GOVT OF KARNATAKA

Department of Technical Education,

Palace Road, Bangalore-560001, Karnataka

PROJECT SYNOPSIS ON

“An Ensemble Learning Based Intrusion Detection Model for

Industrial IoT Security”
Submitted in the partial fulfillment of requirements for the award of the

DIPLOMA

In

COMPUTER SCIENCE AND ENGINEERING

Submitted By:
SL NO REGISTER NUMBER STUDENT NAME ROLE

1 498CS21032 KEERTHANA D M TEAM LEAD

2 498CS21036 MANISH PU DOCUMENT LEAD
3 498CS21043 MOHAMMED AMEEN CODER
KHALANDER
4 498CS21046 MUZAMIL PASHA CODER

COHORT OWNER
Mr. NAVEEN KUMAR V G BE, M.Tech
Lecturer Dept of CSE.
BGS POLYTECHNIC
Chikkaballapura
 DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
BGS POLYTECHNIC [498]
(An ISO 9001:2015 Certified)
BGS (SJCIT) Campus, Chickballapura-562101
2023-2024

|| JAI SRI GURUDEV ||

Sri Adichunchanagiri Shikshana Trust®

BGS POLYTECHNIC
SJCIT CAMPUS, B.B. ROAD, NH No. 7,
CHIKKABALLAPURA -562 101

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

CERTIFICATE
This is to Certify that the project synopsis entitled “A Novel
Intrusion Detection System for Internet of Healthcare Things
Based on Deep Subclasses Dispersion Information” is a bonafide
work carried out by KEERTHANA D M bearing Regno:
498CS21032 respectively in partial fulfillment for the award of
Degree of Diploma in Computer Science and Engineering of the
Board of Technical Education, Bangalore during the year 2023-2024.
It is certified that all the corrections, suggestions indicated for
internal assessment have been incorporated in the synopsis report
deposited in the Departmental library. The project synopsis report has been
approved as it satisfies the academic requirements in aspect of project work
prescribed for the Diploma in Computer Science and Engineering.

………………........... ………………………… ……………………………

Signature of Cohort Owner Signature of HOD Signature of Principal

Mr. NAVEEN KUMAR V G Mr. SHIVA KUMAR G V Prof. Y R MANJUNATH

BE, MTech BE , M.Tech
Lecturer Dept of CSE, HOD Dept of CSE Principal
BGSP, Chikkaballapura BGSP, Chikkaballapura BGSP, Chikkaballapura.

STUDENT DECLARATION

We are hereby declaring that

(i) The project work is our original work

(ii) This project work as not been submitted for the award of any degree or
examination at any other university/college/institute

(iii) This project work does not contain other persons ‘data, pictures, graphs or other
information, unless specifically acknowledged as being sourced from other
persons

(iv) This project work does not contain other persons’ writing, unless specifically
acknowledged being sourced from other researchers where other written
sources have been quoted, then:
a) Their words have been rewritten but the general information attributed to
them has been referenced;
b) Where their exact words have been used, there writing has been placed
inside quotation marks, and referenced.
(v) This project work does not contain text, graphics or tables copied and pasted
from the internet, unless specifically acknowledged, and the source being
detailed in the thesis and in the reference’s sections.
 STUDENT NAME REGISTER NO SIGNATURE

ACKNOWLEDGEMENT
Every project begins with an idea and materializes with concrete efforts. In the beginning, we
would like to thank the almighty God and our parents who gave us the strength and capability to
work on this project.

I sincerely thank B.G.S POLYTECHNIC, Chikkballapura for providing me with this

opportunity to improve my knowledge by giving an opportunity to give this project.

I thank our principal Prof. Mr. Y R MANJUNATH BE, M Tech for providing a congenial working
atmosphere.

We extend our sincere gratitude to Mr. SHIVA KUMAR G V , Head of the

B.E, M TECH

Department, Computer Science and Engineering, for his consistent assistance and guidance
during the course of the project work.

We are extremely grateful to our project guide Mr. NAVEEN KUMAR V G B.E,M.Tech Lecturer
Department of Computer Science and Engineering for the guidance and encouragement.

