ASM1
ASM1
ASM1
Student declaration
I certify that the assignment submission is entirely my own work and I fully understand the consequences of plagiarism. I understand
that making a false declaration is a form of malpractice.
Grading grid
P1 P2 P3 P4 P5 M1 M2 M3 D1 D2
Summative Feedback: Resubmission Feedback:
Page | 2
Table of Contents
I. Introduction .......................................................................................................................................................... 6
1. Project Title ....................................................................................................................................................... 6
2. Abstracts ........................................................................................................................................................... 6
3. Situation ............................................................................................................................................................ 7
4. AI & IOT Functional View .................................................................................................................................. 8
5. Artificial intelligence in internet of things technology ..................................................................................... 9
II. Literature Review ................................................................................................................................................ 10
1. Research Methods .......................................................................................................................................... 10
1.1. Primary Research .................................................................................................................................... 10
1.2. Secondary Research ................................................................................................................................ 13
1.3. Compare Primary Research With Secondary Research .......................................................................... 15
1.4. Qualitative............................................................................................................................................... 16
1.5. Quantitative ............................................................................................................................................ 18
1.6. Compare Qualitative With Quantitative ................................................................................................. 20
1.7. Scientific Method .................................................................................................................................... 21
1.8. Research Process .................................................................................................................................... 23
1.9. Population In Research ........................................................................................................................... 26
2. Research Method Can Be Used To Carried Out .............................................................................................. 27
3. Secondary Research ........................................................................................................................................ 28
3.1. Definition of Internet of Things .............................................................................................................. 28
3.2. AI in IoT with Autonomous Vehicles ....................................................................................................... 29
3.3. The challenges for the definitive implementation of autonomous vehicles .......................................... 30
3.4. AIs and IoT in FPT Corporation's automated vehicles ............................................................................ 31
3.5. How do autonomous cars work? ............................................................................................................ 32
3.6. Challenges and future with autonomous cars ........................................................................................ 33
3.7. Conclusion & Hypothesis ........................................................................................................................ 34
III. Primary Research ............................................................................................................................................ 35
1. Conduct primary research and result evaluation ........................................................................................... 35
1.1. Result evaluation .................................................................................................................................... 38
2. Conclusion ....................................................................................................................................................... 42
IV. Discuss merits, limitations, and pitfalls of approach data collection and analysis ......................................... 43
Page | 3
V. Appendix ............................................................................................................................................................. 44
1. Proposal form ................................................................................................................................................. 44
2. Ethical form ..................................................................................................................................................... 48
VI. Conclusion ....................................................................................................................................................... 52
VII. References ...................................................................................................................................................... 53
Page | 4
Table of Figures
Page | 5
I. Introduction
In the context of technology 4.0 is gradually developing and transforming into industry 5.0. The technological
transformation towards automation and development focuses on enhanced human-machine interaction. This will
be one of the things that help businesses grow quickly and reduce a lot of work processes and operating costs.
For this part of my research, I chose the topic of understanding the development of Machine Learning in Internet of
Things, or what can be called "AI-ML in IoT".
The recent proliferation of IoT devices and their convergence with cloud-based technologies are making it easier to
generate data on building performance – creating a key opportunity for property owners. Building owners apply AI
and ML to make critical financial and operational decisions.
Buildings today have evolved into complex connected technology systems that can be operated to maximize
efficiencies such as cost savings or improved worker productivity and occupant comfort. Companies like Siemens,
PointGrab, Crestron, Aquicore, and others are implementing AI and ML to achieve operational efficiencies that save
building owners energy costs or increase productivity in the workplace.
1. Project Title
The Future of Autonomous Vehicles in Artificial Intelligence And The Internet Of Things
2. Abstracts
The convergence of IoT and industrial AI is a worldwide development trend in the 4.0 era. According to surveys and
research, people who foresaw are predicted to be 5 times more likely to succeed than those who did not. To predict
the future of work, Artificial Intelligence and Machine Learning play an important role in analyzing data and changes.
Statistics regarding the implementation of industrial IoT solutions indicate that early adopters will be able to
generate 5 times more revenue than late adopters.
Ideally, companies should focus on narrowing down the business value drivers they are looking to contribute. This
way, they can position their digital strategy with business goals in mind to make efficient use of IoT platforms.
Page | 6
3. Situation
In the current context, society is being developed day by day, and people's lives are also in need of improvement
thanks to technology applied in people's daily lives.
According to the context of contemporary technical development described in the preceding section. The use of IoT
is transforming the commercial landscape of today (Internet of Things). IoT is assisting in acquiring a significant
amount of data from numerous sources. But gathering, processing, and analyzing the data is difficult due to the
volume of data flowing from so many IoT devices.
It will take an investment in new technology to fully realize the promise of IoT devices in the future. The intersection
of AI (Artificial Intelligence) and IoT has the potential to completely reshape how businesses, economies, and sectors
operate. IoT powered by AI develops intelligent machines that replicate intelligent behavior and aid in decision-
making with little to no human intervention.
Both regular people and specialists gain from the combination of these two streams. AI enables devices to learn
from their data and experience, whereas IoT deals with devices interacting through the internet. This study
emphasizes the necessity for IoT and AI to collaborate.
Page | 7
4. AI & IOT Functional View
IoT is primarily concerned with machine-implanted sensors that provide data streams via internet access. Create,
communicate, aggregate, analyze, and act are the five fundamental stages that all IoT-related services inevitably
follow. Unquestionably, the preliminary study determines the "Act's" value. As a result, the precise value of IoT is
established at its analysis phase. Here, artificial intelligence technology plays a key role.
