SAVITRIBAI PHULE PUNE UNIVERSITY

A PROJECT REPORT ON

Deep Learning Powered Electric Vision

System for Predictive Acquisition and
Optimization

SUBMITTED TOWARDS THE

PARTIAL FULFILLMENT OF THE REQUIREMENTS OF

BACHELOR OF ENGINEERING (Artificial

Intelligence and Data Science Engineering)
BY
Santosh Narwad Exam No: B1902402110
Aditya Rasal Exam No: B1902402143
Vinay More Exam No: B1902402104
Gurukul More Exam No: B1902402066

Under The Guidance of

Prof. Jyotsna Barpute

Department of Artificial Intelligence and Data Science

Engineering

DR.D.Y.PATIL INSTITUTE OF TECHNOLOGY

PIMPRI, PUNE
A.Y 2024-2025

1
 DR.D.Y.PATIL INSTITUTE OF TECHNOLOGY
Department of AI and DS Engineering

CERTIFICATE

This is to certify that the Project Entitled

Deep Learning Powered Electric Vision System for Pre-

dictive Acquisition and Optimization
Submitted by
Santosh Narwad Exam No:B1902402110
Aditya Rasal Exam No:B1902402143
Viniay More Exam No:B1902402104
Gurukul More Exam No:B1902402066
is a bonafide work carried out by Students under the supervision of Prof.
Jyotsna Barpute and it is submitted towards the partial fulfillment of the
requirement of Bachelor of Engineering (Artificial Intelligence and Data Sci-
ence Engineering).

Prof. Jyotsan Barpute Dr. Mithra Venkatesan

Internal Guide H.O.D
Dept. of AI and DS Dept. of AI and DS
Dr. Lalit Wadhwa
Principal
DIT,Pimpri

Signature of Project co-ordinator Signature of External Examiner

2
 PROJECT APPROVAL SHEET

Deep Learning Powered Electric Vision System for Predictive Acquisition

and Optimization

Is successfully completed by

Santosh Narwad Exam No:B1902402110

Aditya Rasal Exam No:B1902402143
Vinay More Exam No:B1902402104
Gurukul More Exam No:B1902402066

at

DEPARTMENT OF ARTIFICIAL INTELLIGENCE AND DATA

SCIENCE

Dr.D.Y.PATIL INSTITUTE OF TECHNOLOGY

SAVITRIBAI PHULE PUNE UNIVERSITY,PUNE

ACADEMIC YEAR 2024-2025

Prof. Jyotsna Barpute Dr. Mithra Venkatesan

Internal Guide H.O.D
Dept. of AI and DS Dept. of AI and DS

3
 Abstract

This paper surveys the recent advancements in electric vision systems for
predictive acquisition and optimization, with a focus on deep learning tech-
niques. We examine the design and implementation of a system that utilizes
the ESP8266 microcontroller, PZEM 004T sensor, and a light sensor for
real-time electricity monitoring. The backend is powered by Python and
deep learning models that forecast electricity usage, while a frontend inter-
face in ReactJS provides users with predictive insights. The system leverages
large language models (LLMs) to generate optimization reports, suggesting
methods to reduce energy consumption. This survey highlights the current
state-of-the-art, identifies existing gaps, and presents a case study of the
proposed system’s application. Keywords: Deep Learning, Electric Vision
Systems, Predictive Acquisition, Energy Optimization, ESP8266, MongoDB

1
 Acknowledgments

Please Write here Acknowledgment.Example given as

It gives us great pleasure in presenting the preliminary project report on
‘Deep Learning Powered Electric Vision System for Predictive
Acquisition and Optimization ’.

I would like to take this opportunity to thank my internal guide Prof. Jyot-
sna Barpute for giving me all the help and guidance I needed. I am really
grateful to them for their kind support. Their valuable suggestions were very
helpful.

I am also grateful to Prof. Mithra Venkatesan Head of AI and DS Engi-

neering Department, CollegeName for his indispensable support, suggestions.

In the end our special thanks to Prof. Vidya Vasekar for providing various
resources such as laboratory with all needed software platforms, continuous
Internet connection, for Our Project.

Santosh Narwad
Aditya Rasal
Vinay More
Gurukul More
(B.E. AI and DS Engg.)

2
Contents

1 Synopsis 8
1.1 Project Title . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
1.2 Project Option . . . . . . . . . . . . . . . . . . . . . . . . . 8
1.3 Internal Guide . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
1.4 Sponsorship and External Guide . . . . . . . . . . . . . . . . 8
1.5 Technical Keywords (As per ACM Keywords) . . . . . . . . . 8
1.6 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . 9
1.7 Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
1.8 Goals and Objectives . . . . . . . . . . . . . . . . . . . . . . . 10
1.9 Key Features and Innovations: . . . . . . . . . . . . . . . . . . 10
1.10 Tools, Technologies, and Platforms: . . . . . . . . . . . . . . . 11
1.11 Relevant mathematics associated with the Project . . . . . . . 11
1.12 Names of Conferences / Journals where papers can be published 12
1.13 Review of Conference/Journal Papers supporting Project idea 13
1.14 Plan of Project Execution . . . . . . . . . . . . . . . . . . . . 13

2 Technical Keywords 14
2.1 Area of Project . . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.2 Technical Keywords . . . . . . . . . . . . . . . . . . . . . . . . 14

3 Introduction 15
3.1 Project Idea . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.2 Motivation of the Project . . . . . . . . . . . . . . . . . . . . 15
3.3 Literature Survey . . . . . . . . . . . . . . . . . . . . . . . . . 16
3.4 Review of the papers . . . . . . . . . . . . . . . . . . . . . . . 16
3.5 Mathematical Terms . . . . . . . . . . . . . . . . . . . . . . . 16

4 Problem Definition and scope 18

4.1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . 18
4.1.1 Goals and objectives . . . . . . . . . . . . . . . . . . . 18
4.1.2 Statement of scope . . . . . . . . . . . . . . . . . . . . 19

3
 4.2 Major Constraints . . . . . . . . . . . . . . . . . . . . . . . . 19
4.3 Methodologies of Problem solving and efficiency issues . . . . 20
4.4 Outcome . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
4.5 Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
4.6 Hardware Resources Required . . . . . . . . . . . . . . . . . . 22
4.7 Software Resources Required . . . . . . . . . . . . . . . . . . . 22