I wish to thank to MY PARENTS and all MY FRIENDS who gave their valuable time and
ideas to complete this report.
Finally, we express our immense pleasure and thanks to all TEACHING STAFF and NON
TEACHING STAFF of the Department of Computer Science and Engineering, for their
cooperation and support.
ABSTRACT
Industrial Internet of Things (IIoT) represents the expansion of the Internet of
Things (IoT) in industrial sectors. It is designed to implicate embedded
technologies in manufacturing fields to enhance their operations. However, IIoT
involves some security vulnerabilities that are more damaging than those of IoT.
Accordingly, Intrusion Detection Systems (IDSs) have been developed to
forestall inevitable harmful intrusions. IDSs survey the environment to identify
intrusions in real time. This study designs an intrusion detection model exploiting
feature engineering and machine learning for IIoT security. We combine Isolation
Forest (IF) with Pearson’s Correlation Coefficient (PCC) to reduce computational
cost and prediction time. IF is exploited to detect and remove outliers from
datasets. We apply PCC to choose the most appropriate features. PCC and IF are
applied exchangeably (PCCIF and IFPCC). The Random Forest (RF) classifier is
implemented to enhance IDS performances. For evaluation, we use the Bot-IoT
and NF-UNSW-NB15-v2 datasets. RF-PCCIF and RF-IFPCC show noteworthy
results with 99.98% and 99.99% Accuracy (ACC) and 6.18 s and 6.25 s
prediction time on Bot-IoT, respectively. The two models also score 99.30% and
99.18% ACC and 6.71 s and 6.87 s prediction time on NF-UNSW-NB15-v2,
respectively.
TABLE OF CONTENTS

SL.NO CONTENTS PAGE NO

1 INTRODUCTION 1

2 LITERATURE SURVEY 2

3 EXISTING SYSTEM 3

4 PROPOSED SYSTEM 4

5 SYSTEM ARCHITECTURE 5

6 SOFTWARE REQUIREMTNS SPECIFICATION 6

7 COST ESTIMATION 7
8 CONCLUSION 8

9 REFERENCES 9
INTRODUCTION
The Internet of Things (IoT) represents an extensive scale network of integrated
sensors and activators, serving a pertinent objective, and does not require human
intervention arbitration. Consequently, researchers suggest conventional tools to
support resolving these issues. In recent years, IoT technology has undergone
quick evolution. Subsequently, its security is a mandatory task to warrant several
services, such as confidentiality, privacy, data, and availability. Due to the
heterogeneous utilized protocols and data in IoT, implementing security
mechanisms is becoming challenging. Node quantity, low memory capability,
processing command, and energy consumption have severely compromised
security techniques. The Industrial Internet of Things (IIoT) denotes linking
devices, activators, and industrial systems to each. This technology gathers and
analyses data to improve the industrial sector proficiency.

LITERATURE SURVEY
Research Paper 1:

P. Ghosal, D. Das, and I. Das, “Extensive survey on cloud-based iot-healthcare

and security using machine learning,” in 2018 Fourth International Conference.

The IoHT has benefited the medical sector through remote monitoring of the
patient’s health status without any visits by him/her to the healthcare facility. This
resulted in time and cost savings, enhanced quality of healthcare services,
improved quality of patient’s health through better support and medication as
healthcare providers can effectively and accurately understand critical health
conditions, patients becoming well-informed about the improvements in their
health status and treatments, and increased patient interest and satisfaction through
simple and effective communication with healthcare providers.

Research Paper 2:

DEPT OF CSE 1 2023-24

Kumar, G. P. Gupta, and R. Tripathi, “An ensemble learning and fog-cloud
architecture-driven cyber-attack detection framework for iomt networks,”
Computer Communications, vol. 166, pp. 110–124, 2021

The Deep SDOSVM intrusion detection system is a three-step process that

includes feature pre-processing, deep clustering using the DynAE model, and
classification using the SDOSVM algorithm. The system is designed to accurately
and efficiently detect IoHT network traffic, which includes both numerical and
categorical values. The system transforms categorical features into numeric ones,
ensuring efficient handling of only numeric values. Feature selection is a method
that identifies and discards relevant features to improve intrusion detection system
performance and reduce processing time in the IoHT environment. This step is
crucial for achieving accurate and efficient results.

EXISTING SYSTEM
The IoT has created a connected network of devices that involves heterogeneous
objects from various aspects. While in the IoT, the network has no unified
protocols or standards. Therefore, it is challenging to allow full security measures
for those devices. While traditional security protocols provide optimal protection
for the IoT architecture against threats on the Internet. Thus, constructing an
efficient IDS relying on Deep Learning (DL) techniques and technologies is
promising. Research papers highlighted that applying novel DL techniques and
frameworks, besides enhancing the existing DL models, presents remarkable
results and strengthens the IDS performance. While it has an accurate and high
prediction rate, it can assist in the maintenance aspect of the IoT network.

Disadvantages:

1. An ensemble learning-based intrusion detection model that combined

Isolation Forest with Pearson’s Correlation Coefficient to reduce
computational cost and prediction time. However, it is possible that some
ensemble models may require more computational resources than other
intrusion detection methods.

DEPT OF CSE 2 2023-24

 2. The Potential false alarms: While ensemble learning-based models can
provide significant accuracy with low false alarm rates (FAR), there is still
a possibility of false alarms. This could lead to unnecessary alerts and
potentially wasted resources if the alerts are not legitimate.
3. The existing model is relies on Ensembles can be less interpretable than
single algorithms. Understanding the decision-making process of the model
and diagnosing issues can be more challenging, which is important in
security applications for debugging and accountability.