IoT gives data, but AI has the ability to unlock replies, providing both creativity and context to guide intelligent
actions. Businesses can make wise decisions because the data from the sensor may be examined with AI. The IoT
with artificial intelligence successfully implements the following adaptable solutions:
Page | 8
5. Artificial intelligence in internet of things technology
With the deployment of IoT, the business world is changing rapidly. IoT is assisting in the significant capture of a
massive amount of data from many sources. Wrapping one's head around the avalanche of data arriving from
innumerable IoT devices, on the other hand, makes data collection, processing, and analysis difficult.
Investment in new technologies will be required to realize the future and full potential of IoT devices. The
combination of AI (Artificial Intelligence) with the Internet of Things (IoT) has the potential to reshape the way
industries, businesses, and economies operate. IoT powered by AI generates intelligent technologies that mimic
intelligent behavior and assist in decision-making with little or no human intervention.
(Techopedia, 2019)
Page | 9
II. Literature Review
1. Research Methods
1.1. Primary Research
Primary research is research you conduct yourself (or hire someone to do for you.) It involves going directly to a
source – usually customers and prospective customers in your target market – to ask questions and gather
information. Examples of primary research are:
When you conduct primary research, you’re typically gathering two basic kinds of information:
Exploratory. This research is general and open-ended, and typically involves lengthy interviews with an individual or
small group. Specific. This research is more precise and is used to solve a problem identified in exploratory research.
It involves more structured, formal interviews.
Primary research usually costs more and often takes longer to conduct than secondary research, but it gives
conclusive results.
(Ford, 2022)
Page | 10
1.1.1. Types of primary research
There are many ways of gathering primary research. The most suitable method will depend on the questions you
want to answer and the problem you’re trying to solve. The most common primary market research methods are
interviews, surveys, focus groups and observations.
Interviews
Interviews take the form of a one-to-one or small group question and answer session, which can be conducted
over the phone or in a face-to-face environment. Interviews are most useful where a large amount of information
needs to be collected from a small sample of subjects. Interviews are often used to obtain information from an
expert about a specialist topic. This type of research is highly personal, so follow-on questions can be asked to ensure
clarity.
Surveys
Surveys are most frequently conducted online using paid or free survey tools and offer a convenient and cost-
effective solution where a response is required from a larger population. Questions are pre-written, offering the
respondent little flexibility if their answer doesn’t fit (making functionality such as skip logic essential) and response
rates can be variable. The length of a survey is a delicate balance: if a survey is too long, participants may get bored
and leave the survey incomplete. However, if the survey is short, not enough data will be collected to form a full
picture.
Focus groups
Focus groups are used to collect data from a small group of people who are often subject matter experts in the
topic of research. Discussion is initiated between the group members to discover their thoughts. This method is
commonly used by businesses to gain insight into niche markets and learn about their customers.
Observations
Observations are carried out impartially, by simply observing an event and taking organized notes. In this
method, there is no direct interaction between the researcher and the subject. This method removes the potential
bias which could be encountered during an interview or survey as the encounters observed are genuine reactions.
Observations can be carried out by camera or by a trained observer. This method is commonly used by toy
manufacturers when testing their products on children.
Page | 11
1.1.2. Advantages of primary research
One of the most important advantages is, data collected is firsthand and is accurate. In other words, there
is no dilution of data. Also, this research method can be customized to suit personal requirements and needs
of organizations or businesses.
Primary research focuses mainly on problem in hand, which means entire attention is directed to find
probable solution to a pinpointed subject matter. Primary research allows researchers to go in depth of a
matter and study all foreseeable options.
Data collected can be controlled. Primary research gives a means to control how data is collected and used.
It’s up to the discretion of businesses or organizations who are collecting data how to best make use of data
to get meaningful research insights.
Primary research is a time-tested method; therefore, one can rely on the results that are obtained from
conducting this type of research.
Page | 12
1.2. Secondary Research
Secondary research is a type of research that has already been compiled, gathered, organized and published by
others. It includes reports and studies by government agencies, trade associations or other businesses in your
industry. For small businesses with limited budgets, most research is typically secondary, because it can be obtained
faster and more affordably than primary research.
A lot of secondary research is available right on the Web, simply by entering key words and phrases for the type of
information you’re looking for. You can also obtain secondary research by reading articles in magazines, trade
journals and industry publications, by visiting a reference library, and by contacting industry associations or trade
organizations.
Identify the topic of research: Before beginning secondary research, identify the topic that needs research.
Once that’s done, list down the research attributes and its purpose.
Identify research sources: Next, narrow down on the information sources that will provide most relevant
data and information applicable to your research.
Collect existing data: Once the data collection sources are narrowed down, check for any previous data that
is available which is closely related to the topic. Data related to research can be obtained from various
sources like newspapers, public libraries, government, and non-government agencies etc.
Combine and compare: Once data is collected, combine, and compare the data for any duplication and
assemble data into a usable format. Make sure to collect data from authentic sources. Incorrect data can
hamper research severely.
Page | 13
Analyze data: Analyze data that is collected and identify if all questions are answered. If not, repeat the
process if there is a need to dwell further into actionable insights.
(Pro, 2022)
Page | 14
1.3. Compare Primary Research With Secondary Research
Point Primary Data Secondary Data
Meaning Primary data is collected directly from the Secondary data is the data that have been
information that you gather for the purpose The data is collected by someone else instead
Main Sources Interview, surveys, questionnaires, field Previous research, mass media products,
Specific to the Always specific to the researcher's needs. Often, it is not specific to the researcher's
Researcher needs.
