VISVESVARAYA TECHNOLOGICAL UNIVERSITY,

BELGAUM

A PROJECT REPORT ON

unstructured HUMAN ACTIVITY DETECTION

Submitted in fulfillment of the requirements for the award of

BACHELOR OF ENGINEERING
DEGREE
IN
COMPUTER SCIENCE AND ENGINEERING
Submitted By:

PROJECT ASSOCIATES
ARUNA L
KAVYASHREE H K
NANDITHA U
NEHA D

3VC10CS016
3VC10CS037
3VC10CS056
3VC11CS057

Under the Guidance of

Asso Prof. CHIDANANDHA H

DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

RAO BAHADUR Y MAHABALESHWARAPPA ENGINEERING

COLLEGE
(Affilated To Visvesvaraya Technological University, Belgaum & Approved By AICTE, New Delhi)
(Formerly VIJAYANAGAR ENGINEERING COLLEGE, BELLARY)
CANTONMENT, BELLARY-583 104 (KARNATAKA)

V.V.SANGHAS

RAO BAHADUR Y MAHABALESHWARAPPA

ENGINEERING COLLEGE
DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING
(Accredited by National Board of Accreditation and Certified ISO 9001:2000)

CERTIFICATE
This is to certify that the Project Work entitled UNSTRUCTURED HUMAN
ACTIVITY DETECTION is a bonafide work carried out by ARUNA
L(3VC10CS016), KAVYASHREE H K (3VC10CS037), NANDITHA U
(3VC10CS056) , NEHA D (3VC11CS057) in partial fulfillment for the Award of
degree of Bachelor of Engineering in Computer Science and Engineering from
Visvesvaraya Technological University, Belgaum during the year 2013-2014. It is
certified that all corrections/suggestions indicated for Internal Assessment have been
incorporated in the report deposited in the departmental library. The project report has
been approved as it satisfies the academic requirements in respect of project work
prescribed for the said Degree.

Signature of Project guide

Signature of HOD

_______________________

___________________

Asso Prof. CHIDANANDA H

Dr. T.HANUMANTHA REDDY

B.E, M.TECH.

B.E., M.TECH, Ph.D

Signature of Principal
________________________
Dr. KUPPAGAL VEERESH
M.E. Ph.D., MIE, FIV

Name of the Examiners:

Signature with date:

1.

2.

ACKNOWLEDGEMENT
With great respect and gratitude,
We would like to express our regards and acknowledgement to all those who
helped in making this project possible. The satisfaction that accompanies the successful
culmination of any task would be incomplete without mentioning those who made it
possible because success is the epitome of hard work, determination, concentration and
dedication.
Firstly we would like to thank our beloved Parents whose everlasting guidance
and support is incredible in completing this project successfully.
We are grateful to the Principal Dr. Kuppagal Veeresh M.E. Ph.D., MIE,
FIV. for providing facilities and untiring zeal, which constantly inspired us towards the
attainment of everlasting knowledge throughout the course.
We are deeply indebted to our beloved HOD Dr. T. Hanumantha Reddy, B.E,
M. Tech, Ph.D. Department of Computer Science and Engineering for the valuable
suggestions and constant encouragement provided for the successful completion of our
project.

We would like to thank our guide Asso Prof. CHIDANANDA H, B.E, M.Tech,
for the constant guidance in the successful completion of our project.
Finally, we would like to thank all the staff members of our Department
Computer Science and Engineering for their guidance and support. We are also thankful
to our friends who continue in giving this best support.
PROJECT ASSOCIATES

ARUNA L
KAVYASHREE H K
NANDITHA U
NEHA D

3VC10CS016
3VC10CS037
3VC10CS056
3VC11CS057

ABSTRACT
Open nature of peer-to-peer systems exposes them to malicious activity.
Building trust relationships among peers can mitigate attacks of malicious peers. This
paper presents distributed algorithms that enable a peer to reason about trustworthiness
of other peers based on past interactions and recommendations. Peers create their own
trust network in their proximity by using local information available and do not try to
learn global trust information. Two contexts of trust, service, and recommendation
contexts, are defined to measure trustworthiness in providing services and giving
recommendations. Interactions and recommendations are evaluated based on
importance, recentness, and peer satisfaction parameters. Additionally, recommenders
trustworthiness and confidence about a recommendation are considered while evaluating
recommendations. Simulation experiments on a file sharing application show that the
proposed model can mitigate attacks on 16 different malicious behavior models. In the
experiments, good peers were able to form trust relationships in their proximity and
isolate malicious peers.