Data Science and Machine Learning
Home Courses

Domain Track: Data Science and Machine Learning

Domain Track: Data Science and Machine Learning

Course Attendees

Still no participant

Course Reviews

Still no reviews

Data Science is an interdisciplinary field that uses scientific methods, processes, algorithms and systems to extract knowledge and insights from noisy, structured and unstructured data, and apply knowledge and actionable insights from data across a broad range of application domains.Machine Learning is the science of getting computers to act without being explicitly programmed.The goal of this domain, Data Science and Machine Learning is to build systems and algorithms to extract knowledge, find patterns, generate insights and predictions from diverse data for various applications and visualization. The Domain deals with structured and un-structured data i.e. text, multimedia, image, video, multispectral and hyperspectral and do the data analysis like prediction, classification, clustering to solve the real life problems. Data has been collected from Internet, IoT and real life fields.

Total Credits ( T-P-P): 26(2-9-15)

Courses Division:

For Batch - 2017 to 2021 & 2018 to 2022
  • Data Analysis and Visualisation Using Python -CUML2000- 4(0+1+3)
  • Machine Learning using Python -CUML2001- 4(1+2+1)
  • ML for Predictive Analysis -CUML2002-4(1+2+1)
  • ML for Image Analytics -CUML2003- 6(0+4+2)
  • ML for Hyperspectral Imaging -CUML2004- 6(0+4+2)
  • Internship -CUML2005- 4(0+0+4)
  • Project CUML2006- 4(0+0+4)

Note: Only one course has to be opted from course-4 & course-5.

For Batch - 2019 to 2023
  • ML for Predictive Analysis -CUML2002-4(1+2+1)
  • ML for Image Analytics -CUML2003- 6(0+4+2)
  • ML for Hyperspectral Imaging -CUML2004- 6(0+4+2)
  • Digital Video Processing -CUML2007- 4(0+2+2)
  • IoT Analytics-CUML2008- 4(0+2+2)
  • Internship -CUML2005- 4(0+0+4)
  • Project - CUML2006 - 4(0+0+4)

Note: Only one course has to be opted from course-2 & course-3.

Domain Track Objectives:

  • Understand the scope, stages, applications, effects and challenges of ML.
  • Understand the mathematical relationships within and across ML algorithms and the paradigms of supervised and unsupervised learning.

Domain Track Learning Outcomes:

  • Ability to Create and incorporate ML solutions in their respective fields of study.
  • Ability to design and implement various machine learning algorithms in a range of real-world applications.
  • Ability to design product/ publish article/ file patent

Job Prospects in the Industry or Self Employment Opportunities:

  • System Engineer
  • Data Scientist
  • Data Analyst
  • Database System Manager
  • Principal NLP Engineer
  • Business Data Analyst
  • Full Stack Developer (m/f/d)
  • Machine Learning Specialist
  • AI SW & Solutions Architect
  • Lead Data Scientist

Domain Achievements:

Year 2016-2020
  • 1 patent granted
  • 17-Paid journals
Year2017-2021
  • 1 Best paper Award
  • 1 Unpaid Journal,
  • 16 Journals
  • Best student award
Year 2018-2022
  • 2 Papers published
  • 2 Papers Accepted in IEEE
  • 5 Papers Submitted in IEEE
  • 1 Best Paper Presentation in IEEE Day Celebration
  • 2 Best Poster Presentation award CSI event in CUTM (Rs 1000)
  • 1 Best Poster Presentation award CSI event in Silicon (Rs 3000)
  • 20 Papers are in final stage
2019-2023
  • 1 Best Paper Presentation in IEEE Day Celebration
  • 9 Students have Best Poster Presentation Award in got GIS Day Celebration
  • 5 Papers Accepted
  • 6 Papers Accepted in Springer Conference
  • 11 Beautiful Posters made for Gajajyoti 2022
  • 10 Papers – working on it

Domain Syllabus:

