Automated Vehicle Detection and Classification with Probabilistic Neural Network
The number of vehicles in the urban areas is rising at high pace. The critical issues are arising with the rise in the number of vehicles for the traffic analysis. The analysis of the vehicle running across the roads is usually done for the density analysis, traffic shaping and many other similar applications. The vehicle detection in the rushed areas produces the real challenge of independent component selection and classification, which requires the precise object detector with deep analytical ability based classification algorithm. In this paper, the unique method with probabilistic neural network (PNN) classification model along with the non-negative matrix factorization for the purpose of vehicular object localization and classification in the urban imagery. The proposed model is expected to solve the problems associated with the accuracy, precision and recall.
Published by: Ramanpreet Kaur, Meenu Talwar
Author: Ramanpreet Kaur
Paper ID: V2I6-1141
Paper Status: published
Published: November 2, 2016
A Review in Cloud Computing Security using Steganography
Cloud Computing is a flexible, cost-efficient, and authentic platform for providing business or consumer IT enabled services on the Internet. However, Cloud computing represents an added level of risk factors because important and essential services are often outsourced to a third party connected to cloud network, which makes it even harder to maintain the level of data security. Steganography is the technique of hiding or encapsulating information in digital media in order to prevent the existence of information. The digital media with hidden information within are called stego media and the data without hidden information are called cover media. Steganography can be used for hiding both the legal as well as illegal information. For example, civilians can use it for maintaining privacy while the government may use it for the security reasons of the country. In this paper we have discussed about the various techniques by which we can enhance the cloud service in relation to security and data privacy.
Published by: Ataussamad, Dr. Shiva Prakash
Author: Ataussamad
Paper ID: V2I6-1138
Paper Status: published
Published: November 2, 2016
Survey on Dynamic Resource Allocation Schemes in Cloud Environment: A Review
Cloud computing environment provisions the supply of computing resources on the basis of demand, as and when needed. It builds upon advances of virtualisation and distributed computing to support cost efficient usage of computing resources, emphasizing on resource scalability and on-demand services. It allows business outcomes to scale up and down their resources based on needs. Managing the customer demand creates the challenges of on demand resource allocation. Further they can make use of company-wide access to applications, based on pay-as-you-go model. Hence there is no need for getting licenses for individual products. Virtual Machine (VM) technology has been employed for resource provisioning. It is expected that using virtualized environment will reduce the average job response time as well as executes the task according to the availability of resources. Effective and dynamic utilization of the resources in cloud can help to balance the load and avoid situations like slow run of systems. In this paper, various resource allocation strategies and their challenges are discussed in detail. It is believed that this paper would benefit both cloud users and researchers in overcoming the challenges faced.
Published by: Roshni Singh, Dr. Shiva Prakash
Author: Roshni Singh
Paper ID: V2I6-1137
Paper Status: published
Published: November 2, 2016
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
