SlideShare a Scribd company logo
1 of 15
Data Acquisition and processing
Learning Objectives
• Define data acquisition and signal conditioning;
• Illustrate the impact of IoT on multiplexing and sampling theory;
• Explain the electrical, temperature and strain measurements;
• Define Machine-to-Machine (M2M) communication (a major component of
the IoT portfolio of technologies);
• Discuss the security issue and challenges of collaborative data acquisition in
IoT.
Introduction
In large-scale IoT applications, thousands of sensors are possible
Examples of large scale IoT applications:
• IoT-based irrigation scheme on a large farm
• An IoT-based monitoring system of a smart power grid
• An IoT-based data collection solution in a large city
• An IoT-based machine-state monitoring system in a large industry
• A fire-monitoring IoT solution covering a large forest or any other place
Introduction
• The data from these sensors may be used to make a single decision
• However, sensor data is often noisy
• A temperature sensor can return 250C and then 260C in the next second, even if
temperature has not changed
• Noise can be caused by the sensor quality or the environment
• Due to noise, sensor data should be filtered to reduce noise effects. This is even
more critical with actuation
• It is also necessary to ensure that the sensors are working within their
specifications and are not damaged by the environmental conditions.
• How do you combine these noisy values to make a single decision?
Data Acquisition and Signal Conditioning
• Data acquisition refers to the process of capturing, measuring and digitizing signals
from various sources, such as sensors, and converting them into a format that can
be processed and analyzed by a computer.
• Data acquisition systems typically include hardware and software components,
such as analog-to-digital converters, signal conditioning circuits, and data
acquisition software.
• Signal conditioning refers to the process of preparing a signal for further
processing or analysis.
• Signal conditioning is an important step in data acquisition, as it can improve the
accuracy and reliability of the data and make it more suitable for further processing
and analysis.
Data Acquisition and Signal Conditioning
Wither App
Sales
App
Coop
App
Heat Controllers
SMS Tea Reports
Withering Tables
and Sensors
Edge
Application
Does the Tea Withering App really want the wither raw
data? Not always, because:
• Data is noisy (pre-processing is necessary)
• Wither app may only need to decide about the wither data
(e.g., is it too hot or not?)
• What kind of data? Is it continuous or discrete-time?
Signal processing is necessary to prepare data into a format
that is useful, addresses the noise, and to filter the
measurements to reduce uncertainties
• Where is processing done?
• If bandwidth is a problem, process closer to the
edge. Otherwise, processing in the cloud is an
option.
Signal Conditioning
• This typically involves amplifying, filtering, or otherwise modifying the signal
to improve its quality or make it more suitable for the intended application.
• Signal conditioning can include various techniques such as:
•Amplification: Increasing the amplitude of a signal to make it stronger or
more easily measurable.
•Filtering: Removing unwanted noise, or unwanted frequency components,
from a signal to improve its quality.
•Offset and Gain adjustment: Adjusting the level of the signal, so it is within
the range of the measuring device or the data acquisition system.
•Linearization: adjusting the non-linearity of the sensor to make the output
linear with respect to the input.
•Isolation: Protecting the measuring device from the electrical noise and
interference of the environment.
Sensor Data Filtering
• Sensor data is subject to uncertainty and noise
• Sensors take periodic readings
• Readings are not always consistent but have uncertainty or contain errors
• Making decisions based on such readings can lead to overall wrong decisions
• Some methods are used to determine the actual value of the stimulus:
• These methods rely on estimation using incoming data to enhance their
accuracy
• They have many applications in computer science e.g.
• In robotics, they help the robot to correct its position in a coordinate system
Kalman Filtering
• Kalman filtering is a mathematical technique used to estimate the state of a
system from noisy and incomplete measurements.
• An iterative mathematical process that uses a set of equations and
consecutive data inputs to estimate the true value (position, velocity, etc).
• The basic idea behind Kalman filtering is to use a prediction-correction
algorithm to estimate the state of the system at each time step, taking into
account the previous state, the current measurement, and the system
dynamics.
• It can be used for prediction, smoothing, and filtering.
• It is widely used in control systems and navigation systems.
• Used in navigation, esp. aircraft
• Robotic motion planning, etc.
Kalman Filtering
• Data being tracked can be multi-
dimensional
• For example, while tracking a plane or
other object, you may track velocity,
acceleration, and position in x, y, and z
directions.
• The Kalman filter helps to narrow down all
these parameters to their actual values
• Obviously, the process is more complex in
multi-dimensional tracking
• This case uses two or more different
parameters to reach a decision
0 10 20 30 40 50 60 70 80 90 100
68
69
70
71
72
73
74
75
Measurement Time
Measurement
Value
Filtered Value
Measured Value
Based on normally distributed values
Kalman filtering applied in:
• Radar tracking of planes, Satellite tracking,
Missile tracking, Drone tracking, Robot
movement, etc.
Kalman Filter
We require as inputs:
• Measured values (current value
and previous value)
• Estimate values (current estimate
and previous estimate)
• We use these to:
• Enhance accuracy of the
estimate, whether measured
values are accurate or not
We could use the average of
measured values but that would
require to have many values
available initially
• May not be as accurate
Error in
Estimate
Calculate the
Kalman Gain (KG)
Calculate Current
Estimate 𝐸𝑆𝑇𝑡
Calculate New Error
in Estimate 𝐸𝑒𝑠𝑡𝑡
Error in
Measurement
Previous
Estimate
Measured
Value
Data Input
Original
Estimate
Original Error
in Estimate
Update
Estimate
Multiplexing and Sampling
Sampling
• IoT devices often have sensors that generate
continuous streams of data, such as
temperature or humidity readings.
• This data must be sampled at regular intervals to
be transmitted over a network and analyzed.
• The high volume of data generated by IoT
devices can put a strain on sampling systems, as
they must be able to handle large amounts of
data in real-time.
• IoT devices generate a large amount of data, which can have an impact on multiplexing and
sampling theory.
• Multiplexing is the process of combining multiple signals into one,
• Sampling is the process of measuring a signal at discrete points in time.
Multiplexing
• In IoT, multiplexing can be used to
combine data from multiple devices
into a single stream for transmission
over a network.
• This can increase the efficiency of
data transmission, as multiple devices
can share a single communication
channel.
Common types of measurement
• Electrical measurements: Typically involve measuring various electrical parameters such
as voltage, current, and power. These measurements can be used to monitor the
performance of electrical systems, detect problems, and optimize energy usage.
• Temperature measurements are used to monitor and control the temperature of various
systems and environments. This can include monitoring the temperature of buildings,
equipment, and industrial processes, as well as monitoring the temperature of food,
pharmaceuticals, and other perishable goods.
• Strain measurements involve measuring the deformation or change in shape of a material
caused by an applied load. This can be used to monitor the health of structures, such as
bridges and buildings, as well as to monitor the performance of mechanical systems, such
as engines and turbines.
• Others:
• Humidity
• Pressure
• Light
• Acceleration etc
Machine to Machine (M2M) communication
• Machine-to-machine (M2M) communication refers to
the automatic, wireless or wired communication
between devices or machines.
• These devices can include sensors, actuators, or other
types of equipment that are connected to a network
and can communicate with each other.
• No human intervention when operating
• This allows for a variety of applications in which
machines can leverage an increasingly prevalent IoT
interconnectivity to work together in a more cohesive
and effective manner.
• M2M communication allows devices to communicate
with each other and with centralized systems,
enabling them to share data and control functionality
M2M communication
M2M communication: Example