Course 1: Data Analysis and Visualisation Using Python (0+1+3)
1.1 Story Board Development:-
  • The objective and flow of the story to be understood through cases.
1.2 Data Reading using Python Functions;-
  • Python libraries: Pandas, NumPy, Plotly, Matplotlib, Seaborn, Dash.
  • Data collection from online data sources
  • Web scrap, data formats such as HTML, CSV, MS Excel.
  • Data compilation, arranging and reading data, data munging
1.3 Data Visualisation using Python Libraries:-
  • Using graphs- Scatterplot, Line chart, Histogram, Bar chart, Bubble chart, Heatmaps .
  • Dashboard Basics- Layout, Reporting, Infographics, Interactive components, live updating.
Projects
  • COVID 19
  • World Development Indicators
  • ERP dashboarding
  • Details of Social/ Empowerment schemes of Govt.
References:
Course 2: Machine Learning using Python (1+2+1)
2.1 Application and Environmental-setup:-
  • Applications of Machine Learning In different fields (Medical science, Agriculture, Automobile, mining and many more).
  • Supervised vs Unsupervised Learning based on problem Definition.
  • Understanding the problem and its possible solutions using IRIS datasets.
  • Python libraries suitable for Machine Learning(numpy, scipy, scikit-learn, opencv)
  • Environmental setup and Installation of important libraries.
2.2 Regression:-
  • Linear Regression
  • Non-linear Regression
  • Model Evaluation in Regression
  • Evaluation Metrics in Regression Models
  • Multiple Linear Regression
  • Feature Reduction using PCA
  • Implementation of regression model on IRIS datasets.
2.3 Classification:-
  • Defining Classification Problem with IRIS datasets.
  • Mathematical formulation of K-Nearest Neighbour Algorithm for binary classification.
  • Implementation of K-Nearest Neighbour Algorithm using sci-kit learn.
  • Classification using Decision tree.
  • Construction of  decision trees based on entropy.
  • Implementation of Decision Trees for Iris datasets .
  • Classification using Support Vector Machines.
  • SVM for Binary classification
  • Regulating different functional parameters of SVM using sci-kit learn.
  • SVM for multi class classification.
  • Implementation of SVM using Iris datasets .
  • Implementation of Model Evaluation Metrics using sci-kit learn and IRIS datasets.
2.4 Unsupervised Learning:-
  • Defining clustering and its application in ML .
  • Mathematical formulation of K-Means Clustering.
  • Defining K value and its importance in K-Means Clustering.
  • Finding appropriate K value using elbow technique for a particular problem.
  • Implementation of K-Means clustering for IRIS datasets
Projects
  • To be defined based on respective study area of student.
References:

 

Text Book:
Web Resource:
Course 3: ML for Predictive Analysis (1+2+1)
Time Series Analysis
  • Prediction of Financial Time Series data
  • Covid-19 cases prediction based time series analysis.
Health Care System
  • Cancer detection
  • Skin disease detection
Concept Required:
3.1 Data pre-processing:-
  • Accessing / collecting the datasets from different online repository.
  • Missing values handling, noise reduction using, finding Correlation between features, outlier elimination.
3.2 Feature extraction and selection: -
  • Principal component analysis (PCA)
  • Linear discriminant analysis (LDA)
3.3 Model building: -
  • Regression (Linear, Polynomial, multiple, logistic), Decision Tree, Random Forest.
  • Artificial Neural Network (Feed Forward Neural Network, Back Propagation Neural Network).
3.4 Performance measures: -
  • Perdition: Root Mean Square Error (RMSE), Mean Average Percentage Error (MAPE).
  • Classification: Confusion Matrix (TN, TP, FP, FN), Sensitivity, Specificity, Overall Accuracy, (Receiver Operating Characteristic) ROC Curve.
Course 4: ML for Image Analytics (0-4-2)
Project/Task: (Choose one among six Tasks)
  • Detection of optometry diseases using retinal fundus imaging.
  • Diabetic Retinopathy
  • Glaucoma
  • Cataract
  • Detection of various diseases using X-ray imaging.
  • Covid19
  • Leaf disease classification using RGB images.
  • Tomato leaf
  • Potato leaf
Concept Required:
4.1 Image Pre-processing:-