5 Project Plan 23
5.1 Project Estimates . . . . . . . . . . . . . . . . . . . . . . . . . 23
5.1.1 Personnel Costs: . . . . . . . . . . . . . . . . . . . . . 23
5.1.2 Project Resources . . . . . . . . . . . . . . . . . . . . . 23
5.2 Risk Management w.r.t. NP Hard analysis . . . . . . . . . . . 24
5.2.1 Risk Identification . . . . . . . . . . . . . . . . . . . . 24
5.2.2 Risk Analysis . . . . . . . . . . . . . . . . . . . . . . . 24
5.2.3 Overview of Risk Mitigation, Monitoring, Management 26
5.3 Project Schedule . . . . . . . . . . . . . . . . . . . . . . . . . 27
5.3.1 Project task set . . . . . . . . . . . . . . . . . . . . . . 27
5.3.2 Task network . . . . . . . . . . . . . . . . . . . . . . . 27
5.3.3 Timeline Chart . . . . . . . . . . . . . . . . . . . . . . 28
5.4 Team Organization . . . . . . . . . . . . . . . . . . . . . . . . 28
5.4.1 Team structure . . . . . . . . . . . . . . . . . . . . . . 28
5.4.2 Management reporting and communication . . . . . . . 28

6 Software requirement specification 30

6.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
6.1.1 Purpose and Scope of Document . . . . . . . . . . . . 30
6.1.2 Overview of responsibilities of Developer . . . . . . . . 30
6.2 Usage Scenario . . . . . . . . . . . . . . . . . . . . . . . . . . 31
6.2.1 User profiles . . . . . . . . . . . . . . . . . . . . . . . . 31
6.2.2 Use-cases . . . . . . . . . . . . . . . . . . . . . . . . . 31
6.2.3 Use Case View . . . . . . . . . . . . . . . . . . . . . . 31
6.3 Data Model and Description . . . . . . . . . . . . . . . . . . . 31
6.3.1 Data Description . . . . . . . . . . . . . . . . . . . . . 31
6.3.2 Data objects and Relationships . . . . . . . . . . . . . 32
6.4 Functional Model and Description . . . . . . . . . . . . . . . . 33
6.4.1 Data Flow Diagram . . . . . . . . . . . . . . . . . . . . 33
6.4.2 Activity Diagram: . . . . . . . . . . . . . . . . . . . . . 34
6.4.3 Non Functional Requirements: . . . . . . . . . . . . . . 34
6.4.4 State Diagram: . . . . . . . . . . . . . . . . . . . . . . 34
6.4.5 Design Constraints . . . . . . . . . . . . . . . . . . . . 35
6.4.6 Software Interface Description . . . . . . . . . . . . . . 36

4
7 Detailed Design Document using Appendix A and B 37
7.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
7.2 Architectural Design . . . . . . . . . . . . . . . . . . . . . . . 37
7.3 Data design (using Appendices A and B) . . . . . . . . . . . . 37
7.3.1 Internal software data structure . . . . . . . . . . . . . 38
7.3.2 Global data structure . . . . . . . . . . . . . . . . . . . 38
7.3.3 Temporary data structure . . . . . . . . . . . . . . . . 38
7.3.4 Database description . . . . . . . . . . . . . . . . . . . 39
7.4 Compoent Design . . . . . . . . . . . . . . . . . . . . . . . . . 39
7.4.1 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . 39

8 References 41

Annexure A References 42

Annexure B Laboratory assignments on Project Analysis of Al-

gorithmic Design 44

Annexure C Laboratory assignments on Project Quality and

Reliability Testing of Project Design 45

Annexure D Project Planner 46

Annexure E Reviewers Comments of Paper Submitted 47

Annexure F Plagiarism Report 48

Annexure G Term-II Project Laboratory Assignments 49

Annexure H Information of Project Group Members 50

5
List of Figures

6.1 Use case diagram . . . . . . . . . . . . . . . . . . . . . . . . . 32

6.2 State transition diagram . . . . . . . . . . . . . . . . . . . . . 36

7.1 Architecture diagram . . . . . . . . . . . . . . . . . . . . . . . 38

7.2 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . 40

6
List of Tables

4.1 Hardware Requirements . . . . . . . . . . . . . . . . . . . . . 22

5.1 Risk Table . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25

5.2 Risk Probability definitions [?] . . . . . . . . . . . . . . . . . . 25
5.3 Risk Impact definitions [?] . . . . . . . . . . . . . . . . . . . . 25

6.1 Use Cases . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31

B.1 IDEA Matrix . . . . . . . . . . . . . . . . . . . . . . . . . . . 44

7
Chapter 1

Synopsis

1.1 Project Title

Deep Learning Powered Electric Vision System for Predictive Acquisition
and Optimization

1.2 Project Option

Internal Project

1.3 Internal Guide

Prof. Jyotsna Barpute

1.4 Sponsorship and External Guide

Not Applicable

1.5 Technical Keywords (As per ACM Key-

words)
Please note ACM Keywords can be found : http://www.acm.org/about/class/ccs98-
html
Example is given as

1. C. Computer Systems Organization

8
 (a) C.2 COMPUTER-COMMUNICATION NETWORKS
i. C.2.4 Distributed Systems
A. Client/server
B. Distributed applications
C. Distributed databases
D. Network operating systems
E. Distributed file systems
F. Security and reliability issues in distributed applications

1.6 Problem Statement

The rising demand for energy-efficient systems has placed an emphasis on
optimizing electricity usage in residential and industrial settings. Predictive
analytics, empowered by deep learning, provides a promising avenue for im-
proving energy management. Traditional energy monitoring systems fail to
provide predictive capabilities, limiting their use fulness in preventing waste-
ful consumption or optimizing for cost-efficiency. This paper explores the in-
tegration of electric vision systems with predictive acquisition through deep
learning. We survey similar systems and discuss the unique contributions of
the Deep Learning Powered Electric Vision System, which combines hard-
ware like the ESP8266 microcontroller and PZEM 004T sensor with software
solutions for real-time electricity monitoring and predictive insights. The
system also generates customized optimization reports using large language
models (LLMs).

