CC5_Iot, AI, Big Data

Internet of Things (IoT)

• Internet is no longer just a network of computers, but a network of physical objects that can interact with each other and the digital world.

• connecting physical objects to the internet to create a more integrated, automated, and data-driven world.

• Can be viewed as a gigantic network consisting of networks of devices and computers connected through a series of intermediate technologies where numerous technologies like RFIDs, wireless connections may act as enablers of this connectivity

Kevin Ashton

Coins the term “Internet of Things” and establishes MIT’s Auto-ID Center, a global research network of academic laboratories focused on RFID and the IoT.

MIT’s Auto-ID Center

global research network of academic laboratories focused on RFID and the IoT.

1980s,

Coke machine,

Carnegie Mellon University

• Year: _____

• The first IoT device, a _____, was connected to the internet at _____.

1999

• Year: _____

• The term "Internet of Things" was coined by Kevin Ashton.

2000s,

RFID (Radio-Frequency Identification)

• Year: _____

• IoT started gaining traction with the introduction of _____ technology.

2010s

IoT devices became increasingly popular, with the proliferation of smartphones, sensors, and cloud computing.

Things

• The term refers to physical objects that are embedded with sensors, software, and connectivity capabilities.

• These objects can range from everyday devices like smartphones and wearables to industrial equipment, vehicles, and even buildings.

Internet

The term refers to the network that connects these physical objects, allowing them to communicate with each other and exchange data.

Interconnectedness,

Sensing and Activation,

Data-Driven Decision Making

Key Aspects of IoT (3)

Interconnectedness

IoT devices are connected to each other and the Internet, enabling them to exchange data and interact with each other.

Sensing and Activation

IoT devices can sense their environment and perform actions based on the data they collect.

Data-Driven Decision Making

IoT devices generate vast amounts of data, which can be analyzed to gain insights and make informed decisions.

Smart Lighting,

Thermostat Control,

Security Systems Come

Smart home IoT Applications (3)

Smart Lighting

Control lighting systems remotely, adjust brightness and color, and automate lighting schedules

Thermostat Control

Regulate temperature, schedule heating and cooling, and optimize energy consumption

Security Systems Come

Monitor and control security cameras, door locks, and alarm systems remotely.

Predictive Maintenance,

Quality Control,

Inventory Management

Industrial automation IoT Applications (3)

Predictive Maintenance

Use sensors to monitor equipment condition, predict maintenance needs, and prevent downtime.

Quality Control

Use sensors and cameras to monitor product quality, detect defects, and optimize production processes.

Inventory Management

Track inventory levels, monitor stock movements, and automate inventory reporting.

Wearable Devices,

Remote Patient Monitoring,

Medical Equipment Tracking

Healthcare IoT Applications (3)

Wearable Devices

Track vital signs, monitor activity levels, and provide personalized health insights.

Remote Patient Monitoring

Monitor patients remotely, track vital signs, and provide timely interventions

Medical Equipment Tracking

Medical equipment location, monitor usage, and optimize maintenance schedules.

Smart Traffic Management,

Vehicle Tracking,

Autonomous Vehicles

Transportation IoT Applications (3)

Smart Traffic Management

Optimize traffic flow, predict traffic congestion, and provide real-time traffic updates.

Vehicle Tracking

Track vehicle location, monitor driver behavior, and optimize route planning period

Autonomous Vehicles

Enable self-driving cars, trucks, and drones to navigate and interact with their environment.

Precision Farming,

Livestock Monitoring,

Crop Yield Prediction

Agriculture IoT Applications (3)

Precision Farming

Use sensors to monitor soil moisture, temperature, and crop health, and optimize irrigation and fertilization.

Livestock Monitoring

Track animal health, monitor behavior, and optimize feeding and breathing schedules.

Crop Yield Prediction

Use sensors and data analytics to predict crop yields, detect diseases, and optimize harvest planning.

IoT Lifecycle

By following this, organizations can unlock the full potential of their IoT devices and data, and make informed decisions to drive business outcomes.