  • Accessing individual pixels using matrix concept

  • Image resize, grey scale conversion, Colour channel splitting
  • Histogram equalisation (CLACH).
4.2 Image Feature Extraction: -
  • Edge detection (Sobel, Canny), Morphological operations
  • Image segmentation, Image Thresholding, Binary conversion
  • Cluster based segmentation
  • Feature extraction based on size, shape and colour
  • Feature extraction using predefined functions: SIFT, SURF, STAR, ORB.
  • Feature Extraction using convolutional neural network (CNN).
4.3 Creation of Feature Matrix by combining Extracted Features: -
  • Matrix flattening, Horizontal stacking, Vertical stacking, padding.
  • Splitting the feature matrix (training/testing)  and labelling.
4.4 Classification algorithms:
  • Support vector machine (SVM)
  • Different kernels of SVM (linear, polynomial, radial basis function).
  • Gradient Boosting (GB)
  • Multi-layer Perceptron (MLP), deep learning.
Course 5: Ml for Hyperspectral Imaging (0-4-2)
Project/Task: (Choose one among four Tasks)
Agriculture
  • Crop yield prediction.
  • Crop quality prediction
  • Soil health monitoring
Mining
  • Iron ore quality prediction
Concept Required:
5.1 Introduction to Remote Sensing: -
  • Multi-Spectral Imagery (MSI)
  • Hyperspectral Imagery (HSI)
5.2 Scientific Principles:
  • Physics of imaging spectroscopy
  • Electromagnetic propagation
  • Sensor physics
  • Atmospheric Corrections.
5.2 Hyperspectral Concepts and System Trade-offs:-
  • Signal-to-Noise ratio (SNR)
  • Spectral resolution, sampling.
5.3 HSI Data Processing Techniques:-
  • Spectral angle mapping
  • Principal Component Analysis (PCA)
  • Minimum Noise Fraction (MNF)
  • Spectral feature fitting.
5.4 Classification Techniques:-
  • Support Vector Machine (SVM)
  • Partial Least Squares Regression (PLSR)
  • Neural Network
  • Deep learning and CNN
5.5 Clustering Techniques:-
  • K-mean clustering

Course 6: Digital Video Processing (0-2-2)

Course 7: IoT Analytics (0-2-2)
7.1  Defining IoT Analytics and Challenges
  • IoT
  • Benefits of Deploying IoT
  • End to End IoT architecture
  • IoT challenges
7.2  IoT Protocols
7.2.1  Wireless Protocol
  • Connectivity Protocols (when Power is Limited)
  • Bluetooth Low Energy (BLE)
  • Zigbee
  • LoRaWAN
  • NFC
7.2.2  Connectivity Protocols (when Power is Not a problem)
  • Wifi
7.2.3   Data Communication Protocol
  • MQTT
  • Web-Socket
  • HTTP
7.2  Sensors
  • Types of Sensors based on communication-I2C, SPI
  • Types of Sensors based on Application
7.3  Overview of 32 -bit Controller
  •  ESP8266
  •  ESP32
  •  Raspberry Pi
7.4  AWS IoT for Cloud
  •  AWS IoT Core services
  •  AWS IoT Analytics services
  •  AWS DynamoDB Services
7.5  Thingspeak for IoT
  •  Getting and posting Data to IoT Cloud using ESP devices
  •  Posting Data to IoT Cloud using Raspberry Pi
7.6  ThingWorx for Industrial IoT
  •  Building Dashboard on Thingworx platform
  •  Binding the senor value to the dashboard
Text Book:
  • Minteer, Andrew. Analytics for the Internet of Things (IoT). Packt Publishing Ltd, 2017.
Reference Books:
  • 2. Geng, Hwaiyu, ed. Internet of things and data analytics handbook. John Wiley & Sons, 2017.
Course 8: Project (0-0-4)
Course 9: Internship (0-0-4)

Session Plan for the Entire Domain:

Data Analysis and Visualisation Using Python (0+1+3) 60 hrs

Session 1
Session 2
Story telling using Visuals & Infographics
Tips on good visuals
Project Groups:
  • Students will be divided into groups and assigned projects. Each group will do two projects.
Session 3
Practice
  • Environmental setup - Anaconad and Jupyter notebook, Anaconda Navigator and Libraries Installation
  • Video Link...
Session 4 & 5
Practice
  • Python Fundamentals, Use Case - Data Analysis, Exploring and learning assignments on Jupyter Notebook
  • Website
  • Website
  • Website
Session 5 & 6
Project - 1
  • For Project -1, the student group has to define the objective/s of the study, identify the data that will be needed and the source of such data
  • Make Presentations groupwise
Session 7, 8 & 9
Practice
    • Data collection/importing and reading using Python function

of different types of files, i.e. CSV, HTML, Excel - Get CSV data files from source and read them, get HTML file and read, Get Excel sheet and read