Needs
Level of the Higher level of control Lack of control over data quality
control over
data quality
Proprietary You are the owner of the data. Thus, the You are not the owner of the data. Your
Information information can remain hidden from the competitors also have access to the data
competitors.
Capability More capable to solve a specific problem Less capable to solve a specific problem
Page | 15
1.4. Qualitative
Qualitative research involves collecting and analyzing non-numerical data (e.g., text, video, or audio) to understand
concepts, opinions, or experiences. It can be used to gather in-depth insights into a problem or generate new ideas
for research.
Qualitative research is the opposite of quantitative research, which involves collecting and analyzing numerical data
for statistical analysis. Qualitative research is commonly used in the humanities and social sciences, in subjects such
as anthropology, sociology, education, health sciences, history, etc.
Each of the research approaches involve using one or more data collection methods. These are some of the most
common qualitative methods:
Observations: recording what you have seen, heard, or encountered in detailed field notes.
Interviews: personally, asking people questions in one-on-one conversations.
Focus groups: asking questions and generating discussion among a group of people.
Surveys: distributing questionnaires with open-ended questions.
Secondary research: collecting existing data in the form of texts, images, audio or video recordings, etc.
Most types of qualitative data analysis share the same five steps:
Prepare and organize your data. This may mean transcribing interviews or typing up fieldnotes.
Review and explore your data. Examine the data for patterns or repeated ideas that emerge.
Develop a data coding system. Based on your initial ideas, establish a set of codes that you can apply to
categorize your data.
Assign codes to the data. For example, in qualitative survey analysis, this may mean going through each
participant’s responses and tagging them with codes in a spreadsheet. As you go through your data, you can
create new codes to add to your system if necessary.
Identify recurring themes. Link codes together into cohesive, overarching themes.
There are several specific approaches to analyzing qualitative data. Although these methods share similar processes,
they emphasize different concepts.
Page | 16
1.4.2. Advantages of qualitative research
Qualitative research often tries to preserve the voice and perspective of participants and can be adjusted as new
research questions arise. Qualitative research is good for:
Flexibility: The data collection and analysis process can be adapted as new ideas or patterns emerge. They
are not rigidly decided beforehand.
Natural settings: Data collection occurs in real-world contexts or in naturalistic ways.
Meaningful insights: Detailed descriptions of people’s experiences, feelings and perceptions can be used in
designing, testing, or improving systems or products.
Generation of new ideas: Open-ended responses mean that researchers can uncover novel problems or
opportunities that they wouldn’t have thought of otherwise.
Unreliability: The real-world setting often makes qualitative research unreliable because of uncontrolled
factors that affect the data.
Subjectivity: Due to the researcher’s primary role in analyzing and interpreting data, qualitative research
cannot be replicated. The researcher decides what is important and what is irrelevant in data analysis, so
interpretations of the same data can vary greatly.
Limited generalizability: Small samples are often used to gather detailed data about specific contexts.
Despite rigorous analysis procedures, it is difficult to draw generalizable conclusions because the data may
be biased and unrepresentative of the wider population.
Labor-intensive: Although software can be used to manage and record large amounts of text, data analysis
often must be checked or performed manually.
Page | 17
1.5. Quantitative
Quantitative research is the process of collecting and analyzing numerical data. It can be used to find patterns and
averages, make predictions, test causal relationships, and generalize results to wider populations.
Quantitative research is the opposite of qualitative research, which involves collecting and analyzing non-numerical
data (e.g., text, video, or audio).
Quantitative research is widely used in the natural and social sciences: biology, chemistry, psychology, economics,
sociology, marketing, etc.
You can use quantitative research methods for descriptive, correlational or experimental research.
In descriptive research, you simply seek an overall summary of your study variables.
In correlational research, you investigate relationships between your study variables.
In experimental research, you systematically examine whether there is a cause-and-effect relationship
between variables.
Correlational and experimental research can both be used to formally test hypotheses, or predictions, using
statistics. The results may be generalized to broader populations based on the sampling method used.
To collect quantitative data, you will often need to use operational definitions that translate abstract concepts (e.g.,
mood) into observable and quantifiable measures (e.g., self-ratings of feelings and energy levels).
Descriptive statistics will give you a summary of your data and include measures of averages and variability. You
can also use graphs, scatter plots and frequency tables to visualize your data and check for any trends or outliers.
Using inferential statistics, you can make predictions or generalizations based on your data. You can test your
hypothesis or use your sample data to estimate the population parameter.
Page | 18
Advantages of quantitative research
Quantitative research is often used to standardize data collection and generalize findings. Strengths of this approach
include:
Replication: Repeating the study is possible because of standardized data collection protocols and tangible
definitions of abstract concepts.
Direct comparisons of results: The study can be reproduced in other cultural settings, times or with different
groups of participants. Results can be compared statistically.
Large samples: Data from large samples can be processed and analyzed using reliable and consistent
procedures through quantitative data analysis.
Hypothesis testing: Using formalized and established hypothesis testing procedures means that you have
to carefully consider and report your research variables, predictions, data collection and testing methods
before coming to a conclusion.
Superficiality: Using precise and restrictive operational definitions may inadequately represent complex
concepts. For example, the concept of mood may be represented with just a number in quantitative
research but explained with elaboration in qualitative research.
Narrow focus: Predetermined variables and measurement procedures can mean that you ignore other
relevant observations.
Structural bias: Despite standardized procedures, structural biases can still affect quantitative research.
Missing data, imprecise measurements or inappropriate sampling methods are biases that can lead to the
wrong conclusions.
Lack of context: Quantitative research often uses unnatural settings like laboratories or fails to consider
historical and cultural contexts that may affect data collection and results.
