Loading...

I'm

Pavithra

Data Scientist, Web Designer, Web Developer, Front End Developer, Apps Designer, Apps Developer

1

Year

of working experience as a Junior Executive

Documentation work to create and close all the records that the organization keeps safetly.

Afordable Prices

High Quality Product

On Time Project Delivery

Read More

Skills & Experience

My Skills

HTML
Beginner
CSS
85%
Java
90%
Javascript
90%
Python
95%
C
85%
Junior Executive

currently working

LENOVO

December 2018

In-Plant Training
M.Tech Data Science

2021 - 2023

Puducherry Technological University
B.Tech CSE

2017 - 2021

Alpha College of Engineering and Technology
Higher Secondary

2016 - 2017

Immaculate Heart of Mary Girl's Higher Secondary School
High School

2014 - 2015

Immaculate Heart of Mary Girl's Higher Secondary School

My Services

Workshop

Attended a Workshop on ETHICAL HACKING & CYBER SECURITY in Pondicherry Engineering college at Puducherry.

Achievement

Participated in PAPER PRESENTATION in AVIATION DAY and PROJECT DEMO in Alpha College of Engineering and Technology at Puducherry.

Internship

Completed the internship on MACHINE LEARNING from the smartknower. Completed the internship on ARTIFICAL INTELLIGENCE from the Pantech solution on youtube.

In-Plant Training

In-Plant Training in LENOVO on Dec 2018.

My Projects

Extremely Randomized trees with Privacy Preservation for distributed structured health data.

In the field of healthcare, artificial intelligence and machine learning have garnered a lot of attention lately. Healthcare applications frequently use data from numerous sources, such as hospitals or patients' own gadgets, to power machine learning algorithms. Analyzing such data without jeopardizing patient privacy and personal information is a major challenge, as this is a major concern in healthcare applications. As a result, we are interested in applying machine learning techniques to distributed data in these applications without revealing sensitive information about the data subjects. In order to learn from distributed data while maintaining privacy, we present a distributed very randomized trees approach in this research. We describe the application of our method (which we call k-PPD-ERT) on a cloud platform and show its effectiveness using mental health datasets (Depresjon and Psykose datasets) related to the Norwegian INTROducing Mental health through Adaptive Technology (INTROMAT) project as well as medical data, such as heart disease and breast cancer.

Secure Data Group sharing and Conditional Distribution With Multi - Owner in Cloud Computing.

In this paper, we propose a conditional dissemination scheme with multi-owner in cloud computing that allows data owners to securely share private data with a group of users via the cloud, and data disseminators to distribute the data to a new group of users if the attributes meet the cipher text's access policies. Additionally, we provide a multiparty access control method over the shared cipher text, allowing the co-owners of the data to add new access policies to the cipher text based on their respective privacy preferences. This paper presents a secure data group sharing and conditional dissemination scheme with multi-owner in cloud computing. Under this scheme, the data owner can securely share private data with a group of users through the cloud, and the data disseminator can distribute the data to a new group of users if the attributes meet the cipher text's access policies. We also introduce a multiparty access control method over the shared cipher text, where co-owners of the data can add new access policies to the cipher text based on their prefered privacy settings.Here, we present a secure data group sharing and conditional dissemination scheme with multi-owner in cloud computing. Under this scheme, the data owner can securely share private data with a group of users through the cloud, and the data disseminator can distribute the data to a new group of users if the attributes meet the cipher text's access policies. We also introduce a multiparty access control method over the shared cipher text, where co-owners of the data can add new access policies to the cipher text based on their privacy preferences.

Brain Tumor Detection by using Lee Sigma Filter Model and Deep Image Prior Techniques

A brain tumor is disease brought by development of irregular head prison cell. A endurance race of persistent exaggerated with Brain Tumor. Brain Tumor can be predictable by Magnetic Resonances Imaging (MRI) images, which acting a significant part in the medical field. The Computer-Aided Diagnosis (CAD) system has contain various issues like, which cannot detect diseases accurately in MRI images. In the existing system, the Deep Convolutional Neural Network (DCNN) architecture with three types of pre- processing steps are used to recover the value of the MRI scan images. In the proposed system, the Deep Image Prior technique will be used to denoise the MRI images, Lee Sigma Filter Model will be castoff to growth the contrast of the MRI image, and Recurrent Convolutional Neural Network Model will increase the accuracy.

Let's Work Together

Address:

No.30, Dhayandha Street, Indhira Nagar, Mudaliarpet, Puducherry - 605004.


Call me:

+91 9150233212


Mail me:

pavithramoorthy1999@gmail.com


Follow me:

© Pavithra, All Right Reserved.
Designed By Pavithra