CP4092 DATA VISUALIZATION TECHNIQUES

COURSE OBJECTIVES:
 To develop skills to both design and critique visualizations.
 To introduce visual perception and core skills for visual analysis.
 To understand technological advancements of data visualization
 To understand various data visualization techniques
 To understand the methodologies used to visualize large data sets

UNIT I INTRODUCTION AND DATA FOUNDATION

Basics - Relationship between Visualization and Other Fields -The Visualization Process - Pseudo co
Foundation - Types of Data - Structure within and between Records - Data Preprocessing - Data Sets

UNIT II FOUNDATIONS FOR VISUALIZATION

Visualization stages - Semiology of Graphical Symbols - The Eight Visual Variables – H
Experimental Semiotics based on Perception Gibson‘s Affordance theory – A Model of Perceptua

UNIT III VISUALIZATION TECHNIQUES

Spatial Data: One-Dimensional Data - Two-Dimensional Data – Three Dimensional Data - Dynamic D
Data : Visualizing Spatial Data - Visualization of Point Data -Visualization of Line Data - Visualiz
Geospatial Data Visualization Multivariate Data : Point-Based Techniques - LineBased Tech
Combinations of Techniques – Trees Displaying Hierarchical Structures – Graphics a
Graphs/Networks.

UNIT IV INTERACTION CONCEPTS AND TECHNIQUES

Text and Document Visualization: Introduction - Levels of Text Representations - The Vector Space
-Document Collection Visualizations – Extended Text Visualizations Interaction Concepts: Interactio
Spaces
- A Unified Framework. Interaction Techniques: Screen Space - Object-Space –Data Space - At
Visualization Structure – Animating Transformations - Interaction Control.

UNIT V RESEARCH DIRECTIONS IN VISUALIZATIONS

Steps in designing Visualizations – Problems in designing effective Visualizations- Issues of Data
Reasoning. Issues of System Design Evaluation , Hardware and Applications

COURSE OUTCOMES:
CO1: Visualize the objects in different dimensions.
CO2: Design and process the data for Visualization.
CO3:Apply the visualization techniques in physical sciences, computer science, applied mathemat
CO4: Apply the virtualization techniques for research projects.
CO5: Identify appropriate data visualization techniques given particular requirements imposed by
REFERENCES
1. Matthew Ward, Georges Grinstein and Daniel Keim, “Interactive Data Visualization
Foundations, Techniques, Applications”, 2010.
2. Colin Ware, “Information Visualization Perception for Design”, 4th edition, Morgan
Kaufmann Publishers, 2021.
3. Robert Spence “Information visualization – Design for interaction”, Pearson Education,

4. Alexandru C. Telea, “Data Visualization: Principles and Practice,” A. K. Peters Ltd, 2008.

IF4071 DEEP LEARNING L T P

C
3 0 2 4
COURSE OBJECTIVES:
 Develop and Train Deep Neural Networks.
 Develop a CNN, R-CNN, Fast R-CNN, Faster-R-CNN, Mask-RCNN for
detection and recognition
 Build and train RNNs, work with NLP and Word Embeddings
 The internal structure of LSTM and GRU and the differences between them
 The Auto Encoders for Image Processing

UNIT I DEEP LEARNING CONCEPTS 6

Fundamentals about Deep Learning. Perception Learning Algorithms. Probabilistic
modelling. Early Neural Networks. How Deep Learning different from Machine Learning.
Scalars. Vectors. Matrixes, Higher Dimensional Tensors. Manipulating Tensors. Vector
Data. Time Series Data. Image Data. Video Data.

UNIT II NEURAL NETWORKS 9

About Neural Network. Building Blocks of Neural Network. Optimizers. Activation
Functions. Loss Functions. Data Pre-processing for neural networks, Feature Engineering.
Overfitting and
Underfitting. Hyperparameters.

UNIT III CONVOLUTIONAL NEURAL NETWORK 10

About CNN. Linear Time Invariant. Image Processing Filtering. Building a convolutional
neural network. Input Layers, Convolution Layers. Pooling Layers. Dense Layers.
Backpropagation Through the Convolutional Layer. Filters and Feature Maps.
Backpropagation Through the Pooling Layers. Dropout Layers and Regularization. Batch
Normalization. Various Activation Functions. Various Optimizers. LeNet, AlexNet,
VGG16, ResNet. Transfer Learning with Image Data. Transfer Learning using Inception
Oxford VGG Model, Google Inception Model, Microsoft ResNet Model. R- CNN, Fast R-
CNN, Faster R-CNN, Mask-RCNN, YOLO

