Objectives of Research:

The purpose of research is to discover answers to questions through the application

of scientific procedures. The main aim of research is to find out the truth which is
hidden and which has not been discovered as yet. Though each research study has
its own specific purpose, we may think of research objectives as falling into a
number of following broad groupings:

1. To gain familiarity with a phenomenon or to achieve new insights into it

2. To portray accurately the characteristics of a particular individual, situation or a
group
3. To determine the frequency with which something occurs or with which it is
associated with something else
4. To test a hypothesis of a causal relationship between variables.

Motivation in Research

What makes people to undertake research? This is a question of fundamental

importance. The possible motives for doing research may be either one or more of
the following:

1. Desire to get a research degree along with its consequential benefits;

2. Desire to face the challenge in solving the unsolved problems, i.e., concern over
practical problems initiates research;
3. Desire to get intellectual joy of doing some creative work;
4. Desire to be of service to society;
5. Desire to get respectability.

Comparison of Descriptive and Analytical Research

Feature Descriptive Research Analytical Research

Describes characteristics, patterns,
Explores relationships, causes, and effects
Definition or trends without investigating
using data analysis.
causes.
To present facts, summarize To analyze, interpret, and establish causal
Objective
observations, and identify trends. relationships.
Observational, survey-based, case Uses statistical, comparative, or
Approach
studies. experimental methods.
Data Surveys, observations, case studies, Uses primary and secondary data for
Collection historical records. interpretation and in-depth analysis.
Provides a detailed account of a Determines "why" or "how" a phenomenon
Outcome
phenomenon. occurs.
Consumer Buying Behavior
Impact of Advertisements on Sales: A
Study: A survey on customers'
Example 1 study analyzing the correlation between
preferences for different
marketing campaigns and product sales.
smartphone brands.
 Feature Descriptive Research Analytical Research
Traffic Congestion Study: Effect of Road Infrastructure on Traffic
Observing traffic flow in different Congestion: Examining whether wider
Example 2
city areas to identify peak roads reduce congestion levels using
congestion times. statistical analysis.

Comparison of Applied and Fundamental Research

Feature Applied Research Fundamental (Basic) Research

Solves specific, practical problems
Expands general knowledge and theories
Definition using existing theories and
without immediate practical applications.
knowledge.
To develop solutions for real-world To enhance understanding and generate new
Objective
problems. theories or principles.
Problem-solving, experimental, Theoretical exploration, lab-based research,
Approach
field studies. conceptual analysis.
Immediate, practical applications in Developing theories, principles, and new
Focus
industries, medicine, or engineering. scientific knowledge.
Leads to new products, techniques,
Outcome Expands scientific theories and concepts.
or technologies.
COVID-19 Vaccine Development: Understanding Virus Mutation Patterns:
Example Research focused on creating an Studying how viruses evolve at the genetic
1 effective vaccine to control the level without an immediate goal of
pandemic. developing a vaccine.
AI-based Medical Diagnosis Study of Neural Networks in AI:
Example System: Developing an AI tool to Researching how neural networks mimic
2 detect diseases from medical human cognition without immediate
images. application.

Applied vs. Fundamental Research in Computer Science

1. Definition:
o Applied Research: Solves specific, practical problems in computing and
technology.
o Fundamental Research: Develops theories and principles in computing
without immediate application.
2. Examples:
o Applied Research:
 Developing an AI-based recommendation system for e-commerce
platforms.
 Improving cybersecurity techniques to detect real-time cyber threats.
 Optimizing database management systems for faster query processing.
 Designing efficient deep learning architectures for medical image
analysis.
o Fundamental Research:
  Exploring new machine learning algorithms without focusing on
specific applications.
 Studying the theoretical limits of quantum computing.
 Investigating novel data structures and algorithms for computational
efficiency.
 Researching formal methods for software verification and correctness.

Comparison of Quantitative and Qualitative Research

Feature Quantitative Research Qualitative Research

Focuses on numerical data,
Focuses on non-numerical data like
Definition statistics, and measurable
opinions, experiences, and themes.
variables.
To quantify data, find patterns, and
To explore meanings, interpretations, and
Objective establish relationships between
deeper understanding of phenomena.
variables.
Structured, statistical, and Unstructured or semi-structured,
Approach
objective. interpretative, and subjective.
Data
Surveys, experiments, structured Interviews, open-ended surveys, focus
Collection
observations, secondary datasets. groups, case studies, ethnography.
Methods
Statistical techniques (e.g.,
Analysis Thematic analysis, content analysis,
regression, hypothesis testing,
Methods narrative analysis.
correlation).
Provides precise, numerical Provides in-depth insights, understanding
Outcome conclusions, trends, and of human behavior, and context-specific
generalizable findings. findings.
Effect of Exercise on Weight Personal Experiences with Fitness
Loss: A study measuring weight Training: Interviews with people
Example 1
reduction in a group of people discussing their motivation and challenges
exercising for 3 months. in maintaining an exercise routine.
Customer Satisfaction Survey: A
Consumer Behavior Study: Focus group
survey collecting ratings on a scale
Example 2 discussions to understand why people
of 1 to 10 to measure customer
prefer certain brands.
satisfaction.

