Approach for improving data security in cloud computing
Multi-client framework for access control to datasets set away in an untrusted cloud condition. Appropriated storing like some other untrusted condition needs the capacity to check share data. Our framework gives a path of authority over the informational index away in the cloud without the supplier adventure. The fundamental instrument of access control structure is the figure content arrangement trademark based encryption plot with dynamic properties. Utilizing a blockchain based decentralized record, our framework gives the steady log of all vital security occasions, for example, key age, get the chance to strategy undertaking, change or refusal, get the chance to ask for. We propose a huge amount of cryptographic conventions guaranteeing the security of cryptographic endeavors requiring conundrum or private keys. Just ciphertexts of hash codes are exchanged through the blockchain record. The model of our structure is acknowledged utilizing sharp contracts and endeavored on square chain sort out. Here is proposed structure as a customer if they are going to enroll in that account director will give assorted keys to each customer it takes after a private key in the wake of selecting a customer they can log in and they can exchange all of the reports what they need while exchanging time the substance everything will be encoded and for that one open key will be produce these all will be secured in cloud database . As a customer they have an alternate privet key which was given by the manager so they can log in and they can get to that account if they have to exchange they can exchange else they have to get any record they can get that record by using of cloud they can see all the customer archives if they need any record they have to send sales to executive .if overseer to recognize that request they can get that interface if the customer need that record they have to click that record in case you clicked that archive, by then it will be asked first it will ask private key . obviously, it will ask with respect to whether two keys was composed then nobody however they can prepared to download else they can't prepared to down weight .
Published by: L. Venkat, Lakshman Babu K., Nikhith, Ethirajulu V.
Author: L. Venkat
Paper ID: V5I2-2091
Paper Status: published
Published: April 25, 2019
Dynamic spectrum sharing among the operators using AODV
Dynamic spectrum sharing aims to produce flexible spectrum usage and improve spectrum utilization with time. we have a tendency to propose two optimization models exploitation random optimization algorithms during which the secondary operator: 1) spends the stripped price to realize the target Grade of Service (GoS) assuming unrestricted budget or 2) gains the highest profit to realize the target GoS assuming restricted budget. we have a tendency to assume that there are spectrum resources accessible for secondary operators to borrow under merchant mode. Results obtained from every model are then compared with results derived from algorithms during which spectrum borrowings are random. Comparisons showed that the gain within the results obtained from our projected stochastic-optimization framework is considerably beyond heuristic counterparts. Second post-optimization performance analysis of the operators in the form of blocking probability in various scenarios is investigated to work out the probable performance gain and degradation of the secondary and primary operators, respectively.
Published by: Julakanti Praveen Reddy, A Abhishek Reddy, G. Vikram
Author: Julakanti Praveen Reddy
Paper ID: V5I2-2086
Paper Status: published
Published: April 25, 2019
Credit card fraud detection using Random Forest Algorithm
This Project is focused on credit card fraud detection in real-world scenarios. Nowadays credit card frauds are drastically increasing in number as compared to earlier times. Criminals are using fake identity and various technologies to trap the users and get the money out of them. Therefore, it is very essential to find a solution to these types of frauds. In this proposed project we designed a model to detect the fraud activity in credit card transactions. This system can provide most of the important features required to detect illegal and illicit transactions. As technology changes constantly, it is becoming difficult to track the behavior and pattern of criminal transactions. To come up with the solution one can make use of technologies with the increase of machine learning, artificial intelligence and other relevant fields of information technology, it becomes feasible to automate this process and to save some of the intensive amounts of labor that is put into detecting credit card fraud. Initially, we will collect the credit card usage data-set by users and classify it as trained and testing dataset using a random forest algorithm and decision trees. Using this feasible algorithm, we can analyze the larger data-set and user provided current data-set. Then augment the accuracy of the result data. Proceeded with the application of processing of some of the attributes provided which can find affected fraud detection in viewing the graphical model of data visualization. The performance of the techniques is gauged based on accuracy, sensitivity, and specificity, precision. The results is indicated concerning the best accuracy for Random Forest are unit 98.6% respectively.
Published by: Vaishnave Jonnalagadda, Priya Gupta, Eesita Sen
Author: Vaishnave Jonnalagadda
Paper ID: V5I2-2081
Paper Status: published
Published: April 25, 2019
Text and label reading using Raspberry Pi and Open CV
In this digital Age with the help of our cognitive abilities, we can see, hear and sense various new technologies and can communicate with them but this is not the case for visually impaired people In order for them to communicate with the world they need assistive technology and adaptive devices. The key idea of the project involves helping the sight challenged people. The Proposal of the project involves capturing an image with the help of a camera, recognizing it and extracting the content in the image using various data algorithmic techniques. With the help of this model people with blindness can be more independent with confidence. The major step in making this project a reality is to obtain images from the real world and recognize them with little to no latency and convert them into audio files that can be played. This can be executed out with the help of Open CV and Raspberry pi the main usage of the latter is its portability and compatibility which can be achieved with the use of battery backup functionality which can also be used for future endeavors. The size of the Raspberry pi soc permits the user to carry it anywhere and use it.
Published by: Shakthi Vel, W. Rohan, R. R. Raghavan, Somdeep Choudhury
Author: Shakthi Vel
Paper ID: V5I2-2009
Paper Status: published
Published: April 24, 2019
Image recognition system
Image recognition has been an active and challenging area of research. In recent years image recognition has received veritable attention from the research communities but it still remained very challenging in real applications. It plays a very important role in today’s world. Though we might have seen various applications and websites of text recognition, label detection and face detection they are all separate applications this review paper tells us how to combine them together so that user don’t need to download numerous software but just a simple image recognition system that uses Google cloud vision API. In image recognition, we have combined 3 things together that is text, label, and face. It should be noted that the combination of these three things together is nowhere found and might be difficult to evolve. This review paper will focus on scattering and separating the image by defining each element of the image by recognizing the text, detecting its label and detecting the face that can make the human work’s easy. By focusing on the history and evolution of the text, label and face recognition system we combine them together so that it can be used for security purposes, organization, computer software and it can also be used in the government field. This review paper will represent the limitations and superiorities of different techniques which are used for image recognition system.
Published by: Swati Dewangan, Sneha Dey, Megha Sahu, Seira Tak
Author: Swati Dewangan
Paper ID: V5I2-2064
Paper Status: published
Published: April 24, 2019
Department Application
The venture brings the whole manual procedure of a specific office online which is manufactured utilizing Android studio/java as a front end and MySQL Server as a backend. The fundamental reason for this task is to improve the way toward dealing with all the manual work by giving a web interface to HOD, Faculty, and Students. The HOD part comprises of various modules where Head of the office is mindful to enlist all the personnel of the specific office. The framework enables HOD to allot resources to the regarded subjects appropriately, likewise can see every one of the exercises done by the Faculty. The Faculty part has thought of enlisting the understudies of specific class relegated by the HOD. Educator performs a different errand, for example, taking the participation of the understudies utilizing QR code, transferring assignments and mark sheet for the specific class understudies as relegated. The Faculty can likewise have a balanced discussion over the application for clearing understudies questions. Understudy interface comprises of review the transferred data by the Faculty or HOD with the application and furthermore getting a warning via telephone for the equivalent. Understudies additionally need to examine the Faculty's QR code for participation.
Published by: Vrushali Kapse, Sachin Birhade, Janki Gupta, Manisha Sonawane
Author: Vrushali Kapse
Paper ID: V5I2-2057
Paper Status: published
Published: April 24, 2019