Sorting data, Missing values & Munging data
Session 10 & 11
Project - 1
  • Data collection and sorting for the assigned project
  • Pandas Tutorial 1. What is Pandas python? Introduction and Installation- Video Link...
  • Pandas Tutorial2. Dataframe and Series Basics- Selecting row and column- Video Link...
  • Pandas Tutorial 3: Different Ways Of Creating DataFrame - Video Link...
  • Python Pandas Tutorial 4: Read Write Excel CSV File- Video Link...
  • Importing data in python - Read excel file - Video Link...
  • Pandas Tutorial 8 | How to import HTML data in Python | Importing HTML data in Python - Video Link...
  • Pandas Tutorial 13, Crosstabs - Video Link...
Session 12 & 13
Practice
  • Basics of Numpy
  • Video Link...
  • Complete Python NumPy Tutorial (Creating Arrays, Indexing, Math, Statistics, Reshaping) - Video Link...
Session 14 & 15
Practice
Session 16 & 17
Practice
Session 18, 19, 20 & 21
Project (work on Project -1)
  • Work on the projects assigned using Python Libraries
  • Pandas Tutorial 1. What is Pandas python? Introduction and Installation- Video Link 1...
  • Pandas Tutorial 3: Different Ways Of Creating DataFrame - Video Link 2...
  • Python Pandas Tutorial 4: Read Write Excel CSV File
  • Video Link...
  • Importing data in python - Read excel file - Video Link...
  • Pandas Tutorial 8 | How to import HTML data in Python | Importing HTML data in Python - Video Link...
  • Pandas Tutorial 13, Crosstabs - Video Link...
Session 22 & 24
Practice
  • Plotly
  • Website
  • Graphing Library - Website
  • Plotly Python - Plotly multi line chart| Plotly Python data visualization- Video Link...
  • Plotly Data Visualization in Python | Part 13 | how to create bar and line combo chart - Video Link...
  • Plotly Web based visualisation - Video Link...
Session 25, 26, 27 & 28
Project (Project-1)
  • Work on Project
  • Interim Presentation
Session 29 & 30
Practice
Session 31 & 32
Practice
  • Web Scrapping
  • Video Link...
  • Web scraping in Python (Part 4)_ Exporting a CSV with pandas - Video Link...
  • Web scraping in Python (Part 2)_ Parsing HTML with Beautiful Soup - Video Link...
  • Webscraping - Mode, Median, Mean, Range, and Standard Deviation- Video Link...
  • Web Scraping Dynamic Graphs to CSV Files using Python - Video Link...
Session 33 & 34
Practice
  • Solve the 10 problem (started from session 7)
  • -students will submit the assignment (in groups)

(upload the assignment ...done by Prof. Ramana)

