Dr Chandra Sekhar Sanaboina
@jntucek.ac.in
Assistant Professor
University College of Engineering Kakinada, JNTUK
RESEARCH INTERESTS
Internet of Things, Machine Learning, Data Science
Scopus Publications
Scholar Citations
Scholar h-index
Scopus Publications
Durga Prasad Kavadi, Chandra Sekhar Sanaboina, Rizwan Patan, and Amir Gandomi
ACM
Social bots are computer programs created for automating general human activities like the generation of messages. The rise of bots in social network platforms has led to malicious activities such as content pollution like spammers or malware dissemination of misinformation. Most of the researchers focused on detecting bot accounts in social media platforms to avoid the damages done to the opinions of users. In this work, n-gram based approach is proposed for a bot or human detection. The content-based features of character n-grams and word n-grams are used. The character and word n-grams are successfully proved in various authorship analysis tasks to improve accuracy. A huge number of n-grams is identified after applying different pre-processing techniques. The high dimensionality of features is reduced by using a feature selection technique of the Relevant Discrimination Criterion. The text is represented as vectors by using a reduced set of features. Different term weight measures are used in the experiment to compute the weight of n-grams features in the document vector representation. Two classification algorithms, Support Vector Machine, and Random Forest are used to train the model using document vectors. The proposed approach was applied to the dataset provided in PAN 2019 competition bot detection task. The Random Forest classifier obtained the best accuracy of 0.9456 for bot/human detection.
Chandra Sekhar Sanaboina, , Srinivasa Rao Odugu, Girish Vanamadi, , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Visual Cryptography is an encryption technique in which the secret image is encoded and divided into n meaningless images called shares. The shares look like black and white dots embedded randomly in an image. These shares don’t reveal any information about the original image. Every share was printed on transparent paper and decrypted through the superimposition of shares without any computer decryption algorithm. When all n shares were overlapped, the original picture would appear. A (k, n)-threshold visual cryptography is a technique in which n is the maximum number of shares that are to be generated and k is the minimum number of shares that are required to decrypt the original image. If the insufficient number of shares, which are less than the k value is given to the decryption function, the decryption function will generate the output, which doesn’t reveal any clue to the original image. This paper presents how the Entropy, Mean Square Error (MSE), Peak Signal Noise Ratio (PSNR) values varies with respect to given same image of different sizes.