Page | 19
1.6. Compare Qualitative With Quantitative
The basic differences between qualitative research methods and quantitative research methods are simple and
straightforward. They differ in:
Types of
questions Open-ended questions Closed-ended questions
asked
Form of data
Descriptive data Numerical data
produced
Quantitative data is structured and accountable. This type of data is formatted in a way so it can be organized,
arranged, and searchable. Qualitative data is considered unstructured. This type of data is formatted (and known
for) being subjective, individualized, and personalized. Anything goes. Because of this, qualitative data is inferior if
it’s the only data in the study.
Because quantitative data is more concrete, it’s generally preferred for data analysis. Numbers don’t lie. But for
complete statistical analysis, using both qualitative and quantitative yields the best results.
Page | 20
1.7. Scientific Method
The scientific method is the process of objectively establishing facts through testing and experimentation. The basic
process involves seeing, forming a hypothesis, making a prediction, conducting an experiment, and finally analyzing
the results. The principals of the scientific method can be applied in many areas, including scientific research,
business, and technology.
Page | 21
1.7.1. The scientific method in technology and computers
The scientific method is incredibly valuable in technology and related fields. It is obviously used in research and
development, but it is also useful in day-to-day operations. Because almost everything can be quantified, testing
hypotheses can be easy.
Most modern computer systems are complicated and difficult to troubleshoot. Using the scientific method of
hypothesis and testing can greatly simplify the process of tracking down errors and it can help find areas of
improvement. It can also help when you evaluate new technologies before implementation.
Step 1: See or ask a question: The first step is to observe something that you would like to learn about or ask a
question that you would like answered. These can be specific or general. Some examples would be "I observe that
our total available network bandwidth drops at noon every weekday" or "How can we increase our website
registration numbers?" Taking the time to establish a well-defined question will help you in later steps.
Step 2: Gather background information: This involves doing research into what is already known about the topic.
This can also involve finding if anyone has already asked the same question.
Step 3: Create a hypothesis: A hypothesis is an explanation for the observation or question. If proven later, it can
become a fact. Some examples would be "Our employees watching online videos during lunch is using our internet
bandwidth" or "Our website visitors don't see our registration form."
Step 4: Create a prediction and perform a test: Create a testable prediction based on the hypothesis. The test
should establish a noticeable change that can be measured or observed using empirical analysis. It is also important
to control for other variables during the test. Some examples would be "If we block video-sharing sites, our available
bandwidth will not go down significantly during lunch" or "If we make our registration box bigger, a greater
percentage of visitors will register for our website than before the change."
Step 5: Analyze the results and draw a conclusion: Use the metrics established before the test see if the results
match the prediction. For example, "After blocking video-sharing sites, our bandwidth utilization only went down
by 10% from before; this is not enough of a change to be the primary cause of the network congestion" or "After
increasing the size of the registration box, the percent of sign-ups went from 2% of total page views to 5%, showing
that making the box larger results in more registrations."
Step 6: Share the conclusion or decide what question to ask next: Document the results of your experiment. By
sharing the results with others, you also increase the total body of knowledge available. Your experiment may have
also led to other questions, or if your hypothesis is disproven you may need to create a new one and test that. For
example, "Because user activity is not the cause of excessive bandwidth use, we now suspect that an automated
process is running at noon every day."
Page | 22
1.8. Research Process
The research process consists of a series of systematic procedures that a researcher must go through in order to
generate knowledge that will be considered valuable by the project and focus on the relevant topic.
To conduct effective research, you must understand the research process steps and follow them. Here are a few
steps in the research process to make it easier for you:
A preliminary survey
Case studies
Interviews with a small group of people
Observational survey
Page | 23
Step 2: Evaluate the Literature
A thorough examination of the relevant studies is essential to the research process. It enables the researcher to
identify the precise aspects of the problem. Once a problem has been found, the investigator or researcher needs
to find out more about it.
This stage gives problem-zone background. It teaches the investigator about previous research, how they were
conducted, and its conclusions. The researcher can build consistency between his work and others through a
literature review. Such a review exposes the researcher to a more significant body of knowledge and helps him
follow the research process efficiently.
It is important for researchers to keep in mind while formulating a hypothesis that it must be based on the research
topic. Researchers are able to concentrate their efforts and stay committed to their objectives when they develop
theories to guide their work.
The research design aims to minimize the time, money, and effort required to acquire meaningful evidence. This
plan fits into four categories:
Suppose a researcher wishes to investigate a certain group of people in the community. In that case, the research
could target a specific age group, males or females, a geographic location, or an ethnic group. A final step in a study’s
design is to specify its sample or population so that the results may be generalized.
Page | 24
Step 6: Data Collection
Data collection is important in obtaining the knowledge or information required to answer the research issue. Every
research collected data, either from the literature or the people being studied. Data must be collected from the two
categories of researchers. These sources may provide primary data.
Experiment
Questionnaire
Observation
Interview
Literature survey
Official, unofficial reports
An approach based on library resources
Data analysis involves a number of closely related stages, such as setting up categories, applying these categories to
raw data through coding and tabulation, and then drawing statistical conclusions. The researcher can examine the
acquired data using a variety of statistical methods.
The Layout: On the first page, the title, date, acknowledgments, and preface should be on the report. A
table of contents should be followed by a list of tables, graphs, and charts if any.
Introduction: It should state the research’s purpose and methods. This section should include the study’s
scope and limits.
Summary of Findings: A non-technical summary of findings and recommendations will follow the
introduction. The findings should be summarized if they’re lengthy.
Principal Report: The main body of the report should make sense and be broken up into sections that are
easy to understand.
Conclusion: The researcher should restate his findings at the end of the main text. It’s the final result.