Session 35 & 36
Practice
Session 37 & 38
Practice
Session 38 & 39
Practice
Session 40 & 41
Practice
Session 42 & 43
Project
  • Work on Project - 1 to make dash boards
Session 44, 45 & 46
Project
  • Final presentation of Project -1
Session 47 & 48
Project -2
  • Start Project - 2 (ERP Dash Board)
  • Define the objective and prepare the flow chart
Session 49 & 50
Project
  • Make presentations on the objective and flow chart of Project-2
Session 50 & 51
Project
  • Work on Project - 2
Session 52 & 53
Project
  • Make interim presentation on Project - 2
Session 54 & 55
Project
  • Work on Project - 2
Session 56 & 58
Project
  • Final Presentation on Project -2
Session 59 & 60
Project
  • Make final changes on Project -1 & Project -2 to make it ready for External Evaluation
Machine Learning using Python (1+2+1) 56 hrs
Session-1
Session-2,3
  • Supervised vs Unsupervised Learning based on problem Definition
  • Video Link...
Session-4,5
  • Understanding the problem and its possible solutions using IRIS datasets.
  • Video Link...
Session-6,7
  • Mathmatical library in Python numpy and its  functions
  • Video Link...
Session-8,9
  • Science library in Python scipy and its  functions
  • Video Link...
session-10,11
  • ML library in Python scikit-learn and its  functions.
  • Video Link...
Session-12
  • Defining student specific Project
Session-13
Session-14
Session-15
Session-16
Session-17,18
Session-19
Session-20
  • Implementation of regression model on IRIS datasets.
  • Video Link...
Session-21
  • Defining Classification Problem with IRIS datasets.
  • Video Link...
Session-22,23
  • Create the train/test set using scikit-learn using scikit-learn
  • Website
Session-24,25
  • Confussion Matrix, Accuraccy, Sensitivity, specificity
  • Website
Session-26
  • Mathematical formulation of K-Nearest Neighbour Algorithm for binary classification.
  • Video Link...
Session-27,28
  • Implementation of K-Nearest Neighbour Algorithm using sci-kit learn.
  • Video Link...
Session-29,30
Session-31,32
  • Construction of  decision trees based on entropy.
  • Video Link...
Session-33,34
  • Implementation of  Decision Tree using sci-kit learn
  • Video Link...
Session-35,36
Session-37,38
Session-39,40
  • Regulating different functional parameters of SVM using sci-kit learn.
  • Video Link...
Session-41,42
Session-43,44
Session-45,46
Session-47,48
Session-49,50
  • Defining K value and its importance in K-Means Clustering.
  • Video Link...
Session-51,52
  • Implementation of K-Means Clustering in  Scikit-learn
  • Video Link...
Session-53,54
  • Finding appropriate K value using elbow technique for a particular problem.
  • Video Link...
Session-55,56
  • predicting iris flower species with k-means clustering.
  • Website
Session-1,2
Session-3,4
Session-5,6
Session-7,8
Session-9,10
Session-11,12
Session-13,14
Session-15,16,17
  • Project Review-1 (Datasets and analysis of datasets)
Session-18,19,20
Session-21,22,23
Session-24,25,26
Session-27,28
Session-29,30
Session-31,32
Session-33,34,35
Session-36,37,38
Session-39,40,41
  • Project review-2(Model selection and implementation)
Session-42,43
Session-44,45
Session-46,47
Session-48,49
Session-50,51,52
Session-53,54,55,56
  • Project review-3(Validation of the model)

ML for Image Analytics (0-4-2) 86hrs

Session-1,2,3
  • Accessing individual pixels using matrix in image
  • Video Link...
Session-4,5,6
Session-7,8,9,10
  • Grey scale conversion and mathematical implementation
  • Video Link...
Session-11,12,13
Session-14,15,16,17
Session-18,19,20,21
Session-22,23,24
Session-25,26,27,28
Session-29,30,31
Session-32,33,34
Session-35,36,37,38
Session-39,40,41,42
  • Feature extraction based on size, shape and colour
  • Video Link...
Session-43,44,45,46
  • Feature extraction using predefined functions: SIFT, SURF, STAR, ORB
  • Video Link...
Session-47,48,49,50
Session-51,52,53,54
Session-55,56,57
Session-58,59,60,61
  • Creation of Feature matrix by padding required number of zeros and ones.
  • Video Link...
Session-62,63,64
Session-65,66,67
Session-68,69,70
Session-71,72,73,74
  • Different kernels of SVM (linear, polynomial, radial basis function)
  • Video Link...
Session-75,76,77
Session-78, 79, 80
Session-881,82,83
Session-84,85,86
  • Deep learning for Image classification using  RNN
  • Video Link...