More Related Content

Similar to Topic 4 Data Processing.pptx

Introduction of Mechatronics
Introduction of MechatronicsIntroduction of Mechatronics
Introduction of MechatronicsDr.P.Parandaman
 
TRANSFORMER DIAGNOSTICS BY AN EXPERT SYSTEM
TRANSFORMER DIAGNOSTICS BY AN EXPERT SYSTEMTRANSFORMER DIAGNOSTICS BY AN EXPERT SYSTEM
TRANSFORMER DIAGNOSTICS BY AN EXPERT SYSTEMGururaj B Rawoor
 
Tutorials - History Evolution and Future of SCADA.pdf
Tutorials - History Evolution and Future of SCADA.pdfTutorials - History Evolution and Future of SCADA.pdf
Tutorials - History Evolution and Future of SCADA.pdfWesamAwad3
 
Numerical Relaying.pptx
Numerical Relaying.pptxNumerical Relaying.pptx
Numerical Relaying.pptxrohith650557
 
Site Verification - Protocols & Tools for Complex Metering Installations
Site Verification - Protocols & Tools for Complex Metering InstallationsSite Verification - Protocols & Tools for Complex Metering Installations
Site Verification - Protocols & Tools for Complex Metering InstallationsTESCO - The Eastern Specialty Company
 
instrumentation electrical engineering Lecture 1.2.pptx
instrumentation electrical engineering Lecture 1.2.pptxinstrumentation electrical engineering Lecture 1.2.pptx
instrumentation electrical engineering Lecture 1.2.pptxmuhammad562811
 