1.7 Abstract
• This paper surveys the recent advancements in electric vision systems
for predictive acquisition and optimization, with a focus on deep learn-
ing techniques. We examine the design and implementation of a sys-
tem that utilizes the ESP8266 microcontroller, PZEM 004T sensor,
and a light sensor for real-time electricity monitoring. The backend is
powered by Python and deep learning models that forecast electricity
usage, while a frontend interface in ReactJS provides users with pre-
dictive insights. The system leverages large language models (LLMs)
to generate optimization reports, suggesting methods to reduce energy
consumption. This survey highlights the current state-of-the-art, iden-
tifies existing gaps, and presents a case study of the proposed system’s

9
 application. Keywords: Deep Learning, Electric Vision Systems, Pre-
dictive Acquisition, Energy Optimization, ESP8266, MongoDB

1.8 Goals and Objectives

• The primary objective of this project is to develop a predictive elec-
tric vision system that integrates hardware components such as the
ESP8266 microcontroller and PZEM 004T sensor with deep learning
models for real-time electricity monitoring and forecasting. The system
aims to provide accurate predictions of electricity consumption, opti-
mize energy usage, and generate personalized optimization reports us-
ing Large Language Models (LLMs). Additionally, the project seeks to
enhance user experience through a ReactJS-based interface that offers
actionable insights into energy consumption patterns. The ultimate
goal is to reduce energy costs, improve the accuracy of consumption
forecasts, and expand the system’s capabilities by incorporating more
sensors and refining predictive models for long-term efficiency.

1.9 Key Features and Innovations:

• Real-time Electricity Monitoring: The system continuously tracks
electricity usage using sensors for voltage, current, and power consump-
tion.

• Deep Learning for Prediction: Utilizes neural network models to

predict future electricity consumption based on historical data.

• Energy Optimization Reports: Integrates LLMs to generate tai-

lored reports with suggestions to reduce electricity usage.

• Hardware-Software Integration: Seamless connection between hard-

ware (ESP8266, PZEM 004T) and cloud-based software for real-time
data processing and storage.

• User-friendly Interface: ReactJS-based web interface that displays

real-time and predictive energy insights, offering users an intuitive ex-
perience.

10
1.10 Tools, Technologies, and Platforms:
• Hardware: ESP8266 Microcontroller for data collection and wireless
communication. PZEM 004T sensor for measuring electricity param-
eters (voltage, current, power). Light Sensor for automating lighting
control.

• Software:

• Frontend: ReactJS for building the web-based user interface.

• Backend: Python for handling data processing and deep learning

model integration.

• Cloud Database: MongoDB for storing historical electricity data.

• Deep Learning:Neural networks for electricity consumption predic-

tion.

• APIs and LLMs:Large Language Models (LLMs) for generating op-

timization reports (using tools like Ollama or similar free APIs).

1.11 Relevant mathematics associated with

the Project
System Description:

• Input: Real-Time Electricity Data and Light Sensor Data,Historical

Electricity Data.

• Output:Electricity Usage Predictions,Optimization Reports and User

Interface.

• Identify data structures: Data Structures:

• Arrays/Lists for storing sensor readings and historical data.

• Dictionaries for mapping sensor data to timestamps.

• DataFrames (from libraries like pandas) for efficient manipulation of

electricity data.

• Classes:

11
 • SensorData: A class representing data from the ESP8266 microcon-
troller and PZEM 004T sensor.
• PredictionModel: A class that encapsulates the deep learning model
used for electricity forecasting.
• ReportGenerator: A class that uses LLMs to create optimization re-
ports.
• Mathematical formulation if possible
• Success Conditions:
• High Predictive Accuracy: The deep learning model achieves a low
MAE (e.g., below 5
• Energy Reduction: Users observe tangible reductions in electricity bills
(e.g., 10
• Seamless System Performance: Real-time data collection, processing,
and report generation without significant delays or failures.
• Failure Conditions:
• Prediction Model Underperformance: The model fails to achieve high
accuracy (e.g., MAE ¿ 5
• Data Loss or Communication Failures: Disruptions in data transmis-
sion from the hardware (e.g., ESP8266 or sensors) or failure in cloud
storage (MongoDB) can hinder system performance.
• Incorrect Optimization Suggestions: If the LLM-generated reports do
not offer actionable or practical advice, users may fail to reduce energy
consumption effectively.

1.12 Names of Conferences / Journals where

papers can be published
• IEEE/ACM Conference/Journal 1
• Conferences/workshops in IITs
• Central Universities or SPPU Conferences
• IEEE/ACM Conference/Journal 2

12
1.13 Review of Conference/Journal Papers sup-
porting Project idea
Atleast 10 papers + White papers or web references
Brief literature survey [ Description containing important description of at
least 10 papers

1.14 Plan of Project Execution

Using planner or alike project management tool.

13
Chapter 2

Technical Keywords

2.1 Area of Project

Project Area In the modern context of energy management, optimizing elec-
tricity usage through predictive systems has become essential. This project
focuses on developing a Predictive Electric Vision System, leveraging deep
learning techniques to analyze and optimize energy consumption in real time.
By integrating IoT components (like the ESP8266 microcontroller and PZEM
004T sensor) with advanced deep learning algorithms, this system gathers
and interprets power consumption data for residential and industrial appli-
cations.

2.2 Technical Keywords

Please note ACM Keywords can be found : http://www.acm.org/about/class/ccs98-
html
Example is given as

1. (a) i. A. Deep Learning

B. Predictive Analytics
C. ESP8266 Microcontroller
D. Internet of Things (IoT)
E. Large Language Models (LLMs)
F. MongoDB Database

14
Chapter 3

Introduction

3.1 Project Idea

• This project aims to develop an intelligent energy management system
that uses deep learning and IoT technology to optimize power con-
sumption in residential and industrial settings. By integrating sensors
with the ESP8266 microcontroller, the system gathers real-time data
on energy usage, which is stored in a MongoDB database for anal-
ysis. Advanced predictive models then analyze this data to forecast
consumption patterns and provide actionable insights for energy opti-
mization. A user-friendly interface allows users to monitor and con-
trol energy usage in real time, while a Large Language Model (LLM)
generates easy-to-understand recommendations, helping users make in-
formed decisions to reduce energy costs and enhance sustainability.

3.2 Motivation of the Project

• The motivation behind this project stems from the growing need for ef-
ficient energy management in today’s technology-driven world. As both
residential and industrial sectors face rising energy costs and environ-
mental concerns, optimizing power consumption has become critical for
cost savings and sustainable practices. Traditional energy monitoring
systems lack the intelligence to predict usage patterns or provide ac-
tionable insights, limiting their effectiveness. By leveraging advanced
deep learning algorithms and IoT-enabled real-time data collection, this
project aims to empower users with a smarter, proactive approach to
energy management. Through predictive analytics and intuitive rec-
ommendations, this system offers a comprehensive solution to reduce

15
 waste, lower costs, and contribute to a more sustainable future.

