ANDRAJU BHANU PRASAD

EDUCATION

M.E CSE Sathyabama University, Chennai, Tamilnadu

RESEARCH INTERESTS

Data Science and Artificial Intelligence

Scopus Publications

Anti Fraud Detection Model Using Deep Learning Approach
VNLN Murthy, A Bhanu Prasad, BJV Varma, and Hariharan Shanmugasundaram
IEEE
Recently, Internet finance has become more and more popular. However, bad debts becamea serious threat to online finance corporations. A commonly used fraud detection models by the traditional monetary companies is logistic regression. In this paper we use dataset consisting large publicloans data of a financial company i.e., Lending Club to check the potential of deep neural networks in fraud detection. Once this dataset is loaded we dealtwith the missing values and data pre-processing. With this pre-processed data, we extracted important features using the XGBoost algorithm and developed a CNN deep neural network to detect loan fraud on the Internet. Extensive experiments were conducted to prove that deep neural networks are superior tocommonly used models. This easy and effective model can give enlightenment for the utilization of deep learning to combat online loan fraud, which can profit the financial engineers of tiny and medium-sized financial corporations.


Lane Detection Using Deep Learning Approach
Shyam Immanuel A, Kaladevi R, Hariharan Shanmugasundaram, Bhanu prasad A, Karthikeyan R, and Mohammad Bilal J
IEEE
The recent advancements in vehicle detection and self-driving capability of autonomous vehicles has become a challenging trend in recent years. Though humans are prone to errors while they drive the car, these automated vehicles are more critical in identifying and ensuring safety. The autonomous detection capability is quiet an interesting and more importantly be an demanding topic of research. The study on detection of appropriate LANE for identifying the road layouts directs for proper route identification. In the study presented here, Convolutional Neural Network was used for effective lane detection. Convolutional Neural Network (CNN) deals with images looking for deep pixel level analysis. For the study presented here, image frames were extracted from running length videos of the driving vehicles which of reasonable length (several minutes of less that 5 in number) from which image frames were extracted and processed. The procedure involves dealing with OpenCV functions, camera calibration and perspective transformation. The results obtained is quiet promising with accuracy level 87.5% as compared to existing algorithms and leads to proper detection of LANE using the deep learning algorithmic procedure used in the study.


Comparative study on modern approaches of recommender system
A. Bhanu Prasad, Dr. N. Sambasiva Rao, K. Subba Rao, and B Lakshmi
Science Publishing Corporation
Recommender system is a kind of tool for filtering information and items of user interest. There are large number of different approaches for filtering data and information. In this paper a comparative study is made on different modern approaches in particular. All the modern approaches along with traditional recommender systems are listed and explained with their merits and demerits. Some common challenges are also addressed in this context. 


Author verification using rich set of linguistic features
A. Bhanu Prasad, S. Rajeswari, A. Venkannababu, and T. Raghunadha Reddy
Springer Singapore
Author Verification is a type of author identification task, which deals with identification of whether two documents were written by the same author or not. Mainly, the detection performance depends on the used feature set for clustering the documents. Linguistic features have been utilized for author identification according to the writing style of a particular author. Disclosing the shallow changes of the author’s writing style is the major problem which should be addressed in the domain of authorship verification. It motivates the computer science researchers to do research on authorship verification in the field of computer forensics. In this work, three types of linguistic features such as stylistic, syntactic, and semantic features are used to improve the accuracy of author verification. The Naive Bayes multinomial classifier is used to build the classification model and good accuracy is achieved for Author Verification.