Distribution System Automation
 Distribution System Automation  Distribution System Automation
Distribution System Automation Adithya Ballaji
 
Automated Substation Monitoring with Thermal Imaging
Automated Substation Monitoring with Thermal Imaging Automated Substation Monitoring with Thermal Imaging
Automated Substation Monitoring with Thermal Imaging Power System Operation
 
basic of measurement and instrumentation.
basic of measurement and instrumentation.basic of measurement and instrumentation.
basic of measurement and instrumentation.SACHINNikam39
 
Measurements lecture 1
Measurements lecture 1Measurements lecture 1
Measurements lecture 1Rosanna Thomas
 
Wireless Water Monitoring System
Wireless Water Monitoring SystemWireless Water Monitoring System
Wireless Water Monitoring SystemPraveen Sharma
 
EMI unit -1 introduction to measurements
EMI unit -1 introduction to measurementsEMI unit -1 introduction to measurements
EMI unit -1 introduction to measurementsGopalakrishnaU
 
Characterics of measuring system.pptx
Characterics of measuring system.pptxCharacterics of measuring system.pptx
Characterics of measuring system.pptxmoviefreak5
 
Lecture+9+-+SCADA+Systems.pptx
Lecture+9+-+SCADA+Systems.pptxLecture+9+-+SCADA+Systems.pptx
Lecture+9+-+SCADA+Systems.pptxsurangagw
 
Sensors2015-Wireless Sensors Future of M2M
Sensors2015-Wireless Sensors Future of M2MSensors2015-Wireless Sensors Future of M2M
Sensors2015-Wireless Sensors Future of M2MRod Montrose
 

Similar to Topic 4 Data Processing.pptx (20)

Introduction of Mechatronics
Introduction of MechatronicsIntroduction of Mechatronics
Introduction of Mechatronics
 
TRANSFORMER DIAGNOSTICS BY AN EXPERT SYSTEM
TRANSFORMER DIAGNOSTICS BY AN EXPERT SYSTEMTRANSFORMER DIAGNOSTICS BY AN EXPERT SYSTEM
TRANSFORMER DIAGNOSTICS BY AN EXPERT SYSTEM
 
Tutorials - History Evolution and Future of SCADA.pdf
Tutorials - History Evolution and Future of SCADA.pdfTutorials - History Evolution and Future of SCADA.pdf
Tutorials - History Evolution and Future of SCADA.pdf
 
PPT_16-9_Template
PPT_16-9_TemplatePPT_16-9_Template
PPT_16-9_Template
 
Numerical Relaying.pptx
Numerical Relaying.pptxNumerical Relaying.pptx
Numerical Relaying.pptx
 
Site Verification - Protocols & Tools for Complex Metering Installations
Site Verification - Protocols & Tools for Complex Metering InstallationsSite Verification - Protocols & Tools for Complex Metering Installations
Site Verification - Protocols & Tools for Complex Metering Installations
 
instrumentation electrical engineering Lecture 1.2.pptx
instrumentation electrical engineering Lecture 1.2.pptxinstrumentation electrical engineering Lecture 1.2.pptx
instrumentation electrical engineering Lecture 1.2.pptx
 
Distribution System Automation
 Distribution System Automation  Distribution System Automation
Distribution System Automation
 
Automated Substation Monitoring with Thermal Imaging
Automated Substation Monitoring with Thermal Imaging Automated Substation Monitoring with Thermal Imaging
Automated Substation Monitoring with Thermal Imaging
 
Matlab
MatlabMatlab
Matlab
 
Av 738 - Adaptive Filtering Lecture 1 - Introduction
Av 738 - Adaptive Filtering Lecture 1 - IntroductionAv 738 - Adaptive Filtering Lecture 1 - Introduction
Av 738 - Adaptive Filtering Lecture 1 - Introduction
 
ESD_Class 3.pptx
ESD_Class 3.pptxESD_Class 3.pptx
ESD_Class 3.pptx
 
ME 313 Mechanical Measurements and Instrumentation Lecture 01
ME 313 Mechanical Measurements and Instrumentation Lecture 01ME 313 Mechanical Measurements and Instrumentation Lecture 01
ME 313 Mechanical Measurements and Instrumentation Lecture 01
 
basic of measurement and instrumentation.
basic of measurement and instrumentation.basic of measurement and instrumentation.
basic of measurement and instrumentation.
 
