Detection and Mitigation of Botnet through Machine Learning in MANET
Botnets are the networks of remotely controlled computer systems infected with a malicious program that allow cyber crimes to control the infected computers or machines without the user’s knowledge. Botnets are the most ever-growing much interested evolved in the design of mobile adhoc networks (MANET). A botnet in mobile network is defined as a collection of nodes containing a malware called mobile malware which are able to bring the different elements into harmonious activities. Unlike Internet botnets, mobile botnets do not need to propagate using centralized structure. With the advent of internet and e-commerce application data security is the most critical issue in transferring the information throughout the internet. Botnets are emerging as the most significant threat facing computing assets and online ecosystems. The sharing of information through internet has been the main driver behind the Elite hacker into criminal activities. Their main target is to steal the vulnerable information from the individuals or from the organizations. In other words we can say their purpose include the distribution of spam emails, coordination of distributed denial of service (DDoS) and automatic identity theft. The proposed method is a classified model in which a Hill Cipher Algorithm and a Support Vector Machine are combined. A MANET environment with real time datasets is simulated for testing this model; the packet data of network flow was also collected. The proposed method was used to identify the critical features that determine the pattern of botnet. The experimental results indicated that the method can be used for identifying the essential botnet features and that the performance of the proposed method was superior to that of Artificial Fish Swarm Algorithm.
Published by: Mariya Ameer, Aashish Gagneja, Navjot Kaur
Author: Mariya Ameer
Paper ID: V2I6-1140
Paper Status: published
Published: November 1, 2016
Protocol Enhancement of Vehicle Collision Avoidance System in Network
In most of the automobile system avoiding collision is a critical issue. A “Vehicle Collision Avoidance System” in an automobile system is a safety system that is designed to reduce the chances of collision .Collision avoidance is one of the most important issues in controlling vehicles automatically. The job of driving vehicles can be made easier by the use of these system, as well as these system ensures to manage the traffic efficiently with road safety. In this paper we consider a VANET scenario for road side safety and to solve the emergency situation. To improve the performance for large scale network having large traffic and communication between vehicles is done by using routing protocol. Here we introduce a PUMA protocol and compare its results. Also we apply Genetic Algorithm on this protocol for the path optimization to achieve maximum results. By varying number of vehicles (nodes) mean throughput, mean delay, jitter, PDR has been calculated. In this paper application and future scope of VANETs is also introduced.
Published by: Mr. Insha Mushtaq, Aashish Gagneja, Navjot Kaur
Author: Mr. Insha Mushtaq
Paper ID: V2I6-1139
Paper Status: published
Published: November 1, 2016
Advanced E-voting System using NFC
The electronic voting is the technology in which the citizens can do the vote using smart phone. It gives functionality to users to give vote from android mobile. E-voting technique have advantages over traditional voting framework like less manpower, it save time, accuracy and transparency ,fast result ,etc. Security pre-requisites E-voting technique has so many challenges associated with voting. Mainly Assimilation and Verification to keep secure voted data. To overcome these challenges we purpose the new e-voting framework in which the NFC tag is used to give more accuracy and transparency in voting framework.The NFC tag store information of voters to check the voter and voters vote in the application. The E-polling technique has three phases.The first involves analyze and verification of user .In second phaseto get OTP and using this OTP user can vote in the framework. In third stage Administrator will count and sort out the votes and declare the result of voting in application.
Published by: Pratiksha Bhosale, Sayali Mokashi, Priyanka Wadkar, Prof P.V.Mahadik
Author: Pratiksha Bhosale
Paper ID: V2I5-1188
Paper Status: published
Published: October 27, 2016
Novel Approach for Routing in MANET by Network Connectivity with Meta Heuristic
. A popular example of opportunistic routing is the “delay tolerant” forwarding to vanet nework when a direct path to destination does not exist. The evaluation of this work is twofold. We implemented two prototypes on off -the-shelf hardware to show the technical feasibility of our opportunistic network concepts. Also, the prototypes were used to carry out a number of runtime measure- ments. Then, we developed a novel two-step simulation method for opportunistic data dissemination. The simulation combines real world user traces with artificial user mobility models, in order to model user movements more realistically. We investigate our opportunistic data dissemination process under various settings, including different communication ranges and user behavior pattern In this use Conventional routing in this case would just “drop” the packet. With opportunistic routing, a node acts upon the available information ,In this thesis optimize the routing by centrality information then refine by ant colony metaheuristics.In this method validate our approach on different parameter like overhead, throughput
Published by: Ramninder Kaur, Harpreet Kaur
Author: Ramninder Kaur
Paper ID: V2I5-1187
Paper Status: published
Published: October 27, 2016
Twitter Stream Analysis for Traffic Detection in Real Time
Now a days,social networking are more popular.for example,twitter,Facebook etc.social networking are used forevent detection in real time.Real time events are traffic detection,earthquake monitoring.In this paper,we use the the twitter for real time traffic event detection.Firstly,the system extract the tweets from twitter and apply the text mining techniques on that tweets.those techniques are tokenization, stop-word removing,stemming.after that classify that on the basis of class label i.e traffic event or no traffic event.In this paper, we present an online method for detection of real-traffic events in Twitter data.
Published by: Rucha Kulkarni, Sayali Dhanawade, Shraddha Raut, Prof.D.S.Lavhkarer
Author: Rucha Kulkarni
Paper ID: V2I5-1186
Paper Status: published
Published: October 26, 2016
Smart Wifi Dustbin System
We realize that Garbage causes damage to local ecosystems, and it is a threat to plant and human life. To avoid all such situations we are going to implement a project called IoT Based Smart Garbage."When somebody dumps trash into a dustbin the bin ashes a unique code, which can be used to gain access to free Wi-Fi". Sensor check garbage lls in dustbin or not and Router pro- vides Wi-Fi to user. Major part of our project depends upon the working of the Wi-Fi module; essential for its implementa- tion. The main aim of this project is to enhancement of a smart city vision.
Published by: Akshay Bandal, Pranay Nate, Rohan Mankar, Rahul Powar
Author: Akshay Bandal
Paper ID: V2I5-1185
Paper Status: published
Published: October 25, 2016
