Assessment Scheme

In order to inculcate better transparency in teaching learning environment in BTech- CSE with
Specialization in AIML & IoT, Data Analytics, Cyber Security and Forensic, Cloud Computation
and Virtualization, Blockchain Technologies programme, it is suggested to follow the tentative
Evaluation Scheme in said programme. The students are advised to take a note of the same.

1. Marks distribution for Theory subjects is as follows:

Theory
Mid Term Marks 30
End Term Marks 50
Teacher Assessment 15
Attendance Marks 05
Total 100

2. Teacher Assessment Evaluation Pattern for Theory Subjects is as follows:

a. Five Quizzes per subject will be conducted in a semester.
b. Three Assignments need to be submitted for each subject in a semester
c. Two Presentations/Activities will be conducted for each subject in a semester

Note: Marks for above 3 points will be scaled for TA component (15 Marks).

Q- I Q - II Q -III Q - IV Q-V A -1 A -2 A -3 Pr-1/Act-1 Pr-1/Act-2 Total

(10) (10) (10) (10) (10) (10) (10) (10) (10) (10) (100)
Q: Quiz, A: Assignment, Pr: Presentation, Act: Activity

3. Marks distribution for practical/lab subjects is as follows:

Practical/Labs
Internal Marks 50
External Marks 40
Attendance Marks 10
Total 100

Teacher Assessment Evaluation Pattern for Practical/Lab Subjects

a. Three Quizzes for each Laboratory subjects in a semester
b. Three Viva-Voce for each subject in a semester

Note: Marks for above 2 points will be scaled for Internal Marks for Lab Component (50 Marks).

Q- I Q - II Q - III V -1 V -2 V -3 Total
(10) (10) (10) (10) (10) (10) (60)
Q: Quiz, V: Viva-Voce
 4. Instruction regarding Project / Field Project

All the students are advised to enrolled in one online course as per your respective project domain.
20 Marks will be awarded in lieu of project for submitting the pass certificate of respective online
course.

5. External Events (Outside campus) participation benefit

The students will be awarded 20 marks in a semester for participation in any external events
(technical/sports/cultural).
SEMESTER -III

SYLLABUS
 BCSE0701: INTRODUCTION TO MACHINE LEARNING

Objective: The objective of this course to introduce basis process of machine learning, mathematical
modeling of the supervised and unsupervised machine learning methods and to utilize combined voting of the
different machine learning methods for solving real-world problems using machine learning. approach.

Credit-03 L-T-P-J:0-0-2-0

Teaching
Module No. Content
Hours

Introduction: Introduction to machine learning, Applications, and motivation,

programming approach vs. machine learning approach in Artificial Intelligence,
components of a learning problem (such as data, model, and error functions), basic
learner, types of learning, features and feature vector, process of learning
(training), testing, bias and variance error.
Python for Data Science-Numpy, Pandas for preprocessing, Matplotlib and
Jupyter Notebook.
Data Preprocessing- Importing the Libraries, Importing the dataset, data
imputation, Encoding Categorical Data, Splitting the dataset into Training and Test
I 21
set, Feature Scaling.
Forecasting and Learning Theory: Predicting numerical values: linear and non-
linear regression. (Implementation on any real-world dataset e.g. Boston Housing),
Regression model using Gradient Descendent.
Validation: True and sample error, over-fitting, role of cross validation,
regularization, bias-variance analysis.
Performance-Measures: Types-of-errors, accuracy, confusion-matrix, precision-
recall.
Project: Estimation of diabeties using regression with gradient descendent.

Dimensionality Reduction: Feature Selection vs. feature extraction, Principal

Component Analysis (PCA), Singular Value Decomposition.
Supervised Learning: support vector machine, decision tree, Naïve Bayes
classifier.
Unsupervised Learning: clustering, Hierarchical clustering
II Ensemble Learning: Introduction, Bagging, Boosting, Improving classification,
21
Ada-Boost algorithm.
Machine learning Approach in NLP- Introduction to NLP libraries e.g. spacy,
NLTK. Text classification using spacy, sentiment classification using spacy on
IMDB dataset.
Introduction of CNN- Difference between ANN and CNN, libraries to implement
CNN and designing an application of image processing using CNN.