3.3 Literature Survey

•

3.4 Review of the papers

• The existing literature on energy management through predictive sys-
tems focuses on the integration of IoT and machine learning for real-
time monitoring and optimization. Several studies have employed tra-
ditional hardware such as Arduino and Raspberry Pi combined with
basic energy-monitoring sensors to gather and analyze consumption
data. However, these conventional systems often lack predictive capa-
bilities, limiting their effectiveness to retrospective analysis. With the
rise of Artificial Neural Networks (ANNs) and Recurrent Neural Net-
works (RNNs), predictive analytics in energy management has gained
traction, offering improved accuracy in capturing non-linear consump-
tion patterns. Some recent works also explore the use of Large Lan-
guage Models (LLMs) to generate optimization suggestions, but this is
still a relatively novel area in energy research.

3.5 Mathematical Terms

• Mean Absolute Error (MAE): A key metric for evaluating the accuracy
of predictive models. MAE is calculated as:
M AE=n1
MAE = 1 =1
i=1 n y i y
y
i where y i represents the actual energy consumption and
i denotes the predicted consumption. Lower MAE values indicate higher
accuracy in the model’s predictions.
Artificial Neural Networks (ANNs): An ANN model with layers of neurons
used for energy consumption prediction. The model maps inputs X (histori-
cal energy data) to outputs Y (predicted future consumption) by optimizing
weights and biases through backpropagation.
Recurrent Neural Networks (RNNs): A type of neural network ideal for time-
series data, where the model processes sequential information. The RNN is

16
designed to capture temporal dependencies in energy consumption patterns,
with output at time t, h t , defined as:
= ( 1+ + ) h t =f(W h h t1 +W x x t +b) where W h and
W x are weight matrices, 1 h t1 is the previous hidden state, x t is the
input, and b is the bias term.
Time-Series Forecasting: Uses historical energy data points to predict future
values. Commonly involves the mathematical function:
= ( 1 , 2 , ... , ) y t =f(y t1 ,y t2 ,. . . ,y tn ) which uses past
energy values to predict current and future consumption.
This literature survey highlights the evolution of energy monitoring systems
and the mathematical foundation behind predictive analytics, underscoring
the importance of precision in predictive models for effective energy manage-
ment.

17
Chapter 4

Problem Definition and scope

4.1 Problem Statement

With the rising demand for energy efficiency across residential and indus-
trial sectors, current energy management systems fall short in providing real-
time insights, predictive analysis, and actionable recommendations. Tradi-
tional monitoring solutions primarily offer retrospective data analysis with-
out proactive energy optimization capabilities. This project aims to address
these limitations by developing a smart energy management system that com-
bines IoT-enabled hardware and advanced deep learning algorithms. The
system will provide users with real-time energy monitoring, accurate con-
sumption predictions, and customized suggestions for energy optimization,
contributing to both cost savings and sustainable energy practices.

4.1.1 Goals and objectives

Goal and Objectives:
• To develop an intelligent energy management system that provides
real-time monitoring, predictive analytics, and actionable insights to
enhance energy efficiency. To bridge the gap between traditional en-
ergy monitoring and proactive energy optimization by integrating IoT
technology with advanced deep learning algorithms.
• To accurately predict energy consumption patterns using deep learning
models, enabling users to make informed decisions and reduce unneces-
sary energy usage. To create a user-friendly interface that allows users
to monitor real-time energy data, receive optimization recommenda-
tions, and control connected appliances remotely for efficient energy
management.

18
4.1.2 Statement of scope
• This project focuses on designing a comprehensive energy management
system capable of real-time monitoring, predictive analytics, and opti-
mization for both residential and industrial energy use. The system will
integrate IoT-enabled hardware, such as the ESP8266 microcontroller
and energy-monitoring sensors, to collect real-time data on power con-
sumption. Using deep learning models, the system will analyze histori-
cal and live data to predict future energy usage patterns. Additionally,
a Large Language Model (LLM) will be employed to generate person-
alized recommendations for reducing energy waste. The system will
feature an intuitive, web-based interface that allows users to view en-
ergy consumption trends, generate optimization reports, and control
connected devices remotely.

4.2 Major Constraints

• Hardware Constraints:
Limited computational resources of the microcontroller (ESP8266) used
for data acquisition and communication. Potential challenges in seam-
lessly integrating multiple sensors and ensuring reliable data collection.
Potential issues with power consumption and battery life for the IoT-
based monitoring system.
• Connectivity and Reliability Concerns:
Dependence on stable network connectivity for cloud-based data stor-
age and processing. Potential vulnerabilities to connectivity issues and
security risks in an IoT-based system. Ensuring reliable data transmis-
sion and storage, even in the event of network disruptions.
• Data Management and Computational Complexity:
Handling and storing large volumes of historical energy consumption
data in the MongoDB database. Balancing the trade-off between data
granularity, storage requirements, and computational resources for the
deep learning models. Ensuring the scalability of the backend frame-
work to accommodate growing data and user demands.
• Predictive Model Limitations:
Achieving high accuracy in energy consumption forecasting, especially
for complex, non-linear consumption patterns. Overcoming the chal-
lenges of training deep learning models, such as the need for extensive

19
 historical data and computational resources. Ensuring the adaptabil-
ity of the predictive models to handle changes in user behavior and
appliance usage over time.

• User Experience and Accessibility:

Designing an intuitive and user-friendly web-based interface for real-
time monitoring, optimization reporting, and appliance control. Ensur-
ing the optimization recommendations generated by the large language
model (LLM) are easily understandable and actionable for end-users.
Addressing the potential for user resistance or lack of engagement due
to the technical complexity of the system.

4.3 Methodologies of Problem solving and ef-

ficiency issues
• Hardware Design and Integration:
Carefully select the microcontroller (ESP8266) and sensors (PZEM
004T) to balance computational power, energy efficiency, and data col-
lection capabilities. Optimize the hardware configuration to minimize
power consumption and ensure reliable long-term operation. Imple-
ment efficient data acquisition and communication protocols between
the hardware components and the backend system.

• Data Management and Storage:

Utilize a scalable and efficient database solution, such as MongoDB,
to handle the growing volume of energy consumption data. Imple-
ment data partitioning, indexing, and other optimization techniques
to ensure fast retrieval and querying of historical data. Explore data
compression or aggregation strategies to reduce storage requirements
without sacrificing the granularity of the data.

• Distributed Processing Architecture:

Leverage the distributed nature of the system by offloading compu-
tationally intensive tasks, such as machine learning model training,
to the backend server. Implement efficient data streaming and asyn-
chronous processing mechanisms to minimize latency between data col-
lection, analysis, and optimization recommendations. Explore the use
of serverless computing or edge computing approaches to further opti-
mize resource utilization and responsiveness.

