Computer Science And Technology - Research Publications

Permanent URI for this collectionhttps://kr.cup.edu.in/handle/32116/82

Browse

Author: search.filters.author.MeenakshiHas files: No

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Comparison and analysis of logistic regression, Na�ve Bayes and KNN machine learning algorithms for credit card fraud detection
    (Springer Science and Business Media B.V., 2020-02-15T00:00:00) Itoo, Fayaz; Meenakshi; Singh, Satwinder
    Financial fraud is a threat which is increasing on a greater pace and has a very bad impact over the economy, collaborative institutions and administration. Credit card transactions are increasing faster because of the advancement in internet technology which leads to high dependence over internet. With the up-gradation of technology and increase in usage of credit cards, fraud rates become challenge for economy. With inclusion of new security features in credit card transactions the fraudsters are also developing new patterns or loopholes to chase the transactions. As a result of which behavior of frauds and normal transactions change constantly. Also the problem with the credit card data is that it is highly skewed which leads to inefficient prediction of fraudulent transactions. In order to achieve the better result, imbalanced or skewed data is pre-processed with the re-sampling (over-sampling or under sampling) technique for better results. The three different proportions of datasets were used in this study and random under-sampling technique was used for skewed dataset. This work uses the three machine learning algorithms namely: logistic regression, Na�ve Bayes and K-nearest neighbour. The performance of these algorithms is recorded with their comparative analysis. The work is implemented in python and the performance of the algorithms is measured based on accuracy, sensitivity, specificity, precision, F-measure and area under curve. On the basis these measurements logistic regression based model for prediction of fraudulent was found to be a better in comparison to other prediction models developed from Na�ve Bayes and K-nearest neighbour. Better results are also seen by applying under sampling techniques over the data before developing the prediction model. � 2020, Bharati Vidyapeeth's Institute of Computer Applications and Management.
  • No Thumbnail Available
    Item
    Implementation and analysis of enhanced obfuscation technique for data security
    (Blue Eyes Intelligence Engineering and Sciences Publication, 2019) Tanuja; Meenakshi
    With the fast development of digital exchange of data in an electronic way, data and information security are becoming more important in both transmission and data storage. Cryptography is used as a solution which plays an important role in data and information security systems against malicious attacks. The encryption technique is used to provide confidentiality to the data during transmission because security threats are more on data during transmission than data at rest. One can also use encryption to secure user's data at data storage (i.e., data at rest). But an encryption algorithm consumes a more amount of computing resources such as processing power, memory and computation time. Obfuscation technique is a very lightweight technique that comes into a picture to protect the data at storage from malicious attacks. There are many obfuscation techniques are available to ensure the confidentiality of the data. In this paper, an obfuscation technique has been proposed and implemented which uses a 128-bit key to improve the security of the data. The experimental results show that the time taken for obfuscation and de-obfuscation is less and also from the security point of view it provides high avalanche effect.
  • No Thumbnail Available
    Item
    Analysis of VANET geographic routing protocols on real city map
    (Institute of Electrical and Electronics Engineers Inc., 2018) Kaur, H.; Meenakshi
    Vehicular Ad hoc network (VANET) is an escalating field of research and laid basis for many newer technologies like Intelligent Transport Systems (ITS). Routing in VANETs plays crucial role in performance of networks. VANET protocols are classified as topology based and position based protocols. Research showed that position based protocols are more suited to VANETs as compared to topology based protocols because geographic routing does not involve an overhead and delay of maintaining routing tables instead geographic position of nodes is used for routing which can be obtained by Global Positioning System (GPS) device on vehicles. In this paper, two geographic routing protocols Anchor based Street and Traffic Aware Routing (A-STAR) and Greedy Perimeter Stateless Routing (GPSR) protocols are evaluated on real city map. Simulation of VANETs on real map scenarios provide accurate results and also useful to design and deploy VANETs in real world. Real world mobility model is important because it reflects real-world performance of protocols considered. Analysis of performance is carried in terms of throughput, packet delivery ratio, packet loss and average delay. Simulation of protocols is carried by varying density of nodes. A-STAR showed better performance on real city map over GPSR because A-STAR adopted Street awareness method of routing whereas GPSR works on Greedy forwarding and Routing around the perimeter methods. ? 2017 IEEE.