Page | 25
1.9. Population In Research
A population is the entire group that you want to draw conclusions about.
In research, a population doesn’t always refer to people. It can mean a group containing elements of anything you
want to study, such as objects, events, organizations, countries, species, organisms, etc.
For larger and more dispersed populations, it is often difficult or impossible to collect data from every individual.
For example, every 10 years, the federal US government aims to count every person living in the country using the
US Census. This data is used to distribute funding across the nation.
However, historically, marginalized, and low-income groups have been difficult to contact, locate and encourage
participation from. Because of non-responses, the population count is incomplete and biased towards some groups,
which results in disproportionate funding across the country.
In cases like this, sampling can be used to make more precise inferences about the population.
Page | 26
2. Research Method Can Be Used To Carried Out
In this research paper, I will combine both research methods including secondary research, and primary research.
In which to collect data and information in the most effective way, I will combine qualitative and quantitative
research to clarify and get the best quality and closest surveys to the research problem. The methods are all done
by me, and I will explain them in the following section.
Quantitative information is organized and responsible. This kind of data is prepared to provide organization,
arrangement, and searchability.
Unstructured data is what qualitative data is. This kind of information is formatted (and is renowned for being)
personalized, subjective, and personalized. It's open season. Because of this, using only qualitative data in a study
is poor. It is still valuable, though.
In general, quantitative data is preferable for data analysis since it is more tangible. Numbers are reliable. However,
combining qualitative and quantitative methods produces the most accurate findings for complete statistical
analysis.
Page | 27
3. Secondary Research
3.1. Definition of Internet of Things
Artificial intelligence of things (AIoT) is a broad term for applying artificial intelligence to the internet of things (IoT),
a new phenomenon that represents many simple digital connections between hardware devices. The internet of
things is comprised of billions of small, connected devices, including traditional devices and appliances networked
together and communicating over internet protocols. Adding AI to IoT brings its own system of challenges and
potential solutions.
Artificial intelligence of things represents technologies that are built into the IoT to make it smart. AI can add value
in helping IoT achieve machine learning goals or in using key data for signaling or developing insights. Where data
analysis on the internet of things is automated, it constitutes artificial intelligence of things. Companies and other
parties are talking about artificial intelligence of things when they talk about efforts to broaden what users can do
over the internet of things or how technologies can utilize the internet of things to function.
(Chukwudozie, 2022)
Page | 28
3.2. AI in IoT with Autonomous Vehicles
For the record, AI and cars have a mutual history, and it was the dream of scientists to create intelligent machines
that could think and act for themselves which gave birth to autonomous vehicles, or self-driving cars, which have
turned out to become one of the best innovations of AI technology.
Autonomous vehicles have neural networks and specific algorithms. These are Artificial Intelligence (AI) and
Machine Language (ML) based object detection algorithms. These serve to collect data, analyze objects, and make
accurate decisions while on the road. These features also enable these intelligent machines to provide solutions to
problems occurring in advance of real time by predicting events through the swift processing of data.
With autopilots
Quite recently, Tesla manufactured electric cars that are self-driving and equipped with autopilots to enable
automatic steering, accelerating braking, lane changing, and parking actions. Added to these features is the fact that
these cars have the potential to reduce emissions globally, a milestone achievement from fuel-driven vehicles.
Today, autonomous vehicles can be found in some of the biggest cities of the world. Even heavy-duty trucks without
drivers that can deliver goods over long distances have been manufactured. This has not only reduced transportation
costs significantly but also reduced the loss of human lives through accidents, much of which arise from human
errors.
Page | 29
3.3. The challenges for the definitive implementation of autonomous vehicles
In the first place, the Internet of Things (IoT), connected technology and Artificial Intelligence (AI) have driven major
changes in society. The IoT will provide vehicles with real-time data that will help them detect operational problems
and understand environmental conditions. In addition, 5G technology’s arrival presents an opportunity to advance
the field of connected technology and boost the establishment of such vehicles in the market. Even so, there are
many technologies needed to make autonomous vehicles possible, and research must continue advancing in the
fields of cloud technology, cybersecurity, robotics, space navigation, lasers and photography for the now-not-so-
futuristic invention to become a reality.
In the second place, the biggest challenge facing these vehicles is to ensure reasonable decisions are made by the
robotized vehicles. This challenge involves not only technology, but also disparate areas like philosophy, ethics and
legal regulation. Consequently, a new concept has emerged from the fusion of philosophy and technology – that of
robotics.
Robotics is a form of applied ethics that looks at the positive and negative implications of robotics for individuals
and society. It aims to inspire the design of so-called smart or autonomous robots and prevent their misuse against
humankind. If vehicles can circulate completely autonomously, they must also be able to make complicated fraction-
of-a-second decisions, such as deciding between striking a child or injuring the car’s occupants to save the child.
These are real ethical concerns that need to be appropriately addressed by professionals, such as philosophers, and
soon it will not be uncommon for tech companies to start using such professionals to assist engineers in developing
algorithms that define robot behavior.
Additionally, the different cultural mindsets of the users of these future robots must be factored into these ethical
assessments when programming. Moral judgements are strongly influenced by one’s culture – as demonstrated by
“Moral Machine”, an online game developed by the Massachusetts Institute of Technology (MIT).
(Chukwudozie, 2022)
Page | 30
3.4. AIs and IoT in FPT Corporation's automated vehicles
As Mr. Pham Quang Viet - FPT Software engineer said, ZED's camera system is a combination of a camera system to
be able to analyze the depth of pixels.
• As for Lidar, it's a 360-camera device that can scan around 100 - 150m.