20
 • Predictive Model Optimization:
Carefully select and fine-tune the deep learning models (e.g., ANNs,
RNNs) to maximize prediction accuracy while minimizing computa-
tional requirements. Investigate techniques like transfer learning, model
pruning, or quantization to reduce the model size and inference time
without significantly impacting performance. Continuously monitor
and update the predictive models to adapt to changes in user behavior
and energy consumption patterns.

• Intelligent Optimization Strategies:

Leverage the capabilities of the large language model (LLM) to gen-
erate personalized, natural language-based optimization reports and
recommendations. Explore ways to further enhance the LLM’s un-
derstanding of the user’s context and preferences to provide more tai-
lored and actionable insights. Investigate the integration of the LLM
with other decision-making algorithms or rule-based systems to create
a more comprehensive optimization framework.

• User Interface and Interaction Design:

Prioritize the development of a user-friendly and intuitive web-based in-
terface for real-time monitoring, optimization reporting, and appliance
control. Incorporate principles of responsive design and accessibility
to ensure the system is usable across various devices and user demo-
graphics. Gather user feedback and iteratively improve the interface to
enhance the overall user experience and engagement.

4.4 Outcome
• The outcome of this project will be a robust, intelligent energy man-
agement system that enables users to monitor, predict, and optimize
their energy consumption effectively. Through the integration of IoT-
enabled sensors and advanced deep learning models, the system will
provide accurate, real-time insights into energy usage patterns, helping
users make informed decisions to reduce costs and enhance efficiency.
Users will benefit from a user-friendly interface that offers detailed opti-
mization reports and actionable recommendations generated by a Large
Language Model (LLM), empowering them to proactively manage en-
ergy consumption and contribute to sustainable energy practices.

21
4.5 Applications
• Smart Homes: Enables homeowners to monitor and optimize energy
usage, reducing electricity bills and promoting sustainable practices.

• Industrial Energy Management: Helps industries analyze energy pat-

terns, predict peak usage, and implement cost-saving optimizations.

• Commercial Buildings: Allows facility managers in offices and malls to

monitor real-time energy use, reducing waste and improving efficiency.

• Smart City Infrastructure: Supports urban sustainability by managing

energy consumption across public infrastructure like streetlights and
buildings.

• Renewable Energy Systems: Optimizes energy storage and distribution

in renewable energy setups, balancing demand with efficient energy
production.

4.6 Hardware Resources Required

Sr. No. Parameter Minimum Requirement Justification

1 CPU Speed 2 GHz Remark Required
2 RAM 3 GB Remark Required

Table 4.1: Hardware Requirements

4.7 Software Resources Required

Platform :

1. Operating System: Linux or Windows

2. IDE: Tools like PyCharm or Visual Studio Code for development.

3. Programming Language : Python, due to its extensive support for

machine learning and deep learning libraries.

22
Chapter 5

Project Plan

5.1 Project Estimates

Use Waterfall model and associated streams derived from assignments 1,2,
3, 4 and 5( Annex A and B) for estimation.

5.1.1 Personnel Costs:

Estimate based on the hourly rate and projected hours for developers, data
scientists, and engineers involved in the project.

5.1.1.1 Hardware Costs:

Include expenses for IoT devices (e.g., ESP8266 microcontrollers, sensors),
servers, and any necessary networking equipment.

5.1.1.2 Software Costs:

Account for any licensed software, cloud storage, computational resources,
and subscription fees for analytical tools.

5.1.1.3 Miscellaneous Costs:

Cover additional expenses such as travel, office supplies, maintenance, or
unforeseen project-related expenses.

5.1.2 Project Resources

Project resources [People, Hardware, Software, Tools and other resources]
based on Memory Sharing, IPC, and Concurrency derived using appendices

23
to be referred.

5.2 Risk Management w.r.t. NP Hard anal-

ysis
This section discusses Project risks and the approach to managing them.

5.2.1 Risk Identification

For risks identification, review of scope document, requirements specifications
and schedule is done. Answers to questionnaire revealed some risks. Each
risk is categorized as per the categories mentioned in [?]. Please refer table 5.1
for all the risks. You can refereed following risk identification questionnaire.

1. Have top software and customer managers formally committed to sup-

port the project?

2. Are end-users enthusiastically committed to the project and the sys-

tem/product to be built?

3. Are requirements fully understood by the software engineering team

and its customers?

4. Have customers been involved fully in the definition of requirements?

5. Do end-users have realistic expectations?

6. Does the software engineering team have the right mix of skills?

7. Are project requirements stable?

8. Is the number of people on the project team adequate to do the job?

9. Do all customer/user constituencies agree on the importance of the

project and on the requirements for the system/product to be built?

5.2.2 Risk Analysis

The risks for the Project can be analyzed within the constraints of time and
quality

24
 Impact
ID Risk Description Probability
Schedule Quality Overall
1 Description 1 Low Low High High
2 Description 2 Low Low High High

Table 5.1: Risk Table

Probability Value Description

High Probability of occurrence is > 75%
Medium Probability of occurrence is 26 − 75%
Low Probability of occurrence is < 25%

Table 5.2: Risk Probability definitions [?]

Impact Value Description

Very high > 10% Schedule impact or Unacceptable quality
High 5 − 10% Schedule impact or Some parts of the project have
low quality
Medium < 5% Schedule impact or Barely noticeable degradation
in quality Low Impact on schedule or Quality can
be incorporated

Table 5.3: Risk Impact definitions [?]

25
5.2.3 Overview of Risk Mitigation, Monitoring, Man-
agement
Following are the details for each risk.

Risk ID 1
Risk Description Description 1
Category Development Environment.
Source Software requirement Specification document.
Probability Low
Impact High
Response Mitigate
Strategy Strategy
Risk Status Occurred

Risk ID 2
Risk Description Description 2
Category Requirements
Source Software Design Specification documentation review.
Probability Low
Impact High
Response Mitigate
Strategy Better testing will resolve this issue.
Risk Status Identified

26
 Risk ID 3
Risk Description Description 3
Category Technology
Source This was identified during early development and test-
ing.
Probability Low
Impact Very High
Response Accept
Strategy Example Running Service Registry behind proxy bal-
ancer
Risk Status Identified

5.3 Project Schedule

5.3.1 Project task set
Major Tasks in the Project stages are:

• Task 1: Requirements Gathering Conduct meetings with stakehold-

ers to finalize requirements.