Collect/Collection,

Communicate/Communication,

Analyze/Analysis,

Act/Action

IoT Lifecycle/Stages of IoT Lifecycle (4)

Data Collection,

Data Types,

Device Management

Collect (3)

Data Collection

IoT devices collect data from various sources, such as sensors, cameras, and other devices.

Data Types

The data collected can be in various forms, including temperature, humidity, motion, pressure, and more.

Device Management

IoT devices need to be managed and monitored to ensure they are functioning correctly and collecting accurate data.

Data Transmission,

Communication Protocols,

Data Security

Communicate (3)

Data Transmission

The collected data is transmitted to a central location, such as a cloud or on premises server, for further processing and analysis

Communication Protocols

IoT devices use various communication protocols, such as Wi-Fi, Bluetooth, or cellular networks, to transmit data.

Data Security

Ensuring the security and integrity of the data being transmitted is crucial to prevent unauthorized access or tampering.

Data Processing,

Insight Generation,

Data Visualization

Analyze (3)

Data Processing

The transmitted data is processed and analyzed using various analytics tools and techniques, such as machine learning and predictive analytics.

Insight Generation

The analysis of the data provides insights into the behavior, performance, entrance of the IoT devices and the environment they are operating in.

Data Visualization

The insights generated are visualized in a way that is easy to understand, using dashboards, charts, and other visualization tools.

Decision Making,

Automation,

Continuous Improvement

Act (3)

Decision Making

Based on the insights generated, decisions are made to take specific actions, such as adjusting settings, scheduling maintenance, or sending alerts.

Automation

IoT devices can be automated to take actions based on the analysis call ma such as turning on or off devices, adjusting temperatures, or sending notifications.

Continuous Improvement

The IoT lifecycle is continuous, and the insights generated are used to improve the performance and efficiency of the IoT devices and the environment they are operating in.

Collection

• Devices and Sensors are collecting data everywhere.

• Example:

  • At your home

  • In your car

  • At the office

  • In the manufacturing plant

Communication

• Sending data and events through networks to some destination

• Example:

  • A cloud platform

  • Private data center

  • Home network

Analysis

• Creating information from the data

• Example:

  • Visualizing the data

  • Building reports

  • Filtering data (paring it down)

Action

• Taking action based on the information and data

• Example:

  • Communicate with another machine (m2m)

  • Send a notification (sms, email, text)

  • Talk to another system

RFID Tags

Small devices that store and transmit data, attached to objects or devices.

RFID Readers

The devices that read the data stored on RFID tags.

Temperature,

Humidity,

Motion,

Pressure, Light

Types of Sensors (4)

Sensors

• Detect changes in the environment and send data to IoT devices or systems.

• To collect and process the data to detect the changes in the physical status of things.

Smart Devices

Devices that can sense, activate, and communicate with other devices and systems.

Artificial Intelligence

Enables devices to make decisions based on data and analytics.

Nanoscale Devices

Devices that operate at the nanoscale, enabling new applications and functionalities.

RFID

To identify and track the data of things

Smart Tech

To enhance the power of the network by developing processing capabilities to different part of the network.

Nano Tech

To make the smaller and smaller things have the ability to connect and interact.

Tagging Things

Real-time item traceability and addressability by RFID

Feeling Things

Sensors act as primary devices to collect data from the environment.

Shrinking Things

Miniaturization and Nanotechnology has provoked the ability of smaller things to interact and connect within the “things” or “smart devices.”

Thinking Things

• Embedded intelligence in devices through sensors has formed the network connection to the Internet.

• It can make the “things” realizing the intelligent control.

Scalability,

Technological Standardization,

Interoperability,

Discovery,

Software Complexity,

Data Volumes and Interpretation,

Power Supply,

Interaction and Short-Range Communication,

Wireless Communication,

Fault Tolerance

Technological Challenges of IoT (10)

Scalability

• As the number of IoT devices grows (billions of them open), the system must still work smoothly.

• IoT networks must handle huge increases in devices, data, and connections without slowing down.

Technological Standardization

• IoT devices from different companies often use different rules, protocols, and formats.

• Because of this, they cannot easily communicate with each other.

• We need common standards to ensure compatibility.

Interoperability

• Needed to standardization–IoT devices, platforms, and apps must work together.