• In the car, the kit of NVIDIA is used - this graphics chip will optimize pixels and use Deep Learning
• The car uses the most advanced technologies and techniques such as Path Planning, Behavior cloning, lidar,
and deep learning researched by FPT Software.
The driver will use this vehicle, then the system will collect data and behavior and then automatically train. That
data after training will automatically be loaded back into the car. And when the car moves, it will automatically
collect pixels from the camera and feed it into data, and then the AI will automatically analyze and decide on how
to move reasonably and close to the driver.
Page | 31
3.5. How do autonomous cars work?
Autonomous cars rely on sensors, actuators, complex algorithms, machine learning systems, and powerful
processors to execute software.
Autonomous cars create and maintain a map of their surroundings based on a variety of sensors situated in different
parts of the vehicle. Radar sensors monitor the position of nearby vehicles. Video cameras detect traffic lights, read
road signs, track other vehicles, and look for pedestrians. Lidar (light detection and ranging) sensors bounce pulses
of light off the car’s surroundings to measure distances, detect road edges, and identify lane markings. Ultrasonic
sensors in the wheels detect curbs and other vehicles when parking.
Sophisticated software then processes all this sensory input, plots a path, and sends instructions to the car’s
actuators, which control acceleration, braking, and steering. Hard-coded rules, obstacle avoidance algorithms,
predictive modeling, and object recognition help the software follow traffic rules and navigate obstacles.
(team, 2022)
Page | 32
3.6. Challenges and future with autonomous cars
Fully autonomous (Level 5) cars are undergoing testing in several pockets of the world, but none are yet available
to the general public. We’re still years away from that. The challenges range from the technological and legislative
to the environmental and philosophical. Here are just some of the unknowns.
Page | 33
3.7. Conclusion & Hypothesis
As secondary research and research papers have been outlined above. Artificial intelligence in the internet of things
technology is gradually being developed based on many different fields. The steps of AI in life are gradually being
synchronized and developed more. In this 4.0 revolution, technology will have to be developed and optimized for
the system to create a convenient, fast and accurate user experience.
Therefore, there are no connectivity issues and no security holes once the technologies required to connect
autonomous vehicles with one another and with the outside world are fully developed and implemented. network,
we'll be able to start creating these automobiles and examine the moral dilemmas associated with giving machines
the ability to make judgments. However, we frequently encounter various set ups and legal frameworks depending
on the nation we are in and do not yet have a uniform worldwide ethic to demand.
According to my personal research in Vietnam, technology corporations like FPT or Viettel have been actively
analyzing 5G technology for a long time. We believe that 5G networks offer tremendous opportunities and can open
new markets for telecommunications, for example in areas such as connected vehicles. Therefore, corporations FPT
and Viettel rank this technology as a “5G challenge”.
Hypothesis
A self-driving automobile is a private or public vehicle that employs sensors, cameras, radar, and artificial
intelligence (AI) to observe, evaluate, and interpret its surroundings by segmenting it into objects (obstacles,
pedestrians), navigability, and other variables (road, pavement, etc.). This route enables it to create various
navigation methods, travel between locations, or carry out particular maneuvers without a human operator.
A functional classification of vehicle automation into five stages, each of which corresponds to a higher level of
automation, has been agreed upon by the automotive industry and the Society of Automotive Engineers in order to
meet this goal.
• Level 1 driver assistance allows the car to control either the steering or the braking, but not at once.
• Level 2 partial automation allows for simultaneous steering and brake assistance, but you must always keep
your eyes on the road. Examples include General Motors' Super Cruise and Tesla's Autopilot.
• Conditional automation, or Level 3, enables the automobile to handle most driving-related tasks while
allowing the driver to momentarily take their eyes off the road.
• Advanced automation, or Level 4, allows the automobile to take complete control under specific
circumstances, freeing the driver to concentrate on other duties.
• Level 5 represents complete automation. In this fictitious scenario, the vehicle can operate without a driver
or even a steering wheel.
However, in Vietnam at the moment, there is no technology unit that can autonomously develop automatic
vehicles above level 3. Anyway, for terrain, the locality is complicated in terms of nature. We can also see that
reaching level 3 is a step in the development and progress of Vietnam's technology industry.
Page | 34
III. Primary Research
1. Conduct primary research and result evaluation
In my research paper, to do primary research, I chose to create a survey in google form so that I can have accurate
information and data. With the online survey, I believe that people can fill out and respond remotely and answer
about their experience. My online survey will open in 07 days. Then I will lock the form so that I can have the most
accurate and most accurate survey results. Link Survey here: https://forms.gle/KYF8oQNK6bTLwjfT7
Figure 9 Question 1
Page | 35
Figure 10 Question 2
Figure 11 Question 3
Figure 12 Question 4
Page | 36
Figure 13 Question 5
Figure 14 Question 6
Figure 15 Question 7
Page | 37
After the above survey, I continued to conduct an interview program for those who have experienced and used
technology for longtime drivers and newbies.
In the list of survey participants, we will choose to publicize the information and survey results of some
participants after asking their opinions:
1.1.1. Survey
Figure 16 Question 8
Based on the survey assessment, I found that 71.4% of survey respondents rated the level of safety as strict enough
and besides, and 28.6% of them think that we need to improve more on safety regulations.
Page | 38
Figure 17 Question 9
According to the survey, 33.3% is a number that is evenly divided among choices such as many, many, and not many.
Most people have also heard of and mentioned automated vehicles.
Figure 18 Question 10
According to the survey, we found that the extremely safe rating only accounted for 9.5% of the reviewers. And
most people choose moderate and moderate safety.
