic flow, predict
congestion, and improve overall transportation efficiency in smart cities.
• Environmental Monitoring
IoT sensors can collect data on air quality, water quality, and other environmental factors. ML can
analyze this data to detect pollution, track changes over time, and provide early warnings for natural
disasters.
• Supply Chain Optimization
ML can optimize inventory management, logistics, and supply chain operations by analyzing IoT data
related to product movement, demand forecasting, and supply chain performance.
• Gesture and Voice Recognition
IoT devices like smart speakers and cameras can benefit from ML-based gesture and voice recognition
to enhance user interactions and control.
• Personalized User Experiences
ML algorithms can analyze user behavior data from IoT devices to offer personalized
recommendations, content, and services, enhancing the overall user experience.
• Security and Fraud Detection
ML can analyze data from IoT devices to detect security breaches, unauthorized access, and fraudulent
activities in real-time, improving overall system security.
• Industrial Automation
In manufacturing and industrial settings, ML can optimize production processes, quality control, and
equipment maintenance by analyzing data from IoT sensors and automation systems.
• Smart Grids
ML helps in managing electricity grids efficiently by analyzing data from IoT sensors to predict energy
demand, optimize distribution, and detect faults or power outages.
• Asset Tracking
ML can help track and manage assets, such as vehicles, equipment, or inventory, using IoT devices with
GPS and other sensors.
• Wildlife Conservation
IoT-based sensor networks combined with ML can be used for wildlife tracking, habitat monitoring, and
poaching detection to aid conservation efforts.
 NEURAL NETWORKS & DEEP LEARNING - IOT APPLICATIONS
PROGRAM ELEMENTS-STRUCTURE
• Image and Video Analysis
Object Detection: Neural networks can identify and locate objects in images and videos captured by
IoT cameras. This is useful in applications like surveillance, automated inspection, and smart
transportation.
• Natural Language Processing (NLP)
1. Voice Recognition: Neural networks can be used for speech recognition in IoT devices like smart
speakers and voice assistants.
2. Language Translation: In IoT applications, neural networks can provide real-time translation
services for multilingual communication.
• Predictive Maintenance
Neural networks can analyze sensor data to detect anomalies in machinery, equipment, or
infrastructure. This aids in predicting and preventing failures.
• Sensor Data Fusion
Neural networks can fuse data from various IoT sensors, including temperature sensors,
accelerometers, and cameras, to gain a more comprehensive understanding of an environment or
system.
• Gesture Recognition
Neural networks can interpret gestures captured by IoT sensors like accelerometers or depth cameras.
This is valuable in applications like gaming, human-computer interaction, and virtual reality.
• Security and Anomaly Detection
Neural networks can identify suspicious patterns or behaviors in network traffic data from IoT devices,
helping to detect and prevent cyberattacks.
• Energy Optimization
Neural networks can optimize energy consumption by analyzing data from IoT devices and adjusting
settings for heating, cooling, lighting, and more in smart buildings.
• Healthcare Monitoring
Neural networks can analyze data from wearable IoT devices to monitor a person's health, detect
abnormal conditions, and provide timely alerts.
• Autonomous Vehicles
In autonomous vehicles and drones, neural networks are used for tasks like object detection, lane
detection, and path planning based on sensor inputs.
• Quality Control
In manufacturing, neural networks can inspect and classify products based on sensor data, ensuring
quality control and reducing defects.
• Environmental Monitoring
Neural networks can analyze data from environmental IoT sensors to monitor air and water quality,
identify pollution sources, and predict environmental changes.
• Precision Agriculture
Neural networks can process data from IoT sensors in agriculture to optimize irrigation, fertilization,
and crop management for increased yields and resource efficiency.
UNIT - 2 [ 13 Periods ]
IoT Cloud Platforms
Microsoft Azure IoT, Amazon Webs Services IoT, IBM WATSON IoT, Google’s cloud
IoT.
Principles and foundation of Artificial intelligence for IoT
Machine Learning Paradigms for IoT - Supervised learning for IoT (Linear regression, Logistic
regression, SVM-Decision Tree, Naive’s bayes), Deep Learning for IoT, Neural Networks for
IoT.

END OF UNIT 2

SUBJECT CODE - CO 314 (EL01)

CLASS DETAILS - IOT V SEM - AUGUST 2023
FACULTY DETAILS - PRUDHVI KIRAN P, Asst. Prof., CSE (IOT), RVR&JC College of Engineering