• For example: a smart fridge, easy, and light bulb from different brands should still connect correctly.

Discovery

• IoT devices need a way to find and recognize each other automatically.

• Example: when you add a new smart bulb, your system

Software Complexity

• IoT devices systems require complex software to manage communication, data, security, updates, etc.

• The bigger the system, the more complicated the programming becomes.

Data Volumes and Interpretation

• IoT devices generate enormous amounts of data (big data).

• Challenges include:

  • Storing data

  • Processing data

  • Analyzing data for useful insights

  • Transferring data quickly

Power Supply

• Many IoT devices run on small batteries (sensors, trackers, wearables).

• Challenges:

  • Long battery life

  • Efficient energy use

  • Sometimes battery-less IoT is needed

Interaction and Short-Range Communication

• IoT often uses Bluetooth, RFID, NFC, Zigbee, etc.

• Challenges:

  • Limited range

  • Interference

  • Maintaining stable communication

Wireless Communication

• IoT depends heavily on wireless networks like Wi-Fi, LTE, and 5G.

• Problems include:

  • Limited bandwidth

  • Congestion

  • Signal loss

  • Security risks

Fault Tolerance

• IoT systems must continue working even if:

  • A device fails

  • A sensor stops sending data

  • The network goes down

  • Building fault-tolerant IoT is hard because devices are distributed everywhere.

Artificial Intelligence (AI)

• is the field of computer science that focuses on creating machines that can think and learn like humans.

• It involves developing algorithms and computer programs that can perform tasks that typically require human intelligence, such as perception, reasoning, and decision-making.

1950

AI has a rich history that dates back to the ___s

Healthcare

Finance,

Manufacturing,

Transportation,

Retail,

Education

AI Applications (6)

Healthcare

AI can help doctors and healthcare professionals make more accurate diagnoses, develop personalized treatment plans, and discover new drugs.

Finance

AI can help banks and financial institutions detect fraudulent activities, make investment decisions, and automate routine tasks.

Manufacturing

AI can help optimize production processes, improve quality control, and reduce costs

Transportation

AI can help develop autonomous vehicles, optimize traffic flows, and improve logistics.

Retail

AI can help retailers analyze customer data, develop personalized marketing campaigns, and improve customer service.

Education

AI can help personalize learning, provide real-time feedback to students, and identify areas where students may need additional support.

Machine Learning

is a subfield of AI that focuses on creating algorithms that can learn from data.

Supervised Learning

Unsupervised Learning

Reinforcement Learning

main types of machine learning algorithms (3)

supervised learning

• the algorithm is given a set of labeled examples to learn from.

• These labeled examples consist of inputs (features) and corresponding outputs (labels).

• The algorithm learns to predict the correct output given a new input.

• Common applications include

  • image classification

  • speech recognition

  • predicting stock prices.

unsupervised learning

• the algorithm is given a set of unlabeled examples to learn from.

• The algorithm tries to find patterns or structure in the data without any prior knowledge of what the output should be.

• Common applications

  • include clustering

  • anomaly detection

  • dimensionality reduction.

reinforcement learning

• the algorithm learns by interacting with an environment and receiving feedback in the form of rewards or punishments.

• The algorithm learns to take actions that maximize the rewards it receives.

• Common applications includ

  • robotics

  • game playing

  • optimizing industrial processes.

Recommender Systems,

Fraud Detection

Speech Recognition,

Image Recognition,

Natural Language Processing

Examples of Machine Learning (5)

Recommender Systems

use machine learning algorithms to suggest products or services to users based on their past behavior or preferences.

Fraud Detection

Machine learning algorithms can be used to detect fraudulent activities in financial transactions, such as credit card fraud.

Speech Recognition

Machine learning algorithms can be used to recognize speech and convert it into text, which can be used in applications like virtual assistants or transcription services.

Image Recognition

Machine learning algorithms can be used to identify objects in images and videos, which can be used in applications like self-driving cars or security systems.

Natural Language Processing

Machine learning algorithms can be used to analyze and understand human language, which can be used in applications like chatbots, sentiment analysis, and language translation.