Qualitative Research

Definition:
Qualitative research focuses on exploring phenomena through non-numerical data to
understand experiences, perceptions, and social contexts. It involves collecting rich, detailed
data through methods like interviews, focus groups, and observations.

Applications in Computer Science:

 1. User Experience (UX) Design: Understanding user behavior and preferences to
improve the usability and design of software and websites through interviews and
observations.
2. Human-Computer Interaction (HCI): Studying interactions between humans and
technologies (e.g., AR, VR) to gain insights into how new tools are used in real-life
scenarios.
3. Software Adoption Studies: Investigating factors affecting the adoption or rejection
of new programming languages or tools by developers, based on organizational
culture or personal experience.
4. Cybersecurity Awareness: Exploring IT professionals' and users' perceptions of
cybersecurity threats and behaviors to enhance security protocols through interviews
and case studies.

Qualitative Research

Definition:
Qualitative research focuses on exploring phenomena through non-numerical data to
understand experiences, perceptions, and social contexts. It involves collecting rich, detailed
data through methods like interviews, focus groups, and observations.

Applications in Computer Science:

1. User Experience (UX) Design: Understanding user behavior and preferences to

improve the usability and design of software and websites through interviews and
observations.
2. Human-Computer Interaction (HCI): Studying interactions between humans and
technologies (e.g., AR, VR) to gain insights into how new tools are used in real-life
scenarios.
3. Software Adoption Studies: Investigating factors affecting the adoption or rejection
of new programming languages or tools by developers, based on organizational
culture or personal experience.
4. Cybersecurity Awareness: Exploring IT professionals' and users' perceptions of
cybersecurity threats and behaviors to enhance security protocols through interviews
and case studies.

Quantitative Research

Definition:
Quantitative research involves collecting and analyzing numerical data to identify patterns,
relationships, and trends. It focuses on measurable variables and uses statistical methods to
test hypotheses and make predictions.

Applications in Computer Science:

1. Algorithm Performance Evaluation: Comparing the efficiency (e.g., time and space
complexity) of various algorithms on different datasets to identify the best solution.
 2. Machine Learning Model Evaluation: Assessing the performance of machine
learning models (e.g., accuracy, precision) through quantitative metrics across diverse
datasets.
3. Network Traffic Analysis: Analyzing network data to detect patterns, optimize
network protocols, and improve performance through statistical models.
4. Software Metrics: Collecting numerical data on software development processes
(e.g., defect rates, code quality) to assess productivity and project success.

Comparison of Conceptual and Empirical Research

Feature Conceptual Research Empirical Research

Based on abstract ideas, theories, and Based on direct observation,
Definition logical reasoning without direct experiments, and real-world data
experimentation. collection.
To develop new theories, refine To test hypotheses, validate theories,
Objective existing ideas, or propose new and derive conclusions from real-world
concepts. evidence.
Philosophical, theoretical, and Experimental, observational, and data-
Approach
analytical. driven.
Data
Uses logical reasoning, literature Uses surveys, experiments, case
Collection
review, and theoretical frameworks. studies, or field studies.
Methods
Analysis Logical deduction, comparative Statistical analysis, hypothesis testing,
Methods analysis, and theoretical discussions. and empirical validation.
Leads to new models, theories, or Provides measurable, tested, and
Outcome frameworks without immediate validated conclusions based on
practical verification. observed data.
Theory of Artificial Intelligence AI Bias Analysis in Hiring
Ethics: Developing a theoretical Algorithms: Conducting an empirical
Example 1
framework for ethical AI use without study on whether AI-based hiring tools
testing it in real-world scenarios. show bias based on gender or race.
Philosophical Study on Neuroscience Experiment on
Consciousness: Exploring different Consciousness: Conducting brain
Example 2
theories on human consciousness and scans to analyze neural activity
its implications. associated with conscious thought.

Conceptual vs. Empirical Research in Computer Science

1. Definition:
o Conceptual Research: Focuses on theoretical models, frameworks, and abstract
ideas without direct experimentation.
o Empirical Research: Involves real-world experiments, data collection, and validation
to test theories or models.

2. Examples:
 o Conceptual Research:
 Proposing a new cryptographic protocol without testing its implementation.
 Developing a theoretical model for explainability in AI.
 Studying the mathematical properties of neural networks.
 Formulating a new algorithmic paradigm, such as a novel sorting technique,
without implementation.
o Empirical Research:
 Testing a new cybersecurity algorithm on real-world attack datasets.
 Measuring the efficiency of different machine learning models on
benchmark datasets.
 Conducting user studies to evaluate the usability of a software interface.
 Experimenting with different hyperparameter tuning strategies for deep
learning models.

WHAT IS A RESEARCH PROBLEM?

A research problem, in general, refers to some difficulty which a

researcher experiences in the context of either a theoretical or practical
situation and wants to obtain a solution for the same.