ML for Hyperspectral Imaging (0-4-2) 86 hrs

Session-1,2,3
Session-4,5,6
Session-7,8,9
  • Hyperspectral remote sensing and its applications
  • Video Link...
Session-10,11,12,13
Session-14,15,16
Session-17,18,19
Session-20,21,22,23
Session-24,25,26
Session-27,28,29
Session-30,31,32,33
  • Image sampling and quantization in digital image processing
  • Video Link...
Session-34,35,36,37
Session-38,39,40,41
  • Principal Component Analysis (PCA) in HSI Imaging
  • Video Link...
Session-42,43,44,45
  • Minimum Noise Fraction (MNF) using different methods
  • Video Link...
Session-46,47,48,49
Session-55,51,52,53
Session-54,55,56,57
Session-58,59,60,62
Session-58,59,60,61
  • K-mean clustering in hyperspectral imaging
  • Website
Session-62,63,64,65
  •  Hyperspectral image classification using multiple spectral and spatial features
  • Video Link...
Session-67,68,69,70
  • Models and Algorithms for Hyperspectral Image Processing
  • Video Link...
Session-71,72,73,74
  • Applied Hyperspectral Imaging Fundamentals and Case Studies
  • Video Link...
Session-75,76,77,78
  • Classification For Hyperspectral Remote Sensing Imaging Using Neural Network
  • Video Link...
Session-79,80,81,82
  • Hyperspectral image classification using Deep learning and CNN
  • Video Link...
Session-83,84,85,86
  • Case study-Implements dimensionality reduction on hyper spectral image(Indian Pines) with classification.
Session-83,84,85,86
IoT Analytics (0+2+2) -60 hrs
Session- 1
Practice 1:
  • Creating Things, Certificates, Policies in AWS IoT core Services
Practice 2:
  • Connect NodeMCU with AWS IoT Core Services
Practice 3:
  • Connect ESP32 with AWS IoT Core Services
Practice 4:
  • Connect Raspberry Pi with AWS IoT Core Services
Practice 5:
  • Posting Sensor Data to AWS IoT Core Services
Practice 6:
  • Controlling Devices from AWS IoT Core Services
Practice 7:
  • Storing Sensor Data into DynamoDB using AWS IoT core
Practice 8:
  • Get Raspberry Pi to interact with Amazon Web Services & push data into the DynamoDB
Practice 9:
  • Posting Sensor Data to the Thingspeak to aggregate, visualize and analyze live data streams in the cloud
Practice 10:
  • Portable IoT Based Fingerprint Biometric Attendance System
Practice 11:
  • IoT-based Covid Patient Blood Oxygen monitor & calling an ambulance on critical blood oxygen levels
Project (CUML2006)- (0+0+4)
  • IoT based Water Management
  • IoT Disease and Pest Management in Smart Agriculture
  • Soil Health Monitoring
  • IoT based Apparel Tracking
  • Intruder Tracking System
Gate Process for Project
  • Gate 0:       Problem Identification
  • Gate 1:       Data Collection
  • Gate 2:       Model Development
  • Gate 3:       Testing and Validation
  • Gate 4:       Publication, Patent, Product

Latest News & Student Testimonials

K. Sai Kishore got Best Paper Award in Springer International Conference, Certificate received from VC Madam

K. Sai Kishore got Best Paper Award in Springer International Conference, Certificate received from VC Madam

K. Sai Kishore got Best Paper Award in Springer International Conference, Certificate received from VC Madam

Read more
Paper presentation by Satabdi in an International Health Informatics Conference (IHIC 2022) Springer, May 17-19, 2022

Paper presentation by Satabdi in an International Health Informatics Conference (IHIC 2022) Springer, May 17-19, 2022

Paper presentation by Satabdi in an International Health Informatics Conference (IHIC 2022) Springer, May 17-19, 2022

Read more

Pest Detection in Rice Plant | Data Science & Machine Learning | CTUM

Major Projects | Computer Vision Based Vehicle Counting & Monitoring System | CTUM

Media

face mask
get_together
get_together2

Our Main Teachers

Dr. Sujata Chakravarty

HoD & Associate Professor, Department of CSE, SoET
VIEW PROFILE

Dr. Sujata Chakravarty is a Senior Member of IEEE, Chair, Technical Activities, Ex-Chair Women in Engineering of IEEE Bhubaneswar Sub-section. She holds membership in different academic bodies like OITS, ISTE, Orissa Bigyan Academy, Institution of Engineers etc.She has been a member of the Academic Council and Board of studies of different Universities/Institutions and also a […]

MANOJ KUMAR BEHERA

Asst. Prof. Dept of CSE
VIEW PROFILE

Manoj Kumar Behera, M. tech. in Computer Science, NIT Rourkela, Qualified GATE in 2008. His research area includes application of machine learning and image processing in the fields of smart agriculture and Bio-medical applications. He has published about 20 articles in many international journals and conferences.