Measurements lecture 1
Measurements lecture 1Measurements lecture 1
Measurements lecture 1
 
Wireless Water Monitoring System
Wireless Water Monitoring SystemWireless Water Monitoring System
Wireless Water Monitoring System
 
EMI unit -1 introduction to measurements
EMI unit -1 introduction to measurementsEMI unit -1 introduction to measurements
EMI unit -1 introduction to measurements
 
Characterics of measuring system.pptx
Characterics of measuring system.pptxCharacterics of measuring system.pptx
Characterics of measuring system.pptx
 
Lecture+9+-+SCADA+Systems.pptx
Lecture+9+-+SCADA+Systems.pptxLecture+9+-+SCADA+Systems.pptx
Lecture+9+-+SCADA+Systems.pptx
 
Sensors2015-Wireless Sensors Future of M2M
Sensors2015-Wireless Sensors Future of M2MSensors2015-Wireless Sensors Future of M2M
Sensors2015-Wireless Sensors Future of M2M
 

More from DukeCalvin

Computer Science Ethics: Deontological ethics.pptx
Computer Science Ethics: Deontological ethics.pptxComputer Science Ethics: Deontological ethics.pptx
Computer Science Ethics: Deontological ethics.pptxDukeCalvin
 
COMPUTER SCIENCE: PACIFISM IN ETHICS AND PEACE STUDIES
COMPUTER SCIENCE: PACIFISM IN ETHICS AND PEACE STUDIESCOMPUTER SCIENCE: PACIFISM IN ETHICS AND PEACE STUDIES
COMPUTER SCIENCE: PACIFISM IN ETHICS AND PEACE STUDIESDukeCalvin
 
Introduction to IoT.pptx
Introduction to IoT.pptxIntroduction to IoT.pptx
Introduction to IoT.pptxDukeCalvin
 
Data types in Python.pptx
Data types in Python.pptxData types in Python.pptx
Data types in Python.pptxDukeCalvin
 
Data structures and algorithms Module-1.pdf
Data structures and algorithms Module-1.pdfData structures and algorithms Module-1.pdf
Data structures and algorithms Module-1.pdfDukeCalvin
 
Python-L1.pptx
Python-L1.pptxPython-L1.pptx
Python-L1.pptxDukeCalvin
 
Entreprenuership skill development.pptx
Entreprenuership skill development.pptxEntreprenuership skill development.pptx
Entreprenuership skill development.pptxDukeCalvin
 

More from DukeCalvin (7)

Computer Science Ethics: Deontological ethics.pptx
Computer Science Ethics: Deontological ethics.pptxComputer Science Ethics: Deontological ethics.pptx
Computer Science Ethics: Deontological ethics.pptx
 
COMPUTER SCIENCE: PACIFISM IN ETHICS AND PEACE STUDIES
COMPUTER SCIENCE: PACIFISM IN ETHICS AND PEACE STUDIESCOMPUTER SCIENCE: PACIFISM IN ETHICS AND PEACE STUDIES
COMPUTER SCIENCE: PACIFISM IN ETHICS AND PEACE STUDIES
 
Introduction to IoT.pptx
Introduction to IoT.pptxIntroduction to IoT.pptx
Introduction to IoT.pptx
 
Data types in Python.pptx
Data types in Python.pptxData types in Python.pptx
Data types in Python.pptx
 
Data structures and algorithms Module-1.pdf
Data structures and algorithms Module-1.pdfData structures and algorithms Module-1.pdf
Data structures and algorithms Module-1.pdf
 
Python-L1.pptx
Python-L1.pptxPython-L1.pptx
Python-L1.pptx
 
Entreprenuership skill development.pptx
Entreprenuership skill development.pptxEntreprenuership skill development.pptx
Entreprenuership skill development.pptx
 

Recently uploaded

Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piececharlottematthew16
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Mark Simos
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 

Recently uploaded (20)

Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
Story boards and shot lists for my a level piece
Story boards and shot lists for my a level pieceStory boards and shot lists for my a level piece
Story boards and shot lists for my a level piece
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
Tampa BSides - Chef's Tour of Microsoft Security Adoption Framework (SAF)
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 