• Task 2: : Data Collection and Preprocessing Gather data from

various sources and perform necessary preprocessing steps

• Task 3: Model Development Design and implement deep learn-

ing models tailored to Predictive Electric Vision Systems for Energy
Optimization.

• Task 4: Model Training and Validation Train models on prepro-

cessed data and validate their performance using metrics.

• Task 5: Deployment and Testing Deploy the trained model and

conduct testing in a real-world scenario.

5.3.2 Task network

• Task 1 (Requirements Gathering) →

27
• Task 2 (Data Collection and Preprocessing) →
• Task 3 (Model Development) →
• Task 4 (Model Training and Validation) →
• Task 5 (Deployment and Testing )→

5.3.3 Timeline Chart

A project timeline chart is presented. This may include a time line for the
entire project. Above points should be covered in Project Planner as Annex
C and you can mention here Please refer Annex C for the planner

5.4 Team Organization

The manner in which staff is organized and the mechanisms for reporting are
noted.

5.4.1 Team structure

The team structure for the project is identified. Roles are defined.
• Project Manager Responsible for overall project coordination, resource
allocation, and stakeholder communication.
• Data Scientists (2) Focus on data analysis, model development, and
performance evaluation.
• Software Developer Handles implementation, integration, and deploy-
ment of the application.

5.4.2 Management reporting and communication

Mechanisms for progress reporting and inter/intra team communication are
identified as per assessment sheet and lab time table.
Weekly Status Meetings Team members will report on progress, chal-
lenges, and next steps.
• Progress Reports Monthly reports will be generated and shared with
stakeholders.
• Project Management Tool (e.g., Jira) Tasks, progress, and deadlines
will be tracked in a centralized tool to enhance transparency.
• Communication Channels Regular updates via email, and instant

28
messaging platforms (e.g., Slack) for quick communication among team
members.

29
Chapter 6

Software requirement
specification

6.1 Introduction
6.1.1 Purpose and Scope of Document
The purpose of this document is to detail the design and development of a
Predictive Electric Vision System that leverages Deep Learning and IoT tech-
nologies for energy consumption monitoring, prediction, and optimization.
This system aims to address the limitations of traditional energy monitoring
systems by providing real-time insights, predictive analytics, and actionable
recommendations to reduce energy usage and costs.

6.1.2 Overview of responsibilities of Developer

Set up and configure IoT sensors (e.g., PZEM 004T) and microcontrollers
(e.g., ESP8266) to collect real-time energy data.
Conduct testing and debugging on hardware setups to ensure accurate data
acquisition and device compatibility.
Implement and manage the backend infrastructure using technologies like
Flask and MongoDB.
Create API endpoints for seamless data exchange between the hardware and
frontend, ensuring real-time processing and data retrieval. Develop deep
learning models to analyze historical data, predict future
energy consumption, and improve system accuracy. Integrate the Large Lan-
guage Model (LLM) to provide natural language processing capabilities, de-
livering optimization insights in an accessible, user-friendly format.

30
Develop a responsive and intuitive web interface, allowing users to monitor
real-time energy usage and control appliances. Implement regular updates
and improvements to enhance model accuracy, UI/UX, and system resilience.
Create comprehensive end-user documentation for system operation, main-
tenance, and troubleshooting.

6.2 Usage Scenario

This section provides various usage scenarios for the system to be developed.

6.2.1 User profiles

The profiles of all user categories are described here.(Actors and their De-
scription)

6.2.2 Use-cases
All use-cases for the software are presented. Description of all main Use cases
using use case template is to be provided.

Sr No. Use Case Description Actors Assumptions

1 Use Case 1 Description Actors Assumption

Table 6.1: Use Cases

6.2.3 Use Case View

Use Case Diagram. Example is given below

6.3 Data Model and Description

6.3.1 Data Description
The User entity stores user information, including authentication credentials,
preferences, and contact details for notifications. The Appliance entity tracks

31
 Figure 6.1: Use case diagram

information on all connected devices within the system, storing details like
appliance ID, type, power rating, and control status. EnergyData records
the real-time and historical energy consumption data collected by sensors,
capturing attributes such as timestamp, appliance ID, power consumption,
voltage, and current. The Prediction entity holds forecasted energy usage
values generated by the machine learning model, along with prediction inter-
vals and error metrics. Additionally, OptimizationReport is linked to both
User and Prediction, detailing personalized recommendations and generated
insights based on historical and predicted data. This structured data model
facilitates efficient data storage, retrieval, and analysis, supporting real-time
monitoring, predictive modeling, and user-specific optimization within the
system.

6.3.2 Data objects and Relationships

User - Appliance: One-to-Many — Each user can have multiple appliances
connected to the system, allowing individualized control and monitoring.
Appliance - EnergyData: One-to-Many — Each appliance has mul-
tiple energy data records over time, providing a historical dataset for analysis.
Appliance - Prediction: One-to-Many — Predictions are generated
for each appliance, forecasting future consumption based on historical data
trends.
User - OptimizationReport: One-to-Many — Each user receives
multiple reports over time, tailored to their consumption patterns and opti-

32
mization recommendations.
Prediction - OptimizationReport: One-to-One — Each prediction
generates a corresponding optimization report, connecting forecasted data
with actionable insights.
User - Notification: One-to-Many — Notifications are sent to users
based on their consumption patterns, offering real-time updates on energy
usage or maintenance alerts.

6.4 Functional Model and Description

A description of each major software function, along with data flow (struc-
tured analysis) or class hierarchy (Analysis Class diagram with class descrip-
tion for object oriented system) is presented.

6.4.1 Data Flow Diagram

6.4.1.1 Level 0 Data Flow Diagram
User: Interacts with the system via the frontend interface to monitor energy
usage, control appliances, and view optimization reports. Sensors/Appliances:
Provide real-time data on energy usage, including power consumption, volt-
age, and current readings.

6.4.1.2 Level 1 Data Flow Diagram

Data Acquisition (Process 1): Sensors collect real-time data from appliances
and send it to the ESP8266 microcontroller, which relays it to the back-
end server. Data Storage and Management (Process 2): The server receives
data and stores it in a MongoDB database, cataloging it by appliance and
timestamp for historical records. Data Analysis and Prediction (Process 3):
Historical data is processed by the machine learning model to predict fu-
ture energy consumption. This model is also used to identify trends and
detect unusual usage patterns. Optimization Report Generation (Process 4):
The Large Language Model (LLM) generates customized optimization rec-
ommendations based on the prediction results, creating an actionable report
for the user. User Interaction and Visualization (Process 5): The frontend
interface displays real-time energy data, historical trends, predictions, and
optimization reports. Users can also control appliances via this interface.