PROPOSED SYSTEM:

We propose and validate a Network IDS (NIDS) model for IIoT security. In
our proposition, Isolation Forest (IF) is integrated to achieve outlier detection.
Pearson’s Correlation Coefficient (PCC) is also applied to choose the most
suitable features for dimensionality reduction. Then, Random Forest (RF)
distinguishes between normal packets and intrusions through binary
classification. The obtained results indicate that our model is promising when
it is compared with other previous related propositions. Our model depends on
the Bot-IoT dataset, known for its imbalance, and on the NFUNSW-NB15-v2
dataset. The strengths of our model appear in its capability to overtake the
imbalance of the Bot-IoT dataset, especially when we remove the outliers and
select the relevant features of the newly generated dataset.

Advantages:

1. We combine Isolation Forest (IF) with Pearson’s Correlation

Coefficient (PCC) to reduce computational cost and prediction time.
2. We apply PCC to choose the most appropriate features. PCC and IF are
applied exchangeably (PCCIF and IFPCC). The Random Forest (RF)
classifier is implemented to enhance IDS performances.
3. For evaluation, we use the Bot-IoT and NF-UNSW-NB15-v2 datasets.
RF-PCCIF and RF-IFPCC show noteworthy results with 99.98% and
99.99% Accuracy (ACC) and 6.18 s and 6.25 s prediction time on Bot-
IoT, respectively. The two models also score 99.30% and 99.18% ACC

DEPT OF CSE 3 2023-24

 and 6.71 s and 6.87 s prediction time on NF-UNSW-NB15-v2,
respectively.
4. By using techniques like ML techniques we can easily implement the
Intrusion Detection System(IDS).

SYSTEM ARCHITECTURE

Fig.1: System architecture

REQUIREMENTS:

The following are the hardware and software requirements that have used to
implement the proposed system

Hardware Requirements

1) Operating System : Windows Only

2) Processor : i5 and above

3) Ram : 4gb and above

DEPT OF CSE 4 2023-24

 4) Hard Disk : 50 GB

Software Requirement

1) Visual Studio Community Version

2) Nodejs ( Version 12.3.1)

3) Python IDEL ( Python 3.7 )

COST ESTIMATION

SLNO PARTICULARS COST

1 PROJECT MANAGEMENT 6000

2 HARDWARE 7000

3 SOFTWARE DEVELOPMENT 9000

4 TESTING 3000

TOTAL 25000

DEPT OF CSE 5 2023-24

CONCLUSION

The proven efficiency of IDS has made it an essential tool, among others, to
mitigate IIoT vulnerabilities. In this study, we implement an IDS for IIoT
networks using the RF model for classification, PCC to select relevant features,
and IF as an outlier detector. We use PCC and IF separately and exchangeably. IF
takes the output of PCC as input and vice versa. Our model shows a great result in
overtaking the imbalance of the Bot-IoT dataset, which can be seen in the
confusion matrix of the RF-IFPCC model. On the NF-UNSW-NB15-v2 dataset,
the results are close to one another with outstanding performances. We intend in
our future work to exploit other datasets, such as the TON-IoT dataset containing
IoT and IIoT data, to have a global view and create and validate an effective IDS
for improving network security in general.

DEPT OF CSE 6 2023-24

REFERENCES

1.P. Ghosal, D. Das, and I. Das, “Extensive survey

on cloud-based iot-healthcare and security using
machine learning,” in 2018 Fourth International
Conference on Research in Computational
Intelligence and Communication Networks (ICRCICN),
2018, pp. 1–5.

2.Kumar, G. P. Gupta, and R. Tripathi, “An

ensemble learning and fog-cloud architecture-driven
cyber-attack detection framework for iomt networks,”
Computer Communications, vol. 166, pp. 110–124,
2021.

3.G. Thamilarasu, A. Odesile, and A. Hoang,“An

intrusion detection system for internet of
medical things,” IEEE Access, vol. 8, pp. 181
560– 181 576, 2020.

4. S. P. R.M., P. K. R. Maddikunta, P. M.,

S. Koppu, T. R. Gadekallu, C. L.
Chowdhary, and M. Alazab, “An effective feature
engineering for dnn using hybrid pca-gwo for
intrusion detection in iomt architecture,” Computer
Communications, vol. 160, pp. 139–149, 2020.

5. J.-P. A. Yaacoub, M. Noura, H. N. Noura, O.

Salman, E. Yaacoub, R. Couturier, and A.
Chehab, “Securing internet of medical things
systems: Limitations, issues and recommendations,” Future
Generation Computer Systems, vol. 105, pp. 581–
606, 2020.

6.. Chaabouni, M. Mosbah, A. Zemmari, C.

Sauvignac, and P. Faruki, “Network intrusion
detection for iot security based on learning
tech- niques,” IEEE Communications Surveys
Tutorials, vol. 21, no. 3, pp. 2671–2701, 2019.

DEPT OF CSE 7 2023-24