Text Books:
● Alpaydin, E. . Introduction to machine learning. MIT press, 2009.
● Bishop, C. M. . Pattern recognition and machine learning (information science and statistics)
springer-verlag new york. Inc. Secaucus, NJ, USA, 2006.
Reference Books:
● Harrington, P. . Machine learning in action. Shelter Island, NY: Manning Publications Co , 2012.

Outcome: After completion of Lab, student will be able to:

● CO1: Apply the basic concepts of machine learning including bias-variance tradeoff.
● CO2: Apply the concepts of regression.
● CO3: Conceptualize supervise and re-enforcement learning for classification.
● CO4: Formulate the ensemble methods for improving classification.
● CO5: Apply ANN with optimization in machine learning.
● CO6: Design and develop projects based on machine learning.
Mapping of Course Outcomes (COs) with Program Outcomes (POs) and Program Specific Outcomes (PSOs):

COs POs/PSOs
CO1 PO1/PSO3
CO2 PO2,PO3/PSO1
CO3 PO4/PSO1,PSO3
CO4 PO2,PO3/PSO4
CO5 PO2,PO4/PSO4
CO6 PO1/PSO2,PSO4
 BCSC XXXX: DATA ENGINEERING AND ViSUALIZATION

Objective: To introduce undergraduate students to the fundamental concepts, techniques, and tools
used in data engineering and visualization, preparing them for handling and managing large-scale data
systems.

Credit: 03 L–T–
P: 3–0–0

Modul Content Teaching

e No. Hours
Introduction to Data Engineering: Overview of Data Engineering: Definition,
Importance, and Applications.
Data Engineering Lifecycle: Data Generation, Collection, Storage, Processing,
and Analysis, The Role of a Data Engineer.
Data Collection: Sources of Data, Data Lake, Batch Processing, Streaming, Web
I Scraping, APIs and Data Extraction. 20
Data Modeling: Concepts, E-R Diagrams, Normalization and denormalization,
OLAP, OLTP
Data Storage: Relational Databases. NoSQL Databases. Data Warehouses.
Data Processing and Transformation: ETL (Extract, Transform, Load)
Processes
Data Cleaning Techniques- Batch Processing vs. Stream Processing
Data Integration: Combining Data from Multiple Sources. Data Integration Tools.
Data Quality and Consistency
Data Pipelines: Designing and Implementing Data Pipelines. Workflow
Orchestration Tools (e.g., Apache Airflow). Monitoring and Maintaining Data
Pipelines
II 20
Data Visualization: Basic Plots with Matplotlib, Line plots, bar plots, histograms,
scatter plots. Customizing plots: titles, labels, legends, and annotations. Saving and
exporting visualizations. Basic Plots with Seaborn: Distribution plots: histograms,
KDE plots. Categorical plots: bar plots, count plots, box plots, violin plots.
Relational plots: scatter plots, line plots.

Textbooks:
 Data Engineering with Python by Paul Crickard.
 Fundamentals of Data Engineering by Joe Reis and Matt Housley.
 Data Visualization with Python and JavaScript by Kyran Dale
Reference Books:
 The Data Warehouse Toolkit: The Definitive Guide to Dimensional Modeling by
Ralph Kimball and Margy Ross.
 Designing Data-Intensive Applications by Martin Kleppmann.
 Big Data: Principles and Best Practices of Scalable Real-Time Data Systems by
Nathan Marz and James Warren.
Outcome:
Upon completion of the course, students will:
 CO1: Understand the basics and importance of data engineering.
 CO2: Learn different data models and schema design techniques.
 CO3: Gain proficiency in data integration and ETL processes.
 CO4: Explore and use various big data technologies and tools.
  CO5: Understand the basics and importance of data visualization.
COs POs/PSOs
CO1 PO1, PO2 / PSO1

CO2 PO3, PO4 / PSO2

CO3 PO5, PO6 / PSO3

CO4 PO1, PO3 / PSO1
CO5 PO2, PO4 / PSO2

CO6 PO7, PO8 / PSO4