Topic 4 Data Processing.pptx

  • 1. Data Acquisition and processing Learning Objectives • Define data acquisition and signal conditioning; • Illustrate the impact of IoT on multiplexing and sampling theory; • Explain the electrical, temperature and strain measurements; • Define Machine-to-Machine (M2M) communication (a major component of the IoT portfolio of technologies); • Discuss the security issue and challenges of collaborative data acquisition in IoT.
  • 2. Introduction In large-scale IoT applications, thousands of sensors are possible Examples of large scale IoT applications: • IoT-based irrigation scheme on a large farm • An IoT-based monitoring system of a smart power grid • An IoT-based data collection solution in a large city • An IoT-based machine-state monitoring system in a large industry • A fire-monitoring IoT solution covering a large forest or any other place
  • 3. Introduction • The data from these sensors may be used to make a single decision • However, sensor data is often noisy • A temperature sensor can return 250C and then 260C in the next second, even if temperature has not changed • Noise can be caused by the sensor quality or the environment • Due to noise, sensor data should be filtered to reduce noise effects. This is even more critical with actuation • It is also necessary to ensure that the sensors are working within their specifications and are not damaged by the environmental conditions. • How do you combine these noisy values to make a single decision?
  • 4. Data Acquisition and Signal Conditioning • Data acquisition refers to the process of capturing, measuring and digitizing signals from various sources, such as sensors, and converting them into a format that can be processed and analyzed by a computer. • Data acquisition systems typically include hardware and software components, such as analog-to-digital converters, signal conditioning circuits, and data acquisition software. • Signal conditioning refers to the process of preparing a signal for further processing or analysis. • Signal conditioning is an important step in data acquisition, as it can improve the accuracy and reliability of the data and make it more suitable for further processing and analysis.
  • 5. Data Acquisition and Signal Conditioning Wither App Sales App Coop App Heat Controllers SMS Tea Reports Withering Tables and Sensors Edge Application Does the Tea Withering App really want the wither raw data? Not always, because: • Data is noisy (pre-processing is necessary) • Wither app may only need to decide about the wither data (e.g., is it too hot or not?) • What kind of data? Is it continuous or discrete-time? Signal processing is necessary to prepare data into a format that is useful, addresses the noise, and to filter the measurements to reduce uncertainties • Where is processing done? • If bandwidth is a problem, process closer to the edge. Otherwise, processing in the cloud is an option.
  • 6. Signal Conditioning • This typically involves amplifying, filtering, or otherwise modifying the signal to improve its quality or make it more suitable for the intended application. • Signal conditioning can include various techniques such as: •Amplification: Increasing the amplitude of a signal to make it stronger or more easily measurable. •Filtering: Removing unwanted noise, or unwanted frequency components, from a signal to improve its quality. •Offset and Gain adjustment: Adjusting the level of the signal, so it is within the range of the measuring device or the data acquisition system. •Linearization: adjusting the non-linearity of the sensor to make the output linear with respect to the input. •Isolation: Protecting the measuring device from the electrical noise and interference of the environment.
  • 7. Sensor Data Filtering • Sensor data is subject to uncertainty and noise • Sensors take periodic readings • Readings are not always consistent but have uncertainty or contain errors • Making decisions based on such readings can lead to overall wrong decisions • Some methods are used to determine the actual value of the stimulus: • These methods rely on estimation using incoming data to enhance their accuracy • They have many applications in computer science e.g. • In robotics, they help the robot to correct its position in a coordinate system
  • 8. Kalman Filtering • Kalman filtering is a mathematical technique used to estimate the state of a system from noisy and incomplete measurements. • An iterative mathematical process that uses a set of equations and consecutive data inputs to estimate the true value (position, velocity, etc). • The basic idea behind Kalman filtering is to use a prediction-correction algorithm to estimate the state of the system at each time step, taking into account the previous state, the current measurement, and the system dynamics. • It can be used for prediction, smoothing, and filtering. • It is widely used in control systems and navigation systems. • Used in navigation, esp. aircraft • Robotic motion planning, etc.
  • 9. Kalman Filtering • Data being tracked can be multi- dimensional • For example, while tracking a plane or other object, you may track velocity, acceleration, and position in x, y, and z directions. • The Kalman filter helps to narrow down all these parameters to their actual values • Obviously, the process is more complex in multi-dimensional tracking • This case uses two or more different parameters to reach a decision 0 10 20 30 40 50 60 70 80 90 100 68 69 70 71 72 73 74 75 Measurement Time Measurement Value Filtered Value Measured Value Based on normally distributed values Kalman filtering applied in: • Radar tracking of planes, Satellite tracking, Missile tracking, Drone tracking, Robot movement, etc.
  • 10. Kalman Filter We require as inputs: • Measured values (current value and previous value) • Estimate values (current estimate and previous estimate) • We use these to: • Enhance accuracy of the estimate, whether measured values are accurate or not We could use the average of measured values but that would require to have many values available initially • May not be as accurate Error in Estimate Calculate the Kalman Gain (KG) Calculate Current Estimate 𝐸𝑆𝑇𝑡 Calculate New Error in Estimate 𝐸𝑒𝑠𝑡𝑡 Error in Measurement Previous Estimate Measured Value Data Input Original Estimate Original Error in Estimate Update Estimate
  • 11. Multiplexing and Sampling Sampling • IoT devices often have sensors that generate continuous streams of data, such as temperature or humidity readings. • This data must be sampled at regular intervals to be transmitted over a network and analyzed. • The high volume of data generated by IoT devices can put a strain on sampling systems, as they must be able to handle large amounts of data in real-time. • IoT devices generate a large amount of data, which can have an impact on multiplexing and sampling theory. • Multiplexing is the process of combining multiple signals into one, • Sampling is the process of measuring a signal at discrete points in time. Multiplexing • In IoT, multiplexing can be used to combine data from multiple devices into a single stream for transmission over a network. • This can increase the efficiency of data transmission, as multiple devices can share a single communication channel.
  • 12. Common types of measurement • Electrical measurements: Typically involve measuring various electrical parameters such as voltage, current, and power. These measurements can be used to monitor the performance of electrical systems, detect problems, and optimize energy usage. • Temperature measurements are used to monitor and control the temperature of various systems and environments. This can include monitoring the temperature of buildings, equipment, and industrial processes, as well as monitoring the temperature of food, pharmaceuticals, and other perishable goods. • Strain measurements involve measuring the deformation or change in shape of a material caused by an applied load. This can be used to monitor the health of structures, such as bridges and buildings, as well as to monitor the performance of mechanical systems, such as engines and turbines. • Others: • Humidity • Pressure • Light • Acceleration etc
  • 13. Machine to Machine (M2M) communication • Machine-to-machine (M2M) communication refers to the automatic, wireless or wired communication between devices or machines. • These devices can include sensors, actuators, or other types of equipment that are connected to a network and can communicate with each other. • No human intervention when operating • This allows for a variety of applications in which machines can leverage an increasingly prevalent IoT interconnectivity to work together in a more cohesive and effective manner. • M2M communication allows devices to communicate with each other and with centralized systems, enabling them to share data and control functionality