UNIT VI NATURAL LANGUAGE PROCESSING USING RNN 10

About NLP & its Toolkits. Language Modeling . Vector Space Model (VSM). Continuous
Bag of Words (CBOW). Skip-Gram Model for Word Embedding. Part of Speech (PoS)
Global Co- occurrence Statistics–based Word Vectors. Transfer Learning. Word2Vec.
Global Vectors for Word Representation GloVe. Backpropagation Through Time.
 BD4151 FOUNDATIONS OF DATA SCIENCE L T P C
3 0 0 3
COURSE OBJECTIVES:
 To apply fundamental algorithms to process data.
Bidirectional
 Learn to apply
RNNs hypotheses
(BRNN) . Long and data
Short into Memory
Term actionable predictions.
(LSTM). Bi-directional LSTM.
Document andModels
Sequence-to-Sequence
 transfer the results
(Seq2Seq). andrecurrent
Gated effectively
unitcommunicate
GRU. the findings
using visualization techniques.
UNIT V DEEP To learn statistical methods
REINFORCEMENT and machine LEARNING
& UNSUPERVISED learning algorithms required for Data 10
Science.
About Deep Reinforcement Learning. Q-Learning. Deep Q-Network (DQN). Policy
 To develop the fundamental knowledge and understand concepts to become a
Gradient Methods. Actor-Critic Algorithm. About Autoencoding. Convolutional Auto
data science professional.
Encoding. Variational Auto Encoding. Generative Adversarial Networks. Autoencoders
for UNIT
Feature
I Extraction. Auto Encoders
INTRODUCTION TOfor Classification.
DATA SCIENCE Denoising Autoencoders. 9
Sparse
Data Autoencoders
science process – roles, stages in data science project – working with
data from files – working with relational databases – exploring data – managing
LIST OF EXPERIMENTS: 30
data – cleaning and sampling for modeling and validation – introduction to
1. Feature Selection from Video and Image Data
NoSQL.
2. Image and video recognition
UNIT II
3. Image MODELING METHODS
Colorization 9
Choosing and evaluating
4. Aspect Oriented models &– Sentiment
Topic Detection mapping Analysis
problems to machine learning,
evaluating clusteringusing
5. Object Detection models, validating models – cluster analysis – K-means
Autoencoder
algorithm, Naïve Bayes – Memorization Methods – Linear and logistic regression
– unsupervised
COURSE OUTCOMES:methods.
CO1: Feature Extraction from Image and Video Data
UNIT III INTRODUCTION TO R 9
CO2: Implement Image Segmentation and Instance Segmentation in Images
Reading and getting data into R – ordered and unordered factors – arrays and
CO3: Implement image recognition and image classification using a pretrained network
matrices – lists and data frames – reading data from files – probability
(Transfer Learning)
distributions – statistical models in R - manipulating objects – data
CO4: Traffic Information analysis using Twitter Data
distribution.
CO5: Autoencoder for Classification & Feature Extraction
UNIT IV MAP REDUCE TOTAL : 45+30=75 PERIODS9
Introduction – distributed file system – algorithms using map reduce, Matrix-
REFERENCES
Vector
1. DeepMultiplication by Map Reduce
Learning A Practitioner’s – Hadoop
Approach - Understanding
Josh Patterson and Adam the Map
Gibson Reduce
O’Reilly
architecture - Writing Hadoop MapReduce Programs - Loading data into HDFS -
Media, Inc.2017
Executing
2. Learn Keras the Map phase
for Deep - Shuffling
Neural and Jojo
Networks, sorting - Reducing
Moolayil, phase execution.
Apress,2018
3. Deep
UNIT V Learning Projects
DATA Using TensorFlow 2, Vinita Silaparasetty, Apress, 2020
VISUALIZATION 9
4. Deep Learning with Python, FRANÇOIS CHOLLET, MANNING SHELTER ISLAND,2017
Documentation and deployment – producing effective presentations – Introduction
5. graphical
to Pro Deep Learning with TensorFlow, Santanu Pattanayak, Apress,2017
analysis – plot() function – displaying multivariate data – matrix plots – multiple
s

plots in one
window - exporting graph using graphics parameters - Case studies.

TOTAL : 45 PERIODS
COURSE OUTCOMES:
CO1: Obtain, clean/process and transform data.
CO2: Analyze and interpret data using an ethically responsible approach.
CO3: Use appropriate models of analysis, assess the quality of input, derive
insight from results, and investigate potential issues.
CO4: Apply computing theory, languages and algorithms, as well as
mathematical and statistical models, and the principles of optimization to
appropriately formulate and use data analyses.
CO5: Formulate and use appropriate models of data analysis to solve business-
related challenges.

REFERENCES:
1. Nina Zumel, John Mount, “Practical Data Science with R”, Manning Publications,
2014.
2. Mark Gardener, “Beginning R - The Statistical Programming Language”,
John Wiley &
Sons, Inc., 2012.