Computer Science And Technology - Research Publications

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

Browse

Author: search.filters.author.Singh S.

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Investigating the role of code smells in preventive maintenance
    (University of Tehran, 2019) Reshi J.A.; Singh S.
    The quest for improving the software quality has given rise to various studies which focus on the enhancement of the quality of software through various processes. Code smells, which are indicators of the software quality have not been put to an extensive study for as to determine their role in the prediction of defects in the software. This study aims to investigate the role of code smells in prediction of non-faulty classes. We examine the Eclipse software with four versions (3.2, 3.3, 3.6, and 3.7) for metrics and smells. Further, different code smells, derived subjectively through iPlasma, are taken into conjugation and three efficient, but subjective models are developed to detect code smells on each of Random Forest, J48 and SVM machine learning algorithms. This model is then used to detect the absence of defects in the four Eclipse versions. The effect of balanced and unbalanced datasets is also examined for these four versions. The results suggest that the code smells can be a valuable feature in discriminating absence of defects in a software.
  • No Thumbnail Available
    Item
    Enhanced routing protocol for VANET
    (Blue Eyes Intelligence Engineering and Sciences Publication, 2019) Kaur R.; Kaur N.; Singh S.
    A class of networks called VANET(vehicular adhoc network),the extension of MANETs(mobile adhoc network) are based on the principle of the formation of wireless network for exchange of data and the creation of network is spontaneous in nature. The mobility constraints, behavior of driver, high speed, limited coverage of wifi, hard delay constraints leads to unique characteristics in VANETS. So the MANET routing protocols are not suitable for VANET. Optimization of routing protocols becomes necessary to make it suitable for VANET. In this paper, various optimized routing protocols are analyzed and their optimization techniques are discussed. Parameters such as end to end delay and energy spent are taken into consideration in order to show the improvement from the routing protocols that are standard protocols. Then a method has been proposed to optimize the fine tuned OLSR (optimized link state routing)protocol with the use of advanced genetic algorithm to further improve the results and to make the protocol more efficient.
  • No Thumbnail Available
    Item
    Fake news detection of Indian and United States election data using machine learning algorithm
    (Blue Eyes Intelligence Engineering and Sciences Publication, 2019) Kumar A.; Singh S.; Kaur G.
    The world of digital media is thriving by the day and hence, there is an urge of businesses to magnify it more gaining them maximum financial benefits. This particular urge calls for more and more expansions concerning creating and developing new content whether it's in the form of websites that aims at branding businesses or could be in the form of online newspapers and magazines. Since from last few decades’ medium of communication had changed. Now a day people are using social networks very extensively for news updates. These networks aim to make social lives better. Today, everyone knows and uses social media which contains unverified article, post, message and news. Nowadays' fake news is making various issues from mocking articles to a created news and plan government publicity in certain outlets. Fake news and the absence of trust in the media are developing issues with immense consequences in our general public. It is needed to look into how the techniques in the fields of computer science using machine learning, natural language processing helps us to detect fake news. Fake news is now observed as one of the major threats to freedom of expression, journalism, and democracy of a country. In this research, a comprehensive way of detecting fake news using machine learning model has been presented that is trained by Fake News data based on US election and trained on recent Indian political Fake news.