Page | 39
Figure 19 Question 10
The usefulness of automated vehicles was rated on a 4/5 scale, accounting for 61.9% of the total participants. This
is a huge number in the survey. Most people find automated vehicles very useful.
Figure 20 Question 11
Page | 40
The selection factors are all evaluated based on vehicle speed and safety. Most people rate the speed of
participation at 81% and safety at 71.4%.
Figure 21 Question 12
Most people expect that automated vehicles will be applied and become common in life.
Page | 41
1.1.2. Interview
In order to be able to communicate correctly with the correct factor and without bias to the respondent, I will keep
the main answer intact to ensure accuracy. I will assist with the English translation.
1. How often do you drive? ‘Yes, I drive every day” – Pham Hoang Minh Most people give the answer,
“Sometimes when I go far away, I will drive, yes and they use transportation
but usually not.” – Pham Duc My | Student every day.
2. What do you think if there is “If so, that's a good thing for the community, Everyone feels that the
a vehicle that automatically which is what all technologies need to development that has it brings
moves and joins traffic? develop and implement these days.” great benefits to society.
Đao Viet Anh | Tech Taxi Driver
3. Do you think it is safe for “Most people think that automatic vehicles For everyone, because this is a
everyone? that enter traffic already sound unsafe, I will new technology product that
feel a bit scared if I sit in that car and move. has not been tested many times,
Actually, I don't really believe it.” they do feel not very confident
Pham Hoang Minh | Taxi Driver in its safety.
4. Does it matter if an “For me, of course, there is a problem, for a Everyone is excited when
automatic car enters traffic? taxi driver like me, using an automatic car everything becomes
makes me lose my job, of course, I wouldn't automated, but taxi drivers feel
want that.” their jobs are being shaken by
Nguyen Van Manh | Student upcoming technologies.
5. Do you wish and think that “I also hope that autonomous vehicles will Most people are looking
this automatic car will improve become more common, and I look forward forward to the results of
the quality of life as well as to using them in the future.” automated vehicles being
more convenience? Nguyen Quoc Huy | Student announced and put into use in
life.
2. Conclusion
After the above primary research, I also gave myself a basic assessment of the research process. Based on the above
interview questions, I felt everyone's expectations in my research project this time. Besides, the survey also had
clear research data for me. This will be one of the important data that help me complete the research in the most
detailed and correct way.
Page | 42
IV. Discuss merits, limitations, and pitfalls of approach data collection and analysis
While collecting information to maximize the value of the data and accuracy of the data, I chose to send the survey
link to the subjects that I selected.
I used primary research, secondary research, quantitative and qualitative analysis, as well as survey approaches, to
gather the data for the research piece mentioned above. utilizing that method. I now understand the advantages,
drawbacks, and dangers of various data collection and analysis techniques:
Quantitative approach: If the answer is affirmative, the data will be expressed numerically or quantified. It can make
statistical manipulation and mathematical calculations much simpler for us.
Qualitative methods: Qualitative data is information that cannot be quantified or measured and cannot be
expressed numerically. Instead, than using numbers or open-ended inquiries, it uses words, pictures, observations,
and symbols. That aids in collecting diverse viewpoints for my research. However, it has a drawback in that the
inquiries cannot be specific.
I used Google Forms to create survey questions and collect user information. It made it simple for me to gather data
rapidly from a sizable population of people via an online survey. Second, compared to other ways, it is inexpensive.
But as I go, I can see some restrictions because the responses might not be truthful. It's possible that some people
just participate in online surveys to claim the incentive. It's possible that many questions won't be resolved and that
some participants won't show there. The data is quite likely to be leaked and is very simple to get while conducting
and analyzing google forms.
Google Forms' analytics feature makes it simple for me to view and compare data in several charts and a table.
Primary research method: When conducting primary research, I have more control over the data that is gathered,
and primary data is frequently updated because it is gathered in real-time rather than using data from earlier
sources. Since the information is gathered through user reviews, its authenticity can be believed. However, it also
has significant drawbacks, such as the lengthy and expensive implementation process.
Regarding the implementation of primary data, the researcher can access it on a variety of platforms. Typically, I
spend less time collecting secondary data than I do gathering primary data. However, as the sources may not be
genuine and authentic, it may not be. My research can be inaccurate if I fall victim to disinformation or outright lies
when conducting primary research.
In conclusion, I encountered numerous restrictions and problems while conducting the research using various
research methodologies and data analysis, but I overcame them and finished the research report.
Page | 43
V. Appendix
1. Proposal form
Student Name: Quach Cong Tuan Student ID: BHAF200014
Propose title:
Research Question:
The Future of Autonomous Vehicles In Artificial Intelligence And The Internet Of Things?
Objectives
I want to learn:
What are artificial intelligence and the internet of things?
What role do automated vehicles play in life?
How will the use of automated vehicles support and benefit life?
How to build and develop automated vehicles?
Application of artificial intelligence in autonomous vehicles?
Ways to analyze and manage data for automated vehicles in AI and IoT?
The future of autonomous vehicles?
Autonomous vehicle challenge in technology?
Automated and efficient media solutions for the moment?
Practical applications of automatic vehicles in life?
Today, artificial intelligence and IoT are developing quite strongly and helping people to change their lives and
develop their lives in a positive way. Realizing the importance of applying AI and IoT in life, I have made judgments
and aimed to analyze the application of AI and IoT in life.
To choose a topic, I realized that participating in traffic in Vietnam is very complicated. Sometimes there are
systems that need us to upgrade and improve. Further, the use of technology to apply to autonomous vehicles
will be a new step in the technology industry.
In Vietnam, I realized that automated vehicles are not yet popular and active, but I see the potential of this
application in the future, so I decided to analyze this project.