Editor's Notes

  1. Tea withering Example
  2. Use equation to calculate new estimate based on data input. Kalman filter does not wait for all values to come in. Keeps iterating and narrowing down as values come in Incoming data has uncertainty Initial estimate is required. As more data is collected, the Kalman filter quickly narrows down to the true estimate. In radar tracking, the values are more than one (velocity, position in XYZ direction etc)
  3. In addition, as IoT devices continue to grow in number, the data generated by these devices will continue to increase, which will require more advanced multiplexing and sampling techniques to handle the increased data throughput. In summary, IoT has a direct impact on multiplexing and sampling theory by creating a need for more efficient data transmission and real-time data handling, which in turn drives the development of advanced multiplexing and sampling methods.
  4. M2M communication typically uses a variety of communication protocols, such as cellular networks, Wi-Fi, Zigbee, Bluetooth, and others, depending on the specific requirements of the application. The devices can communicate with each other using a variety of data formats, such as text, binary, or JSON, and can use a variety of transport protocols, such as TCP/IP, HTTP, or MQTT. M2M communication can be used for a wide range of applications, such as industrial automation, building automation, transportation, healthcare, and more. For example, in industrial automation, machines can use M2M communication to share information about their status, performance, and maintenance needs. In building automation, M2M communication can be used to control lighting, heating, and ventilation systems, and to monitor the use of energy. M2M communication can also be used to connect devices to the Internet of Things (IoT), which allows them to share data with a centralized platform or cloud service. This allows for the data to be analyzed and used to improve the performance of the devices, systems and the overall organization.
  5. For example, M2M communication is enabling industrial automation on a larger scale as previously separate systems can communicate with one another. In addition, it can help to improve industrial safety by employing failsafes and enforcing operating procedures.
  6. One can buy soft drinks, flowers, etc from vending machine in self service manner Once the vending machine detects the item in out-of-stock, it sends message to order management server through 3G/4G communication link which further send information to vendor The vendor re-stocks the vending machine Vending machine stores daily sales data in internal database and sends information to vendor Vendor will know which product has been sold and the total daily revenue