ABOUT ACADEMICS PROJECTS INTERNSHIPS RESEARCH CO-CURRICULAR RESUME
Computational Evaluation of Distributed Machine Learning Algorithms
IEEE 5th International Conference for Convergence in Technology, Pune, India (I2CT, 2019)
The paper focuses on the potential improvements in the existing AdaBoost algorithm.
Generative Adversarial Networks as an Advancement in 2D to 3D Reconstruction Techniques
3rd International Conference on Data Management, Analytics and Innovation, Kuala Lampur, Malaysia (ICDMAI, 2019)
Abstract : Among the various applications of GANs, image synthesis has shown great potential due to the power of two deep neural networks - Generator and Discriminator, trained in a competitive way, which are able to produce reasonably realistic images. Formulation of 3D-GANs - which are able to generate three-dimensional objects from multiple two-dimensional views with impressive accuracy have emerged as a promising solution to the aforementioned issue. This paper provides a comprehensive analysis of deep learning methods used in generating three dimensional objects, reviews the different models and frameworks for three-dimensional object generation, discusses some evaluation metrics and future research direction in using GANs as an alternative for simultaneous localization and environment mapping.
Analysis of Classifiers for Prediction of Type II Diabetes
IEEE 4th International Conference on Computing, Communication, Control And Automation, Pune, India (ICCUBEA, 2018)
Abstract : Diabetes mellitus is a chronic disease and a health challenge all over the world. As per the International Diabetes Federation, 451 million people have diabetes worldwide and this number is expected to rise up to 693 million people by 2045. It has been shown that 80% of the complications arising from type II diabetes can be prevented or delayed by early identification of the people at risk. Diabetes is difficult to diagnose in the early stages as its symptoms grow subtly and gradually. Many of the cases involve the patient being undiagnosed until they are admitted for a heart attack or begin to lose their sight. This paper analyzes the different classification algorithms based on a patient’s health history to aid doctors identify the presence as well as promote early diagnosis and treatment. The experiments were conducted on Pima Indian Diabetes data set. Various classifiers used include K Nearest Neighbors, Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine and Neural network. Results demonstrate that Random Forests performed well on the data set giving an accuracy of 79.7%.
Performance Analysis of DML Operations on NoSQL Databases for Streaming Data
IEEE 4th International Conference on Computing, Communication, Control And Automation, Pune, India (ICCUBEA, 2018)
Abstract: The processing of streaming data has led to major advancements in the fields of finance, security analysis and social media analysis. For processing, organizations must first store this data. Of the few data storage options that satisfy the characteristics to reserve streams of data, NoSQL databases provide a better alternative because of their ability to stored schema-less data which was not possible in RDBMS. Among these, two databases in Elasticsearch and Cassandra have been chosen to demonstrate their performance when tested against a streaming application. The performance comparison is carried out on the basis of Data Manipulation Language operations on both NoSQL datastores. Based on the experiment conducted, it is concluded that higher scalability operations were performed faster by Cassandra while Elasticsearch took smaller execution time for applications that required aggregations and modifications of data. The analysis done thus helps organizations chose the appropriate NoSQL Database for their own requirements.