33
6.4.1.3 Level 2 Data Flow Diagram
EnergyData Store: Holds real-time and historical energy data, organized by
appliance and timestamp for trend analysis and prediction. Prediction Store:
Contains predicted consumption values, including error margins and inter-
vals. OptimizationReport Store: Stores the optimization reports generated
for each user, providing personalized insights based on predictive analysis.

6.4.1.4 Level 3 Data Flow Diagram

Real-Time Data: Sensors ESP8266 Server EnergyData Store Historical
Data for Prediction: EnergyData Store Data Analysis and Prediction Pre-
diction Store Optimization Report: Prediction Store Optimization Report
Generation OptimizationReport Store User Visualization: EnergyData, Pre-
diction, OptimizationReport User Interface Control Commands: User User
Interface Appliances (via ESP8266)

6.4.2 Activity Diagram:

• The Activity diagram represents the steps taken.

6.4.3 Non Functional Requirements:

• Interface Requirements

• Performance Requirements

• The system should be able to process and display real-time energy data
within 1-2 seconds of data acquisition. Prediction models should gen-
erate forecasted energy usage within 10 seconds after historical data
retrieval to provide timely insights. The system should support si-
multaneous data input from multiple sensors without significant lag,
ensuring scalability for homes with many appliances.

6.4.4 State Diagram:

State Transition Diagram
Fig.6.2
Dataset Collection: The state where you collect datasets generated using
modern cryptographic algorithms.
Preprocessing: Data cleaning, feature extraction, normalization, or any
preprocessing done to make the dataset suitable for ML model training.

34
Feature Engineering:
This state involves selecting relevant features that will be used for
training the model. It may include dimensionality reduction, selecting the
most important attributes, or transforming features for better model perfor-
mance.
Model Training:
In this state, you apply different machine learning algorithms (e.g., su-
pervised classification, clustering) to train a model to recognize cryptographic
algorithms from the dataset.
Model Evaluation:
Once the model is trained, you evaluate its performance using metrics
like accuracy, precision, recall, F1-score, or confusion matrix, ensuring the
model can identify algorithms correctly.
Model Tuning/Optimization:
This state focuses on improving the model by fine-tuning hyperparam-
eters, optimizing the performance, or addressing any issues with overfitting
or underfitting.
Deployment:
The model is deployed for real-time or batch processing of crypto-
graphic algorithm identification, integrated into a larger system.
Model Monitoring and Feedback:
After deployment, the model’s performance is monitored, and feedback
is gathered for further improvement.

6.4.5 Design Constraints

The design of the predictive electric vision system is constrained by the hard-
ware and network requirements essential for reliable IoT-based energy moni-
toring. The system depends on compatible IoT sensors and microcontrollers
(e.g., ESP8266 and PZEM 004T), which limit power consumption and con-
nectivity capabilities, necessitating low-power, high-efficiency components.
Network connectivity must be stable and secure, as real-time data process-
ing and remote control rely heavily on continuous, reliable communication
between sensors, backend systems, and the user interface. Additionally, the
system design must account for data storage constraints, as large volumes of
historical data are required for accurate predictions. Finally, the user inter-
face should remain lightweight to support mobile and web access, aligning

35
 state-dig.jpg

Figure 6.2: State transition diagram

with usability and accessibility standards across devices with limited pro-
cessing power.

6.4.6 Software Interface Description

The software interface(s)to the outside world is(are) described. The require-
ments for interfaces to other devices/systems/networks/human are stated.

36
Chapter 7

Detailed Design Document

using Appendix A and B

7.1 Introduction
This Detailed Design Document outlines the architecture, design, and imple-
mentation strategy for the project on identifying cryptographic algorithms
from datasets generated using modern cryptographic methods. The goal is to
develop AI/ML-based solutions for improved recognition and classification of
cryptographic algorithms. The document provides comprehensive details on
the technical specifications, data models, algorithms, and security measures
considered throughout the project.

7.2 Architectural Design

A description of the program architecture is presented. Subsystem design or
Block diagram,Package Diagram,Deployment diagram with description is to
be presented.

7.3 Data design (using Appendices A and B)

A description of all data structures including internal, global, and temporary
data structures, database design (tables), file formats.

37
 Figure 7.1: Architecture diagram

7.3.1 Internal software data structure

Structure: Arrays, Tensors Purpose: Images and video streams are typically
represented as multi-dimensional arrays or tensors (for deep learning). These
will store pixel values in various formats (RGB, grayscale, etc.). For exam-
ple, a color image might be stored as a 3D tensor with dimensions (height,
width, 3) where the 3rd dimension corresponds to RGB channels. Libraries:
TensorFlow, PyTorch, OpenCV, NumPy

7.3.2 Global data structure

Image Data: This will include raw images or video frames from cameras
(e.g., RGB, depth images). Type: Matrix, Tensor (for multidimensional
data) Attributes: Image resolution, timestamp, sensor ID, image metadata
(e.g., geographical location, orientation). Sensor Fusion Data: If multiple
sensors (cameras, LiDAR, radar, etc.) are used, the data should be fused
into a unified format. Type: Array, List, Tensor Attributes: Sensor type,
timestamp, sensor coordinates, fusion algorithm metadata.

7.3.3 Temporary data structure

Images (Frames/Raw Data): Tensor: A multidimensional array repre-
senting the image in raw format (height, width, color channels). This is
the most common data structure for input images in deep learning models.
Numpy Array (or TensorFlow/PyTorch Tensor): For preprocessing,

38
such as resizing, normalizing, and transforming images. Feature Maps (dur-
ing CNN processing): List of Tensors: Represents the intermediate outputs
from convolutional layers as feature maps that capture spatial hierarchies.
2D Arrays: After flattening the feature maps for fully connected layers,
they may be temporarily stored as 2D arrays.

7.3.4 Database description

Database(s) / Files created/used as part of the application is(are) described.

7.4 Compoent Design

All UML diagrams are required. Class diagrams, Interaction Diagrams, Al-
gorithms. Description of each component description required.