Page | 44
I believe that after my research, the application of automation in AI and IoT will be more popular and developed,
helping users have better experiences in life.
2. https://www.softwareag.com/en_corporate/resources/what-is/machine-learning.html
3. https://data-flair.training/blogs/iot-and-machine-learning/l
4. https://www.softwareag.com/en_corporate/resources/what-is/machine-learning.html
5. https://vnexpress.net/khoa-hoc/cuoc-thi-sang-kien-khoa-hoc/y-tuong/ung-dung-tri-tue-nhan-tao-va-
cong-nghe-iot-vao-du-doan-som-nguy-co-bo-hoc-cua-sinh-vien-1076579161
6. https://movan.vn/ung-dung-iot-tri-tue-nhan-tao-va-machine-learning-de-tao-ra-mot-toa-nha-thong-
minh/
7. https://www.iotforall.com/artificial-intelligence-and-autonomous-vehicles
8. https://www.fullstory.com/blog/qualitative-vs-quantitative-
data/#:~:text=Quantitative%20data%20is%20numbers%2Dbased,what%20happened%20behind%20cert
ain%20behaviors
9. https://www.teldat.com/blog/autonomous-cars-with-embedded-connectivity-using-iot-ai-5g-
roboethics/
10. https://impacx.io/blog/autonomous-cars/
11. https://www.analyticssteps.com/blogs/ai-iot-benefits-and-applications
12. https://www.techopedia.com/definition/33768/artificial-intelligence-of-things-aiot
13. https://www.clariontech.com/blog/ai-and-iot-blended-what-it-is-and-why-it-matters
Page | 45
Section Four: Activities and timescales
Page | 46
Comments and agreement from tutor
Comments (Optional):
I confirm that the project is not work which has been or will be submitted for another qualification and is
appropriate.
Agreed: (Name)……………………………………………………………………(Date)………………………………………………….
Comments (Optional):
Agreed: (Name)……………………………………………………………………(Date)………………………………………………….
Page | 47
2. Ethical form
Page | 48
Figure 22 Ethical form
Page | 49
Figure 24 Ethical form
Page | 50
Figure 25 Ethical form
Page | 51
VI. Conclusion
In this part of the research, I have found that the research and development of AI and IoT in life will be a certainty
in the future. The turning points of the technology industry are gradually being demonstrated and technology
companies have also created and offered solutions to life's topics. The importance of AI - IoT will overcome many
tasks in life.
For this part of my research, I saw the potential of automated means. For development and construction processes
that help change the repetitive tasks of life. Just like public transport used in resort complexes, airports, Automated
vehicles will always meet human needs, and this will happen soon.
Page | 52
VII. References
Anand, A., 2021. AI in IoT - Benefits and Applications. [Online]
Available at: https://www.analyticssteps.com/blogs/ai-iot-benefits-and-applications
[Accessed 22 October 2022].
Bhandari, P., 2020. Population vs. Sample | Definitions, Differences & Examples. [Online]
Available at: https://www.scribbr.com/methodology/population-vs-
sample/#:~:text=A%20population%20is%20the%20entire,t%20always%20refer%20to%20people.
[Accessed 19 October 2022].
Bhandari, P., 2020. What Is Qualitative Research? | Methods & Examples. [Online]
Available at: https://www.scribbr.com/methodology/qualitative-research/
[Accessed 19 October 2022].
Bhandari, P., 2020. What Is Quantitative Research? | Definition, Uses & Methods. [Online]
Available at: https://www.scribbr.com/methodology/quantitative-
research/#:~:text=Quantitative%20research%20is%20the%20process,generalize%20results%20to%20wider%20po
pulations.
[Accessed 19 October 2022].
Chukwudozie, J., 2022. Artificial Intelligence (AI) and Autonomous Vehicles. [Online]
Available at: https://www.iotforall.com/artificial-intelligence-and-autonomous-vehicles
[Accessed 23 October 2022].
Embitel, 2019. The 2020 Internet of Things (IoT) Trends That will Disrupt Industry 4.0. [Online]
Available at: https://www.embitel.com/blog/embedded-blog/the-2020-iot-trends-that-will-disrupt-industry-4-0
[Accessed 10 October 2022].
Nashashibi, F., 2021. Are autonomous vehicles really for tomorrow?. [Online]
Available at: https://www.inria.fr/en/autonomous-vehicles-future-mobility
[Accessed 19 October 2022].
Pro, Q., 2020. Qualitative Research: Definition, Types, Methods and Examples. [Online]
Available at: https://www.questionpro.com/blog/qualitative-research-methods/
[Accessed 19 October 2022].
Pro, Q., 2020. Research Process Steps: What they are + How To Follow. [Online]
Available at: https://www.questionpro.com/blog/research-process-steps/
[Accessed 19 October 2022].
Page | 53
Pro, Q., 2022. Primary Research: Definition, Examples, Methods and Purpose. [Online]
Available at: https://www.questionpro.com/blog/primary-research/
[Accessed 18 October 2022].
Pro, Q., 2022. Secondary Research- Definition, Methods and Examples.. [Online]
Available at: https://www.questionpro.com/blog/secondary-research/
[Accessed 18 October 2022].
team, i., 2022. Autonomous Cars and The Internet of Things. [Online]
Available at: https://impacx.io/blog/autonomous-cars/
[Accessed 20 October 2022].
Vinugayathri, 2021. AI and IoT Blended - What It Is and Why It Matters?. [Online]
Available at: https://www.clariontech.com/blog/ai-and-iot-blended-what-it-is-and-why-it-matters
[Accessed 21 October 2022].
Page | 54