Selecting the Research Problem

 Avoid Overdone Topics: Choose a subject that hasn’t been excessively studied, as it may be
hard to add new insights.
 Avoid Controversial Topics: Controversial subjects are challenging and not ideal for average
researchers.
  Avoid Narrow or Vague Problems: Research problems should be clear, focused, and not too
broad or ambiguous.
 Familiar and Feasible Topics: Choose a subject you're familiar with and can access relevant
resources for. Ensure it’s practical and within your reach.
 Expert Guidance: Seek help from a research guide, expert, or professor engaged in the field.
Read current literature and discuss ideas with peers to refine the topic.
 Consider Practical Factors: Ensure the research topic is aligned with:
o Your qualifications and expertise.
o The available budget and resources.
o Cooperation from subjects or participants.
 Preliminary Study: Conduct a feasibility study, especially for new or complex topics, to
ensure the research is practical and the techniques are available.

NECESSITY OF DEFINING THE PROBLEM

Defining the Research Problem

 Clear Problem Statement: A well-defined problem is essential for effective research. It helps
to focus on relevant data and avoid distractions.
 Guides the Research: Proper definition helps the researcher identify what data to collect,
which characteristics to study, and which relationships to explore.
 Prevents Hurdles: An unclear problem can lead to confusion, making it difficult to plan and
execute the research.
 Key Questions to Address:
o What data should be collected?
o What characteristics of the data are relevant?
o What techniques will be used?
 Importance: Defining the problem is more crucial than finding its solution; it forms the basis
for the entire research design.
 Smooth Progress: A well-defined problem enables researchers to follow a clear path and
carry out all subsequent steps effectively.

TECHNIQUE INVOLVED IN DEFINING A PROBLEM

 Statement of the problem in a general way

 Understanding the nature of the problem:
 Surveying the available literature:
 Developing the ideas through discussions:
 Developing the ideas through discussions:

Example in Computer Science (Brief):

 Broad Research Problem:

"Why are some machine learning models more accurate than others?"
This question is too vague, with ambiguities about the model types, accuracy
measures, datasets, and timeframes.
 Refined Research Problem:
"What factors influence the accuracy of neural network models compared to decision
 tree models on the MNIST dataset for image classification?"
This version removes some ambiguities but could still be more specific.
 Final Research Problem:
"To what extent does the architecture of neural network models (e.g., number of
layers, activation functions) affect their accuracy on the MNIST dataset? How does
this compare to decision tree models?"
This formulation clearly defines the models, dataset, and factors being studied,
making the problem actionable.

Example in Medical Image Applications:

 Broad Research Problem:

"Why do some medical image processing techniques produce better results than
others?"
This is vague, with unclear definitions of "better results" and which techniques are
being compared.
 Refined Research Problem:
"What factors contribute to the accuracy of medical image segmentation techniques
for detecting tumors?"
This narrows down the focus to accuracy in tumor detection but lacks specifics on the
techniques or types of images.
 Final Research Problem:
"How does the use of convolutional neural networks (CNNs) for medical image
segmentation compare to traditional thresholding methods in detecting tumors in
MRI brain scans?"
This version clearly defines the techniques (CNNs vs. thresholding), the specific
medical application (tumor detection), and the type of medical image (MRI brain
scans), making the problem actionable and researchable.

What is a Literature Review?

 A literature review surveys and discusses published material about a specific topic or
research question.
 It is essential to be an expert in the study area to ensure accuracy and reliability.
 Findings are shared with the scientific community for further study and development.

How to Write a Literature Review:

1. Choose Your Topic or Research Question:

o Select a topic that’s neither too broad nor too narrow.
o Ensure it can be completed within a feasible time frame.

2. Set the Scope:

 o Define boundaries like the number of sources, time period, and geographical area.

3. Decide on Databases for Searching:

o Use reputable and comprehensive databases to gather literature.

4. Search for Relevant Literature:

o Investigate research using detailed abstracts, bibliographies, and references.
o Keep track of bibliographic details for later use.

5. Review and Appraise the Literature:

o Read the articles critically, assessing methodologies, key questions, design,
execution, and citation frequency.

6. Structure Your Literature Review:

o Introduction: General idea and structure.
o Body: Detailed discussion of the sources.
o Conclusion/Recommendations: Summarize findings, possibly suggesting areas for
further research.

Why Are Literature Reviews Important?

 Literature reviews feed and are fed by new research, creating a cycle that drives scientific
progress.
 Writing a literature review enhances your career and establishes you as an expert in your
field.
 It can be an overwhelming task, so seeking professional editing services (e.g., Elsevier) can
help ensure high-quality writing.

Primary and Secondary Sources in Literature Reviews:

 Primary Sources:
o Provide first-hand, original information directly related to the object of study.
o Common in natural and social sciences, including research reports, academic
journals, speeches, letters, diaries, autobiographies, interviews, court records, and
artifacts.

 Secondary Sources:
o Provide secondhand information, summarizing or analyzing primary sources.
o Examples include textbooks, magazines, biographies, critical studies, and research
summaries.

This structure highlights the importance of literature reviews and the difference between
primary and secondary sources.