7.4.1 Class Diagram

39
class-dig.jpg

Figure 7.2: Class Diagram

40
Chapter 8

References

41
Annexure A

References

M. Shorfuzzaman and M. S. Hossain, ”Predictive analytics of energy usage

by IoT-based smart home appliances for Green Urban Development,” ACM
Transactions on Internet Technology, vol. 22, no. 2, pp. 1–26, 2021.
N. Somu and K. Ramamritham, ”A hybrid model for building energy con-
sumption forecasting using long short term memory networks,” Applied En-
ergy, vol. 261, 2020.
T.-Y. Kim and S.-B. Cho, ”Predicting residential energy consumption using
CNN-LSTM neural networks,” Energy, vol. 182, pp. 72–81, 2019.
S. Seyedzadeh, F. Pour Rahimian, P. Rastogi, and I. Glesk, ”Tuning machine
learning models for prediction of building energy loads,” Sustainable Cities
and Society, vol. 47, p. 101484, 2019.
K. Liang, F. Liu, and Y. Zhang, ”Household power consumption prediction
method based on selective ensemble learning,” IEEE Access, vol. 8, pp.
95657–95666, 2020.
G. Bedi, G. K. Venayagamoorthy, and R. Singh, ”Development of an IoT-
driven building environment for prediction of electric energy consumption,”
IEEE Internet of Things Journal, vol. 7, no. 6, pp. 4912–4921, 2020.
I. Kiprijanovska, S. Stankoski, I. Ilievski, S. Jovanovski, M. Gams, and
H. Gjoreski, ”HousEEC: dayahead household electrical energy consumption
forecasting using deep learning,” Energies, vol. 13, no. 10, p. 2672, 2020.
A. Ullah et al., ”Deep learning assisted buildings energy consumption profil-
ing using smart meter data,” Sensors, vol. 20, no. 3, p. 873, 2020.
T. Le, M. T. Vo, T. Kieu, E. Hwang, S. Rho, and S. W. Baik, ”Multiple
electric energy consumption forecasting using a cluster-based strategy for
transfer learning in Smart Building,” Sensors, vol. 20, no. 9, p. 2668, 2020.

42
M. Hajj-Hassan, M. Awada, H. Khoury, and I. Srour, ”A behavioralbased ma-
chine learning approach for predicting building energy consumption,” Con-
struction Research Congress 2020.
F. Pallonetto, M. De Rosa, and D. P. Finn, ”Impact of intelligent control
algorithms on demand response flexibility and thermal comfort in a smart
grid ready residential building,” Smart Energy, vol. 2, p. 100017, 2021.
R. E. Castro, F. B. L´ıbano, L. F. Chaves, and J. G. Hermes, ”Automated
energy monitoring and targeting system ISO50001 compatible framework,”
in 2013 International Conference on Renewable Energy Research and Appli-
cations (ICRERA), 2013, pp. 298–303.
A. Fichera, R. Volpe, and E. Cutore, ”Energy performance measurement,
monitoring and control for buildings of public organizations: standardized
practices compliant with ISO 50001 and ISO 50006,” Developments in the
Built Environment, vol. 4, p. 100024, 2020.
A. Gambarotta et al., ”Demonstrating a smart controller in a hospital inte-
grated energy system,” Smart Energy, vol. 12, p. 100120, 2023.
S. Kapp, J.-K. Choi, and T. Hong, ”Predicting industrial building energy con-
sumption with statistical and machine-learning models informed by physical
system parameters,” Renewable and Sustainable Energy Reviews, vol. 172,
p. 113045, 2023.

43
Annexure B

Laboratory assignments on
Project Analysis of Algorithmic
Design

• To develop the problem under consideration and justify feasibilty using

concepts of knowledge canvas and IDEA Matrix.
Refer [?] for IDEA Matrix and Knowledge canvas model. Case studies
are given in this book. IDEA Matrix is represented in the following
form. Knowledge canvas represents about identification of opportunity
for product. Feasibility is represented w.r.t. business perspective.

I D E A
Increase Drive Educate Accelerate
Improve Deliver Evaluate Associate
Ignore Decrease Eliminate Avoid

Table B.1: IDEA Matrix

• Project problem statement feasibility assessment using NP-Hard, NP-

Complete or satisfy ability issues using modern algebra and/or relevant
mathematical models.

• input x,output y, y=f(x)

44
Annexure C

Laboratory assignments on
Project Quality and Reliability
Testing of Project Design

It should include assignments such as

• Use of divide and conquer strategies to exploit distributed/parallel/concurrent

processing of the above to identify object, morphisms, overloading in
functions (if any), and functional relations and any other dependencies
(as per requirements). It can include Venn diagram, state diagram,
function relations, i/o relations; use this to derive objects, morphism,
overloading

• Use of above to draw functional dependency graphs and relevant Soft-

ware modeling methods, techniques including UML diagrams or other
necessities using appropriate tools.

• Testing of project problem statement using generated test data (using

mathematical models, GUI, Function testing principles, if any) selec-
tion and appropriate use of testing tools, testing of UML diagram’s
reliability. Write also test cases [Black box testing] for each identified
functions. You can use Mathematica or equivalent open source tool for
generating test data.

• Additional assignments by the guide. If project type as Entreprenaur,

Refer [?],[?],[?], [?]

45
Annexure D

Project Planner

Using planner or alike project management tool.

46
Annexure E

Reviewers Comments of Paper

Submitted

(At-least one technical paper must be submitted in Term-I on the project de-
sign in the conferences/workshops in IITs, Central Universities or UoP Con-
ferences or equivalent International Conferences Sponsored by IEEE/ACM)

1. Paper Title:

2. Name of the Conference/Journal where paper submitted :

3. Paper accepted/rejected :

4. Review comments by reviewer :

5. Corrective actions if any :

47
Annexure F

Plagiarism Report

Plagiarism report

48
Annexure G

Term-II Project Laboratory

Assignments

1. Review of design and necessary corrective actions taking into consid-

eration the feedback report of Term I assessment, and other competi-
tions/conferences participated like IIT, Central Universities, University
Conferences or equivalent centers of excellence etc.

2. Project workstation selection, installations along with setup and instal-

lation report preparations.

3. Programming of the project functions, interfaces and GUI (if any) as

per 1 st Term term-work submission using corrective actions recom-
mended in Term-I assessment of Term-work.

4. Test tool selection and testing of various test cases for the project per-
formed and generate various testing result charts, graphs etc. including
reliability testing.
Additional assignments for the Entrepreneurship Project:

5. Installations and Reliability Testing Reports at the client end.

49
Annexure H

Information of Project Group

Members

one page for each student .

50
 photo.jpg

1. Name :

2. Date of Birth :

3. Gender :

4. Permanent Address :

5. E-Mail :

6. Mobile/Contact No. :

7. Placement Details :

8. Paper Published :

51